|
1
|
Ramos MLF, Chaturvedi AK, Graubard BI, Katki HA. Efficient risk-based collection of biospecimens in cohort studies: designing a prospective study of diagnostic performance for multicancer detection tests. Am J Epidemiol 2025; 194:243-253. [PMID: 38965750 PMCID: PMC12034839 DOI: 10.1093/aje/kwae139] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Revised: 05/02/2024] [Accepted: 06/14/2024] [Indexed: 07/06/2024] Open
Abstract
In cohort studies, it can be infeasible to collect specimens on an entire cohort. For example, to estimate sensitivity of multiple multi-cancer detection (MCD) assays, we desire an extra 80 mL of cell-free DNA (cfDNA) blood, but this much extra blood is too expensive for us to collect on everyone. We propose a novel epidemiologic study design that efficiently oversamples those at highest baseline disease risk from whom to collect specimens, to increase the number of future cases with cfDNA blood collection. The variance reduction ratio from our risk-based subsample versus a simple random (sub)sample (SRS) depends primarily on the ratio of risk model sensitivity to the fraction of the cohort selected for specimen collection subject to constraining the risk model specificity. In a simulation where we chose 34% of the Prostate, Lung, Colorectal, and Ovarian Screening Trial cohort at highest risk of lung cancer for cfDNA blood collection, we could enrich the number of lung cancers 2.42-fold. The standard deviation of lung-cancer MCD sensitivity was 31%-33% reduced versus SRS. Risk-based collection of specimens on a subsample of the cohort could be a feasible and efficient approach to collecting extra specimens for molecular epidemiology.
Collapse
Affiliation(s)
- Mark Louie F Ramos
- Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Department of Health and Human Services, Bethesda, MD 20892, United States
| | - Anil K Chaturvedi
- Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Department of Health and Human Services, Bethesda, MD 20892, United States
| | - Barry I Graubard
- Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Department of Health and Human Services, Bethesda, MD 20892, United States
| | - Hormuzd A Katki
- Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Department of Health and Human Services, Bethesda, MD 20892, United States
| |
Collapse
|
|
2
|
Chatterjee A, Yousuf AN, Engelmann R, Harmath C, Lee G, Medved M, Jamison EB, Lorente Campos A, Gundogdu B, Gerber G, Reynolds LF, Modi PK, Antic T, Giurcanu M, Eggener S, Karczmar GS, Oto A. Prospective Validation of an Automated Hybrid Multidimensional MRI Tool for Prostate Cancer Detection Using Targeted Biopsy: Comparison with PI-RADS-based Assessment. Radiol Imaging Cancer 2025; 7:e240156. [PMID: 39836080 PMCID: PMC11791675 DOI: 10.1148/rycan.240156] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2024] [Revised: 10/10/2024] [Accepted: 12/04/2024] [Indexed: 01/22/2025]
Abstract
Purpose To evaluate the use of an automated hybrid multidimensional MRI (HM-MRI)-based tool to prospectively identify prostate cancer targets before MRI/US fusion biopsy in comparison with Prostate Imaging and Reporting Data System (PI-RADS)-based multiparametric MRI (mpMRI) evaluation by expert radiologists. Materials and Methods In this prospective clinical trial (ClinicalTrials.gov registration no. NCT03585660), 91 male participants (mean age, 65 years ± 8 [SD]) with known or suspected prostate cancer underwent 3-T MRI with a conventional mpMRI protocol and HM-MRI followed by subsequent biopsy between August 2018 and March 2023. Using the HM-MRI tool, tissue composition was calculated using a three-compartment model, and suspected prostate cancer regions with elevated epithelium (>40%) and reduced lumen (<20%) meeting the minimum size requirement of 25 mm2 were identified. Up to two additional biopsy targets per participant were automatically selected with the HM-MRI tool in addition to the biopsy targets selected based on an expert radiologist's mpMRI interpretation (≥PI-RADS 3) using an MRI/US fusion biopsy device. Additional 12-core transrectal US-guided sextant random biopsy cores were also obtained. Detection of clinically significant prostate cancer (≥Gleason 3+4) was compared between HM-MRI and mpMRI by calculating area under the receiver operating characteristic curve and diagnostic accuracy metrics. Results The diagnostic performance of HM-MRI was either higher than mpMRI or showed no evidence of a difference when compared with mpMRI. On a per-participant basis, HM-MRI had significantly higher accuracy (55% vs 44%; P = .02) and specificity (36% vs 14%: P = .002) than mpMRI. On a per-lesion basis, HM-MRI had significantly higher accuracy (58% vs 39%; P < .001) and positive predictive value (31% vs 22%; P = .004) compared with mpMRI. Only one lesion was missed when using the combination of mpMRI and HM-MRI. On a per-sextant basis, HM-MRI showed significantly better performance than mpMRI for all metrics, including primary end points of the area under the receiver operating characteristic curve (0.76 vs 0.65; P < .001) and accuracy (83.9% vs 79.0%; P = .006). Conclusion This study demonstrates that HM-MRI has the potential to improve MRI/US fusion biopsy results for prostate cancer detection by providing complementary information to PI-RADS-based evaluation by expert radiologists. Keywords: Prostate Cancer, Hybrid Multidimensional MRI, Multiparametric MRI, PI-RADS Clinical trial registration no. NCT03585660 ©RSNA, 2025.
Collapse
Affiliation(s)
- Aritrick Chatterjee
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Ambereen N. Yousuf
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Roger Engelmann
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Carla Harmath
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Grace Lee
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Milica Medved
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Ernest B. Jamison
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Abel Lorente Campos
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Batuhan Gundogdu
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Glenn Gerber
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Luke F. Reynolds
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Parth K. Modi
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Tatjana Antic
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Mihai Giurcanu
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Scott Eggener
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Gregory S. Karczmar
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| | - Aytekin Oto
- From the Department of Radiology (A.C., A.N.Y., R.E., C.H., G.L.,
M.M., E.B.J., A.L.C., B.G., G.S.K., A.O.), Sanford J. Grossman Center of
Excellence in Prostate Imaging and Image Guided Therapy (A.C., A.N.Y., M.M.,
A.L.C., B.G.), Department of Surgery, Section of Urology (G.G., L.F.R., P.K.M.,
S.E.), Department of Pathology (T.A.), and Department of Public Health Sciences
(M.G.), University of Chicago, 5841 S Maryland Ave, MC 2026, Chicago, IL
60637
| |
Collapse
|
|
3
|
de Vente C, van Ginneken B, Hoyng CB, Klaver CCW, Sánchez CI. Uncertainty-aware multiple-instance learning for reliable classification: Application to optical coherence tomography. Med Image Anal 2024; 97:103259. [PMID: 38959721 DOI: 10.1016/j.media.2024.103259] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2023] [Revised: 06/17/2024] [Accepted: 06/24/2024] [Indexed: 07/05/2024]
Abstract
Deep learning classification models for medical image analysis often perform well on data from scanners that were used to acquire the training data. However, when these models are applied to data from different vendors, their performance tends to drop substantially. Artifacts that only occur within scans from specific scanners are major causes of this poor generalizability. We aimed to enhance the reliability of deep learning classification models using a novel method called Uncertainty-Based Instance eXclusion (UBIX). UBIX is an inference-time module that can be employed in multiple-instance learning (MIL) settings. MIL is a paradigm in which instances (generally crops or slices) of a bag (generally an image) contribute towards a bag-level output. Instead of assuming equal contribution of all instances to the bag-level output, UBIX detects instances corrupted due to local artifacts on-the-fly using uncertainty estimation, reducing or fully ignoring their contributions before MIL pooling. In our experiments, instances are 2D slices and bags are volumetric images, but alternative definitions are also possible. Although UBIX is generally applicable to diverse classification tasks, we focused on the staging of age-related macular degeneration in optical coherence tomography. Our models were trained on data from a single scanner and tested on external datasets from different vendors, which included vendor-specific artifacts. UBIX showed reliable behavior, with a slight decrease in performance (a decrease of the quadratic weighted kappa (κw) from 0.861 to 0.708), when applied to images from different vendors containing artifacts; while a state-of-the-art 3D neural network without UBIX suffered from a significant detriment of performance (κw from 0.852 to 0.084) on the same test set. We showed that instances with unseen artifacts can be identified with OOD detection. UBIX can reduce their contribution to the bag-level predictions, improving reliability without retraining on new data. This potentially increases the applicability of artificial intelligence models to data from other scanners than the ones for which they were developed. The source code for UBIX, including trained model weights, is publicly available through https://github.com/qurAI-amsterdam/ubix-for-reliable-classification.
Collapse
Affiliation(s)
- Coen de Vente
- Quantitative Healthcare Analysis (QurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, Noord-Holland, Netherlands; Department of Biomedical Engineering and Physics, Amsterdam University Medical Center, Amsterdam, Noord-Holland, Netherlands; Diagnostic Image Analysis Group (DIAG), Department of Radiology and Nuclear Medicine, Radboudumc, Nijmegen, Gelderland, Netherlands.
| | - Bram van Ginneken
- Diagnostic Image Analysis Group (DIAG), Department of Radiology and Nuclear Medicine, Radboudumc, Nijmegen, Gelderland, Netherlands
| | - Carel B Hoyng
- Department of Ophthalmology, Radboudumc, Nijmegen, Gelderland, Netherlands
| | - Caroline C W Klaver
- Department of Ophthalmology, Radboudumc, Nijmegen, Gelderland, Netherlands; Ophthalmology & Epidemiology, Erasmus MC, Rotterdam, Zuid-Holland, Netherlands
| | - Clara I Sánchez
- Quantitative Healthcare Analysis (QurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, Noord-Holland, Netherlands; Department of Biomedical Engineering and Physics, Amsterdam University Medical Center, Amsterdam, Noord-Holland, Netherlands
| |
Collapse
|
|
4
|
de Vente C, Valmaggia P, Hoyng CB, Holz FG, Islam MM, Klaver CCW, Boon CJF, Schmitz-Valckenberg S, Tufail A, Saßmannshausen M, Sánchez CI. Generalizable Deep Learning for the Detection of Incomplete and Complete Retinal Pigment Epithelium and Outer Retinal Atrophy: A MACUSTAR Report. Transl Vis Sci Technol 2024; 13:11. [PMID: 39235402 PMCID: PMC11379096 DOI: 10.1167/tvst.13.9.11] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/06/2024] Open
Abstract
Purpose The purpose of this study was to develop a deep learning algorithm for detecting and quantifying incomplete retinal pigment epithelium and outer retinal atrophy (iRORA) and complete retinal pigment epithelium and outer retinal atrophy (cRORA) in optical coherence tomography (OCT) that generalizes well to data from different devices and to validate in an intermediate age-related macular degeneration (iAMD) cohort. Methods The algorithm comprised a domain adaptation (DA) model, promoting generalization across devices, and a segmentation model for detecting granular biomarkers defining iRORA/cRORA, which are combined into iRORA/cRORA segmentations. Manual annotations of iRORA/cRORA in OCTs from different devices in the MACUSTAR study (168 patients with iAMD) were compared to the algorithm's output. Eye level classification metrics included sensitivity, specificity, and quadratic weighted Cohen's κ score (κw). Segmentation performance was assessed quantitatively using Bland-Altman plots and qualitatively. Results For ZEISS OCTs, sensitivity and specificity for iRORA/cRORA classification were 38.5% and 93.1%, respectively, and 60.0% and 96.4% for cRORA. For Spectralis OCTs, these were 84.0% and 93.7% for iRORA/cRORA, and 62.5% and 97.4% for cRORA. The κw scores for 3-way classification (none, iRORA, and cRORA) were 0.37 and 0.73 for ZEISS and Spectralis, respectively. Removing DA reduced κw from 0.73 to 0.63 for Spectralis. Conclusions The DA-enabled iRORA/cRORA segmentation algorithm showed superior consistency compared to human annotations, and good generalization across OCT devices. Translational Relevance The application of this algorithm may help toward precise and automated tracking of iAMD-related lesion changes, which is crucial in clinical settings and multicenter longitudinal studies on iAMD.
Collapse
Affiliation(s)
- Coen de Vente
- Quantitative Healthcare Analysis (qurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
- Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Amsterdam, The Netherlands
- Diagnostic Image Analysis Group (DIAG), Department of Radiology and Nuclear Medicine, Radboud UMC, Nijmegen, The Netherlands
| | - Philippe Valmaggia
- Department of Biomedical Engineering, Universität Basel, Basel, Basel-Stadt, Switzerland
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Basel-Stadt, Switzerland
| | - Carel B Hoyng
- Department of Ophthalmology, Radboudumc, Nijmegen, The Netherlands
| | - Frank G Holz
- Department of Ophthalmology and GRADE Reading Center, University Hospital Bonn, Germany
| | - Mohammad M Islam
- Quantitative Healthcare Analysis (qurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
- Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Amsterdam, The Netherlands
| | - Caroline C W Klaver
- Department of Ophthalmology, Radboudumc, Nijmegen, The Netherlands
- Ophthalmology and Epidemiology, Erasmus MC, Rotterdam, The Netherlands
| | - Camiel J F Boon
- Department of Ophthalmology, Leiden University Medical Center, Leiden, The Netherlands
- Department of Ophthalmology, Amsterdam University Medical Centers, Amsterdam, The Netherlands
| | - Steffen Schmitz-Valckenberg
- Department of Ophthalmology and GRADE Reading Center, University Hospital Bonn, Germany
- John A. Moran Eye Center, University of Utah, Salt Lake City, UT, USA
| | - Adnan Tufail
- Moorfields Eye Hospital NHS Foundation Trust, London, UK
| | | | - Clara I Sánchez
- Quantitative Healthcare Analysis (qurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
- Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Amsterdam, The Netherlands
| |
Collapse
|
|
5
|
Ganz DA, Esserman D, Latham NK, Kane M, Min LC, Gill TM, Reuben DB, Peduzzi P, Greene EJ. Validation of a Rule-Based ICD-10-CM Algorithm to Detect Fall Injuries in Medicare Data. J Gerontol A Biol Sci Med Sci 2024; 79:glae096. [PMID: 38566617 PMCID: PMC11167485 DOI: 10.1093/gerona/glae096] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2023] [Indexed: 04/04/2024] Open
Abstract
BACKGROUND Diagnosis-code-based algorithms to identify fall injuries in Medicare data are useful for ascertaining outcomes in interventional and observational studies. However, these algorithms have not been validated against a fully external reference standard, in ICD-10-CM, or in Medicare Advantage (MA) data. METHODS We linked self-reported fall injuries leading to medical attention (FIMA) from the Strategies to Reduce Injuries and Develop Confidence in Elders (STRIDE) trial (reference standard) to Medicare fee-for-service (FFS) and MA data from 2015-19. We measured the area under the receiver operating characteristic curve (AUC) based on sensitivity and specificity of a diagnosis-code-based algorithm against the reference standard for presence or absence of ≥1 FIMA within a specified window of dates, varying the window size to obtain points on the curve. We stratified results by source (FFS vs MA), trial arm (intervention vs control), and STRIDE's 10 participating health care systems. RESULTS Both reference standard data and Medicare data were available for 4 941 (of 5 451) participants. The reference standard and algorithm identified 2 054 and 2 067 FIMA, respectively. The algorithm had 45% sensitivity (95% confidence interval [CI]: 43%-47%) and 99% specificity (95% CI: 99%-99%) to identify reference standard FIMA within the same calendar month. The AUC was 0.79 (95% CI: 0.78-0.81) and was similar by FFS or MA data source and by trial arm but showed variation among STRIDE health care systems (AUC range by health care system, 0.71 to 0.84). CONCLUSIONS An ICD-10-CM algorithm to identify fall injuries demonstrated acceptable performance against an external reference standard, in both MA and FFS data.
