Radiomics extracts quantitative features from magnetic resonance images (MRI) and is especially useful in the presence of subtle pathological changes within human soft tissues. This scenario, however, may not cover the effects of intrinsic, e.g., aging-related, (physiological) neurodegeneration of normal brain tissue. The aim of the work was to study the repeatability of radiomic features extracted from an apparently normal area in longitudinally acquired T1-weighted MR brain images using three different intensity normalization approaches typically used in radiomics: Z-score, WhiteStripe and Nyul.

Fifty-nine images of hearing impaired, yet cognitively intact, patients were repeatedly acquired in two different time points within six months. Ninety-one radiomic features were obtained from an area within the pons region, considered to be a healthy brain tissue according to previous analyses and reports. The Intraclass Correlation Coefficient (ICC) and the Concordance Correlation Coefficient (CCC) in the repeatability study were used as metrics.

Features extracted from the MRI normalized with Z-score showed results comparable in both ICC (0.90 (0.82-0.98)) and CCC (0.82 (0.69-0.95)) distribution values, in terms of median and quartiles, with those extracted from the images normalized with WhiteStripe (0.89 (0.84-0.92)) and (0.80 (0.73-0.84)), respectively.

Our findings underline the importance of, providing useful guidelines for, the intensity normalization of brain MRI prior to a longitudinal radiomic analysis.

Radiomics analysis has emerged as a promising approach to aid in cancer diagnosis and treatment. However, radiomics research currently lacks standardization, and radiomics features can be highly dependent on acquisition and pre-processing techniques used. In this study, we aim to investigate the effect of various image normalization techniques on robustness of radiomics features extracted from breast cancer patient MRI scans.

MRI scans from the publicly available MAMA-MIA dataset and an internal breast MRI test set depicting triple negative breast cancer (TNBC) were used. We compared the effect of commonly used image normalization techniques on radiomics feature robustnessusing Concordance-Correlation-Coefficient (CCC) between multiple combinations of normalization approaches. We also trained machine learning-based prediction models of pathologic complete response (pCR) on radiomics after different normalization techniques were used and compared their areas under the receiver operating characteristic curve (ROC-AUC).

For predicting complete pathological response from pre-treatment breast cancer MRI radiomics, the highest overall ROC-AUC was achieved by using a combination of three different normalization techniques indicating their potentially powerful role when working with heterogeneous imaging data. The effect of normalization was more pronounced with smaller training data and normalization may be less important with increasing abundance of training data. Additionally, we observed considerable differences between MRI data sets and their feature robustness towards normalization.

Overall, we were able to demonstrate the importance of selecting and standardizing normalization methods for accurate and reliable radiomics analysis in breast MRI scans especially with small training data sets.

To predict recurrence risk in patients with surgically resected non-small cell lung cancer (NSCLC) using radiomic analysis and clinicopathological factors.

293 patients with surgically resected stage IA-IIIA NSCLC were analyzed. Patients were randomly stratified into development and test cohorts. The development cohort was further divided into training and validation subsets for feature selection and model building, then applied to the test cohort. Pre-treatment computed tomography were segmented and 107 pyRadiomics features were extracted from intratumoral and peritumoral regions. Feature selection was performed using the maximum relevance minimum redundancy algorithm and Lasso regression. Clinical covariates were selected using univariable Cox regression. Radiomic, clinical, and radiomic-clinical models were constructed using a logistic regression classifier and evaluated using area under the curve (AUC). Kaplan-Meier curves for 3-year recurrence-free survival were compared between high-risk and low-risk groups using the log-rank test.

20 percent of patients experienced recurrence within 3 years. The radiomic-clinical model (AUC 0.77) outperformed the radiomic, clinical, and TNM stage models (AUC 0.76, 0.71, and 0.70, respectively) on the test set. Recurrence risk was five times higher in the high-risk group than the low-risk group (p<0.01) after stratification with the radiomic-clinical model. The most important features were regional lymph node metastases, the "GLDM Large Dependence Emphasis" texture, and the "Elongation" shape feature.

Radiomics analysis can be used in combination with clinicopathological features for effective recurrence risk stratification in patients with surgically resected NSCLC.

This study aimed to investigate the value of integrating computed tomography (CT)-based tumor radiomics features with clinical parameters for preoperative prediction of microvascular invasion (MVI) in clear cell renal cell carcinoma (ccRCC).

We retrospectively analyzed data from a single-center cohort of ccRCC patients. Radiomics features were extracted from preoperative multiphasic CT scans (unenhanced, corticomedullary, and nephrographic phases). Following dimensionality reduction and feature selection, eight machine learning algorithms were evaluated to identify the optimal radiomics model. Independent clinical predictors were determined through univariate and multivariate analyses. A nomogram integrating the radiomics signature (rad-score) with significant clinical parameters was subsequently developed. Model performance was assessed using the area under the curve (AUC), decision curve analysis (DCA), and calibration curve analysis (CAC).

Of 143 initially enrolled patients, 110 met inclusion criteria after screening, with 5502 radiomics features extracted. The support vector classifier (SVM) model demonstrated the highest discriminative ability, achieving mean AUCs of 0.976 (training cohort) and 0.892 (test cohort), significantly outperforming the clinical model (training AUC = 0.935, test AUC = 0.933). The nomogram showed superior diagnostic performance, with AUCs of 0.958 (test). DCA and CAC confirmed its clinical utility and robustness.

Multiparametric CT radiomics models enable non-invasive prediction of MVI status in ccRCC, with the SVM-based algorithm showing optimal performance. The integrated nomogram provides excellent and consistent diagnostic accuracy, offering a valuable preoperative tool for clinical decision-making.

