Recent Advances in the Artificial Intelligence –Assisted Detection of Esophageal Neoplasia

AbstractPurpose of reviewGiven the poor outcomes associated with esophageal cancer, there is increasing interest in the use of artificial intelligence (AI) for early detection of esophageal neoplasia and its precursors. In this review, we examine the use of AI in the endoscopic detection of Barrett ’s esophagus (BE)-related neoplasia, esophageal adenocarcinoma (EAC), esophageal squamous cell carcinoma (ESCC), and dysplasia. In addition, we summarize the findings, strengths, and limitations of recent studies evaluating the efficacy of AI in the detection of esophageal neoplasia.Recent findingsOver the past decade, AI has been successfully used to augment the endoscopic detection of BE neoplasia and esophageal carcinoma (EAC and ESCC) across multiple studies with promising results. During this time, the role of AI has evolved and progressed from detecting neoplasia in small image sets to real-time during endoscopy.SummaryAI in endoscopy has the ability to revolutionize the detection and characterization of esophageal dysplastic and neoplastic lesions. While studies to date have been promising, they are not without limitations. Additional prospective, multicenter studies are necessary to more precisely determine the utility of AI in the real-time endoscopic detection of esophageal neoplasia.
Source: Current Treatment Options in Gastroenterology - Category: Gastroenterology Source Type: research