|
1
|
Dhali A, Kipkorir V, Maity R, Srichawla B, Biswas J, Rathna R, Bharadwaj H, Ongidi I, Chaudhry T, Morara G, Waithaka M, Rugut C, Lemashon M, Cheruiyot I, Ojuka D, Ray S, Dhali G. Artificial Intelligence-Assisted Capsule Endoscopy Versus Conventional Capsule Endoscopy for Detection of Small Bowel Lesions: A Systematic Review and Meta-Analysis. J Gastroenterol Hepatol 2025; 40:1105-1118. [PMID: 40083189 PMCID: PMC12062924 DOI: 10.1111/jgh.16931] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/23/2024] [Revised: 01/04/2025] [Accepted: 03/01/2025] [Indexed: 03/16/2025]
Abstract
BACKGROUND Capsule endoscopy (CE) is a valuable tool used in the diagnosis of small intestinal lesions. The study aims to systematically review the literature and provide a meta-analysis of the diagnostic accuracy, specificity, sensitivity, and negative and positive predictive values of AI-assisted CE in the diagnosis of small bowel lesions in comparison to CE. METHODS Literature searches were performed through PubMed, SCOPUS, and EMBASE to identify studies eligible for inclusion. All publications up to 24 November 2024 were included. Original articles (including observational studies and randomized control trials), systematic reviews, meta-analyses, and case series reporting outcomes on AI-assisted CE in the diagnosis of small bowel lesions were included. The extracted data were pooled, and a meta-analysis was performed for the appropriate variables, considering the clinical and methodological heterogeneity among the included studies. Comprehensive Meta-Analysis v4.0 (Biostat Inc.) was used for the analysis of the data. RESULTS A total of 14 studies were included in the present study. The mean age of participants across the studies was 54.3 years (SD 17.7), with 55.4% men and 44.6% women. The pooled accuracy for conventional CE was 0.966 (95% CI: 0.925-0.988), whereas for AI-assisted CE, it was 0.9185 (95% CI: 0.9138-0.9233). Conventional CE exhibited a pooled sensitivity of 0.860 (95% CI: 0.786-0.934) compared with AI-assisted CE at 0.9239 (95% CI: 0.8648-0.9870). The positive predictive value for conventional CE was 0.982 (95% CI: 0.976-0.987), whereas AI-assisted CE had a PPV of 0.8928 (95% CI: 0.7554-0.999). The pooled specificity for conventional CE was 0.998 (95% CI: 0.996-0.999) compared with 0.5367 (95% CI: 0.5244-0.5492) for AI-assisted CE. Negative predictive values were higher in AI-assisted CE at 0.9425 (95% CI: 0.9389-0.9462) versus 0.760 (95% CI: 0.577-0.943) for conventional CE. CONCLUSION AI-assisted CE displays superior diagnostic accuracy, sensitivity, and positive predictive values albeit the lower pooled specificity in comparison with conventional CE. Its use would ensure accurate detection of small bowel lesions and further enhance their management.
Collapse
Affiliation(s)
- Arkadeep Dhali
- Academic Unit of GastroenterologySheffield Teaching Hospitals NHS Foundation TrustSheffieldUK
- School of Medicine and Population HealthUniversity of SheffieldSheffieldUK
| | | | - Rick Maity
- Institute of Post Graduate Medical Education and ResearchKolkataIndia
| | | | | | | | | | - Ibsen Ongidi
- Faculty of Health SciencesUniversity of NairobiNairobiKenya
| | - Talha Chaudhry
- Faculty of Health SciencesUniversity of NairobiNairobiKenya
| | - Gisore Morara
- Faculty of Health SciencesUniversity of NairobiNairobiKenya
| | | | - Clinton Rugut
- Faculty of Health SciencesUniversity of NairobiNairobiKenya
| | | | | | - Daniel Ojuka
- Faculty of Health SciencesUniversity of NairobiNairobiKenya
| | - Sukanta Ray
- Institute of Post Graduate Medical Education and ResearchKolkataIndia
| | | |
Collapse
|
|
2
|
Jiang Q, Yu Y, Ren Y, Li S, He X. A review of deep learning methods for gastrointestinal diseases classification applied in computer-aided diagnosis system. Med Biol Eng Comput 2025; 63:293-320. [PMID: 39343842 DOI: 10.1007/s11517-024-03203-y] [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: 05/22/2024] [Accepted: 09/12/2024] [Indexed: 10/01/2024]
Abstract
Recent advancements in deep learning have significantly improved the intelligent classification of gastrointestinal (GI) diseases, particularly in aiding clinical diagnosis. This paper seeks to review a computer-aided diagnosis (CAD) system for GI diseases, aligning with the actual clinical diagnostic process. It offers a comprehensive survey of deep learning (DL) techniques tailored for classifying GI diseases, addressing challenges inherent in complex scenes, clinical constraints, and technical obstacles encountered in GI imaging. Firstly, the esophagus, stomach, small intestine, and large intestine were located to determine the organs where the lesions were located. Secondly, location detection and classification of a single disease are performed on the premise that the organ's location corresponding to the image is known. Finally, comprehensive classification for multiple diseases is carried out. The results of single and multi-classification are compared to achieve more accurate classification outcomes, and a more effective computer-aided diagnosis system for gastrointestinal diseases was further constructed.
Collapse
Affiliation(s)
- Qianru Jiang
- College of Information Engineering, Zhejiang University of Technology, Hangzhou, 310023, Zhejiang, P.R. China
| | - Yulin Yu
- College of Information Engineering, Zhejiang University of Technology, Hangzhou, 310023, Zhejiang, P.R. China
| | - Yipei Ren
- College of Information Engineering, Zhejiang University of Technology, Hangzhou, 310023, Zhejiang, P.R. China
| | - Sheng Li
- College of Information Engineering, Zhejiang University of Technology, Hangzhou, 310023, Zhejiang, P.R. China
| | - Xiongxiong He
- College of Information Engineering, Zhejiang University of Technology, Hangzhou, 310023, Zhejiang, P.R. China.
| |
Collapse
|
|
3
|
Lu F, Zhou D, Chen H, Liu S, Ling X, Zhu L, Gong T, Sheng B, Liao X, Jin H, Li P, Feng DD. S2P-Matching: Self-Supervised Patch-Based Matching Using Transformer for Capsule Endoscopic Images Stitching. IEEE Trans Biomed Eng 2025; 72:540-551. [PMID: 39302789 DOI: 10.1109/tbme.2024.3462502] [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: 09/22/2024]
Abstract
The Magnetically Controlled Capsule Endoscopy (MCCE) has a limited shooting range, resulting in capturing numerous fragmented images and an inability to precisely locate and examine the region of interest (ROI) as traditional endoscopy can. Addressing this issue, image stitching around the ROI can be employed to aid in the diagnosis of gastrointestinal (GI) tract conditions. However, MCCE images possess unique characteristics, such as weak texture, close-up shooting, and large angle rotation, presenting challenges to current image-matching methods. In this context, a method named S2P-Matching is proposed for self-supervised patch-based matching in MCCE image stitching. The method involves augmenting the raw data by simulating the capsule endoscopic camera's behavior around the GI tract's ROI. Subsequently, an improved contrast learning encoder is utilized to extract local features, represented as deep feature descriptors. This encoder comprises two branches that extract distinct scale features, which are combined over the channel without manual labeling. The data-driven descriptors are then input into a Transformer model to obtain patch-level matches by learning the globally consented matching priors in the pseudo-ground-truth match pairs. Finally, the patch-level matching is refined and filtered to the pixel-level. The experimental results on real-world MCCE images demonstrate that S2P-Matching provides enhanced accuracy in addressing challenging issues in the GI tract environment with image parallax. The performance improvement can reach up to 203 and 55.8% in terms of NCM (Number of Correct Matches) and SR (Success Rate), respectively. This approach is expected to facilitate the wide adoption of MCCE-based gastrointestinal screening.
