Comparison of the performance between an AI-based vision transformer and human endoscopists in predicting the endoscopic and histologic activities of ulcerative colitis

Sep 29, 2026

Upload by SANS

Colonoscopy is essential for assessing disease activity in ulcerative colitis (UC), and biopsy-based histologic evaluation depends on endoscopists’ endoscopic scoring and interpretation. A deep learning approach was developed to classify white-light endoscopic images and predict both endoscopic and histologic activities using an independent evaluation dataset. Video segments from 82 patients were used for training, validation, and testing, with comparisons against multiple senior and young endoscopists. The vision transformer showed comparable accuracy to experienced clinicians and exceeded younger endoscopists for key healing outcomes.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusions

Keywords

Introduction

Comparison of the performance between an AI-based vision transformer and human endoscopists in predicting the endoscopic and histologic activities of ulcerative colitis DIGITAL HEALTH Volume 12: 1–12 © The Author(s) 2026 Article reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/20552076251412694](DOI: 10.1177/20552076251412694)[ ](DOI: 10.1177/20552076251412694)[journals.sagepub.com/home/dhj](journals.sagepub.com/home/dhj) Yuan-Yen Chang 1, Han-Po Yang2, Yang-Yuan Chen3 and Hsu-Heng Yen3,4,5 Abstract Background: Colonoscopy plays a vital role in assessing disease activity in ulcerative colitis (UC), and biopsy via colonoscopy helps to evaluate its histological activity. Endoscopists must report the endoscopic activity and rely on the biopsy results to predict the histological activity. Methods: We aimed to develop a deep learning-based algorithm to evaluate the disease and histological activities of UC based on white-light endoscopic images obtained during the procedure in this research. A deep learning system for classifying the colonoscopic images for assessing the endoscopic and histological activities of UC patients was developed. Its performance was evaluated with an independent dataset. The system was utilized to analyze the captured video segments, and the results were compared with those of human endoscopists. Results: A total of 375 video segments from 82 patients were utilized to develop the endoscopic and histological activity prediction assurance algorithm. Among the 375 video segments, 60%, 20%, and 20% were used for training, validation, and testing the proposed vision transformer (ViT) model, respectively. Moreover, four senior and six young endoscopists reviewed and scored the endoscopic and histological activities based on 77 testing video clips. The accuracies were 77.92%, 71.00%, and 83.12% for histological healing; and 74.35%, 72.51%, and 92.21% for complete mucosal healing (Mayo Endoscopic Score 0 vs 1–3), among senior endoscopists, junior endoscopists, and the ViT model, respectively. Conclusions: Our novel deep learning-based model, based on endoscopic videos, was comparable to that of experienced endoscopists and surpassed that of young endoscopists in predicting histological remission and complete mucosal healing. Keywords Colon, colonoscopy quality, deep learning, ulcerative colitis Received: 27 July 2025; accepted: 16 December 2025 Introduction Inﬂammatory bowel disease (IBD), including Crohn’s disease and ulcerative colitis (UC), is a chronic condition characterized by persistent intestinal inﬂammation that requires continuous treatment and surveillance to monitor disease activity, thereby improving patients’ quality of life and preventing complications.1 Although UC treatment has progressed from steroid, 5-aminosalicylic therapy to the recently introduced advanced therapy, the treatment goal has also evolved from clinical remission to endoscopic and even histologic remission.2 Artiﬁcial intelligence (AI) 1 Department of Computer Science and Information Engineering, National Taichung University of Science, Taichung, Taiwan 2Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan 3Division of Gastroenterology, Changhua Christian Hospital, Changhua, Taiwan 4Artiﬁcial Intelligence Development Center, Changhua Christian Hospital, Changhua, Taiwan 5Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung, Taiwan Corresponding author: Hsu-Heng Yen, Division of Gastroenterology, Changhua Christian Hospital, Changhua, 500, Taiwan. Email: 91646@cch.org.tw Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution NonCommercial 4.0 License ([https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/l

FAQs

What problem does the study address in ulcerative colitis?

Accurate assessment of endoscopic and histologic activity in UC is critical, but traditional scoring systems suffer from subjectivity, interobserver variability, and limited granularity.

How was the AI model developed and evaluated?

A total of 375 video segments from 82 patients were used, and performance was assessed using testing clips scored by four senior and six young endoscopists.

What were the main findings compared with human endoscopists?

The vision transformer model was comparable to experienced endoscopists and surpassed young endoscopists in predicting histological remission and complete mucosal healing.

Sep 29, 2026

Upload by SANS