Deep Learning Model for Diagnosing Gastric Mucosal Lesions Using Endoscopic Images: Development, Validation, and Method Comparison

Abstract

Endoscopic differential diagnoses of gastric mucosal lesions remain challenging. We aimed to develop and validate convolutional neural network-based artificial intelligence models-lesion detection, differential diagnosis, and invasion-depth models. The AI-DDx showed good diagnostic performance for both internal and external validation. The performance of the AI-DDx was better than that of the novice and intermediate endoscopists, but was comparable to the experts in the external validation set. The AI-ID showed fair performances in both internal and external validation sets, which were significantly better than EUS results performed by experts.

Hyungjin Chung

Research Scientist

Generative models, Inverse problems, Multimodality, Motion, and more.