Identifying key mechanisms leading to visual recognition errors for missed colorectal polyps using eye‐tracking technology
Open Access
- 1 February 2023
- journal article
- research article
- Published by Wiley in Journal of Gastroenterology and Hepatology
- Vol. 38 (5), 768-774
- https://doi.org/10.1111/jgh.16127
Abstract
Background and AimLack of visual recognition of colorectal polyps may lead to interval cancers. The mechanisms contributing to perceptual variation, particularly for subtle and advanced colorectal neoplasia, have scarcely been investigated. We aimed to evaluate visual recognition errors and provide novel mechanistic insights. MethodsEleven participants (seven trainees and four medical students) evaluated images from the UCL polyp perception dataset, containing 25 polyps, using eye-tracking equipment. Gaze errors were defined as those where the lesion was not observed according to eye-tracking technology. Cognitive errors occurred when lesions were observed but not recognized as polyps by participants. A video study was also performed including 39 subtle polyps, where polyp recognition performance was compared with a convolutional neural network. ResultsCognitive errors occurred more frequently than gaze errors overall (65.6%), with a significantly higher proportion in trainees (P = 0.0264). In the video validation, the convolutional neural network detected significantly more polyps than trainees and medical students, with per-polyp sensitivities of 79.5%, 30.0%, and 15.4%, respectively. ConclusionsCognitive errors were the most common reason for visual recognition errors. The impact of interventions such as artificial intelligence, particularly on different types of perceptual errors, needs further investigation including potential effects on learning curves. To facilitate future research, a publicly accessible visual perception colonoscopy polyp database was created.Keywords
Funding Information
- Wellcome Trust
- Engineering and Physical Sciences Research Council (203145Z/16/Z)
This publication has 15 references indexed in Scilit:
- New artificial intelligence system: first validation study versus experienced endoscopists for colorectal polyp detectionGut, 2019
- Objective evaluation of the visibility of colorectal lesions using eye trackingDigestive Endoscopy, 2019
- Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directionsThe Lancet Gastroenterology & Hepatology, 2019
- Measuring gaze patterns during colonoscopy: a useful tool to evaluate colon inspection?European Journal of Gastroenterology & Hepatology, 2016
- The learning curve for detection of non-polypoid (flat and depressed) colorectal neoplasmsGut, 2013
- An Endoscopic Quality Improvement Program Improves Detection of Colorectal AdenomasThe American Journal of Gastroenterology, 2013
- Participation by experienced endoscopy nurses increases the detection rate of colon polyps during a screening colonoscopy: a multicenter, prospective, randomized studyGastrointestinal Endoscopy, 2011
- Association Between Visual Gaze Patterns and Adenoma Detection Rate During Colonoscopy: A Preliminary InvestigationThe American Journal of Gastroenterology, 2011
- “Eye-tracking” for assessment of image perception in gastrointestinal endoscopy with narrow-band imaging compared with white-light endoscopyEndoscopy, 2010
- Quality Indicators for Colonoscopy and the Risk of Interval CancerThe New England Journal of Medicine, 2010