Collapse
Affiliation(s)
- David A Ganz
- Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, California, USA
- Geriatric Research, Education and Clinical Center, Veterans Affairs Greater Los Angeles Healthcare System, Los Angeles, California, USA
| | - Denise Esserman
- Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, USA
| | - Nancy K Latham
- Boston Claude D. Pepper Older Americans Independence Center, Research Program in Men’s Health: Aging and Metabolism, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Michael Kane
- Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, USA
| | - Lillian C Min
- Division of Geriatric and Palliative Medicine, Department of Internal Medicine, University of Michigan, Ann Arbor VA Medical Center, Center for Clinical Management Research and Geriatric Research Education Clinical Center (GRECC), Ann Arbor, Michigan, USA
| | - Thomas M Gill
- Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - David B Reuben
- Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, California, USA
| | - Peter Peduzzi
- Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, USA
| | - Erich J Greene
- Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, USA
| |
Collapse
|
|
6
|
Bertani E, Mattana F, Collamati F, Ferrari ME, Bagnardi V, Frassoni S, Pisa E, Mirabelli R, Morganti S, Fazio N, Fumagalli Romario U, Ceci F. Radio-Guided Surgery with a New-Generation β-Probe for Radiolabeled Somatostatin Analog, in Patients with Small Intestinal Neuroendocrine Tumors. Ann Surg Oncol 2024; 31:4189-4196. [PMID: 38652200 DOI: 10.1245/s10434-024-15277-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2024] [Accepted: 03/25/2024] [Indexed: 04/25/2024]
Abstract
BACKGROUND Radio-guided surgery (RGS) holds promise for improving surgical outcomes in neuroendocrine tumors (NETs). Previous studies showed low specificity (SP) using γ-probes to detect radiation emitted by radio-labeled somatostatin analogs. OBJECTIVE We aimed to assess the sensitivity (SE) and SP of the intraoperative RGS approach using a β-probe with a per-lesion analysis, while assessing safety and feasibility as secondary objectives. METHODS This prospective, single-arm, single-center, phase II trial (NCT05448157) enrolled 20 patients diagnosed with small intestine NETs (SI-NETs) with positive lesions detected at 68Ga-DOTA-TOC positron emission tomography/computed tomography (PET/CT). Patients received an intravenous injection of 1.1 MBq/Kg of 68Ga-DOTA-TOC 10 min prior to surgery. In vivo measurements were conducted using a β-probe. Receiver operating characteristic (ROC) analysis was performed, with the tumor-to-background ratio (TBR) as the independent variable and pathology result (cancer vs. non-cancer) as the dependent variable. The area under the curve (AUC), optimal TBR, and absorbed dose for the surgery staff were reported. RESULTS The intraoperative RGS approach was feasible in all cases without adverse effects. Of 134 specimens, the AUC was 0.928, with a TBR cut-off of 1.35 yielding 89.3% SE and 86.4% SP. The median absorbed dose for the surgery staff was 30 µSv (range 12-41 µSv). CONCLUSION This study reports optimal accuracy in detecting lesions of SI-NETs using the intraoperative RGS approach with a novel β-probe. The method was found to be safe, feasible, and easily reproducible in daily clinical practice, with minimal radiation exposure for the staff. RGS might potentially improve radical resection rates in SI-NETs. CLINICAL TRIALS REGISTRATION 68Ga-DOTATOC Radio-Guided Surgery with β-Probe in GEP-NET (RGS GEP-NET) [NCT0544815; https://classic. CLINICALTRIALS gov/ct2/show/NCT05448157 ].
Collapse
Affiliation(s)
- Emilio Bertani
- Neuroendocrine Surgery Tumor Unit, IEO, European Institute of Oncology IRCCS, Milan, Italy.
- Division of Digestive Surgery, IEO, European Institute of Oncology IRCCS, Milan, Italy.
| | - Francesco Mattana
- Division of Nuclear Medicine, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | | | - Mahila E Ferrari
- Division of Medical Physics, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | - Vincenzo Bagnardi
- Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy
| | - Samuele Frassoni
- Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy
| | - Eleonora Pisa
- Division of Pathology, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | - Riccardo Mirabelli
- Istituto Nazionale di Fisica Nucleare INFN, Sezione di Roma, Rome, Italy
- Department of Basic and Applied Sciences for Engineering, Sapienza University of Rome, Rome, Italy
| | - Silvio Morganti
- Istituto Nazionale di Fisica Nucleare INFN, Sezione di Roma, Rome, Italy
| | - Nicola Fazio
- Division of Gastrointestinal and Neuroendocrine Tumors Medical Treatment IEO, European Institute of Oncology IRCCS, Milan, Italy
| | | | - Francesco Ceci
- Division of Nuclear Medicine, IEO, European Institute of Oncology IRCCS, Milan, Italy
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| |
Collapse
|
|
7
|
de Vente C, Vermeer KA, Jaccard N, Wang H, Sun H, Khader F, Truhn D, Aimyshev T, Zhanibekuly Y, Le TD, Galdran A, Ballester MAG, Carneiro G, Devika RG, Sethumadhavan HP, Puthussery D, Liu H, Yang Z, Kondo S, Kasai S, Wang E, Durvasula A, Heras J, Zapata MA, Araujo T, Aresta G, Bogunovic H, Arikan M, Lee YC, Cho HB, Choi YH, Qayyum A, Razzak I, van Ginneken B, Lemij HG, Sanchez CI. AIROGS: Artificial Intelligence for Robust Glaucoma Screening Challenge. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:542-557. [PMID: 37713220 DOI: 10.1109/tmi.2023.3313786] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/16/2023]
Abstract
The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening.
Collapse
|
|
8
|
Liang H, Wang M, Wen Y, Du F, Jiang L, Geng X, Tang L, Yan H. Predicting acute pancreatitis severity with enhanced computed tomography scans using convolutional neural networks. Sci Rep 2023; 13:17514. [PMID: 37845380 PMCID: PMC10579320 DOI: 10.1038/s41598-023-44828-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2023] [Accepted: 10/12/2023] [Indexed: 10/18/2023] Open
Abstract
This study aimed to evaluate acute pancreatitis (AP) severity using convolutional neural network (CNN) models with enhanced computed tomography (CT) scans. Three-dimensional DenseNet CNN models were developed and trained using the enhanced CT scans labeled with two severity assessment methods: the computed tomography severity index (CTSI) and Atlanta classification. Each labeling method was used independently for model training and validation. Model performance was evaluated using confusion matrices, areas under the receiver operating characteristic curve (AUC-ROC), accuracy, precision, recall, F1 score, and respective macro-average metrics. A total of 1,798 enhanced CT scans met the inclusion criteria were included in this study. The dataset was randomly divided into a training dataset (n = 1618) and a test dataset (n = 180) with a ratio of 9:1. The DenseNet model demonstrated promising predictions for both CTSI and Atlanta classification-labeled CT scans, with accuracy greater than 0.7 and AUC-ROC greater than 0.8. Specifically, when trained with CT scans labeled using CTSI, the DenseNet model achieved good performance, with a macro-average F1 score of 0.835 and a macro-average AUC-ROC of 0.980. The findings of this study affirm the feasibility of employing CNN models to predict the severity of AP using enhanced CT scans.
Collapse
Affiliation(s)
- Hongyin Liang
- Department of General Surgery, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
- Sichuan Provincial Key Laboratory of Pancreatic Injury and Repair, Chengdu, 610083, China
| | - Meng Wang
- Department of Traditional Chinese Medicine, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Yi Wen
- Department of General Surgery, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
- Sichuan Provincial Key Laboratory of Pancreatic Injury and Repair, Chengdu, 610083, China
| | - Feizhou Du
- Department of Radiology, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Li Jiang
- Department of Cardiac Surgery, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Xuelong Geng
- Department of Radiology, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
| | - Lijun Tang
- Department of General Surgery, The General Hospital of Western Theater Command (Chengdu Military General Hospital), Chengdu, 610083, China
- Sichuan Provincial Key Laboratory of Pancreatic Injury and Repair, Chengdu, 610083, China
| | - Hongtao Yan
- Department of Liver Transplantation and Hepato-biliary-pancreatic Surgery, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Medicine, University of Electronic Science and Technology of China, Chengdu, 610016, China.
| |
Collapse
|
|
9
|
Stephan P, Eichenlaub M, Waldenmaier D, Pleus S, Rothenbühler M, Haug C, Freckmann G. A Statistical Approach for Assessing the Compliance of Integrated Continuous Glucose Monitoring Systems with Food and Drug Administration Accuracy Requirements. Diabetes Technol Ther 2023; 25:212-216. [PMID: 36306521 DOI: 10.1089/dia.2022.0331] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
To assess the compliance of "integrated" continuous glucose monitoring (CGM) systems with U.S. Food and Drug Administration requirements, the calculation of confidence intervals (CIs) on agreement rates (ARs), that is, the percentage of CGM measurements lying within a certain deviation of a comparator method, is stipulated. However, despite the existence of numerous approaches that could yield different results, a specific procedure for calculating CIs is not described anywhere. This report, therefore, proposes a suitable statistical procedure to allow transparency and comparability between CGM systems. Three existing methods were applied to six data sets from different CGM performance studies. The results indicate that a bootstrap-based method that accounts for the clustered structure of CGM data is reliable and robust. We thus recommend its use for the estimation of CIs of ARs. A software implementation of the proposed method is freely available (https://github.com/IfDTUlm/CGM_Performance_Assessment).
Collapse
Affiliation(s)
| | - Manuel Eichenlaub
- Institut für Diabetes-Technologie Forschungs- und Entwicklungsgesellschaft mbH, Universität Ulm, Ulm, Germany
| | - Delia Waldenmaier
- Institut für Diabetes-Technologie Forschungs- und Entwicklungsgesellschaft mbH, Universität Ulm, Ulm, Germany
| | - Stefan Pleus
- Institut für Diabetes-Technologie Forschungs- und Entwicklungsgesellschaft mbH, Universität Ulm, Ulm, Germany
| | | | - Cornelia Haug
- Institut für Diabetes-Technologie Forschungs- und Entwicklungsgesellschaft mbH, Universität Ulm, Ulm, Germany
| | - Guido Freckmann
- Institut für Diabetes-Technologie Forschungs- und Entwicklungsgesellschaft mbH, Universität Ulm, Ulm, Germany
| |
Collapse
|
|
10
|
Lupușoru R, Sporea I, Rațiu I, Lungeanu D, Popescu A, Dănilă M, Mare R, Marc L, Lascău A, Moga TV, Bende F, Ghiuchici AM, Șirli R. Contrast-Enhanced Ultrasonography with Arrival Time Parametric Imaging as a Non-Invasive Diagnostic Tool for Liver Cirrhosis. Diagnostics (Basel) 2022; 12:3013. [PMID: 36553020 PMCID: PMC9777167 DOI: 10.3390/diagnostics12123013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2022] [Revised: 11/23/2022] [Accepted: 11/26/2022] [Indexed: 12/05/2022] Open
Abstract
Liver biopsy is the gold standard method for staging liver fibrosis, but it is an invasive procedure that is associated with some complications. There are also non-invasive techniques for assessing liver fibrosis, such as elastography and biological tests, but these techniques can fail in detection or generate false measurements depending on the subject’s condition. This study aimed to determine whether liver fibrosis can be evaluated using contrast-enhanced ultrasonography with arrival time parametric imaging using the ultrasound machine’s parametric image software, the method being called (CEUS-PAT). CEUS-PAT was performed on each subject using SonoVue as a contrast agent, and images showing liver parenchyma and the right kidney on a single screen were used for analysis in parametric imaging, which was performed using the proprietary software of the ultrasound system. The ratio between the kidney and liver arrival times was calculated. The study included 64 predominantly male (56.3%) subjects, 37 cirrhotic patients, and 27 healthy volunteers, with a mean age of 58.98 ± 8.90 years. Significant differences were found between the liver cirrhosis and healthy groups regarding CEUS-PAT, 0.83 ± 0.09 vs. 0.49 ± 0.11, p < 0.0001. The correlation between CEUS-PAT and VCTE was r = 0.81. The optimal cut-off value for detecting liver cirrhosis was >0.7, with an AUC of 0.98, p < 0.001, Se = 89.19%, Sp = 100%, PPV = 100%, and NPV = 87.1%. We demonstrate that CEUS-PAT achieves excellent performance in diagnosing liver cirrhosis and is a fast method for diagnosing liver cirrhosis that can even be applied in situations where the use of other methods is excluded.