Radiomics refers to the utilization of automated or semi-automated techniques to extract and analyze numerous quantitative features from medical images, such as computerized tomography (CT) or magnetic resonance imaging (MRI) scans. This study aims to develop a deep learning radiomics (DLR)-based approach for predicting programmed death-ligand 1 (PD-L1) expression in patients with non-small cell lung cancer (NSCLC). Data from 352 NSCLC patients with known PD-L1 expression were collected, of which 48.29% (170/352) were tested positive for PD-L1 expression. Tumor regions of interest (ROI) were semi-automatically segmented based on CT images, and DL features were extracted using Residual Network 50. The least absolute shrinkage and selection operator (LASSO) algorithm was used for feature selection and dimensionality reduction. Seven algorithms were used to build models, and the most optimal ones were identified. A combined model integrating DLR with clinical data was also developed. The predictive performance of each model was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve analysis. The DLR model, based on CT images, demonstrated an AUC of 0.85 (95% confidence interval (CI), 0.82-0.88), sensitivity of 0.80 (0.74-0.85), and specificity of 0.73 (0.70-0.77) for predicting PD-L1 status. The integrated model exhibited superior performance, with an AUC of 0.91 (0.87-0.95), sensitivity of 0.85 (0.82-0.89), and specificity of 0.75 (0.72-0.80). Our findings indicate that the DLR model holds promise as a valuable tool for predicting the PD-L1 status in patients with NSCLC, which can greatly assist in clinical decision-making and the selection of personalized treatment strategies.

Microvascular invasion (MVI) affects the prognosis and treatment of hepatocellular carcinoma (HCC); however, its preoperative diagnosis is challenging. Analysis of computed tomography (CT) images using radiomics can detect MVI, but its effectiveness depends on the imaging conditions. We compared the efficacies of radiomics, clinical, and combined models for predicting MVI in HCC using nonstandardized scanning protocols.

This multicenter study included 533 patients who underwent hepatic resection for HCC. Patients were divided randomly into training (n = 426) and test groups (n = 107). We manually extracted 3D CT features in hepatic arterial, portal venous, and venous phases. The radiomics model was trained by machine learning. A logistic regression model was developed based on clinical information, and a fused model was created integrating clinical information and radiomics prediction score (Rad_Score). We calculated areas under the receiver operating characteristic curves (AUCs) for the radiomics, clinical, and mixed models in the test groups.

The clinical model incorporated hepatitis B virus surface antigen, tumor diameter, and log-transformed α-fetoprotein and des-gamma-carboxyprothrombin. The AUCs of the radiomics and clinical models were comparable (p = 0.76). Rad_Score was not an independent significant factor in the fused model (p = 0.40) and its addition did not improve the accuracy of the clinical model alone (p = 0.51).

A clinical model is as effective as a CT radiomics model for predicting MVI status in patients with HCC based on real-world scanning data, and integration of both models does not improve the predictive performance compared with a clinical model alone.

To develop a nomogram based on CT radiomics features for preoperative prediction of perineural invasion (PNI) in pancreatic ductal adenocarcinoma (PDAC) patients.

A total of 217 patients with histologically confirmed PDAC were enrolled in this retrospective study. Radiomics features were extracted from the whole tumor. Univariate analysis, least absolute shrinkage and selection operator and logistic regression were applied for feature selection and radiomics model construction. Finally, a nomogram combining the radiomics score (Rad-score) and clinical characteristics was established. Receiver operating characteristic curve analysis, calibration curve analysis and decision curve analysis (DCA) were used to evaluate the predictive performance of the nomogram.

According to multivariate analysis, CT features, including the radiologists evaluated PNI status based on CECT (CTPNI) (OR=1.971 [95% CI: 1.165, 3.332], P=0.01), the lymph node status determined on CECT (CTLN) (OR=2.506 [95%: 1.416, 4.333], P=0.001) and the Rad-score (OR=3.666 [95% CI: 2.069, 6.494], P<0.001), were significantly associated with PNI. The area under the receiver operating characteristic curve (AUC) for the nomogram combined with the Rad-score, CTLN and CTPNI achieved favorable discrimination of PNI status, with AUCs of 0.846 and 0.778 in the training and testing cohorts, respectively, which were superior to those of the Rad-score (AUC of 0.720 in the training cohort and 0.640 in the testing cohort) and CTPNI (AUC of 0.610 in the training cohort and 0.675 in the testing cohort). The calibration plot and decision curve showed good results.

The CT-based radiomics nomogram has the potential to accurately predict PNI in patients with PDAC.

The reproducibility of radiomic features (RFs) is essential in lung nodule diagnosis. This study aimed to prospectively investigate the effects of computed tomography (CT) scanning parameters on the reproducibility of RFs in pulmonary nodules.

Patients with pulmonary nodules who underwent chest CT scans at the Cancer Hospital of the Chinese Academy of Medical Sciences between July 2018 and March 2019 were prospectively included in the study. Six sequences with three pairs of different scanning parameters, including the reconstruction algorithm [filtered back projection (FBP) vs. 50% adaptive statistical iterative reconstruction-V (ASiR-V)], radiation dose (low dose vs. standard dose), and contrast agent [contrast-enhanced (CE) CT vs. non-contrast enhanced (NE) CT], were used for each patient. When one of the scanning parameters was changed, the other two remained fixed. The nodules were classified into pure ground-glass nodules (pGGNs), part-solid nodules (PSNs), and solid nodules (SNs) according to the nodule consistency. RFs with an intraclass correlation coefficient (ICC) >0.75 were considered to have good retest reliability. All the RF values of the different scanning parameters and nodule consistency were investigated and compared.

A total of 150 pulmonary nodules, including 50 pGGNs, 50 PSNs, and 50 SNs, in 96 patients (mean age: 52±10 years; 62 females) were included in the study. In total, 320 RFs with an ICC >0.75 were evaluated. The proportion of RFs showed significant difference between FBP and 50% ASiR-V, low dose and standard dose, and CE and NE CT scans was 38.4% (123/320), 63.1% (202/320) and 54.1% (173/320), respectively. The radiation dose and contrast agent affected more RFs than the reconstruction algorithm (both P<0.001). In the subgroup analysis of nodule consistency, regardless of changes in the reconstruction algorithms, radiation doses, or contrast agents, the RFs showed significant difference among the pGGNs, PSNs, and SNs (all P<0.001).

The scanning parameters affected the reproducibility of the RFs, and nodules of different consistency were affected differently. The effects of these parameters should be fully considered in radiomic analysis.

