Search

We developed and validated a deep-learning algorithm for polyp detection. We used a YOLOv2 to develop the algorithm for automatic polyp detection on 8,075 images (503 polyps). We validated the algorithm using three datasets: A: 1,338 images with 1,349 polyps; B: an open, public CVC-clinic database with 612 polyp images; and C: 7 colonoscopy videos with 26 polyps. To reduce the number of false positives in the video analysis, median filtering was applied. We tested the algorithm performance using 15 unaltered colonoscopy videos (dataset D). For datasets A and B, the per-image polyp detection sensitivity was 96.7% and 90.2%, respectively. For video study (dataset C), the per-image polyp detection sensitivity was 87.7%. False positive rates were 12.5% without a median filter and 6.3% with a median filter with a window size of 13. For dataset D, the sensitivity and false positive rate were 89.3% and 8.3%, respectively. The algorithm detected all 38 polyps that the endoscopists detected and 7 additional polyps. The operation speed was 67.16 frames per second. The automatic polyp detection algorithm exhibited good performance, as evidenced by the high detection sensitivity and rapid processing. Our algorithm may help endoscopists improve polyp detection. [ABSTRACT FROM AUTHOR]

Background: The recurrence rate after standard cold forceps polypectomy (CFP) of diminutive polyps of ≤5 mm has not been fully determined. The aim of this study was to analyze the long-term follow-up results and recurrence rate after CFP of diminutive polyps.Methods: We retrospectively reviewed the medical records of 884 (738 men; age 53 years) asymptomatic subjects who underwent surveillance colonoscopy after CFP of 1-2 diminutive adenomatous polyps. Cumulative recurrence at the CFP site and risk factors for recurrence were analyzed.Results: Overall recurrence over 59.7 months was 17 % after CFP of 1111 diminutive polyps. The rate of definite recurrence was 4 %, and probable recurrence was 13 %. Recurrence as advanced adenoma was 0.5 % (5/1111). The cumulative probabilities of recurrence at 3, 5, and 7 years after CFP were 10.0, 16.0, and 21.1 %, respectively. Multivariate analysis revealed that polyp 4-5 mm in size and right colonic polyp were risk factors for recurrence (hazard ratio [HR] 1.37; 95 % confidence interval [CI] 1.01-1.86 and HR 1.49; 95 % CI 1.08-2.04, respectively). The recurrence rate for 10 endoscopists who performed at least 50 CFPs ranged from 11.0 to 25.2 %; the probability of recurrence in those in the top half in terms of recurrence rate was 1.6-fold higher than that of those in the bottom half (95 % CI 1.17-2.19).Conclusions: Although recurrence may develop after standard CFP of diminutive polyps, recurrence as advanced adenoma is rare. Large polyp size, right colon polyp, and endoscopist are risk factors for recurrence after standard CFP. [ABSTRACT FROM AUTHOR]

Background and Aim: This study aimed to develop and validate a risk score model to estimate the probability of a metachronous advanced colorectal neoplasm (ACRN) at surveillance colonoscopy.Methods: A retrospective analysis of a prospectively obtained database of 11,042 asymptomatic subjects who underwent surveillance colonoscopy after a screening colonoscopy was conducted. Subjects were randomly divided into derivation (n = 7730) and validation sets (n = 3312). From the derivation cohort, risk factors for a metachronous ACRN were identified by a multivariable analysis. Risk points were allocated to each risk factor based on the hazard ratio to develop the Metachronous Advanced colorectal neoplasm Prediction Scoring (MAPS) model, the performance of which was assessed in the validation cohort.Results: In the derivation cohort, age, male, sessile serrated adenoma/polyp, and a high-risk CRN (ACRN or ≥3 adenomas) at screening colonoscopy were independent risk factors for a metachronous ACRN. These variables were incorporated into the MAPS model, and the risk score ranged 0-17 (high MAPS risk arbitrarily defined as 10-17). At the 3-year surveillance colonoscopy, ACRN was found in 5.1 % of the high MAPS risk group versus 3.9 % of the high-risk CRN group. The colonoscopy number needed to detect one metachronous ACRN at the 3-year surveillance was 19.5 (95 % CI 11.7-33.2) for the high MAPS risk group versus 25.8 (95 % CI 15.4-44.0) for the high-risk CRN group. These findings were similarly confirmed in the validation cohort.Conclusions: Our MAPS model based on clinical and colonoscopic parameters effectively predicts the risk of a metachronous ACRN. [ABSTRACT FROM AUTHOR]

Background: Current guidelines for the surveillance colonoscopy interval are largely based on the most recent colonoscopy findings. Aim: We aimed to evaluate differences in the probability of high-risk neoplasm recurrence according to the two previous colonoscopy findings. Methods: This was a retrospective cohort study from a tertiary-care center. A total of 4,143 subjects who underwent three or more colonoscopies for screening or surveillance purposes from January 2001 to December 2011 were enrolled. We compared the probability of high-risk neoplasm detection on follow-up colonoscopies after the second colonoscopy based on risk categories in both the second and first colonoscopies. Results: At the final colonoscopy, 370 participants (8.9 %) had high-risk neoplasms. In patients with a normal second colonoscopy, the probability of high-risk neoplasm recurrence was different between those with normal, low-risk, and high-risk findings at the first colonoscopy (3.8, 6.8, and 17.7 %, respectively). The hazard ratio of a high-risk neoplasm at the final colonoscopy for patients with a normal second and low-risk first colonoscopy over a normal second and normal first colonoscopy was 3.07 (95 % CI 2.04-4.64, P < 0.001). The hazard ratio of high-risk neoplasm at the final colonoscopy for patients with a normal second and high-risk first colonoscopy over a normal second with normal first colonoscopy was 7.88 (95 % CI 4.90-12.67, P < 0.001). Conclusions: The rate of high-risk colorectal neoplasm recurrence differs according to the two previous colonoscopy findings. Therefore, surveillance intervals could be adjusted not just only by the most recent colonoscopy findings but also by considering two previous colonoscopy findings. [ABSTRACT FROM AUTHOR]