Evaluating false‐positive detection in a computer‐aided detection system for colonoscopy

Abstract

Background and AimComputer‐aided detection (CADe) systems can efficiently detect polyps during colonoscopy. However, false‐positive (FP) activation is a major limitation of CADe. We aimed to compare the rate and causes of FP using CADe before and after an update designed to reduce FP.MethodsWe analyzed CADe‐assisted colonoscopy videos recorded between July 2022 and October 2022. The number and causes of FPs and excessive time spent by the endoscopist on FP (ET) were compared pre‐ and post‐update using 1:1 propensity score matching.ResultsDuring the study period, 191 colonoscopy videos (94 and 97 in the pre‐ and post‐update groups, respectively) were recorded. Propensity score matching resulted in 146 videos (73 in each group). The mean number of FPs and median ET per colonoscopy were significantly lower in the post‐update group than those in the pre‐update group (4.2 ± 3.7 vs 18.1 ± 11.1; P < 0.001 and 0 vs 16 s; P < 0.001, respectively). Mucosal tags, bubbles, and folds had the strongest association with decreased FP post‐update (pre‐update vs post‐update: 4.3 ± 3.6 vs 0.4 ± 0.8, 0.32 ± 0.70 vs 0.04 ± 0.20, and 8.6 ± 6.7 vs 1.6 ± 1.7, respectively). There was no significant decrease in the true positive rate (post‐update vs pre‐update: 95.0% vs 99.2%; P = 0.09) or the adenoma detection rate (post‐update vs pre‐update: 52.1% vs 49.3%; P = 0.87).ConclusionsThe updated CADe can reduce FP without impairing polyp detection. A reduction in FP may help relieve the burden on endoscopists.

Vision-Based Construction Safety Monitoring Utilizing Temporal Analysis to Reduce False Alarms

“…False detection, false positives, and missed detection contribute significantly to false alarms in real-time monitoring systems. Achieving accurate detection relies on developing precise and generalized models capable of effectively identifying target objects [47]. Borowski et al addressed the challenge of high false-alarm rates within intensive care unit monitoring systems, primarily stemming from irrelevant noise and outliers in the time series of the sensor data.…”