The Histological Detection of Ulcerative Colitis Using a No-Code Artificial Intelligence Model

Yuichiro Hamamoto; Michihiro Kawamura; Hiroki Uchida; Kazuhiro Hiramatsu; Chiaki Katori; Hinako Asai; Shigeki Shimizu; Satoshi Egawa; Kyotaro Yoshida

doi:10.1177/10668969231204955

The Histological Detection of Ulcerative Colitis Using a No-Code Artificial Intelligence Model

Int J Surg Pathol. 2023 Oct 25:10668969231204955. doi: 10.1177/10668969231204955. Online ahead of print.

Authors

Yuichiro Hamamoto^{1

2}, Michihiro Kawamura³, Hiroki Uchida³, Kazuhiro Hiramatsu³, Chiaki Katori³, Hinako Asai³, Shigeki Shimizu⁴, Satoshi Egawa⁵, Kyotaro Yoshida³

Affiliations

¹ Department of Diagnostic Pathology, Kinki Central Hospital of Mutual Aid Association of Public School Teachers, Itami, Hyogo, Japan.
² Faculty of Medicine Division of Medicine, Department of Pathology, Osaka University Graduate School of Medicine, Suita, Japan.
³ Department of Clinical Laboratory, Kinki Central Hospital of Mutual Aid Association of Public School Teachers, Itami, Hyogo, Japan.
⁴ Department of Clinical Laboratory, National Hospital Organization Kinki-Chuo Chest Medical Center, Kita-ku, Sakai, Osaka, Japan.
⁵ Department of Gastroenterology, Kinki Central Hospital of Mutual Aid Association of Public School Teachers, Itami, Hyogo, Japan.

PMID: 37880949
DOI: 10.1177/10668969231204955

Abstract

Ulcerative colitis (UC) is an intractable disease that affects young adults. Histological findings are essential for its diagnosis; however, the number of diagnostic pathologists is limited. Herein, we used a no-code artificial intelligence (AI) platform "Teachable Machine" to train a model that could distinguish between histological images of UC, non-UC coloproctitis, adenocarcinoma, and control. A total of 5100 histological images for training and 900 histological images for testing were prepared by pathologists. Our model showed accuracies of 0.99, 1.00, 0.99, and 0.99, for UC, non-UC coloproctitis, adenocarcinoma, and control, respectively. This is the first report in which a no-code easy AI platform has been able to comprehensively recognize the distinctive histologic patterns of UC.

Keywords: adenocarcinoma; artificial intelligence; inflammatory bowel disease; machine learning; ulcerative colitis.