Measuring Objective Quality of Colonoscopy

Abstract

Advances in video technology are being incorporated into today's healthcare practices. Colonoscopy is regarded as one of the most important diagnostic tools for colorectal cancer. Indeed, colonoscopy has contributed to a decline in the number of colorectal-cancer-related deaths. Although colonoscopy has become the preferred screening modality for prevention of colorectal cancer, recent data suggest that there is a significant miss rate for the detection of large polyps and cancers, and methods to investigate why this occurs are needed. To address this problem, we present a new computer-based method that analyzes a digitized video file of a colonoscopic procedure and produces a number of metrics that likely reflect the quality of the procedure. The method consists of a set of novel image-processing algorithms designed to address new technical challenges due to uncommon characteristics of videos captured during colonoscopy. As these measurements can be obtained automatically, our method enables future quality control in large-scale day-to-day medical practice, which is currently not feasible. In addition, our method can be adapted to other endoscopic procedures such as upper gastrointestinal endoscopy, enteroscopy, and bronchoscopy. Last but not least, our method may be useful to assess progress during colonoscopy training.

Quality assurance of computer-aided detection and diagnosis in colonoscopy

“…17 Because AI serves just as an adjunct to both detection and characterization of colorectal polyps (by no means an autonomous robot), basic insertion and withdrawal skill for colonoscopy is still required, though some AI software was designed to improve the quality of mucosal exposure during colonoscopy withdrawal. 77 In addition, if the AI is designed for special endoscopy such as magnifying endoscopy, endocytoscopy, or confocal laser endomicroscopy, training to capture stable endoscopic images is also required. Once endoscopists acquire these basic skills, they may be able to achieve a high diagnostic performance with the use of AI comparable with that of experts.…”

Automated measurement of quality of mucosa inspection for colonoscopy

“…Post-procedure manual analysis of procedure quality is both time-consuming and subjective since the domain expert needs to review the entire video of a procedure. This limitation motivates researchers to develop automated methods that derive various objective quality metrics that can be compared among endoscopists [11][12][13][14][15]. Other automated analyses included polyp detection [16], appendiceal orifice image detection [17], 3D reconstruction of the colon surface for surgical planning [18,19], image-guided automated colonoscopy [20], and 3D reconstruction of a colon structure [DongHo] from a 2D colonoscopy image.…”

3D Colon Segment and Endoscope Motion Reconstruction from Colonoscopy Video

“…Further improvement is needed. Accurate camera motion directions are useful for evaluating mucosa inspection pattern in detail and for detection of the boundary between the insertion phase and the withdrawal phase of a procedure [69]. The boundary is important for calculating a number of other quality metrics.…”

“…Recent years have seen several advances in colonoscopy. For instance, a number of algorithms have been investigated for measuring objective quality of colonoscopy (i.e., how well the colon was inspected during the procedure) [8][9][10][11], polyp detection [12,13], anatomical landmark detection [14], 3D reconstruction of a cylinder generalized colon from colonoscopy images [15], and 3D reconstruction of the colon surface for surgical planning [16,17], or image-guided automated colonoscopy [18].…”