Collapse
Affiliation(s)
- Raluca Lupușoru
- Center for Modeling Biological Systems and Data Analysis, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Department of Functional Sciences, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
| | - Ioan Sporea
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
| | - Iulia Rațiu
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Diana Lungeanu
- Center for Modeling Biological Systems and Data Analysis, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
| | - Alina Popescu
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Mirela Dănilă
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Ruxandra Mare
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Luciana Marc
- Department of Internal Medicine II, Division of Nephrology, “Victor Babeș” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Centre for Molecular Research in Nephrology and Vascular Disease, Faculty of Medicine, “Victor Babeș” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Nephrology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Andrada Lascău
- Discipline of Accounting and Information System, Faculty of Economics and Business Administration, West University of Timisoara, 300115 Timisoara, Romania
| | - Tudor Voicu Moga
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Felix Bende
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Ana-Maria Ghiuchici
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| | - Roxana Șirli
- Department of Internal Medicine II, Division of Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Advanced Regional Research Center in Gastroenterology and Hepatology, “Victor Babes” University of Medicine and Pharmacy, 300041 Timisoara, Romania
- Gastroenterology and Hepatology Clinic, County Emergency Hospital “Pius Brinzeu”, 300723 Timisoara, Romania
| |
Collapse
|
|
11
|
de Vente C, Boulogne LH, Venkadesh KV, Sital C, Lessmann N, Jacobs C, Sanchez CI, van Ginneken B. Automated COVID-19 Grading With Convolutional Neural Networks in Computed Tomography Scans: A Systematic Comparison. IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE 2022; 3:129-138. [PMID: 35582210 PMCID: PMC9014473 DOI: 10.1109/tai.2021.3115093] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/28/2021] [Revised: 06/02/2021] [Accepted: 09/18/2021] [Indexed: 11/08/2022]
Abstract
Amidst the ongoing pandemic, the assessment of computed tomography (CT) images for COVID-19 presence can exceed the workload capacity of radiologists. Several studies addressed this issue by automating COVID-19 classification and grading from CT images with convolutional neural networks (CNNs). Many of these studies reported initial results of algorithms that were assembled from commonly used components. However, the choice of the components of these algorithms was often pragmatic rather than systematic and systems were not compared to each other across papers in a fair manner. We systematically investigated the effectiveness of using 3-D CNNs instead of 2-D CNNs for seven commonly used architectures, including DenseNet, Inception, and ResNet variants. For the architecture that performed best, we furthermore investigated the effect of initializing the network with pretrained weights, providing automatically computed lesion maps as additional network input, and predicting a continuous instead of a categorical output. A 3-D DenseNet-201 with these components achieved an area under the receiver operating characteristic curve of 0.930 on our test set of 105 CT scans and an AUC of 0.919 on a publicly available set of 742 CT scans, a substantial improvement in comparison with a previously published 2-D CNN. This article provides insights into the performance benefits of various components for COVID-19 classification and grading systems. We have created a challenge on grand-challenge.org to allow for a fair comparison between the results of this and future research.
Collapse
Affiliation(s)
- Coen de Vente
- Radboud University Medical Center, Donders Institute for Brain, Cognition and BehaviourDepartment of Medical Imaging6525GANijmegenThe Netherlands.,Informatics Institute, Faculty of ScienceUniversity of Amsterdam 1012 WX Amsterdam The Netherlands
| | - Luuk H Boulogne
- Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands
| | - Kiran Vaidhya Venkadesh
- Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands
| | - Cheryl Sital
- Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands
| | - Nikolas Lessmann
- Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands
| | - Colin Jacobs
- Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands
| | - Clara I Sanchez
- Informatics Institute, Faculty of ScienceUniversity of Amsterdam 1012 WX Amsterdam The Netherlands
| | - Bram van Ginneken
- Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands
| |
Collapse
|
|
12
|
Obuchowski NA, Bullen J. Multireader Diagnostic Accuracy Imaging Studies: Fundamentals of Design and Analysis. Radiology 2022; 303:26-34. [PMID: 35166584 DOI: 10.1148/radiol.211593] [Citation(s) in RCA: 35] [Impact Index Per Article: 11.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
The design and analysis of multireader multicase (MRMC) studies are quite challenging. These studies differ from most medical studies because they need a reference standard and sampling from two populations (ie, reader and patient populations). They are quite expensive to conduct, requiring a good deal of readers' time for image interpretation. One common problem is the use of imperfect reference standards, often correlated with the test or tests being evaluated. Another common issue is oversimplification of the multidimensional MRMC data. In this study, the fundamentals of MRMC study design and analysis are reviewed. The goal is to provide investigators with a guide to the fundamentals of MRMC design and analysis, with references to more detailed discussions. In addition, readers are updated on newer areas of research, including correction for studies with multiple diagnostic accuracy end points and adjustment for location bias.
Collapse
Affiliation(s)
- Nancy A Obuchowski
- From the Department of Quantitative Health Sciences, Cleveland Clinic Foundation, 9500 Euclid Ave, JJN3, Cleveland, OH 44195
| | - Jennifer Bullen
- From the Department of Quantitative Health Sciences, Cleveland Clinic Foundation, 9500 Euclid Ave, JJN3, Cleveland, OH 44195
| |
Collapse
|
|
13
|
Onorati F, Regalia G, Caborni C, LaFrance WC, Blum AS, Bidwell J, De Liso P, El Atrache R, Loddenkemper T, Mohammadpour-Touserkani F, Sarkis RA, Friedman D, Jeschke J, Picard R. Prospective Study of a Multimodal Convulsive Seizure Detection Wearable System on Pediatric and Adult Patients in the Epilepsy Monitoring Unit. Front Neurol 2021; 12:724904. [PMID: 34489858 PMCID: PMC8418082 DOI: 10.3389/fneur.2021.724904] [Citation(s) in RCA: 36] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2021] [Accepted: 07/27/2021] [Indexed: 12/03/2022] Open
Abstract
Background: Using machine learning to combine wrist accelerometer (ACM) and electrodermal activity (EDA) has been shown effective to detect primarily and secondarily generalized tonic-clonic seizures, here termed as convulsive seizures (CS). A prospective study was conducted for the FDA clearance of an ACM and EDA-based CS-detection device based on a predefined machine learning algorithm. Here we present its performance on pediatric and adult patients in epilepsy monitoring units (EMUs). Methods: Patients diagnosed with epilepsy participated in a prospective multi-center clinical study. Three board-certified neurologists independently labeled CS from video-EEG. The Detection Algorithm was evaluated in terms of Sensitivity and false alarm rate per 24 h-worn (FAR) on all the data and on only periods of rest. Performance were analyzed also applying the Detection Algorithm offline, with a less sensitive but more specific parameters configuration (“Active mode”). Results: Data from 152 patients (429 days) were used for performance evaluation (85 pediatric aged 6–20 years, and 67 adult aged 21–63 years). Thirty-six patients (18 pediatric) experienced a total of 66 CS (35 pediatric). The Sensitivity (corrected for clustered data) was 0.92, with a 95% confidence interval (CI) of [0.85-1.00] for the pediatric population, not significantly different (p > 0.05) from the adult population's Sensitivity (0.94, CI: [0.89–1.00]). The FAR on the pediatric population was 1.26 (CI: [0.87–1.73]), higher (p < 0.001) than in the adult population (0.57, CI: [0.36–0.81]). Using the Active mode, the FAR decreased by 68% while reducing Sensitivity to 0.95 across the population. During rest periods, the FAR's were 0 for all patients, lower than during activity periods (p < 0.001). Conclusions: Performance complies with FDA's requirements of a lower bound of CI for Sensitivity higher than 0.7 and of a FAR lower than 2, for both age groups. The pediatric FAR was higher than the adult FAR, likely due to higher pediatric activity. The high Sensitivity and precision (having no false alarms) during sleep might help mitigate SUDEP risk by summoning caregiver intervention. The Active mode may be advantageous for some patients, reducing the impact of the FAR on daily life. Future work will examine the performance and usability outside of EMUs.
Collapse
Affiliation(s)
| | | | | | - W Curt LaFrance
- Division of Neuropsychiatry and Behavioral Neurology, Rhode Island Hospital, Brown University, Providence, RI, United States
| | - Andrew S Blum
- Department of Neurology, Rhode Island Hospital, Brown University, Providence, RI, United States
| | | | - Paola De Liso
- Department of Neuroscience, Bambino Gesù Children's Hospital, Istituto di Ricovero e Cura a Carattere Scientifico, Rome, Italy
| | - Rima El Atrache
- Department of Neurology, Boston Children's Hospital, Boston, MA, United States
| | - Tobias Loddenkemper
- Department of Neurology, Boston Children's Hospital, Boston, MA, United States
| | | | - Rani A Sarkis
- Department of Neurology, Brigham and Women's Hospital, Boston, MA, United States
| | - Daniel Friedman
- Department of Neurology, New York University Langone Medical Center, New York, NY, United States
| | - Jay Jeschke
- Department of Neurology, New York University Langone Medical Center, New York, NY, United States
| | - Rosalind Picard
- Empatica, Inc., Boston, MA, United States.,MIT Media Lab, Massachusetts Institute of Technology, Cambridge, MA, United States
| |
Collapse
|
|
14
|
Bertl K, Al-Hotheiry M, Sun D, Olofsson J, Lettner S, Gotfredsen K, Stavropoulos A. Are colored periodontal probes reliable to classify the gingival phenotype in terms of gingival thickness? J Periodontol 2021; 93:412-422. [PMID: 34309865 DOI: 10.1002/jper.21-0311] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2021] [Revised: 06/25/2021] [Accepted: 06/25/2021] [Indexed: 11/09/2022]
Abstract
BACKGROUND This cross-sectional study assessed the potential of colored periodontal probes (CPP) to classify gingival phenotype in terms of gingival thickness (GT). METHODS Buccal GT in 3 anterior teeth in each of 50 patients was measured by transgingival sounding and classified by 3 different methods by 8 examiners. Specifically, the diagnostic potential of visual judgement and transparency of a standard periodontal probe (SPP) to discriminate thin and thick gingiva, and of CPP to discriminate thin, medium, thick, or very thick gingiva was assessed. RESULTS GT ranged from 0.57-2.37mm. Using CPP resulted in a medium judgement in 87% of the cases, on average, and only between 1-10 cases/examiner were judged as thick or very thick. Considering 1mm GT as relevant cut-off value, all methods showed a high positive predictive value (≥0.82) to identify thick cases, but also a high false omission rate (≥0.73) indicating that many cases classified as thin were actually thick. Further, 88% of the cases being ≤1mm, were not classified as thin with CPP; this was inferior to SPP, for which, however, still 64% of the cases being ≤1mm thick were wrongly classified. The highest, yet moderate agreement among examiners was achieved by SPP (κ = 0.427), while visual judgement and CPP showed only fair (κ = 0.211) and slight agreement (κ = 0.112), respectively. CONCLUSION Using CPP resulted in most of the cases in a medium judgement. It seems that CPP cannot distinctly discriminate between "thick" and "very thick" cases and fails to capture the thin high-risk cases. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Kristina Bertl
- Department of Periodontology, Faculty of Odontology, University of Malmö, Sweden.,Division of Oral Surgery, University Clinic of Dentistry, Medical University of Vienna, Austria
| | - Mehdi Al-Hotheiry
- Department of Periodontology, Faculty of Odontology, University of Malmö, Sweden
| | - David Sun
- Department of Periodontology, Faculty of Odontology, University of Malmö, Sweden
| | - John Olofsson
- Department of Periodontology, Faculty of Odontology, University of Malmö, Sweden
| | - Stefan Lettner
- Karl Donath Laboratory for Hard Tissue and Biomaterial Research, Division of Oral Surgery, University Clinic of Dentistry, Medical University of Vienna, Austria.,Austrian Cluster for Tissue Regeneration, Vienna, Austria
| | - Klaus Gotfredsen
- Department of Oral Rehabilitation, School of Dentistry, Faculty of Health and Medical Sciences, University of Copenhagen, Denmark
| | - Andreas Stavropoulos
- Department of Periodontology, Faculty of Odontology, University of Malmö, Sweden.,Division of Regenerative Dentistry and Periodontology, University Clinics of Dental Medicine (CUMD), University of Geneva, Geneva, Switzerland.,Division of Conservative Dentistry and Periodontology, University Clinic of Dentistry, Medical University of Vienna, Vienna, Austria
| |
Collapse
|
|
15
|
Ying GS, Maguire MG, Glynn RJ, Rosner B. Tutorial on Biostatistics: Receiver-Operating Characteristic (ROC) Analysis for Correlated Eye Data. Ophthalmic Epidemiol 2021; 29:117-127. [PMID: 33977829 DOI: 10.1080/09286586.2021.1921226] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
Abstract
Purpose: To demonstrate methods for receiver-operating characteristic (ROC) analysis of correlated eye data.Methods: We applied the Obuchowski's nonparametric approach and cluster bootstrap for estimating and comparing the area under ROC curve (AUC) between different sets of predictors to three datasets with varying inter-eye correlation.Results: In an optic neuritis (ON) study of 152 eyes (80 patients), the AUC of optical coherence tomography retinal nerve fiber layer thickness for diagnosing ON (inter-eye kappa = 0.13) was 0.71 [95% confidence interval (95% CI): 0.622, 0.792] from the naïve approach without accounting for inter-eye correlation was narrower than from nonparametric (95% CI: 0.613, 0.801) or cluster bootstrap (95% CI: 0.614, 0.797) approaches. In an analysis of 198 eyes (135 patients), the baseline Age-related Eye disease Study scale predicted 5-year incidence of advanced age-related macular degeneration (inter-eye kappa = 0.23) with AUC of 0.72. The 95% CI from the naïve approach was slightly narrower (0.645, 0.794) than from the nonparametric (0.641, 0.797) or cluster bootstrap (0.641, 0.793) approaches. In an analysis of 1542 eyes (771 infants), birthweight and gestational age predicted treatment-requiring retinopathy of prematurity (inter-eye kappa = 0.98) with AUC of 0.80. Furthermore, the 95% CI from the naïve approach was narrower (0.769, 0.835) than from the nonparametric (0.755, 0.848) or cluster bootstrap (0.755, 0.845) approaches. 95% CIs for AUC differences between different models were narrower in the naïve approach than the nonparametric or cluster bootstrap approaches.Conclusion: In ROC analysis of correlated eye data, ignoring inter-eye correlation leads to narrower 95% CI with underestimation dependent on magnitude of inter-eye correlation. Nonparametric and cluster bootstrap approaches properly account for inter-eye correlation.
