Toshiaki Hirasawa1,2, Kazuharu Aoyama3, Tetsuya Tanimoto4,5, Soichiro Ishihara6,7, Satoki Shichijo8, Tsuyoshi Ozawa6,7, Tatsuya Ohnishi9, Mitsuhiro Fujishiro10, Keigo Matsuo11, Junko Fujisaki12, Tomohiro Tada6,3,13. 1. Department of Gastroenterology, Cancer Institute Hospital Ariake, Japanese Foundation for Cancer Research, 3-10-6 Ariake, Koto-ku, Tokyo, 135-8550, Japan. toshiaki.hirasawa@jfcr.or.jp. 2. Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan. toshiaki.hirasawa@jfcr.or.jp. 3. AI Medical Service Inc., Tokyo, Japan. 4. Medical Governance Research Institute, Tokyo, Japan. 5. Navitas Clinic, Tokyo, Japan. 6. Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan. 7. Surgery Department, Sanno Hospital, International University of Health and Welfare, Tokyo, Japan. 8. Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan. 9. Lalaport Yokohama Clinic, Kanagawa, Japan. 10. Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan. 11. Department of Coloproctology, Tokatsu-Tsujinaka Hospital, Chiba, Japan. 12. Department of Gastroenterology, Cancer Institute Hospital Ariake, Japanese Foundation for Cancer Research, 3-10-6 Ariake, Koto-ku, Tokyo, 135-8550, Japan. 13. Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
Abstract
BACKGROUND: Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images. METHODS: A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN. RESULTS: The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface. CONCLUSION: The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.
BACKGROUND: Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images. METHODS: A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN. RESULTS: The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface. CONCLUSION: The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.
Authors: O Hosokawa; S Tsuda; E Kidani; K Watanabe; Y Tanigawa; S Shirasaki; H Hayashi; T Hinoshita Journal: Endoscopy Date: 1998-10 Impact factor: 10.093
Authors: H Isomoto; S Shikuwa; N Yamaguchi; E Fukuda; K Ikeda; H Nishiyama; K Ohnita; Y Mizuta; J Shiozawa; S Kohno Journal: Gut Date: 2008-11-10 Impact factor: 23.059
Authors: Andreas Kleppe; Ole-Johan Skrede; Sepp De Raedt; Knut Liestøl; David J Kerr; Håvard E Danielsen Journal: Nat Rev Cancer Date: 2021-01-29 Impact factor: 60.716
Authors: Shirley Cohen-Mekelburg; Sameer Berry; Ryan W Stidham; Ji Zhu; Akbar K Waljee Journal: J Gastroenterol Hepatol Date: 2021-02 Impact factor: 4.029