BackgroundRadiomics analysis is widely used to assess tumor prognosis.PurposeTo explore the value of computed tomography (CT) radiomics nomogram in predicting disease-free survival (DFS) of patients with colorectal cancer (CRC) after operation.Material and MethodsA total of 522 CRC patients from three centers were retrospectively included. Radiomics features were extracted from CT images, and the least absolute shrinkage and selection operator Cox regression algorithm was employed to select radiomics features. Clinical risk factors associated with DFS were selected through univariate and multivariate Cox regression analysis to build the clinical model. A predictive nomogram was developed by amalgamating pertinent clinical risk factors and radiomics features. The predictive performance of the nomogram was evaluated using the C-index, calibration curve, and decision curve. DFS probabilities were estimated using the Kaplan-Meier method.ResultsIntegrating the retained eight radiomics features and three clinical risk factors (pathological N stage, microsatellite instability, perineural invasion), a nomogram was constructed. The C-index for the nomogram were 0.819 (95% CI=0.794-0.844), 0.782 (95% CI=0.740-0.824), 0.786 (95% CI=0.753-0.819), and 0.803 (95% CI=0.765-0.841) in the training set, internal validation set, external validation set 1, and external validation set 2, respectively. The calibration curves demonstrated a favorable congruence between the predicted and observed values as depicted by the nomogram. The decision curve analysis underscored that the nomogram yielded a heightened clinical net benefit.ConclusionThe constructed radiomics nomogram, amalgamating the radiomics features and clinical risk factors, exhibited commendable performance in the individualized prediction of postoperative DFS in CRC patients.

Radiomics extracted from cone beam computed tomography (CBCT) can be assessed at time points during treatment and may provide an advantage over assessments in a pre-treatment setting using diagnostic images, like magnetic resonance imaging (MRI) or computed tomography (CT), for prostate cancer (pCa) patients receiving radiotherapy (RT). The purpose of this study was to analyze correlations between prostate radiomic features (RFs) derived from T2-weighted (T2w) MRI, CT, and first fraction CBCT for patients receiving RT for pCa. Forty-seven patients were analyzed. The prostate volumes were manually segmented, and 42 radiomic features were extracted, of which seven volume-normalized RFs were considered. The absolute Spearman correlation was calculated among the RFs of the aforementioned imaging modalities (RM) and prostate volume (RV) since the motivation of this paper was to analyze the strength of the correlation. The Benjamini-Hochberg adjustment was applied to p-values to account for multiple comparisons. No high correlations were found between CT/CBCT vs. T2w. The intramodality RM demonstrated that CT RFs were much higher than the other modalities. For example, intramodality RM≥0.95 the percentage of RFs was 17% for CT, 9% for CBCT, and 4.5% for T2w. The differences in RFs across different modalities can be viewed positively: the lack of correlation between RFs across T2w and CT/CBCT could indicate a fundamental difference in the extractable image information. It could also indicate that some RFs did not have any extractable information. A future study will include evaluating the predictive performance of patient outcomes using radiomic features from CT, CBCT, and T2w, which could help in answering such questions.

Radiomics has seen substantial growth in medical imaging; however, its potential in optical coherence tomography (OCT) has not been widely explored. We systematically evaluate the repeatability and reproducibility of handcrafted radiomics features (HRFs) from OCT scans of benign nevi and examine the impact of bin width (BW) selection on HRF stability. The effect of using stable features on a radiomics classification model was also assessed.

In this prospective study, 20 volunteers underwent test-retest OCT imaging of 40 benign nevi, resulting in 80 scans. The repeatability and reproducibility of HRFs extracted from manually delineated regions of interest (ROIs) were assessed using concordance correlation coefficients (CCCs) across BWs ranging from 5 to 50. A unique set of stable HRFs was identified at each BW after removing highly correlated features to eliminate redundancy. These robust features were incorporated into a multiclass radiomics classifier trained to distinguish benign nevi, basal cell carcinoma (BCC), and Bowen's disease.

Six stable HRFs were identified across all BWs, with a BW of 25 emerging as the optimal choice, balancing repeatability and the ability to capture meaningful textural details. Additionally, intermediate BWs (20-25) yielded 53 reproducible features. A classifier trained with six stable features achieved a 90% accuracy and AUCs of 0.96 and 0.94 for BCC and Bowen's disease, respectively, compared to a 76% accuracy and AUCs of 0.86 and 0.80 for a conventional feature selection approach.

This study highlights the critical role of BW selection in enhancing HRF stability and provides a methodological framework for optimizing preprocessing in OCT radiomics. By demonstrating the integration of stable HRFs into diagnostic models, we establish OCT radiomics as a promising tool to aid non-invasive diagnosis in dermatology.

Background/Objectives: Radiomic features exhibit a correlation with tumor size on pretreatment images. However, on post-treatment images, this association is influenced by treatment efficacy and varies between responders and non-responders. This study introduces a novel model, called baseline-referenced Delta radiomics, which integrates the association between radiomic features and tumor size into Delta radiomics to predict chemotherapy response in liver metastases from breast cancer (BC) and colorectal cancer (CRC). Materials and Methods: A retrospective study analyzed contrast-enhanced computed tomography (CT) scans of 83 BC patients and 84 CRC patients. Among these, 57 BC patients with 106 liver lesions and 37 CRC patients with 109 lesions underwent post-treatment imaging after systemic chemotherapy. Radiomic features were extracted from up to three lesions per patient following manual segmentation. Tumor response was assessed by measuring the longest diameter and classified according to RECIST 1.1 criteria as progressive disease (PD), partial response (PR), or stable disease (SD). Classification models were developed to predict chemotherapy response using pretreatment data only, Delta radiomics, and baseline-referenced Delta radiomics. Model performance was evaluated using confusion matrix metrics. Results: Baseline-referenced Delta radiomics performed comparably or better than established radiomics models in predicting tumor response in chemotherapy-treated patients with liver metastases. The sensitivity, specificity, and balanced accuracy in predicting response ranged from 0.66 to 0.97, 0.81 to 0.97, and 80% to 90%, respectively. Conclusions: By integrating the relationship between radiomic features and tumor size into Delta radiomics, baseline-referenced Delta radiomics offers a promising approach for predicting chemotherapy response in liver metastases from breast and colorectal cancer.

This study aimed to develop a hybrid model combining radiomics and deep learning features derived from computed tomography (CT) images to classify histological subtypes of non-small cell lung cancer (NSCLC). We analyzed CT images and radiomics features from 235 patients with NSCLC, including 110 with adenocarcinoma (ADC) and 112 with squamous cell carcinoma (SCC). The dataset was split into a training set (75%) and a test set (25%). External validation was conducted using the NSCLC-Radiomics database, comprising 24 patients each with ADC and SCC. A total of 1409 radiomics and 8192 deep features underwent principal component analysis (PCA) and ℓ2,1-norm minimization for feature reduction and selection. The optimal feature sets for classification included 27 radiomics features, 20 deep features, and 55 combined features (30 deep and 25 radiomics). The average area under the receiver operating characteristic curve (AUC) for radiomics, deep, and combined features were 0.6568, 0.6689, and 0.7209, respectively, across the internal and external test sets. Corresponding average accuracies were 0.6013, 0.6376, and 0.6564. The combined model demonstrated superior performance in classifying NSCLC subtypes, achieving higher AUC and accuracy in both test datasets. These results suggest that the proposed hybrid approach could enhance the accuracy and reliability of NSCLC subtype classification.

