Artificial Intelligence in Endoscopy

Abstract

<b><i>Background:</i></b> Owing to their rapid development, artificial intelligence (AI) technologies offer a great promise for gastroenterology practice and research. At present, AI-guided image interpretation has already been used with success for endoscopic detection of early malignant lesions. Nonetheless, there are complex challenges and possible shortcomings that must be considered before full implementation can be realized. <b><i>Summary:</i></b> In this review, the current status of AI in endoscopy is summarized. Future perspectives and open questions for further studies are stressed. <b><i>Key Messages:</i></b> The usage of AI algorithms for polyp detection in screening colonoscopy results in a significant increase in the adenoma detection rate, mainly attributed to the identification of diminutive polyps. Computer-aided characterization of colorectal polyps accompanies the detection, but further studies are needed to evaluate the clinical benefit. In contrast to colonoscopy, usage of AI in gastroscopy is currently rather limited. Regarding other fields of endoscopic imaging, capsule endoscopy is the ideal imaging platform for AI, due to the potential of saving time in the video analysis.

Effects of ai-assisted colonoscopy on adenoma miss rate/adenoma detection rate: A protocol for systematic review and meta-analysis

“…ADR is one of the most common outcome indicators used to assess the quality of colonoscopy for many years. [29] Several published systematic reviews and meta-analyses [30][31][32] have shown a significant increase in ADR in AIAC compared to conventional colonoscopy. Several studies showed that the colonic blind spot is an important factor to reduce the detection rate of colorectal lesions, [15] while, AI real-time polyp and adenoma detection system based on convolutional neural network neural network can detect colorectal lesions that cannot be seen by human eyes and improve ADR.…”

Artificial intelligence–assisted ultrasound imaging in hemophilia: research, development, and evaluation of hemarthrosis and synovitis detection

“…The introduction of artificial intelligence (AI) models for diagnosing medical conditions could reduce the burden on healthcare professionals and prevent oversights by alleviating the problem that traditional diagnoses are examiner-dependent [ 17 ]. There has already been success in utilizing AI for endoscopy, chest X-rays, and pathological examinations [ [18] , [19] , [20] , [21] ]. It has been reported that various AI models can facilitate clinical care for professionals, improving diagnosis and treatment for people with hemophilia [ 22 ].…”

Digital Communication Strategies in Visceral Medicine

“…This essentially serves to standardize, improve the detection of pathological findings, and accelerate diagnostics. In their review articles on Artificial Intelligence in Endoscopy [13] and Advances in Digital Pathology [14], the authors Hann and Meining as well as Grosserüschekamp et al [14] summarize the current status of the development and the beginning translation into clinical studies and routine.…”