Application of artificial intelligence in the endoscopic diagnosis of early gastric cancer, atrophic gastritis and H. pylori infection.

Gastric cancer (GC) is one of the most serious health problems worldwide. Chronic atrophic gastritis (CAG) is a gastric precancerous lesion (GPL), most commonly caused by Helicobacter pylori (H. pylori) infection that may also lead to GC by the direct way such as the translocation of CagA. Presently, the diagnosis of early GC (EGC) and CAG mainly relies on endoscopy, which has always been a challenge for endoscopists. And the accuracy of endoscopic diagnosing H. pylori is mostly 70%. The development of artificial intelligence (AI) can assist clinical works in many aspects including detection, invasion depth prediction, boundary delineation and anatomical location of EGC, and has achievable diagnostic ability, even comparable to endoscopists. We try to review the current status of various AI applications in EGC, CAG and H. pylori infection, and point out probable directions for future research in this field to promote the better application of AI in clinical practice. This article is protected by copyright. All rights reserved.