Related Experiment Video
Updated: May 1, 2026
Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
Published on: October 16, 2013
Using Computer Vision to Improve Endoscopic Disease Quantification in Therapeutic Clinical Trials of Ulcerative
Ryan W Stidham1, Lingrui Cai2, Shuyang Cheng2
1Division of Gastroenterology, Department of Internal Medicine, Michigan Medicine, Ann Arbor, Michigan; Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan; Michigan Institute for Data Science, University of Michigan, Ann Arbor, Michigan.
Computer vision analysis of ulcerative colitis (UC) endoscopic video created a Cumulative Disease Score (CDS). This AI-driven CDS better quantifies disease severity and treatment response than traditional methods.
Area of Science:
- Gastroenterology
- Medical Imaging
- Artificial Intelligence
Background:
- Current endoscopic assessment of ulcerative colitis (UC) relies on maximum observed severity, potentially missing nuanced disease variations.
- Objective quantification of mucosal injury in UC is crucial for accurate treatment evaluation.
- Computer vision offers a novel approach to analyze endoscopic findings in UC.
Purpose of the Study:
- To develop and validate a computer vision-based Cumulative Disease Score (CDS) for ulcerative colitis.
- To compare the efficacy of CDS with the Mayo Endoscopic Score (MES) in differentiating treatment responses.
- To assess the statistical power and sample size requirements for detecting endoscopic differences using CDS versus MES.
Main Methods:
- Endoscopic videos from the UNIFI clinical trial (ustekinumab vs. placebo for UC) were analyzed using computer vision to generate CDS.
- CDS was spatially mapped to the Mayo Endoscopic Score (MES) and compared with MES for treatment response and symptomatic remission.
- Statistical power, effect sizes, and sample size calculations were performed for both CDS and MES.
- CDS performance was validated in a separate phase 2 clinical trial replication cohort (JAK-UC).
Main Results:
- CDS was significantly lower in ustekinumab users compared to placebo at weeks 8 and 44 (P < .0001).
- CDS demonstrated strong correlation with MES (P < .0001) and partial Mayo score components (P < .0001).
- CDS was more sensitive to treatment changes than MES, requiring 50% fewer participants to detect endoscopic differences.
- Ustekinumab showed greater efficacy in patients with higher baseline CDS, particularly in severe disease.
Conclusions:
- The Cumulative Disease Score (CDS) provides an automated, quantitative measure of global endoscopic disease severity in UC.
- CDS enhances traditional MES capabilities, offering improved evaluation of UC in clinical trials and potential clinical practice.
- Artificial intelligence-driven CDS analysis represents a significant advancement in assessing UC endoscopic activity.
More Related Videos
09:42Murine Endoscopy for In Vivo Multimodal Imaging of Carcinogenesis and Assessment of Intestinal Wound Healing and Inflammation
Published on: August 26, 2014
07:05Fluorescence-mediated Tomography for the Detection and Quantification of Macrophage-related Murine Intestinal Inflammation
Published on: December 15, 2017
