Automatic anatomical classification of colonoscopic images using deep convolutional neural networks

Hiroaki Saito; Tetsuya Tanimoto; Tsuyoshi Ozawa; Soichiro Ishihara; Mitsuhiro Fujishiro; Satoki Shichijo; Dai Hirasawa; Tomoki Matsuda; Yuma Endo; Tomohiro Tada

doi:10.1093/gastro/goaa078

Automatic anatomical classification of colonoscopic images using deep convolutional neural networks

Gastroenterol Rep (Oxf). 2020 Dec 7;9(3):226-233. doi: 10.1093/gastro/goaa078. eCollection 2021 Jun.

Authors

Hiroaki Saito¹, Tetsuya Tanimoto², Tsuyoshi Ozawa^{3

4}, Soichiro Ishihara^{3

5}, Mitsuhiro Fujishiro⁶, Satoki Shichijo⁷, Dai Hirasawa¹, Tomoki Matsuda¹, Yuma Endo⁸, Tomohiro Tada^{3

5

8}

Affiliations

¹ Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan.
² Department of Internal Medicine, Navitas Clinic, Tokyo, Japan.
³ Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan.
⁴ Department of Surgery, Teikyo University School of Medicine, Tokyo, Japan.
⁵ Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
⁶ Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Aichi, Japan.
⁷ Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan.
⁸ AI Medical Service, Inc., Tokyo, Japan.

Abstract

Background: A colonoscopy can detect colorectal diseases, including cancers, polyps, and inflammatory bowel diseases. A computer-aided diagnosis (CAD) system using deep convolutional neural networks (CNNs) that can recognize anatomical locations during a colonoscopy could efficiently assist practitioners. We aimed to construct a CAD system using a CNN to distinguish colorectal images from parts of the cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum.

Method: We constructed a CNN by training of 9,995 colonoscopy images and tested its performance by 5,121 independent colonoscopy images that were categorized according to seven anatomical locations: the terminal ileum, the cecum, ascending colon to transverse colon, descending colon to sigmoid colon, the rectum, the anus, and indistinguishable parts. We examined images taken during total colonoscopy performed between January 2017 and November 2017 at a single center. We evaluated the concordance between the diagnosis by endoscopists and those by the CNN. The main outcomes of the study were the sensitivity and specificity of the CNN for the anatomical categorization of colonoscopy images.

Results: The constructed CNN recognized anatomical locations of colonoscopy images with the following areas under the curves: 0.979 for the terminal ileum; 0.940 for the cecum; 0.875 for ascending colon to transverse colon; 0.846 for descending colon to sigmoid colon; 0.835 for the rectum; and 0.992 for the anus. During the test process, the CNN system correctly recognized 66.6% of images.

Conclusion: We constructed the new CNN system with clinically relevant performance for recognizing anatomical locations of colonoscopy images, which is the first step in constructing a CAD system that will support us during colonoscopy and provide an assurance of the quality of the colonoscopy procedure.

Keywords: colonoscopy; deep learning; endoscopy; neural network.