Collapse
Affiliation(s)
- Gui-Shuang Ying
- Center for Preventive Ophthalmology and Biostatistics, Department of Ophthalmology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Maureen G Maguire
- Center for Preventive Ophthalmology and Biostatistics, Department of Ophthalmology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Robert J Glynn
- Division of Preventive Medicine and the Channing Lab, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | - Bernard Rosner
- Division of Preventive Medicine and the Channing Lab, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA
| |
Collapse
|
|
16
|
McDonald ES, Romanoff J, Rahbar H, Kitsch AE, Harvey SM, Whisenant JG, Yankeelov TE, Moy L, DeMartini WB, Dogan BE, Yang WT, Wang LC, Joe BN, Wilmes LJ, Hylton NM, Oh KY, Tudorica LA, Neal CH, Malyarenko DI, Comstock CE, Schnall MD, Chenevert TL, Partridge SC. Mean Apparent Diffusion Coefficient Is a Sufficient Conventional Diffusion-weighted MRI Metric to Improve Breast MRI Diagnostic Performance: Results from the ECOG-ACRIN Cancer Research Group A6702 Diffusion Imaging Trial. Radiology 2021; 298:60-70. [PMID: 33201788 PMCID: PMC7771995 DOI: 10.1148/radiol.2020202465] [Citation(s) in RCA: 28] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2020] [Revised: 09/11/2020] [Accepted: 09/28/2020] [Indexed: 12/22/2022]
Abstract
Background The Eastern Cooperative Oncology Group and American College of Radiology Imaging Network Cancer Research Group A6702 multicenter trial helped confirm the potential of diffusion-weighted MRI for improving differential diagnosis of suspicious breast abnormalities and reducing unnecessary biopsies. A prespecified secondary objective was to explore the relative value of different approaches for quantitative assessment of lesions at diffusion-weighted MRI. Purpose To determine whether alternate calculations of apparent diffusion coefficient (ADC) can help further improve diagnostic performance versus mean ADC values alone for analysis of suspicious breast lesions at MRI. Materials and Methods This prospective trial (ClinicalTrials.gov identifier: NCT02022579) enrolled consecutive women (from March 2014 to April 2015) with a Breast Imaging Reporting and Data System category of 3, 4, or 5 at breast MRI. All study participants underwent standardized diffusion-weighted MRI (b = 0, 100, 600, and 800 sec/mm2). Centralized ADC measures were performed, including manually drawn whole-lesion and hotspot regions of interest, histogram metrics, normalized ADC, and variable b-value combinations. Diagnostic performance was estimated by using the area under the receiver operating characteristic curve (AUC). Reduction in biopsy rate (maintaining 100% sensitivity) was estimated according to thresholds for each ADC metric. Results Among 107 enrolled women, 81 lesions with outcomes (28 malignant and 53 benign) in 67 women (median age, 49 years; interquartile range, 41-60 years) were analyzed. Among ADC metrics tested, none improved diagnostic performance versus standard mean ADC (AUC, 0.59-0.79 vs AUC, 0.75; P = .02-.84), and maximum ADC had worse performance (AUC, 0.52; P < .001). The 25th-percentile ADC metric provided the best performance (AUC, 0.79; 95% CI: 0.70, 0.88), and a threshold using median ADC provided the greatest reduction in biopsy rate of 23.9% (95% CI: 14.8, 32.9; 16 of 67 BI-RADS category 4 and 5 lesions). Nonzero minimum b value (100, 600, and 800 sec/mm2) did not improve the AUC (0.74; P = .28), and several combinations of two b values (0 and 600, 100 and 600, 0 and 800, and 100 and 800 sec/mm2; AUC, 0.73-0.76) provided results similar to those seen with calculations of four b values (AUC, 0.75; P = .17-.87). Conclusion Mean apparent diffusion coefficient calculated with a two-b-value acquisition is a simple and sufficient diffusion-weighted MRI metric to augment diagnostic performance of breast MRI compared with more complex approaches to apparent diffusion coefficient measurement. © RSNA, 2020 Online supplemental material is available for this article.
Collapse
Affiliation(s)
- Elizabeth S. McDonald
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Justin Romanoff
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Habib Rahbar
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Averi E. Kitsch
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Sara M. Harvey
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Jennifer G. Whisenant
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Thomas E. Yankeelov
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Linda Moy
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Wendy B. DeMartini
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Basak E. Dogan
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Wei T. Yang
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Lilian C. Wang
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Bonnie N. Joe
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Lisa J. Wilmes
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Nola M. Hylton
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Karen Y. Oh
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Luminita A. Tudorica
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Colleen H. Neal
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Dariya I. Malyarenko
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Christopher E. Comstock
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Mitchell D. Schnall
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Thomas L. Chenevert
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| | - Savannah C. Partridge
- From the Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa (E.S.M., M.D.S.); Center for Statistical Sciences, Brown University, Providence, RI (J.R.); Department of Radiology, University of Washington, 1144 Eastlake Ave E, LG2-200, Seattle, WA 98109 (H.R., A.E.K., S.C.P.); Departments of Radiology and Radiological Sciences (S.M.H.) and Medicine (J.G.W.), Vanderbilt University Medical Center, Nashville, Tenn; Vanderbilt-Ingram Cancer Center, Nashville, Tenn (J.G.W.); Department of Biomedical Engineering, University of Texas, Austin, Tex (T.E.Y.); Department of Radiology, New York University School of Medicine, New York, NY (L.M.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (W.B.D.); Department of Diagnostic Radiology, University of Texas Southwestern Medical Center, Dallas, Tex (B.E.D.); Department of Breast Imaging, MD Anderson Cancer Center, Houston, Tex (W.T.Y.); Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Ill (L.C.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco School of Medicine, San Francisco, Calif (B.N.J., L.J.W., N.M.H.); Department of Radiology, Oregon Health and Science University, Portland, Ore (K.Y.O., L.A.T.); Department of Radiology/MRI, University of Michigan, Ann Arbor, Mich (C.H.N., D.I.M., T.L.C.); and Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (C.E.C.)
| |
Collapse
|
|
17
|
Whisenant JG, Romanoff J, Rahbar H, Kitsch AE, Harvey SM, Moy L, DeMartini WB, Dogan BE, Yang WT, Wang LC, Joe BN, Wilmes LJ, Hylton NM, Oh KY, Tudorica LA, Neal CH, Malyarenko DI, McDonald ES, Comstock CE, Yankeelov TE, Chenevert TL, Partridge SC. Factors Affecting Image Quality and Lesion Evaluability in Breast Diffusion-weighted MRI: Observations from the ECOG-ACRIN Cancer Research Group Multisite Trial (A6702). JOURNAL OF BREAST IMAGING 2021; 3:44-56. [PMID: 33543122 PMCID: PMC7835633 DOI: 10.1093/jbi/wbaa103] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2020] [Indexed: 12/27/2022]
Abstract
OBJECTIVE The A6702 multisite trial confirmed that apparent diffusion coefficient (ADC) measures can improve breast MRI accuracy and reduce unnecessary biopsies, but also found that technical issues rendered many lesions non-evaluable on diffusion-weighted imaging (DWI). This secondary analysis investigated factors affecting lesion evaluability and impact on diagnostic performance. METHODS The A6702 protocol was IRB-approved at 10 institutions; participants provided informed consent. In total, 103 women with 142 MRI-detected breast lesions (BI-RADS assessment category 3, 4, or 5) completed the study. DWI was acquired at 1.5T and 3T using a four b-value, echo-planar imaging sequence. Scans were reviewed for multiple quality factors (artifacts, signal-to-noise, misregistration, and fat suppression); lesions were considered non-evaluable if there was low confidence in ADC measurement. Associations of lesion evaluability with imaging and lesion characteristics were determined. Areas under the receiver operating characteristic curves (AUCs) were compared using bootstrapping. RESULTS Thirty percent (42/142) of lesions were non-evaluable on DWI; 23% (32/142) with image quality issues, 7% (10/142) with conspicuity and/or localization issues. Misregistration was the only factor associated with non-evaluability (P = 0.001). Smaller (≤10 mm) lesions were more commonly non-evaluable than larger lesions (p <0.03), though not significant after multiplicity correction. The AUC for differentiating benign and malignant lesions increased after excluding non-evaluable lesions, from 0.61 (95% CI: 0.50-0.71) to 0.75 (95% CI: 0.65-0.84). CONCLUSION Image quality remains a technical challenge in breast DWI, particularly for smaller lesions. Protocol optimization and advanced acquisition and post-processing techniques would help to improve clinical utility.
Collapse
Affiliation(s)
- Jennifer G Whisenant
- Vanderbilt University Medical Center, Department of Medicine, Nashville, TN
- Vanderbilt-Ingram Cancer Center, Nashville, TN
| | - Justin Romanoff
- Brown University, Center for Statistical Sciences, Providence, RI
| | - Habib Rahbar
- University of Washington, Department of Radiology, Seattle, WA
| | - Averi E Kitsch
- University of Washington, Department of Radiology, Seattle, WA
| | - Sara M Harvey
- Vanderbilt University Medical Center, Department of Radiology and Radiological Sciences, Nashville, TN
| | - Linda Moy
- New York University School of Medicine, Department of Radiology, New York, NY
| | - Wendy B DeMartini
- Stanford University School of Medicine, Department of Radiology, Stanford, CA
| | - Basak E Dogan
- University of Texas Southwestern Medical Center, Department of Diagnostic Radiology, Dallas, TX
| | - Wei T Yang
- MD Anderson Cancer Center, Department of Breast Imaging, Houston, TX
| | - Lilian C Wang
- Northwestern University Feinberg School of Medicine, Department of Radiology, Chicago, IL
| | - Bonnie N Joe
- University of California San Francisco School of Medicine, Department of Radiology and Biomedical Engineering, San Francisco, CA
| | - Lisa J Wilmes
- University of California San Francisco School of Medicine, Department of Radiology and Biomedical Engineering, San Francisco, CA
| | - Nola M Hylton
- University of California San Francisco School of Medicine, Department of Radiology and Biomedical Engineering, San Francisco, CA
| | - Karen Y Oh
- Oregon Health and Science University, Department of Radiology, Portland, OR
| | | | - Colleen H Neal
- University of Michigan, Department of Radiology/MRI, Ann Arbor, MI
| | | | - Elizabeth S McDonald
- University of Pennsylvania Perelman School of Medicine, Department of Radiology, Philadelphia, PA
| | | | - Thomas E Yankeelov
- University of Texas Austin, Department of Biomedical Engineering, Austin, TX
| | | | | |
Collapse
|
|
18
|
Feng Q, Song Q, Zhang L, Zheng S, Pan J. Integration of Moderation and Mediation in a Latent Variable Framework: A Comparison of Estimation Approaches for the Second-Stage Moderated Mediation Model. Front Psychol 2020; 11:2167. [PMID: 33013556 PMCID: PMC7511593 DOI: 10.3389/fpsyg.2020.02167] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2020] [Accepted: 08/03/2020] [Indexed: 11/23/2022] Open
Abstract
An increasing number of studies have focused on models that integrate moderation and mediation. Four approaches can be used to test integrated mediation and moderation models: path analysis (PA), product indicator analysis (PI, constrained approach and unconstrained approach), and latent moderated structural equations (LMS). To the best of our knowledge, few studies have compared the performances of PA, PI, and LMS in evaluating integrated mediation and moderation models. As a result, it is difficult for applied researchers to choose an appropriate method in their data analysis. This study investigates the performance of different approaches in analyzing the models, using the second-stage moderated mediation model as a representative model to be evaluated. Four approaches with bootstrapped standard errors are compared under different conditions. Moreover, LMS with robust standard errors and Bayesian estimation of LMS and PA were also considered. Results indicated that LMS with robust standard errors is the superior evaluation method in all study settings. And PA estimates could be severely underestimated as they ignore measurement errors. Furthermore, it is found that the constrained PI and unconstrained PI only provide acceptable estimates when the multivariate normal distribution assumption is satisfied. The practical guidelines were also provided to illustrate the implementation of LMS. This study could help to extend the application of LMS in psychology and social science research.
Collapse
Affiliation(s)
- Qingqing Feng
- Department of Psychology, Sun Yat-sen University, Guangzhou, China
| | - Qiongya Song
- Department of Psychology, Sun Yat-sen University, Guangzhou, China
| | - Lijin Zhang
- Department of Psychology, Sun Yat-sen University, Guangzhou, China
| | - Shufang Zheng
- Department of Psychology, Sun Yat-sen University, Guangzhou, China
| | - Junhao Pan
- Department of Psychology, Sun Yat-sen University, Guangzhou, China
| |
Collapse
|
|
19
|
Hossen Z, Abrar MA, Ara SR, Hasan MK. RATE-iPATH: On the design of integrated ultrasonic biomarkers for breast cancer detection. Biomed Signal Process Control 2020. [DOI: 10.1016/j.bspc.2020.102053] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
|
20
|
Kim K, Kim S, Lee YH, Lee SH, Lee HS, Kim S. Performance of the deep convolutional neural network based magnetic resonance image scoring algorithm for differentiating between tuberculous and pyogenic spondylitis. Sci Rep 2018; 8:13124. [PMID: 30177857 PMCID: PMC6120953 DOI: 10.1038/s41598-018-31486-3] [Citation(s) in RCA: 36] [Impact Index Per Article: 5.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2018] [Accepted: 08/20/2018] [Indexed: 12/16/2022] Open
Abstract
The purpose of this study was to evaluate the performance of the deep convolutional neural network (DCNN) in differentiating between tuberculous and pyogenic spondylitis on magnetic resonance (MR) imaging, compared to the performance of three skilled radiologists. This clinical retrospective study used spine MR images of 80 patients with tuberculous spondylitis and 81 patients with pyogenic spondylitis that was bacteriologically and/or histologically confirmed from January 2007 to December 2016. Supervised training and validation of the DCNN classifier was performed with four-fold cross validation on a patient-level independent split. The object detection and classification model was implemented as a DCNN and was designed to calculate the deep-learning scores of individual patients to reach a conclusion. Three musculoskeletal radiologists blindly interpreted the images. The diagnostic performances of the DCNN classifier and of the three radiologists were expressed as receiver operating characteristic (ROC) curves, and the areas under the ROC curves (AUCs) were compared using a bootstrap resampling procedure. When comparing the AUC value of the DCNN classifier (0.802) with the pooled AUC value of the three readers (0.729), there was no significant difference (P = 0.079). In differentiating between tuberculous and pyogenic spondylitis using MR images, the performance of the DCNN classifier was comparable to that of three skilled radiologists.