This study aims to construct an effective prediction model for the two-year postoperative survival probability of patients with non-small cell lung cancer (NSCLC). It particularly focuses on integrating radiomics features, including the erector spinae and whole-lung imaging features, to enhance the accuracy and stability of prognostic predictions.

The study included 37 NSCLC patients diagnosed and surgically treated at the First Affiliated Hospital of Anhui Medical University from January 2020 to December 2021. The average age of the patients was 59 years, with the majority being female and non-smokers. Additionally, CT imaging data from 98 patients were obtained from The Cancer Imaging Archive (TCIA) public database. All imaging data were derived from preoperative chest CT scans and standardized using 3D Slicer software. The study extracted radiomic features from the tumor, whole lung, and erector spinae muscles of the patients and applied 11 machine learning algorithms to construct prediction models. Subsequently, the classification performance of all constructed models was compared to select the optimal prediction model.

Univariate Cox regression analysis showed no significant correlation between the collected clinical factors and patient survival time. In the external validation set, the K-Nearest Neighbors (KNN) model based on bilateral erector spinae features performed the best, with accuracy and AUC (Area Under the Curve) values consistently above 0.7 in both the training and external testing sets. Among the prognostic models based on whole-lung imaging features, the AdaBoost model also performed well, but its AUC value was below 0.6 in the external validation set, indicating overall classification performance still inferior to the KNN model based on erector spinae features.

This study is the first to introduce erector spinae imaging features into lung cancer research, successfully developing a stable and well-performing prediction model for the postoperative survival of NSCLC patients. The research results provide new perspectives and directions for the application of radiomics in cancer research and emphasize the importance of incorporating multi-organ imaging features to improve the accuracy and stability of prediction models.

To study the application of radiomics in cancer imaging with a focus on lung cancer, renal cell carcinoma, gastrointestinal cancer, and head and neck cancer.

Different electronic databases were considered. Articles published in the last five years were analyzed (January 2019 and December 2023). Papers were selected by two investigators with over 15 years of experience in Radiomics analysis in cancer imaging. The methodological quality of each radiomics study was performed using the Radiomic Quality Score (RQS) by two different readers in consensus and then by a third operator to solve disagreements between the two readers.

19 articles are included in the review. Among the analyzed studies, only one study achieved an RQS of 18 reporting multivariable analyzes with also non-radiomics features and using the validation phase considering two datasets from two distinct institutes and open science and data domain.

This informative review has brought attention to the increasingly consolidated potential of Radiomics, although there are still several aspects to be evaluated before the transition to routine clinical practice. There are several challenges to address, including the need for standardization at all stages of the workflow and the potential for cross-site validation using heterogeneous real-world datasets. It will be necessary to establish and promote an imaging data acquisition protocol, conduct multicenter prospective quality control studies, add scanner differences and vendor-dependent characteristics; to collect images of individuals at additional time points, to report calibration statistics.

The impact of novel photon-counting detector (PCD)-CT technology on in-vivo radiomics is not fully understood. This study aimed to compare the intra-individual stability and reproducibility of pericoronary adipose tissue (PCAT) radiomic features between PCD-CT and energy-integrating detector (EID)-CT in patients undergoing coronary CT angiography (CCTA) on both systems.

Patients undergoing clinically indicated CCTA on an EID-CT were prospectively enrolled for research PCD-CCTA within 30 days. Image acquisition parameters were standardized; PCD-CT datasets were reconstructed both down-sampled to 0.6 mm to match the clinical scan (PCD-CTDS) and at 0.2 mm ultrahigh-resolution mode (PCD-CTUHR). Automatic PCAT segmentation was performed; a total of 110 radiomic feature classes were extracted and compared across the three datasets (EID-CT, PCD-CTDS, and PCD-CDUHR). Feature stability was assessed using paired t-test filtered for false discoveries using Benjamini-Hochberg method, and reproducibility using intraclass correlation coefficient (ICC).

A total of 42 patients (34 male [81.0 %]; 67.9 ± 7.6 years) were included. Feature stability was 91 % for EID-CT vs. PCD-CTDS, but decreased for UHR datasets (EID-CT vs. PCD-CTUHR: 55 %; PCD-CTDS vs. PCD-CTUHR: 51 %). However, inter-scanner reproducibility was poor in both comparisons (EID-CT vs. PCD-CTDS median ICC: 0.43 [0.03-0.69]; EID-CT vs. PCD-CTUHR: 0.29 [0.01-0.51]). Nevertheless, reproducibility improved within PCD-CT datasets (PCD-CTDS vs. PCD-CTUHR: 0.72 [0.48-0.83]), regardless of the difference in slice thickness.

Most PCAT radiomic features remained stable between EID-CT and PCD-CTDS, although inter-scanner reproducibility was poor, emphasizing the significant impact of detector technology. Conversely, reproducibility of features within PCD-CT datasets showed more consistent results, even when comparing standard to UHR.

Definitive radiotherapy (RT) has been shown to be a successful method of treating prostate cancer (PCa) patients. Through radiomics, a quantitative analysis of medical images, it is possible to adapt treatment early on, which may prevent or mitigate future adverse events. During RT of PCa, low-field magnetic resonance (MR) images, taken with a LINAC onboard imaging system in a process known as magnetic resonance-guided radiotherapy (MRgRT), are used to improve treatment accuracy via superior setup compared to x-ray methods. This work investigated baseline repeatability of radiomic features (RFs) by comparing planning MR images (pMR) with first-fraction setup images (FX1) taken with onboard MRI. The changes in RFs following RT were also looked at with the use of last-fraction setup images (FX5). Earlier research has investigated the use of planning images from cone beam CT (CBCT), but to our knowledge no research has previously shown the relationship with onboard MRI. The correlation between FX1 images and 3T diagnostic MR (dT2) images was also studied. Forty-three first and second order radiomic features extracted from these images were compared by calculating Lin's concordance correlation coefficient (with Benjamini-Hochberg correction for multiple comparisons) between the modalities. FX1 and pMR images were correlated (p<0.05) for all but one RF. 12 RFs correlated between pMR and dT2 images. There was a noticeable change in correlation values for RFs when looking at FX1 and FX5 images, with only 15 correlating significantly. The change in correlation values between pMR and FX5 images was comparable to that between FX1 and FX5 images, with 33 features having a CCC value deviation of less than 0.1. These results demonstrate that RF features are repeatable across different images of the same modality without treatment intervention. This study has also shown a noticeable, reproducible change in RFs as RT goes on. Reproducibility of RFs between different modalities was not strong. This study demonstrated that we can reliably use onboard MRI to observe day-to-day feature changes as a result of RT.