Collapse
|
|
4
|
Linu Babu P, Jana S. Gastrointestinal tract disease detection via deep learning based Duo-Feature Optimized Hexa-Classification model. Biomed Signal Process Control 2025; 100:106994. [DOI: 10.1016/j.bspc.2024.106994] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/04/2025]
|
|
5
|
Xiao ZG, Chen XQ, Zhang D, Li XY, Dai WX, Liang WH. Image detection method for multi-category lesions in wireless capsule endoscopy based on deep learning models. World J Gastroenterol 2024; 30:5111-5129. [PMID: 39735271 PMCID: PMC11612692 DOI: 10.3748/wjg.v30.i48.5111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/02/2024] [Revised: 09/08/2024] [Accepted: 10/08/2024] [Indexed: 11/29/2024] Open
Abstract
BACKGROUND Wireless capsule endoscopy (WCE) has become an important noninvasive and portable tool for diagnosing digestive tract diseases and has been propelled by advancements in medical imaging technology. However, the complexity of the digestive tract structure, and the diversity of lesion types, results in different sites and types of lesions distinctly appearing in the images, posing a challenge for the accurate identification of digestive tract diseases. AIM To propose a deep learning-based lesion detection model to automatically identify and accurately label digestive tract lesions, thereby improving the diagnostic efficiency of doctors, and creating significant clinical application value. METHODS In this paper, we propose a neural network model, WCE_Detection, for the accurate detection and classification of 23 classes of digestive tract lesion images. First, since multicategory lesion images exhibit various shapes and scales, a multidetection head strategy is adopted in the object detection network to increase the model's robustness for multiscale lesion detection. Moreover, a bidirectional feature pyramid network (BiFPN) is introduced, which effectively fuses shallow semantic features by adding skip connections, significantly reducing the detection error rate. On the basis of the above, we utilize the Swin Transformer with its unique self-attention mechanism and hierarchical structure in conjunction with the BiFPN feature fusion technique to enhance the feature representation of multicategory lesion images. RESULTS The model constructed in this study achieved an mAP50 of 91.5% for detecting 23 lesions. More than eleven single-category lesions achieved an mAP50 of over 99.4%, and more than twenty lesions had an mAP50 value of over 80%. These results indicate that the model outperforms other state-of-the-art models in the end-to-end integrated detection of human digestive tract lesion images. CONCLUSION The deep learning-based object detection network detects multiple digestive tract lesions in WCE images with high accuracy, improving the diagnostic efficiency of doctors, and demonstrating significant clinical application value.
Collapse
Affiliation(s)
- Zhi-Guo Xiao
- School of Computer Science Technology, Changchun University, Changchun 130022, Jilin Province, China
- School of Computer Science Technology, Beijing Institute of Technology, Beijing 100811, China
| | - Xian-Qing Chen
- School of Computer Science Technology, Changchun University, Changchun 130022, Jilin Province, China
| | - Dong Zhang
- School of Computer Science Technology, Changchun University, Changchun 130022, Jilin Province, China
| | - Xin-Yuan Li
- School of Computer Science Technology, Changchun University, Changchun 130022, Jilin Province, China
| | - Wen-Xin Dai
- School of Computer Science Technology, Changchun University, Changchun 130022, Jilin Province, China
| | - Wen-Hui Liang
- School of Computer Science Technology, Changchun University, Changchun 130022, Jilin Province, China
| |
Collapse
|
|
6
|
Wei X, Xi P, Chen M, Wen Y, Wu H, Wang L, Zhu Y, Ren Y, Gu Z. Capsule robots for the monitoring, diagnosis, and treatment of intestinal diseases. Mater Today Bio 2024; 29:101294. [PMID: 39483392 PMCID: PMC11525164 DOI: 10.1016/j.mtbio.2024.101294] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2024] [Revised: 09/21/2024] [Accepted: 10/06/2024] [Indexed: 11/03/2024] Open
Abstract
Current evidence suggests that the intestine as the new frontier for human health directly impacts both our physical and mental health. Therefore, it is highly desirable to develop the intelligent tool for the enhanced diagnosis and treatment of intestinal diseases. During the past 20 years, capsule robots have opened new avenues for research and clinical applications, potentially revolutionizing human health monitor, disease diagnosis and treatment. In this review, we summarize the research progress of edible multifunctional capsule robots in intestinal diseases. To begin, we introduce the correlation between the intestinal microbiome, intestinal gas and human diseases. After that, we focus on the technical structure of edible multifunctional robots. Subsequently, the biomedical applications in the monitoring, diagnosis and treatment of intestinal diseases are discussed in detail. Last but not least, the main challenges of multifunctional capsule robots during the development process are summarized, followed by a vision for future development opportunities.
Collapse
Affiliation(s)
- Xiangyu Wei
- Department of Rheumatology, Research Center of Immunology, Affiliated Hospital of Nantong University, Nantong University, Nantong, 226001, China
- Department of Rheumatology, Affiliated Municipal Hospital of Xuzhou Medical University, Xuzhou, 221100, China
- Suzhou Medical College, Soochow University, Suzhou, 215123, China
| | - Peipei Xi
- Department of Emergency, Affiliated Hospital of Nantong University, Nantong University, Nantong, 226001, China
- Suzhou Medical College, Soochow University, Suzhou, 215123, China
| | - Minjie Chen
- Research Center of Clinical Medicine, Affiliated Hospital of Nantong University, Nantong, 226001, China
| | - Ya Wen
- Research Center of Clinical Medicine, Affiliated Hospital of Nantong University, Nantong, 226001, China
| | - Hao Wu
- Department of Otolaryngology, Affiliated Hospital of Nantong University, Nantong University, Nantong, 226001, China
| | - Li Wang
- Institutes of Biomedical Sciences and the Shanghai Key Laboratory of Medical Epigenetics, Shanghai Medical College, Fudan University, Shanghai, 200032, China
| | - Yujuan Zhu
- Research Center of Clinical Medicine, Affiliated Hospital of Nantong University, Nantong, 226001, China
| | - Yile Ren
- Department of Rheumatology, Affiliated Municipal Hospital of Xuzhou Medical University, Xuzhou, 221100, China
| | - Zhifeng Gu
- Department of Rheumatology, Research Center of Immunology, Affiliated Hospital of Nantong University, Nantong University, Nantong, 226001, China
| |
Collapse
|
|
7
|
Cao Q, Deng R, Pan Y, Liu R, Chen Y, Gong G, Zou J, Yang H, Han D. Robotic wireless capsule endoscopy: recent advances and upcoming technologies. Nat Commun 2024; 15:4597. [PMID: 38816464 PMCID: PMC11139981 DOI: 10.1038/s41467-024-49019-0] [Citation(s) in RCA: 14] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Accepted: 05/21/2024] [Indexed: 06/01/2024] Open
Abstract
Wireless capsule endoscopy (WCE) offers a non-invasive evaluation of the digestive system, eliminating the need for sedation and the risks associated with conventional endoscopic procedures. Its significance lies in diagnosing gastrointestinal tissue irregularities, especially in the small intestine. However, existing commercial WCE devices face limitations, such as the absence of autonomous lesion detection and treatment capabilities. Recent advancements in micro-electromechanical fabrication and computational methods have led to extensive research in sophisticated technology integration into commercial capsule endoscopes, intending to supersede wired endoscopes. This Review discusses the future requirements for intelligent capsule robots, providing a comparative evaluation of various methods' merits and disadvantages, and highlighting recent developments in six technologies relevant to WCE. These include near-field wireless power transmission, magnetic field active drive, ultra-wideband/intrabody communication, hybrid localization, AI-based autonomous lesion detection, and magnetic-controlled diagnosis and treatment. Moreover, we explore the feasibility for future "capsule surgeons".
Collapse
Affiliation(s)
- Qing Cao
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Runyi Deng
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Yue Pan
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Ruijie Liu
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Yicheng Chen
- Sir Run-Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, 310016, China
| | - Guofang Gong
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Jun Zou
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Huayong Yang
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Dong Han
- State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China.
- School of Mechanical Engineering, Zhejiang University, Hangzhou, 310027, China.
| |
Collapse
|
|
8
|
Mahmoodian N, Rezapourian M, Inamdar AA, Kumar K, Fachet M, Hoeschen C. Enabling Low-Dose In Vivo Benchtop X-ray Fluorescence Computed Tomography through Deep-Learning-Based Denoising. J Imaging 2024; 10:127. [PMID: 38921604 PMCID: PMC11204716 DOI: 10.3390/jimaging10060127] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2024] [Revised: 05/10/2024] [Accepted: 05/18/2024] [Indexed: 06/27/2024] Open
Abstract
X-ray Fluorescence Computed Tomography (XFCT) is an emerging non-invasive imaging technique providing high-resolution molecular-level data. However, increased sensitivity with current benchtop X-ray sources comes at the cost of high radiation exposure. Artificial Intelligence (AI), particularly deep learning (DL), has revolutionized medical imaging by delivering high-quality images in the presence of noise. In XFCT, traditional methods rely on complex algorithms for background noise reduction, but AI holds promise in addressing high-dose concerns. We present an optimized Swin-Conv-UNet (SCUNet) model for background noise reduction in X-ray fluorescence (XRF) images at low tracer concentrations. Our method's effectiveness is evaluated against higher-dose images, while various denoising techniques exist for X-ray and computed tomography (CT) techniques, only a few address XFCT. The DL model is trained and assessed using augmented data, focusing on background noise reduction. Image quality is measured using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), comparing outcomes with 100% X-ray-dose images. Results demonstrate that the proposed algorithm yields high-quality images from low-dose inputs, with maximum PSNR of 39.05 and SSIM of 0.86. The model outperforms block-matching and 3D filtering (BM3D), block-matching and 4D filtering (BM4D), non-local means (NLM), denoising convolutional neural network (DnCNN), and SCUNet in both visual inspection and quantitative analysis, particularly in high-noise scenarios. This indicates the potential of AI, specifically the SCUNet model, in significantly improving XFCT imaging by mitigating the trade-off between sensitivity and radiation exposure.
Collapse
Affiliation(s)
- Naghmeh Mahmoodian
- Chair of Medical Systems Technology, Institute for Medical Technology, Faculty of Electrical Engineering and Information Technology, Otto von Guericke University, 39106 Magdeburg, Germany; (M.R.); (A.A.I.); (K.K.); (M.F.); (C.H.)
| | | | | | | | | | | |
Collapse
|
|
9
|
Siddiqui S, Akram T, Ashraf I, Raza M, Khan MA, Damaševičius R. CG‐Net: A novel CNN framework for gastrointestinal tract diseases classification. INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2024; 34. [DOI: 10.1002/ima.23081] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/30/2023] [Accepted: 03/31/2024] [Indexed: 09/23/2024]
Abstract
AbstractThe classification of medical images has had a significant influence on the diagnostic techniques and therapeutic interventions. Conventional disease diagnosis procedures require a substantial amount of time and effort to accurately diagnose. Based on global statistics, gastrointestinal cancer has been recognized as a major contributor to cancer‐related deaths. The complexities involved in resolving gastrointestinal tract (GIT) ailments arise from the need for elaborate methods to precisely identify the exact location of the problem. Therefore, doctors frequently use wireless capsule endoscopy to diagnose and treat GIT problems. This research aims to develop a robust framework using deep learning techniques to effectively classify GIT diseases for therapeutic purposes. A CNN based framework, in conjunction with the feature selection method, has been proposed to improve the classification rate. The proposed framework has been evaluated using various performance measures, including accuracy, recall, precision, F1 measure, mean absolute error, and mean squared error.
Collapse
Affiliation(s)
- Samra Siddiqui
- Department of Computer Science HITEC University Taxila Pakistan
- Department of Computer Science COMSATS University Islamabad Wah Campus Pakistan
| | - Tallha Akram
- Department of Information Systems, College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al‐Kharj Saudi Arabia
- Department of Machine Learning Convex Solutions Pvt (Ltd) Islamabad Pakistan
| | - Imran Ashraf
- Department of Computer Science, Department of Computer Science NUCES (FAST) Islamabad Pakistan
| | - Muddassar Raza
- Department of Computer Science HITEC University Taxila Pakistan
| | | | | |
Collapse
|
|
10
|
Srinivasan S, Francis D, Mathivanan SK, Rajadurai H, Shivahare BD, Shah MA. A hybrid deep CNN model for brain tumor image multi-classification. BMC Med Imaging 2024; 24:21. [PMID: 38243215 PMCID: PMC10799524 DOI: 10.1186/s12880-024-01195-7] [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: 11/07/2023] [Accepted: 01/08/2024] [Indexed: 01/21/2024] Open
Abstract
The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-classification system for brain malignancies. This article aims to leverage a deep convolutional neural network (CNN) to enhance early detection and presents three distinct CNN models designed for different types of classification tasks. The first CNN model achieves an impressive detection accuracy of 99.53% for brain tumors. The second CNN model, with an accuracy of 93.81%, proficiently categorizes brain tumors into five distinct types: normal, glioma, meningioma, pituitary, and metastatic. Furthermore, the third CNN model demonstrates an accuracy of 98.56% in accurately classifying brain tumors into their different grades. To ensure optimal performance, a grid search optimization approach is employed to automatically fine-tune all the relevant hyperparameters of the CNN models. The utilization of large, publicly accessible clinical datasets results in robust and reliable classification outcomes. This article conducts a comprehensive comparison of the proposed models against classical models, such as AlexNet, DenseNet121, ResNet-101, VGG-19, and GoogleNet, reaffirming the superiority of the deep CNN-based approach in advancing the field of brain tumor classification and early detection.
Collapse
Affiliation(s)
- Saravanan Srinivasan
- Department of Computer Science and Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Chennai, 600062, India
| | - Divya Francis
- Department of Electronics and Communication Engineering, PSNA College of Engineering and Technology, Dindigul, 624622, India
| | | | - Hariharan Rajadurai
- School of Computing Science and Engineering, VIT Bhopal University, Bhopal-Indore Highway Kothrikalan, Sehore, 466114, India
| | - Basu Dev Shivahare
- School of Computing Science and Engineering, Galgotias University, Greater Noida, 203201, India
| | - Mohd Asif Shah
- Department of Economics, Kabridahar University, Po Box 250, Kebri Dehar, Ethiopia.
- Centre of Research Impact and Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, 140401, India.
- Division of Research and Development, Lovely Professional University, Phagwara, Punjab, 144001, India.
| |
Collapse
|
|
11
|
Zhang W, Lu F, Su H, Hu Y. Dual-branch multi-information aggregation network with transformer and convolution for polyp segmentation. Comput Biol Med 2024; 168:107760. [PMID: 38064849 DOI: 10.1016/j.compbiomed.2023.107760] [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: 04/19/2023] [Revised: 10/21/2023] [Accepted: 11/21/2023] [Indexed: 01/10/2024]
Abstract
Computer-Aided Diagnosis (CAD) for polyp detection offers one of the most notable showcases. By using deep learning technologies, the accuracy of polyp segmentation is surpassing human experts. In such CAD process, a critical step is concerned with segmenting colorectal polyps from colonoscopy images. Despite remarkable successes attained by recent deep learning related works, much improvement is still anticipated to tackle challenging cases. For instance, the effects of motion blur and light reflection can introduce significant noise into the image. The same type of polyps has a diversity of size, color and texture. To address such challenges, this paper proposes a novel dual-branch multi-information aggregation network (DBMIA-Net) for polyp segmentation, which is able to accurately and reliably segment a variety of colorectal polyps with efficiency. Specifically, a dual-branch encoder with transformer and convolutional neural networks (CNN) is employed to extract polyp features, and two multi-information aggregation modules are applied in the decoder to fuse multi-scale features adaptively. Two multi-information aggregation modules include global information aggregation (GIA) module and edge information aggregation (EIA) module. In addition, to enhance the representation learning capability of the potential channel feature association, this paper also proposes a novel adaptive channel graph convolution (ACGC). To validate the effectiveness and advantages of the proposed network, we compare it with several state-of-the-art (SOTA) methods on five public datasets. Experimental results consistently demonstrate that the proposed DBMIA-Net obtains significantly superior segmentation performance across six popularly used evaluation matrices. Especially, we achieve 94.12% mean Dice on CVC-ClinicDB dataset which is 4.22% improvement compared to the previous state-of-the-art method PraNet. Compared with SOTA algorithms, DBMIA-Net has a better fitting ability and stronger generalization ability.
Collapse
Affiliation(s)
- Wenyu Zhang
- School of Information Science and Engineering, Lanzhou University, China
| | - Fuxiang Lu
- School of Information Science and Engineering, Lanzhou University, China.
| | - Hongjing Su
- School of Information Science and Engineering, Lanzhou University, China
| | - Yawen Hu
- School of Information Science and Engineering, Lanzhou University, China
| |
Collapse
|
|
12
|
Wu S, Zhang R, Yan J, Li C, Liu Q, Wang L, Wang H. High-Speed and Accurate Diagnosis of Gastrointestinal Disease: Learning on Endoscopy Images Using Lightweight Transformer with Local Feature Attention. Bioengineering (Basel) 2023; 10:1416. [PMID: 38136007 PMCID: PMC10741161 DOI: 10.3390/bioengineering10121416] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Revised: 12/04/2023] [Accepted: 12/10/2023] [Indexed: 12/24/2023] Open
Abstract
In response to the pressing need for robust disease diagnosis from gastrointestinal tract (GIT) endoscopic images, we proposed FLATer, a fast, lightweight, and highly accurate transformer-based model. FLATer consists of a residual block, a vision transformer module, and a spatial attention block, which concurrently focuses on local features and global attention. It can leverage the capabilities of both convolutional neural networks (CNNs) and vision transformers (ViT). We decomposed the classification of endoscopic images into two subtasks: a binary classification to discern between normal and pathological images and a further multi-class classification to categorize images into specific diseases, namely ulcerative colitis, polyps, and esophagitis. FLATer has exhibited exceptional prowess in these tasks, achieving 96.4% accuracy in binary classification and 99.7% accuracy in ternary classification, surpassing most existing models. Notably, FLATer could maintain impressive performance when trained from scratch, underscoring its robustness. In addition to the high precision, FLATer boasted remarkable efficiency, reaching a notable throughput of 16.4k images per second, which positions FLATer as a compelling candidate for rapid disease identification in clinical practice.
Collapse
Affiliation(s)
- Shibin Wu
- Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China; (S.W.); (R.Z.); (J.Y.)
| | - Ruxin Zhang
- Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China; (S.W.); (R.Z.); (J.Y.)
| | - Jiayi Yan
- Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China; (S.W.); (R.Z.); (J.Y.)
| | - Chengquan Li
- School of Clinical Medicine, Tsinghua University, Beijing 100084, China;
| | - Qicai Liu
- Vanke School of Public Health, Tsinghua University, Beijing 100084, China;
| | - Liyang Wang
- School of Clinical Medicine, Tsinghua University, Beijing 100084, China;
| | - Haoqian Wang
- Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China; (S.W.); (R.Z.); (J.Y.)
| |
Collapse
|
|
13
|
Lu W, Jiang J, Shi Y, Zhong X, Gu J, Huangfu L, Gong M. Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition. Front Neurosci 2023; 17:1259652. [PMID: 37799340 PMCID: PMC10547885 DOI: 10.3389/fnins.2023.1259652] [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: 07/16/2023] [Accepted: 08/14/2023] [Indexed: 10/07/2023] Open
Abstract
Introduction In the medical field, electronic medical records contain a large amount of textual information, and the unstructured nature of this information makes data extraction and analysis challenging. Therefore, automatic extraction of entity information from electronic medical records has become a significant issue in the healthcare domain. Methods To address this problem, this paper proposes a deep learning-based entity information extraction model called Entity-BERT. The model aims to leverage the powerful feature extraction capabilities of deep learning and the pre-training language representation learning of BERT(Bidirectional Encoder Representations from Transformers), enabling it to automatically learn and recognize various entity types in medical electronic records, including medical terminologies, disease names, drug information, and more, providing more effective support for medical research and clinical practices. The Entity-BERT model utilizes a multi-layer neural network and cross-attention mechanism to process and fuse information at different levels and types, resembling the hierarchical and distributed processing of the human brain. Additionally, the model employs pre-trained language and sequence models to process and learn textual data, sharing similarities with the language processing and semantic understanding of the human brain. Furthermore, the Entity-BERT model can capture contextual information and long-term dependencies, combining the cross-attention mechanism to handle the complex and diverse language expressions in electronic medical records, resembling the information processing method of the human brain in many aspects. Additionally, exploring how to utilize competitive learning, adaptive regulation, and synaptic plasticity to optimize the model's prediction results, automatically adjust its parameters, and achieve adaptive learning and dynamic adjustments from the perspective of neuroscience and brain-like cognition is of interest. Results and discussion Experimental results demonstrate that the Entity-BERT model achieves outstanding performance in entity recognition tasks within electronic medical records, surpassing other existing entity recognition models. This research not only provides more efficient and accurate natural language processing technology for the medical and health field but also introduces new ideas and directions for the design and optimization of deep learning models.
Collapse
Affiliation(s)
- Weijia Lu
- Science and Technology Department, Affiliated Hospital of Nantong University, Nantong, China
- Jianghai Hospital of Nantong Sutong Science and Technology Park, Nantong, China
| | - Jiehui Jiang
- Department of Biomedical Engineering, Shanghai University, Shanghai, China
| | - Yaxiang Shi
- Network Information Center, Zhongda Hospital Southeast University, Nanjing, China
| | - Xiaowei Zhong
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China
| | - Jun Gu
- Department of Respiratory, Affiliated Hospital Nantong University, Nantong, China
| | - Lixia Huangfu
- Information Center Department, Affiliated Hospital of Nantong University, Nantong, China
| | - Ming Gong
- Information Center Department, Affiliated Hospital of Nantong University, Nantong, China
| |
Collapse
|
|
14
|
Bidokh E, Hassanpour H. Enhancing Wireless Capsule Endoscopy images from intense illumination specular reflections using the homomorphic filter. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/08/2023]
|
|
15
|
Horovistiz A, Oliveira M, Araújo H. Computer vision-based solutions to overcome the limitations of wireless capsule endoscopy. J Med Eng Technol 2023; 47:242-261. [PMID: 38231042 DOI: 10.1080/03091902.2024.2302025] [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: 09/09/2022] [Accepted: 12/28/2023] [Indexed: 01/18/2024]
Abstract
Endoscopic investigation plays a critical role in the diagnosis of gastrointestinal (GI) diseases. Since 2001, Wireless Capsule Endoscopy (WCE) has been available for small bowel exploration and is in continuous development. Over the last decade, WCE has achieved impressive improvements in areas such as miniaturisation, image quality and battery life. As a result, WCE is currently a very useful alternative to wired enteroscopy in the investigation of various small bowel abnormalities and has the potential to become the leading screening technique for the entire gastrointestinal tract. However, commercial solutions still have several limitations, namely incomplete examination and limited diagnostic capacity. These deficiencies are related to technical issues, such as image quality, motion estimation and power consumption management. Computational methods, based on image processing and analysis, can help to overcome these challenges and reduce both the time required by reviewers and human interpretation errors. Research groups have proposed a series of methods including algorithms for locating the capsule or lesion, assessing intestinal motility and improving image quality.In this work, we provide a critical review of computational vision-based methods for WCE image analysis aimed at overcoming the technological challenges of capsules. This article also reviews several representative public datasets used to evaluate the performance of WCE techniques and methods. Finally, some promising solutions of computational methods based on the analysis of multiple-camera endoscopic images are presented.
Collapse
Affiliation(s)
- Ana Horovistiz
- Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal
| | - Marina Oliveira
- Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal
- Department of Electrical and Computer Engineering (DEEC), Faculty of Sciences and Technology, University of Coimbra, Coimbra, Portugal
| | - Helder Araújo
- Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal
- Department of Electrical and Computer Engineering (DEEC), Faculty of Sciences and Technology, University of Coimbra, Coimbra, Portugal
| |
Collapse
|
|
16
|
Liver CT Image Recognition Method Based on Capsule Network. INFORMATION 2023. [DOI: 10.3390/info14030183] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/17/2023] Open
Abstract
The automatic recognition of CT (Computed Tomography) images of liver cancer is important for the diagnosis and treatment of early liver cancer. However, there are problems such as single model structure and loss of pooling layer information when using a traditional convolutional neural network to recognize CT images of liver cancer. Therefore, this paper proposes an efficient method for liver CT image recognition based on the capsule network (CapsNet). Firstly, the liver CT images are preprocessed, and in the process of image denoising, the traditional non-local mean (NLM) denoising algorithm is optimized with a superpixel segmentation algorithm to better protect the information of image edges. After that, CapsNet was used for image recognition for liver CT images. The experimental results show that the average recognition rate of liver CT images reaches 92.9% when CapsNet is used, which is 5.3% higher than the traditional CNN model, indicating that CapsNet has better recognition accuracy for liver CT images.
Collapse
|
|
17
|
Satrya GB, Ramatryana INA, Shin SY. Compressive Sensing of Medical Images Based on HSV Color Space. SENSORS (BASEL, SWITZERLAND) 2023; 23:2616. [PMID: 36904821 PMCID: PMC10006955 DOI: 10.3390/s23052616] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Revised: 02/06/2023] [Accepted: 02/21/2023] [Indexed: 06/18/2023]
Abstract
Recently, compressive sensing (CS) schemes have been studied as a new compression modality that exploits the sensing matrix in the measurement scheme and the reconstruction scheme to recover the compressed signal. In addition, CS is exploited in medical imaging (MI) to support efficient sampling, compression, transmission, and storage of a large amount of MI. Although CS of MI has been extensively investigated, the effect of color space in CS of MI has not yet been studied in the literature. To fulfill these requirements, this article proposes a novel CS of MI based on hue-saturation value (HSV), using spread spectrum Fourier sampling (SSFS) and sparsity averaging with reweighted analysis (SARA). An HSV loop that performs SSFS is proposed to obtain a compressed signal. Next, HSV-SARA is proposed to reconstruct MI from the compressed signal. A set of color MIs is investigated, such as colonoscopy, magnetic resonance imaging of the brain and eye, and wireless capsule endoscopy images. Experiments were performed to show the superiority of HSV-SARA over benchmark methods in terms of signal-to-noise ratio (SNR), structural similarity (SSIM) index, and measurement rate (MR). The experiments showed that a color MI, with a resolution of 256×256 pixels, could be compressed by the proposed CS at MR of 0.1, and could be improved in terms of SNR being 15.17% and SSIM being 2.53%. The proposed HSV-SARA can be a solution for color medical image compression and sampling to improve the image acquisition of medical devices.
Collapse
Affiliation(s)
| | - I Nyoman Apraz Ramatryana
- Department of IT Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, Republic of Korea
| | - Soo Young Shin
- Department of IT Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, Republic of Korea
| |
Collapse
|
|
18
|
Liu S, Wang H, Li Y, Li X, Cao G, Cao W. AHU-MultiNet: Adaptive loss balancing based on homoscedastic uncertainty in multi-task medical image segmentation network. Comput Biol Med 2022; 150:106157. [PMID: 37859277 DOI: 10.1016/j.compbiomed.2022.106157] [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: 05/30/2022] [Revised: 09/05/2022] [Accepted: 09/24/2022] [Indexed: 11/19/2022]
Abstract
Medical image segmentation is an important field in medical image analysis and a vital part of computer-aided diagnosis. Due to the challenges in acquiring image annotations, semi-supervised learning has attracted high attention in medical image segmentation. Despite their impressive performance, most existing semi-supervised approaches lack attention to ambiguous regions (e.g., some edges or corners around the organs). To achieve better performance, we propose a novel semi-supervised method called Adaptive Loss Balancing based on Homoscedastic Uncertainty in Multi-task Medical Image Segmentation Network (AHU-MultiNet). This model contains the main task for segmentation, one auxiliary task for signed distance, and another auxiliary task for contour detection. Our multi-task approach can effectively and sufficiently extract the semantic information of medical images by auxiliary tasks. Simultaneously, we introduce an inter-task consistency to explore the underlying information of the images and regularize the predictions in the right direction. More importantly, we notice and analyze that searching an optimal weighting manually to balance each task is a difficult and time-consuming process. Therefore, we introduce an adaptive loss balancing strategy based on homoscedastic uncertainty. Experimental results show that the two auxiliary tasks explicitly enforce shape-priors on the segmentation output to further generate more accurate masks under the adaptive loss balancing strategy. On several standard benchmarks, the 2018 Atrial Segmentation Challenge and the 2017 Liver Tumor Segmentation Challenge, our proposed method achieves improvements and outperforms the new state-of-the-art in semi-supervised learning.
Collapse
Affiliation(s)
- Shasha Liu
- The MOE Research Center for Software/Hardware Co-Design Engineering, East China Normal University, Shanghai, China.
| | - Hailing Wang
- The MOE Research Center for Software/Hardware Co-Design Engineering, East China Normal University, Shanghai, China.
| | - Yan Li
- The MOE Research Center for Software/Hardware Co-Design Engineering, East China Normal University, Shanghai, China.
| | - Xiaohu Li
- The MOE Research Center for Software/Hardware Co-Design Engineering, East China Normal University, Shanghai, China.
| | - Guitao Cao
- The MOE Research Center for Software/Hardware Co-Design Engineering, East China Normal University, Shanghai, China.
| | - Wenming Cao
- The College of Information Engineering, Shenzhen University, Shenzhen, China.
| |
Collapse
|
|
19
|
Gilabert P, Vitrià J, Laiz P, Malagelada C, Watson A, Wenzek H, Segui S. Artificial intelligence to improve polyp detection and screening time in colon capsule endoscopy. Front Med (Lausanne) 2022; 9:1000726. [PMCID: PMC9606587 DOI: 10.3389/fmed.2022.1000726] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2022] [Accepted: 09/23/2022] [Indexed: 11/13/2022] Open
Abstract
Colon Capsule Endoscopy (CCE) is a minimally invasive procedure which is increasingly being used as an alternative to conventional colonoscopy. Videos recorded by the capsule cameras are long and require one or more experts' time to review and identify polyps or other potential intestinal problems that can lead to major health issues. We developed and tested a multi-platform web application, AI-Tool, which embeds a Convolution Neural Network (CNN) to help CCE reviewers. With the help of artificial intelligence, AI-Tool is able to detect images with high probability of containing a polyp and prioritize them during the reviewing process. With the collaboration of 3 experts that reviewed 18 videos, we compared the classical linear review method using RAPID Reader Software v9.0 and the new software we present. Applying the new strategy, reviewing time was reduced by a factor of 6 and polyp detection sensitivity was increased from 81.08 to 87.80%.
Collapse
Affiliation(s)
- Pere Gilabert
- Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain,*Correspondence: Pere Gilabert
| | - Jordi Vitrià
- Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain
| | - Pablo Laiz
- Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain
| | - Carolina Malagelada
- Digestive System Research Unit, University Hospital Vall d'Hebron, Barcelona, Spain,Department of Medicine, Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Angus Watson
- Department of Colorectal Surgery, Raigmore Hospital, NHS Highland, Inverness, United Kingdom
| | - Hagen Wenzek
- CorporateHealth International ApS, Odense, Denmark
| | - Santi Segui
- Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain
| |
Collapse
|
|
20
|
How Resilient Are Deep Learning Models in Medical Image Analysis? The Case of the Moment-Based Adversarial Attack (Mb-AdA). Biomedicines 2022; 10:biomedicines10102545. [PMID: 36289807 PMCID: PMC9599099 DOI: 10.3390/biomedicines10102545] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Revised: 10/08/2022] [Accepted: 10/10/2022] [Indexed: 11/17/2022] Open
Abstract
In the past years, deep neural networks (DNNs) have become popular in many disciplines such as computer vision (CV). One of the most important challenges in the CV area is Medical Image Analysis (MIA). However, adversarial attacks (AdAs) have proven to be an important threat to vision systems by significantly reducing the performance of the models. This paper proposes a new black-box adversarial attack, which is based οn orthogonal image moments named Mb-AdA. Additionally, a corresponding defensive method of adversarial training using Mb-AdA adversarial examples is also investigated, with encouraging results. The proposed attack was applied in classification and segmentation tasks with six state-of-the-art Deep Learning (DL) models in X-ray, histopathology and nuclei cell images. The main advantage of Mb-AdA is that it does not destroy the structure of images like other attacks, as instead of adding noise it removes specific image information, which is critical for medical models' decisions. The proposed attack is more effective than compared ones and achieved degradation up to 65% and 18% in terms of accuracy and IoU for classification and segmentation tasks, respectively, by also presenting relatively high SSIM. At the same time, it was proved that Mb-AdA adversarial examples can enhance the robustness of the model.
Collapse
|
|
21
|
Nian B, Wang B, Wang L, Yi L. A Cohort Study to Compare Effects between Ulcer- and Nonulcer-Related Nonvariceal Upper Gastrointestinal Bleeding. Appl Bionics Biomech 2022; 2022:3342919. [PMID: 35721238 PMCID: PMC9205735 DOI: 10.1155/2022/3342919] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2022] [Revised: 05/09/2022] [Accepted: 05/17/2022] [Indexed: 11/18/2022] Open
Abstract
Objective The aim of this study was to better understand the characteristics and etiology of acute nonvariceal upper gastrointestinal bleeding (ANVUGIB) in recent years in this region and to provide evidence-based medical evidence. Methods 100 patients with acute nonvariceal upper gastrointestinal bleeding (ANVUGIB) who met the clinical diagnostic criteria of ANVUGIB admitted to Suzhou First People's Hospital from January 2017 to December 2021 were analyzed, as well as the age difference and change rule. According to age, 100 patients were divided into young (18-39 years), middle-aged (40-59 years), and elderly (60 years and above), and the differences in the three groups were compared. The etiology was confirmed by endoscopic examination and was recorded one by one in a well-designed ANVUGIB case data registration form. Statistical software SPSS 23.0 was used for analysis. Results Gastric ulcer was the main cause in the elderly group (50.0%), duodenal ulcer was the main cause in the middle and young groups, and gastrointestinal cancer (7.1%) and marginal ulcer (2.3%) in the elderly group were higher than those in the young group. Nonsteroidal anti-inflammatory drugs (52.3%) were the main inducement in the elderly group, which was significantly higher than in the middle-aged group (13.1%) and the young group (5%) (P < 0.01). Drinking, fatigue, and emotional excitement led to a higher proportion in the middle-aged group and the young group, in comparison to the elderly group (P < 0.01). Conclusion Peptic ulcer is the most common cause of acute nonvariceal upper gastrointestinal bleeding, followed by acute gastric mucosal lesions and upper digestive system tumors, compared with nonulcer.
Collapse
Affiliation(s)
- Bi Nian
- Department of Gastroenterology, Suzhou First People's Hospital, China
| | - Bangping Wang
- Department of Gastroenterology, Suzhou First People's Hospital, China
| | - Long Wang
- Gastroenterology Department, Suzhou Municipal Hospital, China
| | - Lanjuan Yi
- Department of Gastroenterology, Yantai Mountain Hospital, Yantai, China
| |
Collapse
|
|
22
|
Macedo Silva V, Freitas M, Boal Carvalho P, Dias de Castro F, Cúrdia Gonçalves T, Rosa B, Moreira MJ, Cotter J. Apex Score: Predicting Flares in Small-Bowel Crohn's Disease After Mucosal Healing. Dig Dis Sci 2022; 67:1278-1286. [PMID: 34291329 DOI: 10.1007/s10620-021-07148-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/03/2020] [Accepted: 12/30/2020] [Indexed: 01/04/2023]
Abstract
BACKGROUND Optimal strategies for using small-bowel capsule endoscopy (SBCE) in established small-bowel Crohn's disease (CD) remain uncertain. Mucosal healing (MH) has emerged as a valuable predictor of a flare-free disease. We aimed to evaluate the occurrence of disease flare on patients with small-bowel CD and MH, as well as to create a score identifying patients in higher risk for this outcome. METHODS We analyzed consecutive patients submitted to SBCE for assessment of MH and included those where MH was confirmed. The incidence of disease flare was assessed during follow-up (minimum 12 months). A score predicting disease flare was created from several analyzed variables. RESULTS From 47 patients with MH, 12 (25.5%) had a flare (versus 48.3% in excluded patients without MH; p = 0.01). Age ≤ 30 years (OR = 70; p = 0.048), platelet count ≥ 280 × 103/L (OR = 12.24; p = 0.045) and extra-intestinal manifestations (OR = 11.76; p = 0.033) were associated with increased risk of CD flare during the first year after SBCE with MH. These variables were used to compute a risk-predicting score-the APEX score-which assigned the patients to having low (0-3 points) or high-risk (4-7 points) of disease flare and had excellent accuracy toward predicting disease relapse (AUC = 0.82; 95%CI 0.64-0.99). CONCLUSION Patients with small-bowel CD and MH were not free of disease flares on the subsequent year, despite presenting lower rates when compared to those without MH. The APEX score demonstrated excellent accuracy at stratifying patients relapse risk and guiding further therapeutic options for patients achieving MH.
Collapse
Affiliation(s)
- Vítor Macedo Silva
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal.
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal.
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal.
| | - Marta Freitas
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal
| | - Pedro Boal Carvalho
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal
| | - Francisca Dias de Castro
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal
| | - Tiago Cúrdia Gonçalves
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal
| | - Bruno Rosa
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal
| | - Maria João Moreira
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal
| | - José Cotter
- Gastroenterology Department, Hospital da Senhora da Oliveira, Rua Dos Cutileiros, Creixomil, 4835-044, Guimarães, Portugal
- Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal
- ICVS/3B's, PT Government Associate Laboratory, Braga/Guimarães, Portugal
| |
Collapse
|
|
23
|
Reuss J, Pascual G, Wenzek H, Seguí S. Sequential Models for Endoluminal Image Classification. Diagnostics (Basel) 2022; 12:501. [PMID: 35204591 PMCID: PMC8871077 DOI: 10.3390/diagnostics12020501] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2021] [Revised: 02/04/2022] [Accepted: 02/11/2022] [Indexed: 11/30/2022] Open
Abstract
Wireless Capsule Endoscopy (WCE) is a procedure to examine the human digestive system for potential mucosal polyps, tumours, or bleedings using an encapsulated camera. This work focuses on polyp detection within WCE videos through Machine Learning. When using Machine Learning in the medical field, scarce and unbalanced datasets often make it hard to receive a satisfying performance. We claim that using Sequential Models in order to take the temporal nature of the data into account improves the performance of previous approaches. Thus, we present a bidirectional Long Short-Term Memory Network (BLSTM), a sequential network that is particularly designed for temporal data. We find the BLSTM Network outperforms non-sequential architectures and other previous models, receiving a final Area under the Curve of 93.83%. Experiments show that our method of extracting spatial and temporal features yields better performance and could be a possible method to decrease the time needed by physicians to analyse the video material.
Collapse
Affiliation(s)
- Joana Reuss
- Department of Mathematics and Computer Science, Universitat de Barcelona, 08007 Barcelona, Spain; (G.P.); (S.S.)
- Chair of Remote Sensing Technology, Technical University of Munich, 80333 Munich, Germany
| | - Guillem Pascual
- Department of Mathematics and Computer Science, Universitat de Barcelona, 08007 Barcelona, Spain; (G.P.); (S.S.)
| | - Hagen Wenzek
- CorporateHealth International ApS, 5230 Odense, Denmark;
| | - Santi Seguí
- Department of Mathematics and Computer Science, Universitat de Barcelona, 08007 Barcelona, Spain; (G.P.); (S.S.)
| |
Collapse
|
|
24
|
AIM in Endoscopy Procedures. Artif Intell Med 2022. [DOI: 10.1007/978-3-030-64573-1_164] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
|
|
25
|
Gastrointestinal Tract Disease Classification from Wireless Endoscopy Images Using Pretrained Deep Learning Model. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2021; 2021:5940433. [PMID: 34545292 PMCID: PMC8449743 DOI: 10.1155/2021/5940433] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/10/2021] [Revised: 07/03/2021] [Accepted: 08/16/2021] [Indexed: 12/28/2022]
Abstract
Wireless capsule endoscopy is a noninvasive wireless imaging technology that becomes increasingly popular in recent years. One of the major drawbacks of this technology is that it generates a large number of photos that must be analyzed by medical personnel, which takes time. Various research groups have proposed different image processing and machine learning techniques to classify gastrointestinal tract diseases in recent years. Traditional image processing algorithms and a data augmentation technique are combined with an adjusted pretrained deep convolutional neural network to classify diseases in the gastrointestinal tract from wireless endoscopy images in this research. We take advantage of pretrained models VGG16, ResNet-18, and GoogLeNet, a convolutional neural network (CNN) model with adjusted fully connected and output layers. The proposed models are validated with a dataset consisting of 6702 images of 8 classes. The VGG16 model achieved the highest results with 96.33% accuracy, 96.37% recall, 96.5% precision, and 96.5% F1-measure. Compared to other state-of-the-art models, the VGG16 model has the highest Matthews Correlation Coefficient value of 0.95 and Cohen's kappa score of 0.96.
Collapse
|
|
26
|
Jain S, Seal A, Ojha A, Yazidi A, Bures J, Tacheci I, Krejcar O. A deep CNN model for anomaly detection and localization in wireless capsule endoscopy images. Comput Biol Med 2021; 137:104789. [PMID: 34455302 DOI: 10.1016/j.compbiomed.2021.104789] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2021] [Revised: 08/18/2021] [Accepted: 08/18/2021] [Indexed: 12/22/2022]
Abstract
Wireless capsule endoscopy (WCE) is one of the most efficient methods for the examination of gastrointestinal tracts. Computer-aided intelligent diagnostic tools alleviate the challenges faced during manual inspection of long WCE videos. Several approaches have been proposed in the literature for the automatic detection and localization of anomalies in WCE images. Some of them focus on specific anomalies such as bleeding, polyp, lesion, etc. However, relatively fewer generic methods have been proposed to detect all those common anomalies simultaneously. In this paper, a deep convolutional neural network (CNN) based model 'WCENet' is proposed for anomaly detection and localization in WCE images. The model works in two phases. In the first phase, a simple and efficient attention-based CNN classifies an image into one of the four categories: polyp, vascular, inflammatory, or normal. If the image is classified in one of the abnormal categories, it is processed in the second phase for the anomaly localization. Fusion of Grad-CAM++ and a custom SegNet is used for anomalous region segmentation in the abnormal image. WCENet classifier attains accuracy and area under receiver operating characteristic of 98% and 99%. The WCENet segmentation model obtains a frequency weighted intersection over union of 81%, and an average dice score of 56% on the KID dataset. WCENet outperforms nine different state-of-the-art conventional machine learning and deep learning models on the KID dataset. The proposed model demonstrates potential for clinical applications.
Collapse
Affiliation(s)
- Samir Jain
- PDPM Indian Institute of Information Technology, Design and Manufacturing, Jabalpur, 482005, India
| | - Ayan Seal
- PDPM Indian Institute of Information Technology, Design and Manufacturing, Jabalpur, 482005, India.
| | - Aparajita Ojha
- PDPM Indian Institute of Information Technology, Design and Manufacturing, Jabalpur, 482005, India
| | - Anis Yazidi
- Department of Computer Science, OsloMet - Oslo Metropolitan University, Oslo, Norway; Department of Plastic and Reconstructive Surgery, Oslo University Hospital, Oslo, Norway; Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
| | - Jan Bures
- Second Department of Internal Medicine-Gastroenterology, Charles University, Faculty of Medicine in Hradec Kralove and University Hospital Hradec Kralove, Sokolska 581, Hradec Kralove, 50005, Czech Republic
| | - Ilja Tacheci
- Second Department of Internal Medicine-Gastroenterology, Charles University, Faculty of Medicine in Hradec Kralove and University Hospital Hradec Kralove, Sokolska 581, Hradec Kralove, 50005, Czech Republic
| | - Ondrej Krejcar
- Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Hradecka 1249, Hradec Kralove, 50003, Czech Republic; Malaysia Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100, Kuala Lumpur, Malaysia
| |
Collapse
|
|
27
|
Smedsrud PH, Thambawita V, Hicks SA, Gjestang H, Nedrejord OO, Næss E, Borgli H, Jha D, Berstad TJD, Eskeland SL, Lux M, Espeland H, Petlund A, Nguyen DTD, Garcia-Ceja E, Johansen D, Schmidt PT, Toth E, Hammer HL, de Lange T, Riegler MA, Halvorsen P. Kvasir-Capsule, a video capsule endoscopy dataset. Sci Data 2021; 8:142. [PMID: 34045470 PMCID: PMC8160146 DOI: 10.1038/s41597-021-00920-z] [Citation(s) in RCA: 42] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2020] [Accepted: 04/15/2021] [Indexed: 12/12/2022] Open
Abstract
Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.
Collapse
Affiliation(s)
- Pia H Smedsrud
- SimulaMet, Oslo, Norway.
- University of Oslo, Oslo, Norway.
- Augere Medical AS, Oslo, Norway.
| | | | - Steven A Hicks
- SimulaMet, Oslo, Norway
- Oslo Metropolitan University, Oslo, Norway
| | | | | | - Espen Næss
- SimulaMet, Oslo, Norway
- University of Oslo, Oslo, Norway
| | - Hanna Borgli
- SimulaMet, Oslo, Norway
- University of Oslo, Oslo, Norway
| | - Debesh Jha
- SimulaMet, Oslo, Norway
- UIT The Arctic University of Norway, Tromsø, Norway
| | | | | | | | | | | | | | | | - Dag Johansen
- UIT The Arctic University of Norway, Tromsø, Norway
| | - Peter T Schmidt
- Karolinska Institutet, Department of Medicine, Solna, Sweden
- Ersta Hospital, Department of Medicine, Stockholm, Sweden
| | - Ervin Toth
- Department of Gastroenterology, Skåne University Hospital, Malmö Lund University, Malmö, Sweden
| | - Hugo L Hammer
- SimulaMet, Oslo, Norway
- Oslo Metropolitan University, Oslo, Norway
| | - Thomas de Lange
- Department of Medical Research, Bærum Hospital, Gjettum, Norway
- Augere Medical AS, Oslo, Norway
- Medical Department, Sahlgrenska University Hospital-Mölndal Hospital, Göteborg, Sweden
- Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg, Göteborg, Sweden
| | | | - Pål Halvorsen
- SimulaMet, Oslo, Norway
- Oslo Metropolitan University, Oslo, Norway
| |
Collapse
|
|
28
|
Rahim T, Novamizanti L, Apraz Ramatryana IN, Shin SY. Compressed medical imaging based on average sparsity model and reweighted analysis of multiple basis pursuit. Comput Med Imaging Graph 2021; 90:101927. [PMID: 33930735 DOI: 10.1016/j.compmedimag.2021.101927] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2020] [Revised: 02/17/2021] [Accepted: 04/05/2021] [Indexed: 11/28/2022]
Abstract
In medical imaging and applications, efficient image sampling and transfer are some of the key fields of research. The compressed sensing (CS) theory has shown that such compression can be performed during the data retrieval process and that the uncompressed image can be retrieved using a computationally flexible optimization method. The objective of this study is to propose compressed medical imaging for a different type of medical images, based on the combination of the average sparsity model and reweighted analysis of multiple basis pursuit (M-BP) reconstruction methods, referred to as multiple basis reweighted analysis (M-BRA). The proposed algorithm includes the joint multiple sparsity averaging to improves the signal sparsity in M-BP. In this study, four types of medical images are opted to fill the gap of lacking a detailed analysis of M-BRA in medical images. The medical dataset consists of magnetic resonance imaging (MRI) data, computed tomography (CT) data, colonoscopy data, and endoscopy data. Employing the proposed approach, a signal-to-noise ratio (SNR) of 30 dB was achieved for MRI data on a sampling ratio of M/N=0.3. SNR of 34, 30, and 34 dB are corresponding to CT, colonoscopy, and endoscopy data on the same sampling ratio of M/N=0.15. The proposed M-BRA performance indicates the potential for compressed medical imaging analysis with high reconstruction image quality.
Collapse
Affiliation(s)
- Tariq Rahim
- Department of IT Convergence Engineering, Kumoh National Institute of Technology (KIT), Gumi 39177, South Korea
| | - Ledya Novamizanti
- School of Electrical Engineering, Telkom University, Bandung 40257, Indonesia
| | - I Nyoman Apraz Ramatryana
- Department of IT Convergence Engineering, Kumoh National Institute of Technology (KIT), Gumi 39177, South Korea
| | - Soo Young Shin
- Department of IT Convergence Engineering, Kumoh National Institute of Technology (KIT), Gumi 39177, South Korea.
| |
Collapse
|
|
29
|
Rathnamala S, Jenicka S. Automated bleeding detection in wireless capsule endoscopy images based on color feature extraction from Gaussian mixture model superpixels. Med Biol Eng Comput 2021; 59:969-987. [PMID: 33837919 DOI: 10.1007/s11517-021-02352-8] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2020] [Accepted: 03/19/2021] [Indexed: 12/22/2022]
Abstract
Wireless capsule endoscopy is the commonly employed modality in the treatment of gastrointestinal tract pathologies. However, the time taken for interpretation of these images is very high due to the large volume of images generated. Automated detection of disorders with these images can facilitate faster clinical interventions. In this paper, we propose an automated system based on Gaussian mixture model superpixels for bleeding detection and segmentation of candidate regions. The proposed system is realized with a classic binary support vector machine classifier trained with seven features including color and texture attributes extracted from the Gaussian mixture model superpixels of the WCE images. On detection of bleeding images, bleeding regions are segmented from them, by incrementally grouping the superpixels based on deltaE color differences. Tested with standard datasets, this system exhibits best performance compared to the state-of-the-art approaches with respect to classification accuracy, feature selection, computational time, and segmentation accuracy. The proposed system achieves 99.88% accuracy, 99.83% sensitivity, and 100% specificity signifying the effectiveness of the proposed system in bleeding detection with very few classification errors.
Collapse
Affiliation(s)
- S Rathnamala
- Department of Information Technology, Sethu Institute of Technology, Virudhunagar District, Kariapatti, Tamil Nadu, 626115, India.
| | - S Jenicka
- Department of CSE, Sethu Institute of Technology, Virudhunagar District, Kariapatti, Tamil Nadu, 626115, India
| |
Collapse
|
|
30
|
3D-semantic segmentation and classification of stomach infections using uncertainty aware deep neural networks. COMPLEX INTELL SYST 2021. [DOI: 10.1007/s40747-021-00328-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
AbstractWireless capsule endoscopy (WCE) might move through human body and captures the small bowel and captures the video and require the analysis of all frames of video due to which the diagnosis of gastrointestinal infections by the physician is a tedious task. This tiresome assignment has fuelled the researcher’s efforts to present an automated technique for gastrointestinal infections detection. The segmentation of stomach infections is a challenging task because the lesion region having low contrast and irregular shape and size. To handle this challenging task, in this research work a new deep semantic segmentation model is suggested for 3D-segmentation of the different types of stomach infections. In the segmentation model, deep labv3 is employed as a backbone of the ResNet-50 model. The model is trained with ground-masks and accurately performs pixel-wise classification in the testing phase. Similarity among the different types of stomach lesions accurate classification is a difficult task, which is addressed in this reported research by extracting deep features from global input images using a pre-trained ResNet-50 model. Furthermore, the latest advances in the estimation of uncertainty and model interpretability in the classification of different types of stomach infections is presented. The classification results estimate uncertainty related to the vital features in input and show how uncertainty and interpretability might be modeled in ResNet-50 for the classification of the different types of stomach infections. The proposed model achieved up to 90% prediction scores to authenticate the method performance.
Collapse
|
|
31
|
Marzullo A, Moccia S, Calimeri F, De Momi E. AIM in Endoscopy Procedures. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_164-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/07/2022]
|
|
32
|
Laiz P, Vitrià J, Wenzek H, Malagelada C, Azpiroz F, Seguí S. WCE polyp detection with triplet based embeddings. Comput Med Imaging Graph 2020; 86:101794. [PMID: 33130417 DOI: 10.1016/j.compmedimag.2020.101794] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2020] [Revised: 09/17/2020] [Accepted: 09/18/2020] [Indexed: 12/20/2022]
Abstract
Wireless capsule endoscopy is a medical procedure used to visualize the entire gastrointestinal tract and to diagnose intestinal conditions, such as polyps or bleeding. Current analyses are performed by manually inspecting nearly each one of the frames of the video, a tedious and error-prone task. Automatic image analysis methods can be used to reduce the time needed for physicians to evaluate a capsule endoscopy video. However these methods are still in a research phase. In this paper we focus on computer-aided polyp detection in capsule endoscopy images. This is a challenging problem because of the diversity of polyp appearance, the imbalanced dataset structure and the scarcity of data. We have developed a new polyp computer-aided decision system that combines a deep convolutional neural network and metric learning. The key point of the method is the use of the Triplet Loss function with the aim of improving feature extraction from the images when having small dataset. The Triplet Loss function allows to train robust detectors by forcing images from the same category to be represented by similar embedding vectors while ensuring that images from different categories are represented by dissimilar vectors. Empirical results show a meaningful increase of AUC values compared to state-of-the-art methods. A good performance is not the only requirement when considering the adoption of this technology to clinical practice. Trust and explainability of decisions are as important as performance. With this purpose, we also provide a method to generate visual explanations of the outcome of our polyp detector. These explanations can be used to build a physician's trust in the system and also to convey information about the inner working of the method to the designer for debugging purposes.
Collapse
Affiliation(s)
- Pablo Laiz
- Department of Mathematics and Computer Science, Universitat de Barcelona, Barcelona, Spain.
| | - Jordi Vitrià
- Department of Mathematics and Computer Science, Universitat de Barcelona, Barcelona, Spain
| | | | - Carolina Malagelada
- Digestive System Research Unit, University Hospital Vall d'Hebron, Barcelona, Spain
| | - Fernando Azpiroz
- Digestive System Research Unit, University Hospital Vall d'Hebron, Barcelona, Spain
| | - Santi Seguí
- Department of Mathematics and Computer Science, Universitat de Barcelona, Barcelona, Spain
| |
Collapse
|