Development and Validation of a Deep Neural Network for Accurate Evaluation of Endoscopic Images From Patients With Ulcerative Colitis

Kento Takenaka; Kazuo Ohtsuka; Toshimitsu Fujii; Mariko Negi; Kohei Suzuki; Hiromichi Shimizu; Shiori Oshima; Shintaro Akiyama; Maiko Motobayashi; Masakazu Nagahori; Eiko Saito; Katsuyoshi Matsuoka; Mamoru Watanabe

doi:10.1053/j.gastro.2020.02.012

Development and Validation of a Deep Neural Network for Accurate Evaluation of Endoscopic Images From Patients With Ulcerative Colitis

Gastroenterology. 2020 Jun;158(8):2150-2157. doi: 10.1053/j.gastro.2020.02.012. Epub 2020 Feb 12.

Affiliations

¹ Department of Gastroenterology and Hepatology, Tokyo Medical and Dental University, Tokyo, Japan.
² Department of Human Pathology, Tokyo Medical and Dental University, Tokyo, Japan.
³ LE Development Department, R&D Division, Medical Business Group, Sony Imaging Products & Solutions Inc., Kanagawa, Japan.
⁴ Department of Gastroenterology and Hepatology, Tokyo Medical and Dental University, Tokyo, Japan. Electronic address: mamoru.gast@tmd.ac.jp.

PMID: 32060000
DOI: 10.1053/j.gastro.2020.02.012

Abstract

Background & aims: There are intra- and interobserver variations in endoscopic assessment of ulcerative colitis (UC) and biopsies are often collected for histologic evaluation. We sought to develop a deep neural network system for consistent, objective, and real-time analysis of endoscopic images from patients with UC.

Methods: We constructed the deep neural network for evaluation of UC (DNUC) algorithm using 40,758 images of colonoscopies and 6885 biopsy results from 2012 patients with UC who underwent colonoscopy from January 2014 through March 2018 at a single center in Japan (the training set). We validated the accuracy of the DNUC algorithm in a prospective study of 875 patients with UC who underwent colonoscopy from April 2018 through April 2019, with 4187 endoscopic images and 4104 biopsy specimens. Endoscopic remission was defined as a UC endoscopic index of severity score of 0; histologic remission was defined as a Geboes score of 3 points or less.

Results: In the prospective study, the DNUC identified patients with endoscopic remission with 90.1% accuracy (95% confidence interval [CI] 89.2%-90.9%) and a kappa coefficient of 0.798 (95% CI 0.780-0.814), using findings reported by endoscopists as the reference standard. The intraclass correlation coefficient between the DNUC and the endoscopists for UC endoscopic index of severity scoring was 0.917 (95% CI 0.911-0.921). The DNUC identified patients in histologic remission with 92.9% accuracy (95% CI 92.1%-93.7%); the kappa coefficient between the DNUC and the biopsy result was 0.859 (95% CI 0.841-0.875).

Conclusions: We developed a deep neural network for evaluation of endoscopic images from patients with UC that identified those in endoscopic remission with 90.1% accuracy and histologic remission with 92.9% accuracy. The DNUC can therefore identify patients in remission without the need for mucosal biopsy collection and analysis. Trial number: UMIN000031430.

Keywords: Artificial Intelligence; Diagnostic; IBD; Mucosal Healing.

Publication types

Research Support, Non-U.S. Gov't
Validation Study

MeSH terms

Adolescent
Adult
Aged
Aged, 80 and over
Biopsy
Colitis, Ulcerative / pathology*
Colitis, Ulcerative / therapy
Colon / pathology*
Colonoscopy*
Databases, Factual
Deep Learning*
Diagnosis, Computer-Assisted*
Female
Humans
Image Interpretation, Computer-Assisted*
Male
Middle Aged
Predictive Value of Tests
Prospective Studies
Remission Induction
Reproducibility of Results
Severity of Illness Index
Treatment Outcome
Wound Healing
Young Adult