This study addresses the limited noninvasive tools for Head and Neck Squamous Cell Carcinoma (HNSCC) progression-free survival (PFS) prediction by identifying Computed Tomography (CT)-based biomarkers for predicting prognosis. A retrospective analysis was conducted on data from 203 HNSCC patients. An ensemble feature selection involving correlation analysis, univariate survival analysis, best-subset selection, and the LASSO-Cox algorithm was used to select functional features, which were then used to build final Cox Proportional Hazards models (CPH). Our CPH achieved a 0.69 concordance index in an external indepedent cohort of 77 patients. The model identified five CT-based radiomics features, Gradient ngtdm Contrast, Logσ=33D-FirstorderRootMeanSquared, Logσ=0.13D-glszm SmallAreaLowGrayLevelEmphasis, Exponential-gldm LargeDependenceHighGrayLevelEmphasis, and Gradient ngtdm Strength as survival biomarkers (p-value < 0.05). These findings contribute to our knowledge of how radiomics can be used to predict the outcome so that treatment plans can be tailored for people with HNSCC to improve their prognosis.

Radiological imaging is a cornerstone in the clinical workup of lung diseases. Radiomics represents a significant advancement in clinical lung imaging, offering a powerful tool to complement traditional qualitative image analysis. Radiomic features are quantitative and computationally describe shape, intensity, texture and wavelet characteristics from medical images that can uncover detailed and often subtle information that goes beyond the visual capabilities of radiological examiners. By extracting this quantitative information, radiomics can provide deep insights into the pathophysiology of lung diseases and support clinical decision-making as well as personalised medicine approaches. In this educational review, we provide a step-by-step guide to radiomics-based medical image analysis, discussing the technical challenges and pitfalls, and outline the potential clinical applications of radiomics in diagnosing, prognosticating and evaluating treatment responses in respiratory medicine.

To develop and validate a model for predicting suboptimal debulking surgery (SDS) of serous ovarian carcinoma (SOC) using radiomics method, clinical and MRI features.

228 patients eligible from institution A (randomly divided into the training and internal validation cohorts) and 45 patients from institution B (external validation cohort) were collected and retrospectively analyzed. All patients underwent abdominal pelvic enhanced MRI scan, including T2-weighted imaging fat-suppressed fast spin-echo (T2FSE), T1-weighted dual-echo magnetic resonance imaging (T1DEI), diffusion weighted imaging (DWI), and T1 with contrast enhancement (T1CE). We extracted, selected and eliminated highly correlated radiomic features for each sequence. Then, Radiomic models were made by each single sequence, dual-sequence (T1CE + T2FSE), and all-sequence, respectively. Univariate and multivariate analyses were performed to screen the clinical and MRI independent predictors. The radiomic model with the highest area under the curve (AUC) was used to combine the independent predictors as a combined model.

The optimal radiomic model was based on dual sequences (T2FSE + T1CE) among the five radiomic models (AUC = 0.720, P < 0.05). Serum carbohydrate antigen 125, the relationship between sigmoid colon/rectum and ovarian mass or mass implanted in Douglas' pouch, diaphragm nodules, and peritoneum/mesentery nodules were considered independent predictors. The AUC of the radiomic-clinical-radiological model was higher than either the optimal radiomic model or the clinical-radiological model in the training cohort (AUC = 0.908 vs. 0.720/0.854).

The radiomic-clinical-radiological model has an overall algorithm reproducibility and may help create individualized treatment programs and improve the prognosis of patients with SOC.

The purpose of this study was to investigate the dosiomics features of the interplay between CT density and dose distribution in lung SBRT plans, and to develop a model to predict treatment failure following lung SBRT treatment.

A retrospective study was conducted involving 179 lung cancer patients treated with SBRT at the University of Nebraska Medical Center (UNMC) between October 2007 and June 2022. Features from the CT image, Biological Effective Dose (BED) and five interaction matrices between CT and BED were extracted using radiomics mathematics. Our in-house feature selection pipeline was utilized to evaluate and rank features based on their importance and redundancy, with only the selected non-redundant features being used for predictive modeling. We randomly selected 151 cases and 28 cases as training and test datasets. Four different models were trained utilizing the Balanced Random Forest framework on the same training dataset to differentiate between failure and non-failure cases. These four models utilized the same number of selected features extracted from CT-only, BED-only, a combination of CT and BED, and a composite of CT and BED including their interaction matrices, respectively.

The cohort included 125 non-failure cases and 54 failure cases, with a median follow-up time of 34.4 months. We selected the top 17 important and non-redundant features (with the Pearsons's coefficient < 0.5) in each model. When evaluated on the same independent test set, the four models-CT features-only, BED features-only, a combination of CT and BED features, and a composite model including features from CT and BED that includes their interaction matrices-achieved AUC values of 0.56, 0.75, 0.73, and 0.82, respectively, with corresponding accuracies of 0.61, 0.79, 0.71, and 0.79. The composite model demonstrated the highest AUC and accuracy, indicating that incorporating interactions between CT and BED reveals more predictive capabilities in distinguishing between failure and non-failure cases.

The dosiomics model integrating the interaction between CT and Dose can effectively predict treatment failure following lung SBRT treatment and may serve as a useful tool to proactively evaluate and select lung SBRT treatment plans to reduce treatment failure in the future.

Chronic obstructive pulmonary disease (COPD) is a major global health concern, and while traditional pulmonary function tests are effective, recent radiomics advancements offer enhanced evaluation by providing detailed insights into the heterogeneous lung changes.

