High pooled performance of convolutional neural networks in computer-aided diagnosis of GI ulcers and/or hemorrhage on wireless capsule endoscopy images: a systematic review and meta-analysis

Gastroenterology & Hepatology, University of Utah, Salt Lake City, Utah, USA. Gastroenterology, Rush University Medical Center, Chicago, Illinois, USA. Internal Medicine, Mayo Clinic, Rochester, Minnesota, USA. Internal Medicine, Roanoke Medical Center, Roanoke, Virginia, USA. Gastroenterology and Hepatology, University of Nebraska Medical Center, Omaha, Nebraska, USA. Gastroenterology, University of Oklahoma/Saint Anthony Hospital, Oklahoma City, Oklahoma, USA. Gastroenterology and Hepatology, University of California, San Diego, California, USA. Division of Gastroenterology and Hepatology, Allegheny Health Network, Pittsburgh, Pennsylvania, USA. Electronic address: Gursimran.Kochhar@ahn.org.

Gastrointest Endosc. 2020
Full text from:
Abstract
BACKGROUND AND AIMS Diagnosis of gastrointestinal (GI) ulcers and/or hemorrhage by wireless capsule endoscopy (WCE) is limited by the physician-dependent, tedious, time-consuming process of image and/ or video classification. Computer-aided diagnosis (CAD) by convolutional neural networks (CNN) based machine learning may help reduce this burden. Our aim was to conduct a meta-analysis and appraise the reported data. METHODS Multiple databases were searched (from inception to November 2019) and studies that reported on the performance of CNN in the diagnosis of GI ulcerations and/ or hemorrhage on WCE were selected. Random effects model was used to calculate the pooled rates. In cases where multiple 2X2 contingency tables were provided for different thresholds, we assumed the data tables as independent from each other. Heterogeneity was assessed by I(2)% and 95% prediction intervals. RESULTS Nine studies were included in our final analysis that evaluated the performance of CNN based CAD of GI ulcers and/ or hemorrhage by WCE. The pooled accuracy was 95.4% (95% CI, 94.3-96.3), sensitivity was 95.5% (95% CI, 94-96.5), specificity was 95.8% (95% CI, 94.7-96.6), positive predictive value was 95.8% (95% CI, 90.5-98.2) and negative predictive value was 96.8% (95% CI, 94.9-98.1). I(2)% heterogeneity was negligible except for the pooled positive predictive value. CONCLUSIONS Based on our meta-analysis, CNN based CAD of GI ulcerations and/ or hemorrhage on WCE achieves high-level performance. The quality of evidence is robust and therefore CNN based CAD has the potential to become the first-choice of machine learning to optimize WCE image/video reading.
Study details
Study Design : Systematic Review
Language : eng
Credits : Bibliographic data from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine