Key points are not available for this paper at this time.
Aims Gastric cancer (GC) is a significant healthcare concern and the recognition of high-risk patients is crucial 1. The common mechanism for the progression of GC is the Correa cascade, which outlines a multi-step progression from chronic gastritis through atrophic gastritis, intestinal metaplasia (IM), dysplasia and finally GC. The detection of IM in the stomach is not always easy, especially when it is focal. While electronic chromoendoscopy has demonstrated high diagnostic accuracy for IM 2, its limited availability, and the variable expertise of endoscopists pose challenges. Additionally, the potential of artificial intelligence (AI) to aid endoscopists has obtained significant attention. This study aims to develop a deep-learning system to assist in IM diagnosis based on endoscopic image patches.
Ligato et al. (Mon,) studied this question.