To develop and validate a radiomics nomogram based on clinical and whole-lung computed tomography (CT) radiomics features to stratify COPD severity.

One thousand ninety-nine patients with COPD (including 308, 132, and 659 in the training, internal and external validation sets, respectively), confirmed by pulmonary function test, were enrolled from two institutions. The whole-lung radiomics features were obtained after a fully automated segmentation. Thereafter, a clinical model, radiomics signature, and radiomics nomogram incorporating radiomics signature as well as independent clinical factors were constructed and validated. Additionally, receiver-operating characteristic (ROC) curve, area under the ROC curve (AUC), decision curve analysis (DCA), and the DeLong test were used for performance assessment and comparison.

In comparison with clinical model, both radiomics signature and radiomics nomogram outperformed better on COPD severity (GOLD I-II and GOLD III-IV) in three sets. The AUC of radiomics nomogram integrating age, height and Radscore, was 0.865 (95% CI, 0.818-0.913), 0.851 (95% CI, 0.778-0.923), and 0.781 (95% CI, 0.740-0.823) in three sets, which was the highest among three models (0.857; 0.850; 0.774, respectively) but not significantly different (P > 0.05). Decision curve analysis demonstrated the superiority of the radiomics nomogram in terms of clinical usefulness.

The present work constructed and verified the novel, diagnostic radiomics nomogram for identifying the severity of COPD, showing the added value of chest CT to evaluate not only the pulmonary structure but also the lung function status.

To develop a CT radiomics model to predict pathological complete response (pCR) of advanced esophageal squamous cell carcinoma (ESCC) toneoadjuvant chemotherapy using paclitaxel and cisplatin.

326 consecutive patients with advanced ESCC from two hospitals undergoing baseline contrast-enhanced CT followed by neoadjuvant chemotherapy using paclitaxel and cisplatin were enrolled, including 115 patients achieving pCR and 211 patients without pCR. Of the 271 cases from 1st hospital, 188 and 83 cases were randomly allocated to the training and test cohorts, respectively. The 55 patients from a second hospital were assigned as an external validation cohort. Region of interest was segmented on the baseline thoracic contrast-enhanced CT. Useful radiomics features were generated by dimension reduction using least absolute shrinkage and selection operator. The optimal radiomics features were chosen using support vector machine (SVM). Discriminating performance was assessed with area under the receiver operating characteristic curve (ROC) and F-1score. The calibration curves and Brier score were used to evaluate the predictive accuracy.

Eight radiomics features were selected to create radiomics models related to pCR of advanced ESCC (P-values < 0.01 for both the training and test cohorts). SVM model showed the best performance (AUCs = 0.929, 0.868 and 0.866, F-1scores = 0.857, 0.847 and 0.737 in the training, test and external validation cohorts, respectively). The calibration curves and Brier scores indicated goodness-of-fit and its great predictive accuracy.

CT radiomics models could well help predict pCR of advanced ESCC, and SVM model could be a suitable predictive model.

Current imaging methods for diagnosing breast cancer (BC) are associated with limited sensitivity and specificity and modest positive predictive power. The recent progress in image analysis using artificial intelligence (AI) has created great promise to improve BC diagnosis and subtype differentiation. In this case, novel quantitative computational methods, such as radiomics, have been developed to enhance the sensitivity and specificity of early BC diagnosis and classification. The potential of radiomics in improving the diagnostic efficacy of imaging studies has been shown in several studies. In this review article, we discuss the radiomics workflow and current handcrafted radiomics methods in the diagnosis and classification of BC based on the most recent studies on different imaging modalities, e.g., MRI, mammography, contrast-enhanced spectral mammography (CESM), ultrasound imaging, and digital breast tumosynthesis (DBT). We also discuss current challenges and potential strategies to improve the specificity and sensitivity of radiomics in breast cancer to help achieve a higher level of BC classification and diagnosis in the clinical setting. The growing field of AI incorporation with imaging information has opened a great opportunity to provide a higher level of care for BC patients.

We assessed the feasibility of using deep learning-based image harmonization to improve the reproducibility of radiomics features in abdominal CT scans. In CT imaging, harmonization adjusts images from different institutions to ensure consistency despite variations in scanners and acquisition protocols. This process is essential because such differences can lead to variability in radiomics features, affecting reproducibility and accuracy. Harmonizing images minimizes these inconsistencies, supporting more reliable and clinically applicable results across diverse settings. A pre-trained harmonization algorithm was applied to 63 dual-energy abdominal CT images, which were reconstructed into four different types, and 10 regions of interest (ROIs) were analyzed. From the original 455 radiomics features per ROI, 387 were used after excluding redundant features. Reproducibility was measured using the intraclass correlation coefficient (ICC), with a threshold of ICC ≥ 0.85 indicating acceptable reproducibility. The region-based analysis revealed significant improvements in reproducibility post-harmonization, especially in vessel features, which increased from 14% to 69%. Other regions, including the spleen, kidney, muscle, and liver parenchyma, also saw notable improvements, although air reproducibility slightly decreased from 95% to 94%, impacting only a few features. In patient-based analysis, reproducible features increased from 18% to 65%, with an average of 179 additional reproducible features per patient after harmonization. These results demonstrate that deep learning-based harmonization can significantly enhance the reproducibility of radiomics features in abdominal CT, offering promising potential for advancing radiomics development and its clinical applications.

The BRCA1-associated protein 1 (BAP1) gene is of great interest because somatic (BAP1) mutations are the most common alteration associated with pleural mesothelioma (PM). Further, germline mutation of the BAP1 gene has been linked to the development of PM. This study aimed to explore the potential of radiomics on computed tomography scans to identify somatic BAP1 gene mutations and assess the feasibility of radiomics in future research in identifying germline mutations.

A cohort of 149 patients with PM and known somatic BAP1 mutation status was collected, and a previously published deep learning model was used to first automatically segment the tumor, followed by radiologist modifications. Image preprocessing was performed, and texture features were extracted from the segmented tumor regions. The top features were selected and used to train 18 separate machine learning models using leave-one-out cross-validation (LOOCV). The performance of the models in distinguishing between BAP1-mutated (BAP1+) and BAP1 wild-type (BAP1-) tumors was evaluated using the receiver operating characteristic area under the curve (ROC AUC).

A decision tree classifier achieved the highest overall AUC value of 0.69 (95% confidence interval: 0.60 and 0.77). The features selected most frequently through the LOOCV were all second-order (gray-level co-occurrence or gray-level size zone matrices) and were extracted from images with an applied transformation.

