Satoki Shichijo1, Yuma Endo2, Kazuharu Aoyama2, Yoshinori Takeuchi3, Tsuyoshi Ozawa4, Hirotoshi Takiyama5, Keigo Matsuo6, Mitsuhiro Fujishiro7,8, Soichiro Ishihara9, Ryu Ishihara1, Tomohiro Tada2,9,10. 1. a Department of Gastrointestinal Oncology , Osaka International Cancer Institute , Osaka , Japan. 2. b AI Medical Service , Tokyo , Japan. 3. c Department of Biostatistics , School of Public Health, Graduate School of Medicine, University of Tokyo , Tokyo , Japan. 4. d Department of colorectal surgery , Teikyo University Hospital , Tokyo , Japan. 5. e Hospital of National Institute of Radiological Sciences, National Institutes for Quantum and Radiological Science and Technology , Chiba , Japan. 6. f Department of Gastroenterology , Tokatsu-Tsujinaka Hospital , Chiba , Japan. 7. g Department of Gastroenterology , Graduate School of Medicine, University of Tokyo , Tokyo , Japan. 8. h Department of Gastroenterology , Graduate School of Medicine, Nagoya University , Nagoya , Japan. 9. i Department of Surgical Oncology , Graduate School of Medicine, University of Tokyo , Tokyo , Japan. 10. j Tada Tomohiro Institute of Gastroenterology and Proctology , Saitama , Japan.
Abstract
BACKGROUND AND AIM: We recently reported the role of artificial intelligence in the diagnosis of Helicobacter pylori (H. pylori) gastritis on the basis of endoscopic images. However, that study included only H. pylori-positive and -negative patients, excluding patients after H. pylori-eradication. In this study, we constructed a convolutional neural network (CNN) and evaluated its ability to ascertain all H. pylori infection statuses. METHODS: A deep CNN was pre-trained and fine-tuned on a dataset of 98,564 endoscopic images from 5236 patients (742 H. pylori-positive, 3649 -negative, and 845 -eradicated). A separate test data set (23,699 images from 847 patients; 70 positive, 493 negative, and 284 eradicated) was evaluated by the CNN. RESULTS: The trained CNN outputs a continuous number between 0 and 1 as the probability index for H. pylori infection status per image (Pp, H. pylori-positive; Pn, negative; Pe, eradicated). The most probable (largest number) of the three infectious statuses was selected as the 'CNN diagnosis'. Among 23,699 images, the CNN diagnosed 418 images as positive, 23,034 as negative, and 247 as eradicated. Because of the large number of H. pylori negative findings, the probability of H. pylori-negative was artificially re-defined as Pn -0.9, after which 80% (465/582) of negative diagnoses were accurate, 84% (147/174) eradicated, and 48% (44/91) positive. The time needed to diagnose 23,699 images was 261 seconds. CONCLUSION: We used a novel algorithm to construct a CNN for diagnosing H. pylori infection status on the basis of endoscopic images very quickly. ABBREVIATIONS: H. pylori: Helicobacter pylori; CNN: convolutional neural network; AI: artificial intelligence; EGD: esophagogastroduodenoscopies.
BACKGROUND AND AIM: We recently reported the role of artificial intelligence in the diagnosis of Helicobacter pylori (H. pylori) gastritis on the basis of endoscopic images. However, that study included only H. pylori-positive and -negative patients, excluding patients after H. pylori-eradication. In this study, we constructed a convolutional neural network (CNN) and evaluated its ability to ascertain all H. pylori infection statuses. METHODS: A deep CNN was pre-trained and fine-tuned on a dataset of 98,564 endoscopic images from 5236 patients (742 H. pylori-positive, 3649 -negative, and 845 -eradicated). A separate test data set (23,699 images from 847 patients; 70 positive, 493 negative, and 284 eradicated) was evaluated by the CNN. RESULTS: The trained CNN outputs a continuous number between 0 and 1 as the probability index for H. pylori infection status per image (Pp, H. pylori-positive; Pn, negative; Pe, eradicated). The most probable (largest number) of the three infectious statuses was selected as the 'CNN diagnosis'. Among 23,699 images, the CNN diagnosed 418 images as positive, 23,034 as negative, and 247 as eradicated. Because of the large number of H. pylori negative findings, the probability of H. pylori-negative was artificially re-defined as Pn -0.9, after which 80% (465/582) of negative diagnoses were accurate, 84% (147/174) eradicated, and 48% (44/91) positive. The time needed to diagnose 23,699 images was 261 seconds. CONCLUSION: We used a novel algorithm to construct a CNN for diagnosing H. pylori infection status on the basis of endoscopic images very quickly. ABBREVIATIONS: H. pylori: Helicobacter pylori; CNN: convolutional neural network; AI: artificial intelligence; EGD: esophagogastroduodenoscopies.
Authors: Sebastian Rupp; Apostolis Papaefthymiou; Eleftherios Chatzimichael; Stergios A Polyzos; Stefan Spreitzer; Michael Doulberis; Thomas Kuntzen; Jannis Kountouras Journal: Ann Gastroenterol Date: 2022-06-02