Deep learning for diagnosis of precancerous lesions in upper gastrointestinal endoscopy: A review

Abstract

Upper gastrointestinal (GI) cancers are the leading cause of cancer-related deaths worldwide. Early identification of precancerous lesions has been shown to minimize the incidence of GI cancers and substantiate the vital role of screening endoscopy. However, unlike GI cancers, precancerous lesions in the upper GI tract can be subtle and difficult to detect. Artificial intelligence techniques, especially deep learning algorithms with convolutional neural networks, might help endoscopists identify the precancerous lesions and reduce interobserver variability. In this review, a systematic literature search was undertaken of the Web of Science, PubMed, Cochrane Library and Embase, with an emphasis on the deep learning-based diagnosis of precancerous lesions in the upper GI tract. The status of deep learning algorithms in upper GI precancerous lesions has been systematically summarized. The challenges and recommendations targeting this field are comprehensively analyzed for future research.

Keywords: Artificial intelligence, Deep learning, Convolutional neural network, Precancerous lesions, Endoscopy

Core Tip: Artificial intelligence techniques, especially deep learning algorithms with convolutional neural networks, have revolutionized upper gastrointestinal endoscopy. In recent years, several deep learning-based artificial intelligence systems have emerged in the gastrointestinal community for endoscopic detection of precancerous lesions. The current review provides an analysis and status of the deep learning-based diagnosis of precancerous lesions in the upper gastrointestinal tract and identifies future challenges and recommendations.