William E. Karnes

Use of the Endocuff during routine colonoscopy examination improves adenoma detection: A meta-analysis

AIM To perform meta-analysis of the use of Endocuff during average risk screening colonoscopy. METHODS Scopus, Cochrane databases, MEDLINE/PubMed, and CINAHL were searched in April 2016. Abstracts from Digestive Disease Week, United European Gastroenterology, and the American College of Gastroenterology meeting were also searched from 2004-2015. Studies comparing EC-assisted colonoscopy (EAC) to standard colonoscopy, for any indication, were included in the analysis. The analysis was conducted by using the Mantel-Haenszel or DerSimonian and Laird models with the odds ratio (OR) to assess adenoma detection, cecal intubation rate, and complications performed. RESULTS Nine studies (n = 5624 patients) were included in the analysis. Compared to standard colonoscopy, procedures performed with EC had higher frequencies for adenoma (OR = 1.49, 95%CI: 1.23-1.80; P = 0.03), and sessile serrated adenomas detection (OR = 2.34 95%CI: 1.63-3.36; P < 0.001). There was no significant difference in cecal intubation rates between the EAC group and standard colonoscopy (OR = 1.26, 95%CI: 0.70-2.27, I2 = 0%; P = 0.44). EAC was associated with a higher risk of complications, most commonly being superficial mucosal injury without higher frequency for perforation. CONCLUSION The use of an EC on colonoscopy appears to improve pre-cancerous polyp detection without any difference in cecal intubation rates compared to standard colonoscopy.

Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy

BACKGROUND & AIMS The benefit of colonoscopy for colorectal cancer prevention depends on the adenoma detection rate (ADR). The ADR should reflect the adenoma prevalence rate, which is estimated to be higher than 50% in the screening-age population. However, the ADR by colonoscopists varies from 7% to 53%. It is estimated that every 1% increase in ADR lowers the risk of interval colorectal cancers by 3%-6%. New strategies are needed to increase the ADR during colonoscopy. We tested the ability of computer-assisted image analysis using convolutional neural networks (CNNs; a deep learning model for image analysis) to improve polyp detection, a surrogate of ADR. METHODS We designed and trained deep CNNs to detect polyps using a diverse and representative set of 8,641 hand-labeled images from screening colonoscopies collected from more than 2000 patients. We tested the models on 20 colonoscopy videos with a total duration of 5 hours. Expert colonoscopists were asked to identify all polyps in 9 de-identified colonoscopy videos, which were selected from archived video studies, with or without benefit of the CNN overlay. Their findings were compared with those of the CNN using CNN-assisted expert review as the reference. RESULTS When tested on manually labeled images, the CNN identified polyps with an area under the receiver operating characteristic curve of 0.991 and an accuracy of 96.4%. In the analysis of colonoscopy videos in which 28 polyps were removed, 4 expert reviewers identified 8 additional polyps without CNN assistance that had not been removed and identified an additional 17 polyps with CNN assistance (45 in total). All polyps removed and identified by expert review were detected by the CNN. The CNN had a false-positive rate of 7%. CONCLUSION In a set of 8,641 colonoscopy images containing 4,088 unique polyps, the CNN identified polyps with a cross-validation accuracy of 96.4% and an area under the receiver operating characteristic curve of 0.991. The CNN system detected and localized polyps well within real-time constraints using an ordinary desktop machine with a contemporary graphics processing unit. This system could increase the ADR and decrease interval colorectal cancers but requires validation in large multicenter trials.