Collapse
Affiliation(s)
- Kiwook Kim
- Department of Radiology, Gangnam Severance Hospital, Yonsei University College of Medicine, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Seoul, South Korea
| | - Sungwon Kim
- Department of Radiology, Severance Hospital, Yonsei University College of Medicine, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Seoul, South Korea
| | - Young Han Lee
- Department of Radiology, Severance Hospital, Yonsei University College of Medicine, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Seoul, South Korea
| | - Seung Hyun Lee
- Department of Radiology, National Health Insurance Service Ilsan Hospital, Goyang-si, Gyeonggi-do, South Korea
| | - Hye Sun Lee
- Biostatistics Collaboration Unit, Research Center for Future Medicine, Yonsei University College of Medicine, Seoul, South Korea
| | - Sungjun Kim
- Department of Radiology, Gangnam Severance Hospital, Yonsei University College of Medicine, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Seoul, South Korea.
| |
Collapse
|
|
21
|
Bandos AI, Obuchowski NA. Evaluation of diagnostic accuracy in free-response detection-localization tasks using ROC tools. Stat Methods Med Res 2018; 28:1808-1825. [DOI: 10.1177/0962280218776683] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Diagnostic systems designed to detect possibly multiple lesions per patient (e.g. multiple polyps during CT colonoscopy) are often evaluated in “free-response” studies that allow for diagnostic responses unconstrained in their number and locations. Analysis of free-response studies requires extensions of the traditional receiver operating characteristic (ROC) analysis, which are termed free-response ROC (FROC) methodology. Despite substantial developments in this area, FROC tools and approaches are much more cumbersome than traditional ROC methods. Alternative approaches that use well-known ROC tools (e.g. ROI-ROC) require defining and physically delineating regions of interest (ROI) and combine FROC data within ROIs. We propose an approach that allows analyzing FROC data using conventional ROC tools without delineating the actual ROIs or reducing data. The design parameters of FROC study are used to make FROC data analyzable using ROC tools and to calibrate the corresponding FROC and ROC curves on both conceptual and numerical levels. Differences in the performance indices of the nonparametric FROC and the new approach are shown to be asymptotically negligible and typically rather small in practice. Data from a large multi-reader study of colon cancer detection are used to illustrate the new approach.
Collapse
Affiliation(s)
- Andriy I Bandos
- Department of Biostatistics, Graduate School of Public Health, University of Pittsburgh, Pittsburgh, PA, USA
| | - Nancy A Obuchowski
- Quantitative Health Sciences, Cleveland Clinic Foundation, Cleveland, OH, USA
| |
Collapse
|
|
22
|
Jambor I, Kuisma A, Kähkönen E, Kemppainen J, Merisaari H, Eskola O, Teuho J, Perez IM, Pesola M, Aronen HJ, Boström PJ, Taimen P, Minn H. Prospective evaluation of 18F-FACBC PET/CT and PET/MRI versus multiparametric MRI in intermediate- to high-risk prostate cancer patients (FLUCIPRO trial). Eur J Nucl Med Mol Imaging 2017; 45:355-364. [PMID: 29147764 DOI: 10.1007/s00259-017-3875-1] [Citation(s) in RCA: 54] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2017] [Accepted: 11/03/2017] [Indexed: 12/31/2022]
Abstract
PURPOSE The purpose of this study was to evaluate 18F-FACBC PET/CT, PET/MRI, and multiparametric MRI (mpMRI) in detection of primary prostate cancer (PCa). METHODS Twenty-six men with histologically confirmed PCa underwent PET/CT immediately after injection of 369 ± 10 MBq 18F-FACBC (fluciclovine) followed by PET/MRI started 55 ± 7 min from injection. Maximum standardized uptake values (SUVmax) were measured for both hybrid PET acquisitions. A separate mpMRI was acquired within a week of the PET scans. Logan plots were used to calculate volume of distribution (VT). The presence of PCa was estimated in 12 regions with radical prostatectomy findings as ground truth. For each imaging modality, area under the curve (AUC) for detection of PCa was determined to predict diagnostic performance. The clinical trial registration number is NCT02002455. RESULTS In the visual analysis, 164/312 (53%) regions contained PCa, and 41 tumor foci were identified. PET/CT demonstrated the highest sensitivity at 87% while its specificity was low at 56%. The AUC of both PET/MRI and mpMRI significantly (p < 0.01) outperformed that of PET/CT while no differences were detected between PET/MRI and mpMRI. SUVmax and VT of Gleason score (GS) >3 + 4 tumors were significantly (p < 0.05) higher than those for GS 3 + 3 and benign hyperplasia. A total of 442 lymph nodes were evaluable for staging, and PET/CT and PET/MRI demonstrated true-positive findings in only 1/7 patients with metastatic lymph nodes. CONCLUSIONS Quantitative 18F-FACBC imaging significantly correlated with GS but failed to outperform MRI in lesion detection. 18F-FACBC may assist in targeted biopsies in the setting of hybrid imaging with MRI.
Collapse
Affiliation(s)
- Ivan Jambor
- Department of Diagnostic Radiology, University of Turku, Kiinamyllynkatu 4-8, P.O. Box 52, FI-20521, Turku, Finland.
- Department of Radiology, University of Massachusetts Medical School - Baystate, Springfield, MA, USA.
- Turku PET Centre, Turku, Finland.
| | - Anna Kuisma
- Department of Oncology and Radiotherapy, Turku University Hospital, Turku, Finland
| | - Esa Kähkönen
- Department of Urology, Turku University Hospital, Turku, Finland
| | - Jukka Kemppainen
- Turku PET Centre, Turku, Finland
- Department of Clinical Physiology and Nuclear Medicine, Turku University Hospital, Turku, Finland
| | - Harri Merisaari
- Department of Diagnostic Radiology, University of Turku, Kiinamyllynkatu 4-8, P.O. Box 52, FI-20521, Turku, Finland
- Turku PET Centre, Turku, Finland
- Department of Information Technology, University of Turku, Turku, Finland
| | | | | | - Ileana Montoya Perez
- Department of Diagnostic Radiology, University of Turku, Kiinamyllynkatu 4-8, P.O. Box 52, FI-20521, Turku, Finland
- Department of Information Technology, University of Turku, Turku, Finland
- Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Marko Pesola
- Department of Diagnostic Radiology, University of Turku, Kiinamyllynkatu 4-8, P.O. Box 52, FI-20521, Turku, Finland
| | - Hannu J Aronen
- Department of Diagnostic Radiology, University of Turku, Kiinamyllynkatu 4-8, P.O. Box 52, FI-20521, Turku, Finland
- Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Peter J Boström
- Department of Urology, Turku University Hospital, Turku, Finland
| | - Pekka Taimen
- Department of Pathology, University of Turku and Turku University Hospital, Turku, Finland
| | - Heikki Minn
- Turku PET Centre, Turku, Finland
- Department of Oncology and Radiotherapy, Turku University Hospital, Turku, Finland
| |
Collapse
|
|
23
|
Nicolas C, Le Gouge A, d’Alteroche L, Ayoub J, Georgescu M, Vidal V, Castaing D, Cercueil JP, Chevallier P, Roumy J, Trillaud H, Boyer L, Le Pennec V, Perret C, Giraudeau B, Perarnau JM, STIC-TIPS group. Evaluation of Doppler-ultrasonography in the diagnosis of transjugular intrahepatic portosystemic shunt dysfunction: A prospective study. World J Hepatol 2017; 9:1125-1132. [PMID: 29026464 PMCID: PMC5620422 DOI: 10.4254/wjh.v9.i27.1125] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/28/2017] [Revised: 08/24/2017] [Accepted: 09/05/2017] [Indexed: 02/06/2023] Open
Abstract
AIM To prospectively evaluate the performance of Doppler-ultrasonography (US) for the detection of transjugular intrahepatic portosystemic shunt (TIPS) dysfunction within a multicenter cohort of cirrhotic patients.
METHODS This study was conducted in 10 french teaching hospitals. After TIPS insertion, angiography and liver Doppler-US were carried out every six months to detect dysfunction (defined by a portosystemic gradient ≥ 12 mmHg and/or a stent stenosis ≥ 50%). The association between ultrasonographic signs and dysfunction was studied by logistic random-effects models, and the diagnostic performance of each Doppler criterion was estimated by the bootstrap method. This study was approved by the ethics committee of Tours.
RESULTS Two hundred and eighteen pairs of examinations performed on 87 cirrhotic patients were analyzed. Variables significantly associated with dysfunction were: The speed of flow in the portal vein (P = 0.008), the reversal of flow in the right (P = 0.038) and left (P = 0.049) portal branch, the loss of modulation of portal flow by the right atrium (P = 0.0005), ascites (P = 0.001) and the overall impression of the operator (P = 0.0001). The diagnostic performances of these variables were low; sensitivity was < 58% and negative predictive value was < 73%. Therefore, dysfunction cannot be ruled out from Doppler-US.
CONCLUSION The performance of Doppler-US for the detection of TIPS dysfunction is poor compared to angiography. New tools are needed to improve diagnosis of TIPS dysfunction.
Collapse
Affiliation(s)
- Charlotte Nicolas
- Service d’Hépato-Gastroentérologie, Hôpital Trousseau, CHRU Tours, 37044 Tours, France
| | - Amélie Le Gouge
- CIC, CHRU de Tours, 37044 Tours, France
- INSERM, CIC 202, 37044 Tours, France
| | - Louis d’Alteroche
- Service d’Hépato-Gastroentérologie, Hôpital Trousseau, CHRU Tours, 37044 Tours, France
| | - Jean Ayoub
- Unité d’échographie-doppler, Hôpital Trousseau, CHRU Tours, 37044 Tours, France
| | - Monica Georgescu
- Unité d’échographie-doppler, Hôpital Trousseau, CHRU Tours, 37044 Tours, France
| | - Vincent Vidal
- Service de Radiologie, Hôpital de la Timone, 13385 Marseille, France
| | - Denis Castaing
- Centre Hépato-Biliaire, Hôpital Paul Brousse, 94800 Villejuif, France
| | | | - Patrick Chevallier
- Service d’Imagerie Médicale Diagnostique et interventionnelle Hôpital de l’Archet II Nice, 06200 Nice, France
| | - Jérôme Roumy
- Service de Radiologie et Echographie, CHRU Poitiers, 86021 Poitiers, France
| | - Hervé Trillaud
- Service d’Imagerie Médicale Hôpital Saint André, CHRU Bordeaux, 33000 Bordeaux, France
| | - Louis Boyer
- Service d’Imagerie viscérale et vasculaire, CHRU Clermont Ferrand, 63003 Clermont Ferrand, France
| | | | | | - Bruno Giraudeau
- CIC, CHRU de Tours, 37044 Tours, France
- INSERM, CIC 202, 37044 Tours, France
| | - Jean-Marc Perarnau
- Service d’Hépato-Gastroentérologie, Hôpital Trousseau, CHRU Tours, 37044 Tours, France
| | | |
Collapse
|
|
24
|
Early Detection and Serial Monitoring of Anthracycline-Induced Cardiotoxicity Using T1-mapping Cardiac Magnetic Resonance Imaging: An Animal Study. Sci Rep 2017; 7:2663. [PMID: 28572614 PMCID: PMC5453985 DOI: 10.1038/s41598-017-02627-x] [Citation(s) in RCA: 44] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2016] [Accepted: 04/13/2017] [Indexed: 11/26/2022] Open
Abstract
A reliable, non-invasive diagnostic method is needed for early detection and serial monitoring of cardiotoxicity, a well-known side effect of chemotherapy. This study aimed to assess the feasibility of T1-mapping cardiac magnetic resonance imaging (CMR) for evaluating subclinical myocardial changes in a doxorubicin-induced cardiotoxicity rabbit model. Adult male New Zealand White rabbits were injected twice-weekly with doxorubicin and subjected to CMR on a clinical 3T MR system before and every 2–4 weeks post-drug administration. Native T1 and extracellular volume (ECV) values were measured at six mid-left ventricle (LV) and specific LV lesions. Histological assessments evaluated myocardial injury and fibrosis. Three pre-model and 11 post-model animals were included. Myocardial injury was observed from 3 weeks. Mean LV myocardium ECV values increased significantly from week 3 before LV ejection fraction decreases (week 6), and ECVs of the RV upper/lower insertion sites and papillary muscle exceeded those of the LV. The mean native T1 value in the mid-LV increased significantly increased from week 6, and LV myocardium ECV correlated strongly with the degree of fibrosis (r = 0.979, p < 0.001). Myocardial T1 mapping, particularly ECV values, reliably and non-invasively detected early cardiotoxicity, allowing serial monitoring of chemotherapy-induced cardiotoxicity.
Collapse
|
|
25
|
Hogeweg L, Sánchez CI, Maduskar P, Philipsen RH, van Ginneken B. Fast and effective quantification of symmetry in medical images for pathology detection: Application to chest radiography. Med Phys 2017; 44:2242-2256. [DOI: 10.1002/mp.12127] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2016] [Revised: 01/13/2017] [Accepted: 01/15/2017] [Indexed: 11/10/2022] Open
Affiliation(s)
- Laurens Hogeweg
- Diagnostic Image Analysis Group; Radboud University Medical Center; Nijmegen 6521GA The Netherlands
| | - Clara I. Sánchez
- Diagnostic Image Analysis Group; Radboud University Medical Center; Nijmegen 6521GA The Netherlands
| | - Pragnya Maduskar
- Diagnostic Image Analysis Group; Radboud University Medical Center; Nijmegen 6521GA The Netherlands
| | - Rick H.H.M. Philipsen
- Diagnostic Image Analysis Group; Radboud University Medical Center; Nijmegen 6521GA The Netherlands
| | - Bram van Ginneken
- Diagnostic Image Analysis Group; Radboud University Medical Center; Nijmegen 6521GA The Netherlands
| |
Collapse
|
|
26
|
Affiliation(s)
| | - Jennifer A. Bullen
- Quantitative Health Sciences, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Nancy A. Obuchowski
- Quantitative Health Sciences, Cleveland Clinic Foundation, Cleveland, OH, USA
| |
Collapse
|
|
27
|
Melendez J, Sánchez CI, Philipsen RHHM, Maduskar P, Dawson R, Theron G, Dheda K, van Ginneken B. An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information. Sci Rep 2016; 6:25265. [PMID: 27126741 PMCID: PMC4850474 DOI: 10.1038/srep25265] [Citation(s) in RCA: 54] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2015] [Accepted: 04/13/2016] [Indexed: 11/09/2022] Open
Abstract
Lack of human resources and radiological interpretation expertise impair tuberculosis (TB) screening programmes in TB-endemic countries. Computer-aided detection (CAD) constitutes a viable alternative for chest radiograph (CXR) reading. However, no automated techniques that exploit the additional clinical information typically available during screening exist. To address this issue and optimally exploit this information, a machine learning-based combination framework is introduced. We have evaluated this framework on a database containing 392 patient records from suspected TB subjects prospectively recruited in Cape Town, South Africa. Each record comprised a CAD score, automatically computed from a CXR, and 12 clinical features. Comparisons with strategies relying on either CAD scores or clinical information alone were performed. Our results indicate that the combination framework outperforms the individual strategies in terms of the area under the receiving operating characteristic curve (0.84 versus 0.78 and 0.72), specificity at 95% sensitivity (49% versus 24% and 31%) and negative predictive value (98% versus 95% and 96%). Thus, it is believed that combining CAD and clinical information to estimate the risk of active disease is a promising tool for TB screening.
