Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective

Abstract

aims to review the history, recent advances, evidence, and challenges of artificial intelligence (AI) in colonoscopy. Although it is mainly focused on polyp detection and characterization, it also considers other potential applications (i.e., inflammatory bowel disease) and future perspectives. Some of the most recent algorithms show promising results that are similar to human expert performance. The integration of AI in routine clinical practice will be challenging, with significant issues to overcome (i.e., regulatory, reimbursement). Medico-legal issues will also need to be addressed. With the exception of an AI system that is already available in selected countries (GI Genius; Medtronic, Minneapolis, MN, USA), the majority of the technology is still in its infancy and has not yet been proven to reach a sufficient diagnostic performance to be adopted in the clinical practice. However, larger players will enter the arena of AI in the next few months. Clin Endosc 2021 Jan 13. [Epub ahead of print]

Artificial Intelligence-Based Colorectal Polyp Histology Prediction: High Accuracy in Larger Polyps

“…Second, AI will not be able to compensate for the risk of suboptimal colonoscopy in cases of inadequate cleaning that may affect the classification of the surface pattern of each polyp. 6 Although smaller numbers of SSL were found in this study, this flat and isochromic polyp is frequently covered with a mucus cap or debris during routine colonoscopy, which may hinder the original character. 7 Third, this system is a proprietary specification system developed in a single center, and there may be an uneven spectrum of diagnostic features, including pathology.…”

“…The system used in this study involved human interaction in selecting good-quality areas, which may build an inherent bias into the system from the start. Second, AI will not be able to compensate for the risk of suboptimal colonoscopy in cases of inadequate cleaning that may affect the classification of the surface pattern of each polyp [ 6 ]. Although smaller numbers of SSL were found in this study, this flat and isochromic polyp is frequently covered with a mucus cap or debris during routine colonoscopy, which may hinder the original character [ 7 ].…”

Predictors of Positive Video Capsule Endoscopy Findings for Chronic Unexplained Abdominal Pain: Single-Center Retrospective Study and Meta-Analysis

“…VCE has become a powerful non-invasive modality since its introduction to clinical practice in 2001 and since then, there has been a significant advance in the diagnostic ability of VCE in various small bowel lesions [14] It can evaluate whole small-bowel mucosa and can detect abnormalities that were previously undetectable by small-bowel radiography and abdominal pelvic CT, and angiography [15][16][17][18][19][20][21][22][23][24][25].…”

Diagnostic accuracy of a novel artificial intelligence system for adenoma detection in daily practice: a prospective nonrandomized comparative study

“…The GI Genius (Medtronic, USA) system is a novel AI system that is now commercially available in many countries [13]. Therefore, the aim of this study was to evaluate the diagnostic performance of the GI Genius AI system in clinical practice in a large endoscopy center.…”

“…Most studies agree that AI significantly increased the detection rate of small adenomas < 10 mm [13]. Given that adenomas of this size are unlikely to be cancerous, the clinical relevance of the use of AI systems is often questioned.…”