Current Status in AI for Endoscopy
Talk Abstract
Background: Artificial intelligence (AI) using deep learning systems has recently been utilized in various medical fields. In the field of gastroenterology, AI is utilized primarily in the realm of gastrointestinal (GI) endoscopy. In GI endoscopy, computer-aided detection/diagnosis (CAD) systems assist endoscopists in detecting GI neoplasm or differentiating lesions as cancerous or non-cancerous. Several AI systems for colorectal polyps have already been applied in colonoscopy. In esophagogastroduodenoscopy (EGD), a few CAD systems for upper GI neoplasms have already launched in Asian countries. The usefulness of these CAD systems in GI endoscopy will become evident over time.
Methods: We review remarkable articles of endoscopic AI systems for GI neoplasms, focusing on esophageal squamous cell carcinoma (ESCC), esophageal adenocarcinoma (EAC), gastric cancer (GC), and colorectal polyps before then discussing the prospect of endoscopic AI.
Results: In ESCC and EAC, computer-aided detection (CADe) systems were mainly developed, and a recent meta-analysis study showed sensitivities of 91.2% and 93.1% and specificities of 80% and 86.9%, respectively. In GC, a recent meta-analysis study on CADe systems demonstrated sensitivity and specificity as high as 90%. A randomized controlled trial (RCT) also showed that the use of the CADe system reduced lesion miss rate. Most studies have demonstrated expert-level performance regarding computer-aided diagnosis (CADx) systems for GC. In colorectal polyps, multiple RCTs have shown the usefulness of the CADe system for improving polyp detection rate. Regarding CADx systems for colorectal polyps, the first RCT in 2024 showed that the CADx system had equivalent accuracy to expert endoscopists.
Conclusion: Most analyses of endoscopic AI systems suggested that AI performance was better than that of non-expert endoscopists and equivalent to that of expert endoscopists. Endoscopic AI systems can be useful for reducing the risk of overlooking lesions and improving the diagnostic performance of endoscopists.