Diagnosis of gastric lesions through a deep convolutional neural network

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.

Automated summary

A deep convolutional neural network was utilized to achieve fast and accurate AI-assisted diagnosis of early gastric cancer and other gastric lesions based on endoscopic images, with higher specificity and PPV than experienced endoscopists. This system can help reduce the workload of endoscopists by providing rapid auxiliary diagnostic capabilities.