This proof-of-concept work demonstrated the potential of radiomics to differentiate among BAP1+/- in patients with PM. Future work will extend these methods to the assessment of germline BAP1 mutation status through image analysis for improved patient prognostication.

The aim of this study was to determine whether MRI radiomic features of key cerebral structures differ between women and men, and whether detection of such differences depends on the image resolution.

Ultrahigh resolution (UHR) 3D MP2RAGE (magnetization-prepared 2 rapid acquisition gradient echo) T1-weighted MR images (voxel size, 0.7 × 0.7 × 0.7 mm 3 ) of the brain of 30 subjects (18 women and 12 men; mean age, 39.0 ± 14.8 years) without abnormal findings on MRI were retrospectively included. MRI was performed on a whole-body 7 T MR system. A convolutional neural network was used to segment the following structures: frontal cortex, frontal white matter, thalamus, putamen, globus pallidus, caudate nucleus, and corpus callosum. Eighty-seven radiomic features were extracted respectively: gray-level histogram (n = 18), co-occurrence matrix (n = 24), run-length matrix (n = 16), size-zone matrix (n = 16), and dependence matrix (n = 13). Feature extraction was performed at UHR and, additionally, also after resampling to 1.4 × 1.4 × 1.4 mm 3 voxel size (standard clinical resolution). Principal components (PCs) of radiomic features were calculated, and independent samples t tests with Cohen d as effect size measure were used to assess differences in PCs between women and men for the different cerebral structures.

At UHR, at least a single PC differed significantly between women and men in 6/7 cerebral structures: frontal cortex ( d = -0.79, P = 0.042 and d = -1.01, P = 0.010), frontal white matter ( d = -0.81, P = 0.039), thalamus ( d = 1.43, P < 0.001), globus pallidus ( d = 0.92, P = 0.020), caudate nucleus ( d = -0.83, P = 0.039), and corpus callosum ( d = -0.97, P = 0.039). At standard clinical resolution, only a single PC extracted from the corpus callosum differed between sexes ( d = 1.05, P = 0.009).

Nonnegligible differences in radiomic features of several key structures of the brain exist between women and men, and need to be accounted for. Very high spatial resolution may be required to uncover and further investigate the sexual dimorphism of brain structures on MRI.

Generative artificial intelligence (AI) has been applied to images for image quality enhancement, domain transfer, and augmentation of training data for AI modeling in various medical fields. Image-generative AI can produce large amounts of unannotated imaging data, which facilitates multiple downstream deep-learning tasks. However, their evaluation methods and clinical utility have not been thoroughly reviewed. This article summarizes commonly used generative adversarial networks and diffusion models. In addition, it summarizes their utility in clinical tasks in the field of radiology, such as direct image utilization, lesion detection, segmentation, and diagnosis. This article aims to guide readers regarding radiology practice and research using image-generative AI by 1) reviewing basic theories of image-generative AI, 2) discussing the methods used to evaluate the generated images, 3) outlining the clinical and research utility of generated images, and 4) discussing the issue of hallucinations.

This study aimed to investigate the ability of radiomics features extracted from magnetic resonance imaging (MRI) images to differentiate between responders and non-responders for hepatocellular carcinoma (HCC) cases who received Y-90 transarterial radioembolization treatment.

Thirty-six cases of HCC who underwent MRI scans after Y-90 radioembolization were included in this study. Tumors were segmented from MRI T2 images, and then 87 radiomic features were extracted through the LIFEx package software. Treatment response was determined 9 months after treatment through the modified response evaluation criteria in solid tumours (mRECIST).

According to mRECIST, 28 cases were responders and 8 cases were non-responders. Two radiomics features, "Grey Level Size Zone Matrix (GLSZM)-Small Zone Emphasis" and "GLSZM-Normalized Zone Size Non-Uniformity", were the radiomics features that could predict treatment response with the area under curve (AUC)= 0.71, sensitivity= 0.93, and specificity= 0.62 for both features. Whereas the other 4 features (kurtosis, intensity histogram root mean square, neighbourhood gray-tone difference matrix strength, and GLSZM normalized grey level non-uniformity) have a relatively lower but acceptable discrimination ability range from AUC= 0.6 to 0.66.

MRI radiomics analysis could be used to assess the treatment response for HCC cases treated with Y-90 radioembolization.

Although radiomics has revealed an intriguing perspective for quantitative radiology, the impact of scanning parameters on its outcomes must be considered. In this study, the effects of changes in the region of interest (ROI) sizes, Hounsfield Unit (HU), and resolution of computed tomography (CT) on feature reproducibility have been investigated.

The GAMMEX 464 phantom was used to evaluate the reproducibility of radiomics features across different ROI sizes, HU, and resolution. Data were acquired using a consistent system setup, with the phantom repositioned for each scan. The first acquisition series examined the effects of different ROI sizes and resolutions (1, 3, and 5 mm) on feature reproducibility. The second series assessed the impact of different HU and resolution. Segmentation and feature extraction were performed using LIFEx 7.1.0 software, focusing on textural radiomics features. Statistical analysis involved calculating the coefficient of variation (COV) to categorize feature variability. COV <5 % was considered highly stable.

Out of the 32 textural features studied, the analysis of changes in ROI size with a resolution of 1 mm, 3 mm, and 5 mm revealed that 16, 17, and 18 features had high reproducibility, with a COV<5 %. Polyethylene, acrylic, and water also demonstrated stable textural features across changes in scan parameters and image resolutions, with 4 reproducible features in all resolutions. The grey-level run length matrix (GLRLM) and grey-level zone length matrix (GLZLM) radiomics groups were highly stable in the context of variations in scan parameters and different materials.

The results of this study highlight the importance of standardizing radiomics studies to reduce the influence of pre-analysis steps on feature values. This standardization is crucial for guaranteeing the consistency of radiomics features under various imaging conditions. Additional research is required to enhance these results.

To ensure the reproducibility and reliability of radiomics features, it is imperative to standardize scanning parameters and pre-analysis protocols. This standardization will enhance the consistency of radiomics applications in both clinical and research environments.

