The diagnostic ability to classify neoplasias occurring in inflammatory bowel disease by artificial intelligence and endoscopists: A pilot study

Abstract

Background and Aim Although endoscopic resection with careful surveillance instead of total proctocolectomy become to be permitted for visible low‐grade dysplasia, it is unclear how accurately endoscopists can differentiate these lesions, as classifying neoplasias occurring in inflammatory bowel disease (IBDN) is exceedingly challenging due to background chronic inflammation. We evaluated a pilot model of an artificial intelligence (AI) system for classifying IBDN and compared it with the endoscopist's ability. Methods This study used a deep convolutional neural network, the EfficientNet‐B3. Among patients who underwent treatment for IBDN at two hospitals between 2003 and 2021, we selected 862 non‐magnified endoscopic images from 99 IBDN lesions and utilized 6 375 352 images that were increased by data augmentation for the development of AI. We evaluated the diagnostic ability of AI using two classifications: the “adenocarcinoma/high‐grade dysplasia” and “low‐grade dysplasia/sporadic adenoma/normal mucosa” groups. We compared the diagnostic accuracy between AI and endoscopists (three non‐experts and four experts) using 186 test set images. Results The diagnostic ability of the experts/non‐experts/AI for the two classifications in the test set images had a sensitivity of 60.5% (95% confidence interval [CI]: 54.5–66.3)/70.5% (95% CI: 63.8–76.6)/72.5% (95% CI: 60.4–82.5), specificity of 88.0% (95% CI: 84.7–90.8)/78.8% (95% CI: 74.3–83.1)/82.9% (95% CI: 74.8–89.2), and accuracy of 77.8% (95% CI: 74.7–80.8)/75.8% (95% CI: 72–79.3)/79.0% (95% CI: 72.5–84.6), respectively. Conclusions The diagnostic accuracy of the two classifications of IBDN was higher than that of the experts. Our AI system is valuable enough to contribute to the next generation of clinical practice.

Present and future of endoscopy precision for inflammatory bowel disease

“…86,87 Also, computer-aided systems able to detect adenoma and predict histology of colorectal polyps have been developed, but only in non-IBD populations. 88 Yamamoto et al 89 tested an AI system for characterizing neoplasia occurring in IBD. The model classified lesions into two groups: "adenocarcinoma/high-grade dysplasia" and "low-grade dysplasia/sporadic adenoma/normal mucosa."…”

Next-Generation Endoscopy in Inflammatory Bowel Disease

“…Computer-aided systems able to detect dysplastic lesions and predict histology have been developed, but mainly in non-IBD populations. Few systems have been assessed on IBD patients [97,98].…”

Artificial intelligence for the diagnosis of dysplasia in inflammatory bowel diseases

“…The AI system appeared to perform better than endoscopists, with the diagnostic accuracy of the AI system being 79.0%, compared to 75.8% by non-expert endoscopists and 77.8% by expert endoscopists. 6 With prior studies focusing only on AI prediction of disease activity in IBD, both in terms of endoscopy and histology, 7 this is the first to investigate the use of AI for diagnosing dysplasia and classifying IBDN. Although promising, these are but preliminary results with a need to further improve the diagnostic performance of the AI system.…”

“…The AI system was developed using non‐magnified still images of CRC, high‐grade dysplasia (HGD), low‐grade dysplasia (LGD), SA, and normal mucosa (NM) to differentiate the “CRC/HGD” group from the “LGD/SA/NM” group. The AI system appeared to perform better than endoscopists, with the diagnostic accuracy of the AI system being 79.0%, compared to 75.8% by non‐expert endoscopists and 77.8% by expert endoscopists 6 . With prior studies focusing only on AI prediction of disease activity in IBD, both in terms of endoscopy and histology, 7 this is the first to investigate the use of AI for diagnosing dysplasia and classifying IBDN.…”