Collapse
Affiliation(s)
- Jaime Melendez
- Department of Radiology and Nuclear Medicine, Radboud university medical center, Nijmegen, Gelderland, the Netherlands
| | - Clara I. Sánchez
- Department of Radiology and Nuclear Medicine, Radboud university medical center, Nijmegen, Gelderland, the Netherlands
| | - Rick H. H. M. Philipsen
- Department of Radiology and Nuclear Medicine, Radboud university medical center, Nijmegen, Gelderland, the Netherlands
| | - Pragnya Maduskar
- Department of Radiology and Nuclear Medicine, Radboud university medical center, Nijmegen, Gelderland, the Netherlands
| | - Rodney Dawson
- Lung Infection and Immunity Unit, Division of Pulmonology and UCT Lung Institute, University of Cape Town, Cape Town, Western Cape, South Africa
| | - Grant Theron
- Lung Infection and Immunity Unit, Division of Pulmonology and UCT Lung Institute, University of Cape Town, Cape Town, Western Cape, South Africa
- DST/NRF of Excellence for Biomedical Tuberculosis Research, and MRC Centre for Molecular and Cellular Biology, Division of Molecular Biology and Human Genetics, Faculty of Medicine and Health Sciences, Stellenbosch University, Tygerberg, South Africa
| | - Keertan Dheda
- Lung Infection and Immunity Unit, Division of Pulmonology and UCT Lung Institute, University of Cape Town, Cape Town, Western Cape, South Africa
| | - Bram van Ginneken
- Department of Radiology and Nuclear Medicine, Radboud university medical center, Nijmegen, Gelderland, the Netherlands
| |
Collapse
|
|
28
|
Ciompi F, de Hoop B, van Riel SJ, Chung K, Scholten ET, Oudkerk M, de Jong PA, Prokop M, van Ginneken B. Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box. Med Image Anal 2015; 26:195-202. [PMID: 26458112 DOI: 10.1016/j.media.2015.08.001] [Citation(s) in RCA: 146] [Impact Index Per Article: 14.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2015] [Revised: 07/05/2015] [Accepted: 08/10/2015] [Indexed: 01/11/2023]
Abstract
In this paper, we tackle the problem of automatic classification of pulmonary peri-fissural nodules (PFNs). The classification problem is formulated as a machine learning approach, where detected nodule candidates are classified as PFNs or non-PFNs. Supervised learning is used, where a classifier is trained to label the detected nodule. The classification of the nodule in 3D is formulated as an ensemble of classifiers trained to recognize PFNs based on 2D views of the nodule. In order to describe nodule morphology in 2D views, we use the output of a pre-trained convolutional neural network known as OverFeat. We compare our approach with a recently presented descriptor of pulmonary nodule morphology, namely Bag of Frequencies, and illustrate the advantages offered by the two strategies, achieving performance of AUC = 0.868, which is close to the one of human experts.
Collapse
Affiliation(s)
- Francesco Ciompi
- Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands.
| | | | - Sarah J van Riel
- Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Kaman Chung
- Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Ernst Th Scholten
- Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands
| | | | | | - Mathias Prokop
- Department of Radiology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Bram van Ginneken
- Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands; Fraunhofer Mevis, Bremen, Germany
| |
Collapse
|
|
29
|
Jambor I, Kuisma A, Ramadan S, Huovinen R, Sandell M, Kajander S, Kemppainen J, Kauppila E, Auren J, Merisaari H, Saunavaara J, Noponen T, Minn H, Aronen HJ, Seppänen M. Prospective evaluation of planar bone scintigraphy, SPECT, SPECT/CT, 18F-NaF PET/CT and whole body 1.5T MRI, including DWI, for the detection of bone metastases in high risk breast and prostate cancer patients: SKELETA clinical trial. Acta Oncol 2015; 55:59-67. [PMID: 25833330 DOI: 10.3109/0284186x.2015.1027411] [Citation(s) in RCA: 135] [Impact Index Per Article: 13.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
PURPOSE Detection of bone metastases in breast and prostate cancer patients remains a major clinical challenge. The aim of the current trial was to compare the diagnostic accuracy of (99m)Tc-hydroxymethane diphosphonate ((99m)Tc-HDP) planar bone scintigraphy (BS), (99m)Tc-HDP SPECT, (99m)Tc-HDP SPECT/CT, (18)F-NaF PET/CT and whole body 1.5 Tesla magnetic resonance imaging (MRI), including diffusion weighted imaging, (wbMRI+DWI) for the detection of bone metastases in high risk breast and prostate cancer patients. MATERIAL AND METHODS Twenty-six breast and 27 prostate cancer patients at high risk of bone metastases underwent (99m)Tc-HDP BS, (99m)Tc-HDP SPECT, (99m)Tc-HDP SPECT/CT, (18)F-NaF PET/CT and wbMRI+DWI. Five independent reviewers interpreted each individual modality without the knowledge of other imaging findings. The final metastatic status was based on the consensus reading, clinical and imaging follow-up (minimal and maximal follow-up time was 6, and 32 months, respectively). The bone findings were compared on patient-, region-, and lesion-level. RESULTS (99m)Tc-HDP BS was false negative in four patients. In the region-based analysis, sensitivity values for (99m)Tc-HDP BS, (99m)Tc-HDP SPECT, (99m)Tc-HDP SPECT/CT, (18)F-NaF PET/CT, and wbMRI+DWI were 62%, 74%, 85%, 93%, and 91%, respectively. The number of equivocal findings for (99m)Tc-HDP BS, (99m)Tc-HDP SPECT, (99m)Tc-HDP SPECT/CT, (18)F-NaF PET/CT and wbMRI+DWI was 50, 44, 5, 6, and 4, respectively. CONCLUSION wbMRI+DWI showed similar diagnostic accuracy to (18)F-NaF PET/CT and outperformed (99m)Tc-HDP SPECT/CT, and (99m)Tc-HDP BS.
Collapse
Affiliation(s)
- Ivan Jambor
- Department of Diagnostic Radiology, University of Turku, Turku, Finland
| | - Anna Kuisma
- Department of Oncology and Radiotherapy, University of Turku, Turku, Finland
| | - Susan Ramadan
- Department of Oncology and Radiotherapy, University of Turku, Turku, Finland
| | - Riikka Huovinen
- Department of Oncology and Radiotherapy, University of Turku, Turku, Finland
| | - Minna Sandell
- Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | | | | | - Esa Kauppila
- Department of Clinical Physiology and Nuclear Medicine, North-Karelia Central Hospital, Joensuu, Finland
| | - Joakim Auren
- Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | | | - Jani Saunavaara
- Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Tommi Noponen
- Department of Clinical Physiology and Nuclear Medicine, Turku University Hospital, Turku, Finland
| | - Heikki Minn
- Department of Oncology and Radiotherapy, University of Turku, Turku, Finland
- Turku PET Centre, Turku, Finland
| | - Hannu J. Aronen
- Department of Diagnostic Radiology, University of Turku, Turku, Finland
- Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Marko Seppänen
- Turku PET Centre, Turku, Finland
- Department of Clinical Physiology and Nuclear Medicine, Turku University Hospital, Turku, Finland
| |
Collapse
|
|
30
|
Jambor I, Kähkönen E, Taimen P, Merisaari H, Saunavaara J, Alanen K, Obsitnik B, Minn H, Lehotska V, Aronen HJ. Prebiopsy multiparametric 3T prostate MRI in patients with elevated PSA, normal digital rectal examination, and no previous biopsy. J Magn Reson Imaging 2014; 41:1394-404. [PMID: 24956412 DOI: 10.1002/jmri.24682] [Citation(s) in RCA: 44] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2014] [Accepted: 06/06/2014] [Indexed: 12/22/2022] Open
Abstract
PURPOSE To find the diagnostic accuracy of 3T multiparametric magnetic resonance imaging (mpMRI) and mpMRI targeted transrectal ultrasound (TRUS)-guided biopsy using visual coregistration (TB) in patients with elevated prostate-specific antigen (PSA), normal digital rectal examination, and no previous biopsy. MATERIALS AND METHODS Fifty-five patients at two institutions underwent mpMRI, consisting of anatomical T2 -weighted imaging (T2 W), diffusion-weighted imaging (DWI), proton magnetic resonance spectroscopy ((1) H-MRS), and dynamic contrast-enhanced MRI (DCE-MRI), followed by TB in addition to 12 core systematic TRUS-guided biopsy (SB). Histopathological scorings of biopsy (n = 38) and prostatectomy (n = 17) specimens were used as the reference standard for calculation of diagnostic accuracy values. Clinically significant prostate cancer (SPCa) was defined as 3 mm core length of Gleason score 3+3 or any Gleason grade 4. RESULTS The sensitivity, specificity, accuracy, and area under the curve (AUC) values for the detection of SPCa on the sextant level for T2 W+DWI+(1) H-MRS+DCE-MRI were 72%, 89%, 85%, and 0.81, respectively. The corresponding values for T2 wi+DWI were 61%, 96%, 87%, and 0.79, respectively. The overall PCa detection rate per core in 53 patients was 21% (138 of 648 cores) for SB and 43% (33 of 77 cores) for TB (P < 0.001). CONCLUSION Prebiopsy mpMRI is an accurate tool for PCa detection and biopsy targeting in patients with elevated PSA.
Collapse
Affiliation(s)
- Ivan Jambor
- Department of Diagnostic Radiology, University of Turku, Turku, Finland
| | | | | | | | | | | | | | | | | | | |
Collapse
|
|
31
|
Petrick N, Sahiner B, Armato SG, Bert A, Correale L, Delsanto S, Freedman MT, Fryd D, Gur D, Hadjiiski L, Huo Z, Jiang Y, Morra L, Paquerault S, Raykar V, Samuelson F, Summers RM, Tourassi G, Yoshida H, Zheng B, Zhou C, Chan HP. Evaluation of computer-aided detection and diagnosis systems. Med Phys 2014; 40:087001. [PMID: 23927365 DOI: 10.1118/1.4816310] [Citation(s) in RCA: 65] [Impact Index Per Article: 5.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/09/2023] Open
Abstract
Computer-aided detection and diagnosis (CAD) systems are increasingly being used as an aid by clinicians for detection and interpretation of diseases. Computer-aided detection systems mark regions of an image that may reveal specific abnormalities and are used to alert clinicians to these regions during image interpretation. Computer-aided diagnosis systems provide an assessment of a disease using image-based information alone or in combination with other relevant diagnostic data and are used by clinicians as a decision support in developing their diagnoses. While CAD systems are commercially available, standardized approaches for evaluating and reporting their performance have not yet been fully formalized in the literature or in a standardization effort. This deficiency has led to difficulty in the comparison of CAD devices and in understanding how the reported performance might translate into clinical practice. To address these important issues, the American Association of Physicists in Medicine (AAPM) formed the Computer Aided Detection in Diagnostic Imaging Subcommittee (CADSC), in part, to develop recommendations on approaches for assessing CAD system performance. The purpose of this paper is to convey the opinions of the AAPM CADSC members and to stimulate the development of consensus approaches and "best practices" for evaluating CAD systems. Both the assessment of a standalone CAD system and the evaluation of the impact of CAD on end-users are discussed. It is hoped that awareness of these important evaluation elements and the CADSC recommendations will lead to further development of structured guidelines for CAD performance assessment. Proper assessment of CAD system performance is expected to increase the understanding of a CAD system's effectiveness and limitations, which is expected to stimulate further research and development efforts on CAD technologies, reduce problems due to improper use, and eventually improve the utility and efficacy of CAD in clinical practice.
Collapse
Affiliation(s)
- Nicholas Petrick
- Center for Devices and Radiological Health, U.S. Food and Drug Administration, 10903 New Hampshire Avenue, Silver Spring, Maryland 20993, USA
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
|
32
|
Wang S, Kim SJ, Poptani H, Woo JH, Mohan S, Jin R, Voluck MR, O'Rourke DM, Wolf RL, Melhem ER, Kim S. Diagnostic utility of diffusion tensor imaging in differentiating glioblastomas from brain metastases. AJNR Am J Neuroradiol 2014; 35:928-34. [PMID: 24503556 DOI: 10.3174/ajnr.a3871] [Citation(s) in RCA: 47] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
BACKGROUND AND PURPOSE Differentiation of glioblastomas and solitary brain metastases is an important clinical problem because the treatment strategy can differ significantly. The purpose of this study was to investigate the potential added value of DTI metrics in differentiating glioblastomas from brain metastases. MATERIALS AND METHODS One hundred twenty-eight patients with glioblastomas and 93 with brain metastases were retrospectively identified. Fractional anisotropy and mean diffusivity values were measured from the enhancing and peritumoral regions of the tumor. Two experienced neuroradiologists independently rated all cases by using conventional MR imaging and DTI. The diagnostic performances of the 2 raters and a DTI-based model were assessed individually and combined. RESULTS The fractional anisotropy values from the enhancing region of glioblastomas were significantly higher than those of brain metastases (P < .01). There was no difference in mean diffusivity between the 2 tumor types. A classification model based on fractional anisotropy and mean diffusivity from the enhancing regions differentiated glioblastomas from brain metastases with an area under the receiver operating characteristic curve of 0.86, close to those obtained by 2 neuroradiologists using routine clinical images and DTI parameter maps (area under the curve = 0.90 and 0.85). The areas under the curve of the 2 radiologists were further improved to 0.96 and 0.93 by the addition of the DTI classification model. CONCLUSIONS Classification models based on fractional anisotropy and mean diffusivity from the enhancing regions of the tumor can improve diagnostic performance in differentiating glioblastomas from brain metastases.