To further optimize radiotherapy, a more personalized treatment towards individual patient's risk profiles, dissecting both patient-specific tumor and normal tissue response to multimodality treatments is needed. Novel developments in radiobiology, using in vitro patient-specific complex tissue resembling 3D models and multiomics approaches at a spatial single-cell level, may provide unprecedented insight into the radiation responses of tumors and normal tissue. Here, we describe the necessary team effort, including all disciplines in radiation oncology, to integrate such data into clinical prediction models and link the relatively "big data" from the clinical practice, allowing accurate patient stratification for personalized treatment approaches.

To evaluate radiomics in soft tissue sarcomas (STSs) for diagnostic accuracy, grading, and treatment response assessment, with a focus on clinical relevance.

In this diagnostic accuracy study, radiomics was applied using multiple MRI sequences and AI classifiers, with histopathological diagnosis as the reference standard. Statistical analysis involved meta-analysis, random-effects model, and Deeks' funnel plot asymmetry test.

Among 579 unique titles and abstracts, 24 articles were included in the systematic review, with 21 used for meta-analysis. Radiomics demonstrated a pooled sensitivity of 84% (95% CI: 80-87) and specificity of 63% (95% CI: 56-70), AUC of 0.93 for diagnosis, sensitivity of 84% (95% CI: 82-87) and specificity of 73% (95% CI: 68-77), AUC of 0.91 for grading, and sensitivity of 83% (95% CI: 67-94) and specificity of 67% (95% CI: 59-74), AUC of 0.87 for treatment response assessment.

Radiomics exhibits potential for accurate diagnosis, grading, and treatment response assessment in STSs, emphasizing the need for standardization and prospective trials.

Radiomics offers precise tools for STS diagnosis, grading, and treatment response assessment, with implications for optimizing patient care and treatment strategies in this complex malignancy.

Lung cancer, the second most common cancer, presents persistently dismal prognoses. Radiomics, a promising field, aims to provide novel imaging biomarkers to improve outcomes. However, clinical translation faces reproducibility challenges, despite efforts to address them with quality scoring tools.

This study had two objectives: 1) identify radiomics biomarkers in post-radiotherapy stage III/IV nonsmall cell lung cancer (NSCLC) patients, 2) evaluate research quality using the CLEAR (CheckList_for_EvaluAtion_of_Radiomics_research), RQS (Radiomics_Quality_Score) frameworks, and formulate an amalgamated CLEAR-RQS tool to enhance scientific rigor.

A systematic literature review (Jun-Aug 2023, MEDLINE/PubMed/SCOPUS) was conducted concerning stage III/IV NSCLC, radiotherapy, and radiomic features (RF). Extracted data included study design particulars, such as sample size, radiotherapy/CT technique, selected RFs, and endpoints. CLEAR and RQS were merged into a CLEAR-RQS checklist. Three readers appraised articles utilizing CLEAR, RQS, and CLEAR-RQS metrics.

Out of 871 articles, 11 met the inclusion/exclusion criteria. The Median cohort size was 91 (range: 10-337) with 9 studies being single-center. No common RF were identified. The merged CLEAR-RQS checklist comprised 61 items. Most unreported items were within CLEAR's "methods" and "open-source," and within RQS's "phantom-calibration," "registry-enrolled prospective-trial-design," and "cost-effective-analysis" sections. No study scored above 50% on RQS. Median CLEAR scores were 55.74% (32.33/58 points), and for RQS, 17.59% (6.3/36 points). CLEAR-RQS article ranking fell between CLEAR and RQS and aligned with CLEAR.

Radiomics research in post-radiotherapy stage III/IV NSCLC exhibits variability and frequently low-quality reporting. The formulated CLEAR-RQS checklist may facilitate education and holds promise for enhancing radiomics research quality.

Current radiomics research in the field of stage III/IV postradiotherapy NSCLC is heterogenous, lacking reproducibility, with no identified imaging biomarker. Radiomics research quality assessment tools may enhance scientific rigor and thereby facilitate radiomics translation into clinical practice.

There is heterogenous and low radiomics research quality in postradiotherapy stage III/IV nonsmall cell lung cancer. Barriers to reproducibility are small cohort size, nonvalidated studies, missing technical parameters, and lack of data, code, and model sharing. CLEAR (CheckList_for_EvaluAtion_of_Radiomics_research), RQS (Radiomics_Quality_Score), and the amalgamated CLEAR-RQS tool are useful frameworks for assessing radiomics research quality and may provide a valuable resource for educational purposes in the field of radiomics.

Cardiovascular disease affects the carotid arteries, coronary arteries, aorta and the peripheral arteries. Radiomics involves the extraction of quantitative data from imaging features that are imperceptible to the eye. Radiomics analysis in cardiovascular disease has largely focused on CT and MRI modalities. This scoping review aims to summarise the existing literature on radiomic analysis techniques in cardiovascular disease.

MEDLINE and Embase databases were searched for eligible studies evaluating radiomic techniques in living human subjects derived from CT, MRI or PET imaging investigating atherosclerotic disease. Data on study population, imaging characteristics and radiomics methodology were extracted.

Twenty-nine studies consisting of 5753 patients (3752 males) were identified, and 78.7% of patients were from coronary artery studies. Twenty-seven studies employed CT imaging (19 CT carotid angiography and 6 CT coronary angiography (CTCA)), and two studies studied PET/CT. Manual segmentation was most frequently undertaken. Processing techniques included voxel discretisation, voxel resampling and filtration. Various shape, first-order, second-order and higher-order radiomic features were extracted. Logistic regression was most commonly used for machine learning.

Most published evidence was feasibility/proof of concept work. There was significant heterogeneity in image acquisition, segmentation techniques, processing and analysis between studies. There is a need for the implementation of standardised imaging acquisition protocols, adherence to published reporting guidelines and economic evaluation.

Magnetic resonance imaging (MRI) is known for its accurate soft tissue delineation of tumors and normal tissues. This development has significantly impacted the imaging and treatment of cancers. Radiomics is the process of extracting high-dimensional features from medical images. Several studies have shown that these extracted features may be used to build machine-learning models for the prediction of treatment outcomes of cancer patients. Various feature selection techniques and machine models interrogate the relevant radiomics features for predicting cancer treatment outcomes. This study aims to provide an overview of MRI radiomics features used in predicting clinical treatment outcomes with machine learning techniques. The review includes examples from different disease sites. It will also discuss the impact of magnetic field strength, sample size, and other characteristics on outcome prediction performance.

To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.

In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.

A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The "original_shape_Flatness" feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.

The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance.