Deep‐learning system for real‐time differentiation between Crohn's disease, intestinal Behçet's disease, and intestinal tuberculosis

Abstract

Background and Aim: Pattern analysis of big data can provide a superior direction for the clinical differentiation of diseases with similar endoscopic findings. This study aimed to develop a deep-learning algorithm that performs differential diagnosis between intestinal Behçet's disease (BD), Crohn's disease (CD), and intestinal tuberculosis (ITB) using colonoscopy images. Methods: The typical pattern for each disease was defined as a typical image. We implemented a convolutional neural network (CNN) using Pytorch and visualized a deep-learning model through Gradient-weighted Class Activation Mapping. The performance of the algorithm was evaluated using the area under the receiver operating characteristic curve (AUROC). Results: A total of 6617 colonoscopy images of 211 CD, 299 intestinal BD, and 217 ITB patients were used. The accuracy of the algorithm for discriminating the three diseases (all-images: 65.15% vs typical images: 72.01%, P = 0.024) and discriminating between intestinal BD and CD (all-images: 78.15% vs typical images: 85.62%, P = 0.010) was significantly different between all-images and typical images. The CNN clearly differentiated colonoscopy images of the diseases (AUROC from 0.7846 to 0.8586). Algorithmic prediction AUROC for typical images ranged from 0.8211 to 0.9360. Conclusion:This study found that a deep-learning model can discriminate between colonoscopy images of intestinal BD, CD, and ITB. In particular, the algorithm demonstrated superior discrimination ability for typical images. This approach presents a beneficial method for the differential diagnosis of the diseases. manuscript writing, and revision of the manuscript. Jun Gu Kang performed the concept, design, data collection, computational analysis, interpretation of data, manuscript writing, and revision of the manuscript. Sungwon Kim made the concept, design, data collection, critical revision of the manuscript, and final approval. Jae Hee Cheon made the concept, design, data collection, revise the manuscript, critical revision of the manuscript, and final approval.

Clinical application and diagnostic accuracy of artificial intelligence in colonoscopy for inflammatory bowel disease: systematic review

“…Table 1 summarizes the study characteristics of all articles included in the systematic review, including the study design, the clinical application, size of the dataset and AI algorithm used. Eight studies 20 21 22 23 24 25 26 with 7086 patients were on the use of AI in ulcerative colitis (UC) and one study 27 with 727 patients evaluated the use of AI in differentiation of CD from Bechet’s disease and intestinal tuberculosis. The first article on the topic of AI in colonoscopic imaging of IBD appeared in 2019.…”

“…The first article on the topic of AI in colonoscopic imaging of IBD appeared in 2019. Five studies were conducted in the United States, 20 23 24 25 28 three in Japan, 21 22 26 and one in South Korea 27 . Five studies were single-center and retrospective in study design.…”

Differentiation of intestinal tuberculosis and Crohn’s disease through an explainable machine learning method

“…Israrahmed et al conduct a prospective study, which proposed multiple variables to arrive at the final diagnosis of CD and ITB 41 . Especially, Kim et al develop a deep-learning system for differentiation between Crohn’s disease, intestinal Behcet’s disease (BD) and intestinal tuberculosis using 6617 colonoscopy images of 211 CD, 299 BD and 217 ITB patients 42 . It is undeniable that the larger the sample size, the more meaningful the results are.…”

“…Better method for improved differentiation is needed to reduce the need for ATT trial. Many researchers have been established several models to address this issue by using the clinical symptoms, laboratory tests, endoscopic findings and so on 42 . It is undeniable that the larger the sample size, the more meaningful the results are.…”

Evolution in the Practice of Pediatric Endoscopy and Sedation

“…With AI steadily on the rise, endoscopy centers interested in cutting edge technology should consider pioneering these systems within the pediatric population. AI has already been used to differentiate inflammatory lesions of the colon and diagnose celiac disease with surprising accuracy (60,61) and to differentiate Crohn's from ulcerative colitis in pediatric patients (62). These reports indicate that AI may eventually assist physicians with real-time endoscopic diagnostic and therapeutic decision making.…”