Collapse
Affiliation(s)
- S Wang
- From the Departments of Radiology (S.W., H.P., J.H.W., S.M., M.R.V., R.L.W.)
| | - S J Kim
- Department of Radiology (S.J.K.), University of Ulsan, Asan Medical Center, Seoul, Republic of Korea
| | - H Poptani
- From the Departments of Radiology (S.W., H.P., J.H.W., S.M., M.R.V., R.L.W.)
| | - J H Woo
- From the Departments of Radiology (S.W., H.P., J.H.W., S.M., M.R.V., R.L.W.)
| | - S Mohan
- From the Departments of Radiology (S.W., H.P., J.H.W., S.M., M.R.V., R.L.W.)
| | - R Jin
- Medical Data Research Center (R.J.), Providence Health and Services, Portland, Oregon
| | - M R Voluck
- From the Departments of Radiology (S.W., H.P., J.H.W., S.M., M.R.V., R.L.W.)
| | - D M O'Rourke
- Neurosurgery (D.M.O.), Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - R L Wolf
- From the Departments of Radiology (S.W., H.P., J.H.W., S.M., M.R.V., R.L.W.)
| | - E R Melhem
- Department of Diagnostic Radiology and Nuclear Medicine (E.R.M.), University of Maryland Medical Center, Baltimore, Maryland
| | - S Kim
- Department of Radiology (S.K.), New York University School of Medicine, New York, New York
| |
Collapse
|
|
33
|
Hogeweg L, Sanchez CI, van Ginneken B. Suppression of translucent elongated structures: applications in chest radiography. IEEE TRANSACTIONS ON MEDICAL IMAGING 2013; 32:2099-2113. [PMID: 23880041 DOI: 10.1109/tmi.2013.2274212] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/02/2023]
Abstract
Projection images, such as those routinely acquired in radiological practice, are difficult to analyze because multiple 3-D structures superimpose at a single point in the 2-D image. Removal of particular superimposed structures may improve interpretation of these images, both by humans and by computers. This work therefore presents a general method to isolate and suppress structures in 2-D projection images. The focus is on elongated structures, which allows an intensity model of a structure of interest to be extracted using local information only. The model is created from profiles sampled perpendicular to the structure. Profiles containing other structures are detected and removed to reduce the influence on the model. Subspace filtering, using blind source separation techniques, is applied to separate the structure to be suppressed from other structures. By subtracting the modeled structure from the original image a structure suppressed image is created. The method is evaluated in four experiments. In the first experiment ribs are suppressed in 20 artificial radiographs simulated from 3-D lung computed tomography (CT) images. The proposed method with blind source separation and outlier detection shows superior suppression of ribs in simulated radiographs, compared to a simplified approach without these techniques. Additionally, the ability of three observers to discriminate between patches containing ribs and containing no ribs, as measured by the area under the receiver operating characteristic curve (AUC), reduced from 0.99-1.00 on original images to 0.75-0.84 on suppressed images. In the second experiment clavicles are suppressed in 253 chest radiographs. The effect of suppression on clavicle visibility is evaluated using the clavicle contrast and border response, showing a reduction of 78% and 34%, respectively. In the third experiment nodules extracted from CT were simulated close to the clavicles in 100 chest radiographs. It was found that after suppression contrast of the nodules was higher than of the clavicles (1.35 and 0.55, respectively) than on original images (1.83 and 2.46, respectively). In the fourth experiment catheters were suppressed in chest radiographs. The ability of three observers to discriminate between patches originating from 36 images with and 21 images without catheters, as measured by the AUC, reduced from 0.98-0.99 on original images to 0.64-0.74 on suppressed images. We conclude that the presented method can markedly reduce the visibility of elongated structures in chest radiographs and shows potential to enhance diagnosis.
Collapse
|
|
34
|
Blons H, Rouleau E, Charrier N, Chatellier G, Côté JF, Pages JC, de Fraipont F, Boyer JC, Merlio JP, Morel A, Gorisse MC, de Cremoux P, Leroy K, Milano G, Ouafik L, Merlin JL, Le Corre D, Aucouturier P, Sabourin JC, Nowak F, Frebourg T, Emile JF, Durand-Zaleski I, Laurent-Puig P, on behalf of the MOKAECM collaborative group. Performance and cost efficiency of KRAS mutation testing for metastatic colorectal cancer in routine diagnosis: the MOKAECM study, a nationwide experience. PLoS One 2013; 8:e68945. [PMID: 23935912 PMCID: PMC3723748 DOI: 10.1371/journal.pone.0068945] [Citation(s) in RCA: 22] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2013] [Accepted: 06/04/2013] [Indexed: 12/13/2022] Open
Abstract
Purpose Rapid advances in the understanding of cancer biology have transformed drug development thus leading to the approval of targeted therapies and to the development of molecular tests to select patients that will respond to treatments. KRAS status has emerged as a negative predictor of clinical benefit from anti-EGFR antibodies in colorectal cancer, and anti-EGFR antibodies use was limited to KRAS wild type tumors. In order to ensure wide access to tumor molecular profiling, the French National Cancer Institute (INCa) has set up a national network of 28 regional molecular genetics centers. Concurrently, a nationwide external quality assessment for KRAS testing (MOKAECM) was granted to analyze reproducibility and costs. Methods 96 cell-line DNAs and 24 DNA samples from paraffin embedded tumor tissues were sent to 40 French laboratories. A total of 5448 KRAS results were collected and analyzed and a micro-costing study was performed on sites for 5 common methods by an independent team of health economists. Results This work provided a baseline picture of the accuracy and reliability of KRAS analysis in routine testing conditions at a nationwide level. Inter-laboratory Kappa values were >0.8 for KRAS results despite differences detection methods and the use of in-house technologies. Specificity was excellent with only one false positive in 1128 FFPE data, and sensitivity was higher for targeted techniques as compared to Sanger sequencing based methods that were dependent upon local expertise. Estimated reagent costs per patient ranged from €5.5 to €19.0. Conclusion The INCa has set-up a network of public laboratories dedicated to molecular oncology tests. Our results showed almost perfect agreements in KRAS testing at a nationwide level despite different testing methods ensuring a cost-effective equal access to personalized colorectal cancer treatment.
Collapse
Affiliation(s)
- Hélène Blons
- UMR-S775, INSERM, Paris, France
- Université Paris Descartes, Paris, France
- Assistance Publique Hôpitaux de Paris Department of biology, Hôpital Européen Georges Pompidou, Paris, France
| | | | - Nathanaël Charrier
- Assistance Publique Hôpitaux de Paris, Henri Mondor-Albert Chenevier Hospitals, Department of Public Health, Creteil; URCEco Ile de France, Paris, France
| | - Gilles Chatellier
- Université Paris Descartes, Paris, France
- Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges Pompidou, URC Paris, France
| | - Jean-François Côté
- EA4340, Université de Versailles St Quentin en Yvelines; Assistance Publique Hôpitaux de Paris Hôpital Ambroise Paré, Department of Pathology; Boulogne-Billancourt, France
| | - Jean-Christophe Pages
- INSERM U966, Université François Rabelais de Tours, Faculté de Médecine, Tours, France
| | | | | | - Jean Philippe Merlio
- Bordeaux University Hospital Segalene Department of Tumor Biology, Pessac; Bordeaux University EA 2406, Bordeaux, France
| | - Alain Morel
- Cancer Center Paul Papin; INSERM U892; University of Angers, Angers, France
| | | | - Patricia de Cremoux
- Assistance Publique Hôpitaux de Paris, Saint Louis Hospital, Molecular oncology unit, Department of biochemistry, Paris, France
| | - Karen Leroy
- Assistance Publique Hôpitaux de Paris Department of pathology Henri Mondor Hospital, Creteil, France
| | | | - L’Houcine Ouafik
- Aix-Marseille Université, Inserm-CRO2 UMR911, AP-HM, CHU Nord, Service de Transfert d’Oncologie Biologique, Marseille, France
| | | | | | - Pascaline Aucouturier
- Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges Pompidou, URC Paris, France
| | - Jean-Christophe Sabourin
- Rouen University Hospital Department of surgical and molecular pathology; Inserm U1079, Rouen, France
| | | | - Thierry Frebourg
- Rouen University Hospital Department of Genetics, Inserm U614, Rouen, France
| | - Jean-François Emile
- EA4340, Université de Versailles St Quentin en Yvelines; Assistance Publique Hôpitaux de Paris Hôpital Ambroise Paré, Department of Pathology; Boulogne-Billancourt, France
| | - Isabelle Durand-Zaleski
- Assistance Publique Hôpitaux de Paris, Henri Mondor-Albert Chenevier Hospitals, Department of Public Health, Creteil; URCEco Ile de France, Paris, France
| | - Pierre Laurent-Puig
- UMR-S775, INSERM, Paris, France
- Université Paris Descartes, Paris, France
- Assistance Publique Hôpitaux de Paris Department of biology, Hôpital Européen Georges Pompidou, Paris, France
- * E-mail:
| | | |
Collapse
|
|
35
|
A brief history of free-response receiver operating characteristic paradigm data analysis. Acad Radiol 2013; 20:915-9. [PMID: 23583665 DOI: 10.1016/j.acra.2013.03.001] [Citation(s) in RCA: 45] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2013] [Revised: 03/01/2013] [Accepted: 03/07/2013] [Indexed: 11/23/2022]
Abstract
In the receiver operating characteristic paradigm the observer assigns a single rating to each image and the location of the perceived abnormality, if any, is ignored. In the free-response receiver operating characteristic paradigm the observer is free to mark and rate as many suspicious regions as are considered clinically reportable. Credit for a correct localization is given only if a mark is sufficiently close to an actual lesion; otherwise, the observer's mark is scored as a location-level false positive. Until fairly recently there existed no accepted method for analyzing the resulting relatively unstructured data containing random numbers of mark-rating pairs per image. This report reviews the history of work in this field, which has now spanned more than five decades. It introduces terminology used to describe the paradigm, proposed measures of performance (figures of merit), ways of visualizing the data (operating characteristics), and software for analyzing free-response receiver operating characteristic studies.
Collapse
|
|
36
|
Soh BP, Lee W, McEntee MF, Kench PL, Reed WM, Heard R, Chakraborty DP, Brennan PC. Screening mammography: test set data can reasonably describe actual clinical reporting. Radiology 2013; 268:46-53. [PMID: 23481165 PMCID: PMC3689446 DOI: 10.1148/radiol.13122399] [Citation(s) in RCA: 34] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
PURPOSE To establish the extent to which test set reading can represent actual clinical reporting in screening mammography. MATERIALS AND METHODS Institutional ethics approval was granted, and informed consent was obtained from each participating screen reader. The need for informed consent with respect to the use of patient materials was waived. Two hundred mammographic examinations were selected from examinations reported by 10 individual expert screen readers, resulting in 10 reader-specific test sets. Data generated from actual clinical reports were compared with three test set conditions: clinical test set reading with prior images, laboratory test set reading with prior images, and laboratory test set reading without prior images. A further set of five expert screen readers was asked to interpret a common set of images in two identical test set conditions to establish a baseline for intraobserver variability. Confidence scores (from 1 to 4) were assigned to the respective decisions made by readers. Region-of-interest (ROI) figures of merit (FOMs) and side-specific sensitivity and specificity were described for the actual clinical reporting of each reader-specific test set and were compared with those for the three test set conditions. Agreement between pairs of readings was performed by using the Kendall coefficient of concordance. RESULTS Moderate or acceptable levels of agreement were evident (W = 0.69-0.73, P < .01) when describing group performance between actual clinical reporting and test set conditions that were reasonably close to the established baseline (W = 0.77, P < .01) and were lowest when prior images were excluded. Higher median values for ROI FOMs were demonstrated for the test set conditions than for the actual clinical reporting values; this was possibly linked to changes in sensitivity. CONCLUSION Reasonable levels of agreement between actual clinical reporting and test set conditions can be achieved, although inflated sensitivity may be evident with test set conditions.
Collapse
Affiliation(s)
- BaoLin P Soh
- Medical Image Optimisation and Perception Group, Discipline of Medical Radiation Sciences (C42 Cumberland Campus, University of Sydney, East Street, Room M221, Sydney, NSW 2141, Australia.
| | | | | | | | | | | | | | | |
Collapse
|
|
37
|
Chan EW, Liao J, Foo RCM, Loon SC, Aung T, Wong TY, Cheng CY. Diagnostic Performance of the ISNT Rule for Glaucoma Based on the Heidelberg Retinal Tomograph. Transl Vis Sci Technol 2013; 2:2. [PMID: 24049722 DOI: 10.1167/tvst.2.5.2] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2013] [Accepted: 05/14/2013] [Indexed: 11/24/2022] Open
Abstract
PURPOSE We determined the accuracy of the inferior > superior > nasal > temporal (ISNT) neuroretinal rim area rule and its variants in adult Asian populations, and evaluated whether disc area impacts its performance characteristics. METHODS Participants in the Singapore Malay Eye Study (SiMES) and Singapore Indian Eye Study (SINDI) underwent standardized ocular examinations, including optic disc imaging with the Heidelberg retinal tomograph (HRT). Glaucoma was defined using the ISGEO criteria. HRT rim areas in the superior, inferior, nasal, and temporal quadrants were quantified. We determined sensitivity, specificity, and positive (PPV) and negative (NPV) predictive values of violating the ISNT rule and 4 variants (I > S > T, I > S, I > T, and combined I > T and S > T). The influence of disc area was analyzed with multivariate marginal logistic regression. RESULTS There were 6112 participants (mean age: 57.6 ± 10.3 years). Glaucoma was present in 194 individuals (3.2%). Among 11,840 eyes, 232 (93.2%) of 249 glaucomatous eyes and 9768 (84.3%) of 11,591 nonglaucomatous eyes, violated the ISNT rule. The ISNT rule had highest sensitivity (93.5%), but lowest specificity (15.7%); I > T had highest specificity (98.2%), but low sensitivity (7.4%). For all variants, PPVs were low (2.1%-8.4%) and NPVs were high (97.9-99.1%). Larger disc area was associated with reduced specificity for the ISNT rule (P < 0.001), and reduced sensitivity (P = 0.01) and increased specificity for I > S > T (P < 0.05). PPV increased (P < 0.05) and NPV decreased (P < 0.001) with increasing disc area. CONCLUSIONS The ISNT rule based on HRT has high sensitivity, and the I > T, S > T, and combined I > T and S > T variants have high specificity. Disc area influences sensitivity, specificity, PPV, and NPV of the ISNT rule and its variants. TRANSLATIONAL RELEVANCE The high sensitivity of the ISNT rule, and high specificities of its variants, may have potential utility when used in combination with other HRT algorithms for glaucoma assessment.
