Fully automated diagnostic system with artificial intelligence using endocytoscopy to identify the presence of histologic inflammation associated with ulcerative colitis (with video)

Abstract

Background and Aims: In the treatment of ulcerative colitis (UC), an incremental benefit of achieving histologic healing beyond that of endoscopic mucosal healing has been suggested; persistent histologic inflammation increases the risk of exacerbation and dysplasia. However, identification of persistent histologic inflammation is extremely difficult using conventional endoscopy. Furthermore, the reproducibility of endoscopic disease activity is poor. We developed and evaluated a computer-aided diagnosis (CAD) system to predict persistent histologic inflammation using endocytoscopy (EC; 520-fold ultra-magnifying endoscope). Methods: We evaluated the accuracy of the CAD system using test image sets. First, we retrospectively reviewed the data of 187 patients with UC from whom biopsy samples were obtained after endocytoscopic observation. EC images and biopsy samples of each patient were collected from 6 colorectal segments: cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum. All EC images were tagged with reference to the biopsy sample's histologic activity. For validation samples, 525 validation sets of 525 independent segments were collected from 100 patients, and 12,900 EC images from the remaining 87 patients were used for machine learning to construct CAD. The primary outcome measure was the diagnostic ability of CAD to predict persistent histologic inflammation. Its reproducibility for all test images was also assessed.

Artificial Intelligence in Gastrointestinal Endoscopy

“…29 Maeda et al used EC to examine histologic inflammation in ulcerative colitis. 30 With EC, they developed an AI model that identified persistent histologic inflammation with 74% sensitivity and 97% specificity. It accurately detected histologic inflammation in 90% of cases.…”

Quality assurance of computer-aided detection and diagnosis in colonoscopy

“…Another limitation is the lack of data on detection of inflammation and dysplasia in ulcerative and Crohn's colitis, though pilot studies in this field can be found. 47,48 The black-box nature of the current DL algorithms can be another limitation; DL algorithms fail to reason the machine generated decision on polyp classification in CADx. Reasons causing the decision of the DL model are being investigated, and interpretable deep learning has already become an active area of research.…”

Application of artificial intelligence in gastrointestinal endoscopy

“…CADe was shown to achieve the threshold of preservation and incorporation of valuable endoscopic innovations for a “diagnose‐and‐leave” strategy, namely a >90% negative predictive value (NPV) for diminutive adenomas . Moreover, some studies have attempted to apply AI to inflammatory bowel diseases . Ozawa et al constructed a CADx system using a CNN to identify normal mucosa (Mayo 0) and the mucosal healing state (Mayo 0–1) with area under receiver operating characteristic curves (AUROCs) of 0.86 and 0.98.…”

“…Ozawa et al constructed a CADx system using a CNN to identify normal mucosa (Mayo 0) and the mucosal healing state (Mayo 0–1) with area under receiver operating characteristic curves (AUROCs) of 0.86 and 0.98. Maeda et al also developed a CADx system to predict persistent histological inflammation in patients with ulcerative colitis, and achieved a high accuracy (91%) and specificity (97%).…”