Artificial intelligence-assisted colonoscopy: a narrative review of current data and clinical applications

Abstract

Colonoscopy is the reference standard procedure for the prevention and diagnosis of colorectal cancer, which is a leading cause of cancer-related deaths in Singapore. Artificial intelligence systems are automated, objective and reproducible. Artificial intelligence-assisted colonoscopy has recently been introduced into clinical practice as a clinical decision support tool. This review article provides a summary of the current published data and discusses ongoing research and current clinical applications of artificial intelligence-assisted colonoscopy.

Use of artificial intelligence in the management of T1 colorectal cancer: a new tool in the arsenal or is deep learning out of its depth?

“…DL, a subbranch of the ML field, is the most commonly used tool in the literature on AI and colonoscopy. 25,82 In this method, multiple linear and nonlinear processing units are arranged in a deep architecture to extract useful information automatically and construct a model that generates the required output. DL models perform these tasks without requiring predefined features, which is characteristic of conventional ML techniques.…”

Precision endoscopy in the era of climate change and sustainability

“…Computer-aided diagnosis (CADx) systems can provide endoscopists with an automated real-time output for the characterization of polyps detected during colonoscopy. 78,79 In a study by Minegishi et al, 80 the real-time use of a CADx system when paired with endoscopist high-confidence optical diagnosis using NBI achieved an NPV for adenomatous histology of 94.1% (95% CI 83.8-98.8%) in diminutive rectosigmoid colon polyps. The COMBO-CAD study, 81 which was designed as a single-center, head-to-head noninferiority comparison of two commercially available CADx systems, similarly demonstrated high NPVs for adenomatous histology in diminutive rectosigmoid colon polyps (97.0% and 97.7%).…”

“…Computer‐aided diagnosis (CADx) systems can provide endoscopists with an automated real‐time output for the characterization of polyps detected during colonoscopy 78,79 . In a study by Minegishi et al ., 80 the real‐time use of a CADx system when paired with endoscopist high‐confidence optical diagnosis using NBI achieved an NPV for adenomatous histology of 94.1% (95% CI 83.8–98.8%) in diminutive rectosigmoid colon polyps.…”

The imitation game: a review of the use of artificial intelligence in colonoscopy, and endoscopists’ perceptions thereof

“…CADx involves characterizing polyps based on morphological parameters, such as surface, vascular patterns, shape, size, and location, to generate probability scores for malignancy or nonmalignancy [ 41 ]. This helps to improve the accuracy of optical biopsies, which refer to the in vivo prediction of polyp histology before resection and formal histological analysis [ 42 ]. Most of these systems use image-enhanced endoscopy techniques such as narrow-band imaging and blue laser imaging (BLI) to enhance the accuracy of predictions.…”