Yusuke Horiuchi1, Kazuharu Aoyama2, Yoshitaka Tokai3, Toshiaki Hirasawa3, Shoichi Yoshimizu3, Akiyoshi Ishiyama3, Toshiyuki Yoshio3, Tomohiro Tsuchida3, Junko Fujisaki3, Tomohiro Tada2,4. 1. Department of Gastroenterology, Cancer Institute Hospital, 3-10-6 Ariake, Koto-ku, Tokyo, 135-8550, Japan. yusuke.horiuchi@jfcr.or.jp. 2. AI Medical Service Inc., Arai Building 2F, 1-10-13 Minami Ikebukuro, Toshima-ku, Tokyo, 171-0022, Japan. 3. Department of Gastroenterology, Cancer Institute Hospital, 3-10-6 Ariake, Koto-ku, Tokyo, 135-8550, Japan. 4. Tada Tomohiro Institute of Gastroenterology and Proctology, 7-2-1 Bessho, Minami-ku, Saitama, 336-0021, Japan.
Abstract
BACKGROUND: Early detection of early gastric cancer (EGC) allows for less invasive cancer treatment. However, differentiating EGC from gastritis remains challenging. Although magnifying endoscopy with narrow band imaging (ME-NBI) is useful for differentiating EGC from gastritis, this skill takes substantial effort. Since the development of the ability to convolve the image while maintaining the characteristics of the input image (convolution neural network: CNN), allowing the classification of the input image (CNN system), the image recognition ability of CNN has dramatically improved. AIMS: To explore the diagnostic ability of the CNN system with ME-NBI for differentiating between EGC and gastritis. METHODS: A 22-layer CNN system was pre-trained using 1492 EGC and 1078 gastritis images from ME-NBI. A separate test data set (151 EGC and 107 gastritis images based on ME-NBI) was used to evaluate the diagnostic ability [accuracy, sensitivity, positive predictive value (PPV), and negative predictive value (NPV)] of the CNN system. RESULTS: The accuracy of the CNN system with ME-NBI images was 85.3%, with 220 of the 258 images being correctly diagnosed. The method's sensitivity, specificity, PPV, and NPV were 95.4%, 71.0%, 82.3%, and 91.7%, respectively. Seven of the 151 EGC images were recognized as gastritis, whereas 31 of the 107 gastritis images were recognized as EGC. The overall test speed was 51.83 images/s (0.02 s/image). CONCLUSIONS: The CNN system with ME-NBI can differentiate between EGC and gastritis in a short time with high sensitivity and NPV. Thus, the CNN system may complement current clinical practice of diagnosis with ME-NBI.
BACKGROUND: Early detection of early gastric cancer (EGC) allows for less invasive cancer treatment. However, differentiating EGC from gastritis remains challenging. Although magnifying endoscopy with narrow band imaging (ME-NBI) is useful for differentiating EGC from gastritis, this skill takes substantial effort. Since the development of the ability to convolve the image while maintaining the characteristics of the input image (convolution neural network: CNN), allowing the classification of the input image (CNN system), the image recognition ability of CNN has dramatically improved. AIMS: To explore the diagnostic ability of the CNN system with ME-NBI for differentiating between EGC and gastritis. METHODS: A 22-layer CNN system was pre-trained using 1492 EGC and 1078 gastritis images from ME-NBI. A separate test data set (151 EGC and 107 gastritis images based on ME-NBI) was used to evaluate the diagnostic ability [accuracy, sensitivity, positive predictive value (PPV), and negative predictive value (NPV)] of the CNN system. RESULTS: The accuracy of the CNN system with ME-NBI images was 85.3%, with 220 of the 258 images being correctly diagnosed. The method's sensitivity, specificity, PPV, and NPV were 95.4%, 71.0%, 82.3%, and 91.7%, respectively. Seven of the 151 EGC images were recognized as gastritis, whereas 31 of the 107 gastritis images were recognized as EGC. The overall test speed was 51.83 images/s (0.02 s/image). CONCLUSIONS: The CNN system with ME-NBI can differentiate between EGC and gastritis in a short time with high sensitivity and NPV. Thus, the CNN system may complement current clinical practice of diagnosis with ME-NBI.
Authors: Fei Kuang; Juan Du; Mengjia Zhou; Xiangdong Liu; Xinchen Luo; Yong Tang; Bo Li; Song Su Journal: Front Oncol Date: 2022-06-10 Impact factor: 5.738
Authors: Jiang Kailin; Jiang Xiaotao; Pan Jinglin; Wen Yi; Huang Yuanchen; Weng Senhui; Lan Shaoyang; Nie Kechao; Zheng Zhihua; Ji Shuling; Liu Peng; Li Peiwu; Liu Fengbin Journal: Front Med (Lausanne) Date: 2021-03-15