Literature DB >> 32721487

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.

Babu P Mohan1, Shahab R Khan2, Lena L Kassab3, Suresh Ponnada4, Saurabh Chandan5, Tauseef Ali6, Parambir S Dulai7, Douglas G Adler1, Gursimran S Kochhar8.   

Abstract

BACKGROUND AND AIMS: Diagnosis of 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 network (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. A random-effects model was used to calculate the pooled rates. In cases where multiple 2 × 2 contingency tables were provided for different thresholds, we assumed the data tables were independent from each other. Heterogeneity was assessed by I2% 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% confidence interval [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). I2% 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 a high-level performance. The quality of the 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.
Copyright © 2021 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.

Entities:  

Mesh:

Year:  2020        PMID: 32721487     DOI: 10.1016/j.gie.2020.07.038

Source DB:  PubMed          Journal:  Gastrointest Endosc        ISSN: 0016-5107            Impact factor:   9.427


  9 in total

1.  Quality assessment standards in artificial intelligence diagnostic accuracy systematic reviews: a meta-research study.

Authors:  Shruti Jayakumar; Viknesh Sounderajah; Pasha Normahani; Leanne Harling; Sheraz R Markar; Hutan Ashrafian; Ara Darzi
Journal:  NPJ Digit Med       Date:  2022-01-27

2.  Application of Optimized GA-BPNN Algorithm in English Teaching Quality Evaluation System.

Authors:  Yaowu Zhu; Junnong Xu; Sihong Zhang
Journal:  Comput Intell Neurosci       Date:  2021-12-31

Review 3.  Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis.

Authors:  Chang Seok Bang; Jae Jun Lee; Gwang Ho Baik
Journal:  J Med Internet Res       Date:  2021-12-14       Impact factor: 5.428

Review 4.  Recent developments in small bowel endoscopy: the "black box" is now open!

Authors:  Luigina Vanessa Alemanni; Stefano Fabbri; Emanuele Rondonotti; Alessandro Mussetto
Journal:  Clin Endosc       Date:  2022-07-14

Review 5.  Pooled diagnostic parameters of artificial intelligence in EUS image analysis of the pancreas: A descriptive quantitative review.

Authors:  Babu P Mohan; Antonio Facciorusso; Shahab R Khan; Deepak Madhu; Lena L Kassab; Suresh Ponnada; Saurabh Chandan; Stefano F Crino; Gursimran S Kochhar; Douglas G Adler; Michael B Wallace
Journal:  Endosc Ultrasound       Date:  2022 May-Jun       Impact factor: 5.275

6.  Comparison of Different Convolutional Neural Network Activation Functions and Methods for Building Ensembles for Small to Midsize Medical Data Sets.

Authors:  Loris Nanni; Sheryl Brahnam; Michelangelo Paci; Stefano Ghidoni
Journal:  Sensors (Basel)       Date:  2022-08-16       Impact factor: 3.847

7.  Ultrasound-based deep learning using the VGGNet model for the differentiation of benign and malignant thyroid nodules: A meta-analysis.

Authors:  Pei-Shan Zhu; Yu-Rui Zhang; Jia-Yu Ren; Qiao-Li Li; Ming Chen; Tian Sang; Wen-Xiao Li; Jun Li; Xin-Wu Cui
Journal:  Front Oncol       Date:  2022-09-28       Impact factor: 5.738

Review 8.  Convolution neural network for the diagnosis of wireless capsule endoscopy: a systematic review and meta-analysis.

Authors:  Kaiwen Qin; Jianmin Li; Yuxin Fang; Yuyuan Xu; Jiahao Wu; Haonan Zhang; Haolin Li; Side Liu; Qingyuan Li
Journal:  Surg Endosc       Date:  2021-08-23       Impact factor: 4.584

Review 9.  Artificial intelligence in gastrointestinal endoscopy for inflammatory bowel disease: a systematic review and new horizons.

Authors:  Gian Eugenio Tontini; Alessandro Rimondi; Marta Vernero; Helmut Neumann; Maurizio Vecchi; Cristina Bezzio; Flaminia Cavallaro
Journal:  Therap Adv Gastroenterol       Date:  2021-06-10       Impact factor: 4.409

  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.