Liming Zhang1, Yang Zhang2, Li Wang1, Jiangyuan Wang1, Yulan Liu1. 1. Department of Gastroenterology, Peking University People's Hospital, Beijing, China. 2. Internet Medical Department of Love Life Insurance Company, Beijing, China.
Abstract
BACKGROUND AND AIMS: A deep convolutional neural network (CNN) was used to achieve fast and accurate artificial intelligence (AI)-assisted diagnosis of early gastric cancer (GC) and other gastric lesions based on endoscopic images. METHODS: A CNN-based diagnostic system based on a ResNet34 residual network structure and a DeepLabv3 structure was constructed and trained using 21,217 gastroendoscopic images of five gastric conditions, peptic ulcer (PU), early gastric cancer (EGC) and high-grade intraepithelial neoplasia (HGIN), advanced gastric cancer (AGC), gastric submucosal tumors (SMTs), and normal gastric mucosa without lesions. The trained CNN was evaluated using a test dataset of 1091 images. The accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the CNN were calculated. The CNN diagnosis was compared with those of 10 endoscopists with over 8 years of experience in endoscopic diagnosis. RESULTS: The diagnostic specificity and PPV of the CNN were higher than that of the endoscopists for the EGC and HGIN images (specificity: 91.2% vs. 86.7%, by 4.5%, 95% CI 2.8-7.2%; PPV: 55.4% vs. 41.7%, by 13.7%, 95% CI 11.2-16.8%) and the diagnostic accuracy of the CNN was close to those of the endoscopists for the lesion-free, EGC and HGIN, PU, AGC, and SMTs images. The CNN had image recognition time of 42 s for all the test set images. CONCLUSION: The constructed CNN system could be used as a rapid auxiliary diagnostic instrument to detect EGC and HGIN, as well as other gastric lesions, to reduce the workload of endoscopists.
BACKGROUND AND AIMS: A deep convolutional neural network (CNN) was used to achieve fast and accurate artificial intelligence (AI)-assisted diagnosis of early gastric cancer (GC) and other gastric lesions based on endoscopic images. METHODS: A CNN-based diagnostic system based on a ResNet34 residual network structure and a DeepLabv3 structure was constructed and trained using 21,217 gastroendoscopic images of five gastric conditions, peptic ulcer (PU), early gastric cancer (EGC) and high-grade intraepithelial neoplasia (HGIN), advanced gastric cancer (AGC), gastric submucosal tumors (SMTs), and normal gastric mucosa without lesions. The trained CNN was evaluated using a test dataset of 1091 images. The accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the CNN were calculated. The CNN diagnosis was compared with those of 10 endoscopists with over 8 years of experience in endoscopic diagnosis. RESULTS: The diagnostic specificity and PPV of the CNN were higher than that of the endoscopists for the EGC and HGIN images (specificity: 91.2% vs. 86.7%, by 4.5%, 95% CI 2.8-7.2%; PPV: 55.4% vs. 41.7%, by 13.7%, 95% CI 11.2-16.8%) and the diagnostic accuracy of the CNN was close to those of the endoscopists for the lesion-free, EGC and HGIN, PU, AGC, and SMTs images. The CNN had image recognition time of 42 s for all the test set images. CONCLUSION: The constructed CNN system could be used as a rapid auxiliary diagnostic instrument to detect EGC and HGIN, as well as other gastric lesions, to reduce the workload of endoscopists.
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