Collapse
Affiliation(s)
- Errol Wei'en Chan
- Department of Ophthalmology, National University of Singapore and National University Health System, Singapore
| | | | | | | | | | | | | |
Collapse
|
|
38
|
Bandos AI, Rockette HE, Gur D. Subject-centered free-response ROC (FROC) analysis. Med Phys 2013; 40:051706. [PMID: 23635254 DOI: 10.1118/1.4799843] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE To develop an approach of estimating subject-centered free-response receiver operating characteristic (FROC) curve for providing patient-centered inferences regarding detection-localization characteristics of a diagnostic system. METHODS The authors examine properties of the conventional, target-centered, FROC curve and demonstrate that in scenarios where the diagnostic performance correlates with the total number of targets on a subject, it may lead to inadequate inferences from the perspective of possible benefits to a patient. Following solutions to patient-centered approaches in other applications, the authors define a subject-centered FROC curve and develop its formulation as a covariate-adjusted FROC curve. The authors also conduct a numerical study illustrating the relative properties of the conventional and subject-centered approach and provide an example. RESULTS A simple-to-implement approach for estimating the subject-centered FROC curve and its overall index can be formulated as a type of stratified FROC analysis. The authors demonstrate that when diagnostic performance is associated with the number of targets, the diagnostic system with apparently superior target-centered characteristics (conventional approach) can be actually inferior from the subject-centered perspective. The authors show that under some clinically reasonable conditions the magnitude of disagreement in results could be substantial. An example from an actual observer performance study illustrates the natural setting where the developed approach would be relevant and lead to conclusions that are contradictory to those obtained from conventional analysis. CONCLUSIONS The authors developed a subject-centered FROC curve and its overall index provides tools for inferences that may be relevant from a perspective of potential benefits to a patient.
Collapse
Affiliation(s)
- Andriy I Bandos
- Department of Biostatistics, Graduate School of Public Health, University of Pittsburgh, 130 DeSoto Street, Pittsburgh, Pennsylvania 15261, USA.
| | | | | |
Collapse
|
|
39
|
Abstract
OBJECTIVE Calculating the sample size for a multireader, multicase study of readers' diagnostic accuracy is complicated. Studies in which patients can have multiple findings, as is common in many computer-aided detection (CAD) studies, are particularly challenging to design. MATERIALS AND METHODS We modified existing methods for sample size estimation for multireader, multicase studies to accommodate multiple findings on the same case. We use data from two large multireader, multicase CAD studies as ballpark estimates of parameter values. RESULTS Sample size tables are presented to provide an estimate of the number of patients and readers required for a multireader, multicase study with multiple findings per case; these estimates may be conservative for many CAD studies. Two figures can be used to adjust the number of readers when there is some data on the between-reader variability. CONCLUSION The sample size tables are useful in determining whether a proposed study is feasible with the available resources; however, it is important that investigators compute sample size for their particular study using any available pilot data.
Collapse
|
|
40
|
Yakar D, Heijmink SWTPJ, Hulsbergen-van de Kaa CA, Huisman H, Barentsz JO, Fütterer JJ, Scheenen TWJ. Initial results of 3-dimensional 1H-magnetic resonance spectroscopic imaging in the localization of prostate cancer at 3 Tesla: should we use an endorectal coil? Invest Radiol 2011; 46:301-6. [PMID: 21217527 DOI: 10.1097/rli.0b013e3182007503] [Citation(s) in RCA: 21] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
PURPOSE The purpose of this study was to compare the diagnostic performance of 3 Tesla, 3-dimensional (3D) magnetic resonance spectroscopic imaging (MRSI) in the localization of prostate cancer (PCa) with and without the use of an endorectal coil (ERC). MATERIALS AND METHODS Our prospective study was approved by the institutional review board, and written informed consent was obtained from all patients. Between October 2004 and January 2006, 18 patients with histologically proven PCa on biopsy and scheduled for radical prostatectomy were included and underwent 3D-MRSI with and without an ERC. The prostate was divided into 14 regions of interest (ROIs). Four readers independently rated (on a 5-point scale) their confidence that cancer was present in each of these ROIs. These findings were correlated with whole-mount prostatectomy specimens. Areas under the receiver-operating characteristic curve were determined. A difference with a P < 0.05 was considered significant. RESULTS A total of 504 ROIs were rated for the presence and absence of PCa. Localization of PCa with MRSI with the use of an ERC had a significantly higher areas under the receiver-operating characteristic curve (0.68) than MRSI without the use of an ERC (0.63) (P = 0.015). CONCLUSION The use of an ERC in 3D MRSI in localizing PCa at 3 Tesla slightly but significantly increased the localization performance compared with not using an ERC.
Collapse
Affiliation(s)
- Derya Yakar
- Departments of Radiology, Radboud University Nijmegen Medical Centre, The Netherlands.
| | | | | | | | | | | | | |
Collapse
|
|
41
|
Kallenberg MGJ, Lokate M, van Gils CH, Karssemeijer N. Automatic breast density segmentation: an integration of different approaches. Phys Med Biol 2011; 56:2715-29. [DOI: 10.1088/0031-9155/56/9/005] [Citation(s) in RCA: 39] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
|
|
42
|
Abstract
Medical images constitute a core portion of the information a physician utilizes to render diagnostic and treatment decisions. At a fundamental level, this diagnostic process involves two basic processes: visually inspecting the image (visual perception) and rendering an interpretation (cognition). The likelihood of error in the interpretation of medical images is, unfortunately, not negligible. Errors do occur, and patients' lives are impacted, underscoring our need to understand how physicians interact with the information in an image during the interpretation process. With improved understanding, we can develop ways to further improve decision making and, thus, to improve patient care. The science of medical image perception is dedicated to understanding and improving the clinical interpretation process.
Collapse
|
|
43
|
Vos PC, Hambrock T, Barenstz JO, Huisman HJ. Computer-assisted analysis of peripheral zone prostate lesions using T2-weighted and dynamic contrast enhanced T1-weighted MRI. Phys Med Biol 2010; 55:1719-34. [DOI: 10.1088/0031-9155/55/6/012] [Citation(s) in RCA: 80] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
|
44
|
Shah DN, Wilson CM, Ying GS, Karp KA, Fielder AR, Ng J, Mills MD, Quinn GE. Semiautomated digital image analysis of posterior pole vessels in retinopathy of prematurity. J AAPOS 2009; 13:504-6. [PMID: 19840732 DOI: 10.1016/j.jaapos.2009.06.007] [Citation(s) in RCA: 14] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/11/2009] [Revised: 06/02/2009] [Accepted: 06/03/2009] [Indexed: 10/20/2022]
Abstract
Plus disease is a major indicator for treatment in retinopathy of prematurity (ROP), and computer-assisted image analysis of vessel caliber and tortuosity in the posterior pole may indicate disease progression and severity. We sought to determine whether semiautomated digital analysis of posterior pole vessels using narrow field images with varying severity of ROP correlated with vessel width and tortuosity.
Collapse
|
|
45
|
Obuchowski NA, Mazzone PJ, Dachman AH. Bias, underestimation of risk, and loss of statistical power in patient-level analyses of lesion detection. Eur Radiol 2009; 20:584-94. [PMID: 19763582 DOI: 10.1007/s00330-009-1590-4] [Citation(s) in RCA: 26] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2009] [Revised: 07/15/2009] [Accepted: 07/27/2009] [Indexed: 11/28/2022]
Abstract
PURPOSE Sensitivity and the false positive rate are usually defined with the patient as the unit of observation, i.e., the diagnostic test detects or does not detect disease in a patient. For tests designed to find and diagnose lesions, e.g., lung nodules, the usual definitions of sensitivity and specificity may be misleading. In this paper we describe and compare five measures of accuracy of lesion detection. METHODS The five levels of evaluation considered were patient level without localization, patient level with localization, region of interest (ROI) level without localization, ROI level with localization, and lesion level. RESULTS We found that estimators of sensitivity that do not require the reader to correctly locate the lesion overstate sensitivity. Patient-level estimators of sensitivity can be misleading when there is more than one lesion per patient and they reduce study power. Patient-level estimators of the false positive rate can conceal important differences between techniques. Referring clinicians rely on a test's reported accuracy to both choose the appropriate test and plan management for their patients. If reported sensitivity is overstated, the clinician could choose the test for disease screening, and have false confidence that a negative test represents the true absence of lesions. Similarly, the lower false positive rate associated with patient-level estimators can mislead clinicians about the diagnostic value of the test and consequently that a positive finding is real. CONCLUSION We present clear recommendations for studies assessing and comparing the accuracy of tests tasked with the detection and interpretation of lesions...
Collapse
Affiliation(s)
- Nancy A Obuchowski
- Department of Quantitative Health Sciences/JJN3 and the Imaging Institute, Cleveland Clinic Foundation, 9500 Euclid Ave, Cleveland, OH 44195, USA.
| | | | | |
Collapse
|
|
46
|
Chakraborty DP. Counterpoint to "Performance assessment of diagnostic systems under the FROC paradigm" by Gur and Rockette. Acad Radiol 2009; 16:507-10. [PMID: 19268864 PMCID: PMC2671808 DOI: 10.1016/j.acra.2008.12.011] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2008] [Revised: 12/25/2008] [Accepted: 11/25/2008] [Indexed: 11/23/2022]
Affiliation(s)
- Dev P Chakraborty
- Department of Radiology, University of Pittsburgh, 3520 Forbes Ave, Suite 109, Pittsburgh, PA 15261, USA.
| |
Collapse
|
|
47
|
Abstract
Free-response assessment of diagnostic systems continues to gain acceptance in areas related to the detection, localization, and classification of one or more "abnormalities" within a subject. A free-response receiver operating characteristic (FROC) curve is a tool for characterizing the performance of a free-response system at all decision thresholds simultaneously. Although the importance of a single index summarizing the entire curve over all decision thresholds is well recognized in ROC analysis (e.g., area under the ROC curve), currently there is no widely accepted summary of a system being evaluated under the FROC paradigm. In this article, we propose a new index of the free-response performance at all decision thresholds simultaneously, and develop a nonparametric method for its analysis. Algebraically, the proposed summary index is the area under the empirical FROC curve penalized for the number of erroneous marks, rewarded for the fraction of detected abnormalities, and adjusted for the effect of the target size (or "acceptance radius"). Geometrically, the proposed index can be interpreted as a measure of average performance superiority over an artificial "guessing" free-response process and it represents an analogy to the area between the ROC curve and the "guessing" or diagonal line. We derive the ideal bootstrap estimator of the variance, which can be used for a resampling-free construction of asymptotic bootstrap confidence intervals and for sample size estimation using standard expressions. The proposed procedure is free from any parametric assumptions and does not require an assumption of independence of observations within a subject. We provide an example with a dataset sampled from a diagnostic imaging study and conduct simulations that demonstrate the appropriateness of the developed procedure for the considered sample sizes and ranges of parameters.
Collapse
Affiliation(s)
- Andriy I Bandos
- Department of Biostatistics, Graduate School of Public Health, University of Pittsburgh, Pittsburgh, Pennsylvania 15261, USA.
| | | | | | | |
Collapse
|
|
48
|
Vos PC, Hambrock T, Barenstz JO, Huisman HJ. Automated calibration for computerized analysis of prostate lesions using pharmacokinetic magnetic resonance images. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2009; 12:836-43. [PMID: 20426189 DOI: 10.1007/978-3-642-04271-3_101] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
Abstract
The feasibility of an automated calibration method for estimating the arterial input function when calculating pharmacokinetic parameters from Dynamic Contrast Enhanced MRI is shown. In a previous study, it was demonstrated that the computer aided diagnoses (CADx) system performs optimal when per patient calibration was used, but required manual annotation of reference tissue. In this study we propose a fully automated segmentation method that tackles this limitation and tested the method with our CADx system when discriminating prostate cancer from benign areas in the peripheral zone. A method was developed to automatically segment normal peripheral zone tissue (PZ). Context based segmentation using the Otsu histogram based threshold selection method and by Hessian based blob detection, was developed to automatically select PZ as reference tissue for the per patient calibration. In 38 consecutive patients carcinoma, benign and normal tissue were annotated on MR images by a radiologist and a researcher using whole mount step-section histopathology as standard of reference. A feature set comprising pharmacokinetic parameters was computed for each ROI and used to train a support vector machine (SVM) as classifier. In total 42 malignant, 29 benign and 37 normal regions were annotated. The diagnostic accuracy obtained for differentiating malignant from benign lesions using a conventional general patient plasma profile showed an accuracy of 0.65 (0.54-0.76). Using the automated segmentation per patient calibration method the diagnostic value improved to 0.80 (0.71-0.88), whereas the manual segmentation per patient calibration showed a diagnostic performance of 0.80 (0.70-0.90). These results show that an automated per-patient calibration is feasible, a significant better discriminating performance compared to the conventional fixed calibration was obtained and the diagnostic accuracy is similar to using manual per-patient calibration.
Collapse
Affiliation(s)
- Pieter C Vos
- Department of Radiology, University Medical Centre Nijmegen, The Netherlands.
| | | | | | | |
Collapse
|
|
49
|
Gardner CM, Tan H, Hull EL, Lisauskas JB, Sum ST, Meese TM, Jiang C, Madden SP, Caplan JD, Burke AP, Virmani R, Goldstein J, Muller JE. Detection of Lipid Core Coronary Plaques in Autopsy Specimens With a Novel Catheter-Based Near-Infrared Spectroscopy System. JACC Cardiovasc Imaging 2008; 1:638-48. [DOI: 10.1016/j.jcmg.2008.06.001] [Citation(s) in RCA: 312] [Impact Index Per Article: 18.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/18/2008] [Revised: 05/12/2008] [Accepted: 06/10/2008] [Indexed: 11/25/2022]
|
|
50
|
Vos PC, Hambrock T, Hulsbergen-van de Kaa CA, Fütterer JJ, Barentsz JO, Huisman HJ. Computerized analysis of prostate lesions in the peripheral zone using dynamic contrast enhanced MRI. Med Phys 2008; 35:888-99. [PMID: 18404925 DOI: 10.1118/1.2836419] [Citation(s) in RCA: 74] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
A novel automated computerized scheme has been developed for determining a likelihood measure of malignancy for cancer suspicious regions in the prostate based on dynamic contrast-enhanced magnetic resonance imaging (MRI) (DCE-MRI) images. Our database consisted of 34 consecutive patients with histologically proven adenocarcinoma in the peripheral zone of the prostate. Both carcinoma and non-malignant tissue were annotated in consensus on MR images by a radiologist and a researcher using whole mount step-section histopathology as standard of reference. The annotations were used as regions of interest (ROIs). A feature set comprising pharmacokinetic parameters and a T1 estimate was extracted from the ROIs to train a support vector machine as classifier. The output of the classifier was used as a measure of likelihood of malignancy. Diagnostic performance of the scheme was evaluated using the area under the ROC curve. The diagnostic accuracy obtained for differentiating prostate cancer from non-malignant disorders in the peripheral zone was 0.83 (0.75-0.92). This suggests that it is feasible to develop a computer aided diagnosis system capable of characterizing prostate cancer in the peripheral zone based on DCE-MRI.
Collapse
Affiliation(s)
- Pieter C Vos
- Department of Radiology, Radboud University Nijmegen Medical Centre, Geert Grooteplein 18, 6525 GA Nijmegen, The Netherlands.
| | | | | | | | | | | |
Collapse
|