Literature DB >> 33577791

Glaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study.

Michael Chiang1, Daniel Guth2, Anmol A Pardeshi1, Jasmeen Randhawa3, Alice Shen1, Meghan Shan1, Justin Dredge1, Annie Nguyen1, Kimberly Gokoffski1, Brandon J Wong1, Brian Song1, Shan Lin4, Rohit Varma5, Benjamin Y Xu6.   

Abstract

PURPOSE: To compare the performance of a novel convolutional neural network (CNN) classifier and human graders in detecting angle closure in EyeCam (Clarity Medical Systems, Pleasanton, California, USA) goniophotographs.
DESIGN: Retrospective cross-sectional study.
METHODS: Subjects from the Chinese American Eye Study underwent EyeCam goniophotography in 4 angle quadrants. A CNN classifier based on the ResNet-50 architecture was trained to detect angle closure, defined as inability to visualize the pigmented trabecular meshwork, using reference labels by a single experienced glaucoma specialist. The performance of the CNN classifier was assessed using an independent test dataset and reference labels by the single glaucoma specialist or a panel of 3 glaucoma specialists. This performance was compared to that of 9 human graders with a range of clinical experience. Outcome measures included area under the receiver operating characteristic curve (AUC) metrics and Cohen kappa coefficients in the binary classification of open or closed angle.
RESULTS: The CNN classifier was developed using 29,706 open and 2,929 closed angle images. The independent test dataset was composed of 600 open and 400 closed angle images. The CNN classifier achieved excellent performance based on single-grader (AUC = 0.969) and consensus (AUC = 0.952) labels. The agreement between the CNN classifier and consensus labels (κ = 0.746) surpassed that of all non-reference human graders (κ = 0.578-0.702). Human grader agreement with consensus labels improved with clinical experience (P = 0.03).
CONCLUSION: A CNN classifier can effectively detect angle closure in goniophotographs with performance comparable to that of an experienced glaucoma specialist. This provides an automated method to support remote detection of patients at risk for primary angle closure glaucoma.
Copyright © 2021 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Angle closure; artificial intelligence; goniophotography; gonioscopy; primary angle closure glaucoma

Mesh:

Year:  2021        PMID: 33577791      PMCID: PMC8286291          DOI: 10.1016/j.ajo.2021.02.004

Source DB:  PubMed          Journal:  Am J Ophthalmol        ISSN: 0002-9394            Impact factor:   5.488


  21 in total

Review 1.  Angle closure and angle-closure glaucoma: what we are doing now and what we will be doing in the future.

Authors:  David S Friedman; Paul J Foster; Tin Aung; Mingguang He
Journal:  Clin Exp Ophthalmol       Date:  2012-04-05       Impact factor: 4.207

2.  Angle assessment by EyeCam, goniophotography, and gonioscopy.

Authors:  Mani Baskaran; Shamira A Perera; Monisha E Nongpiur; Tin A Tun; Judy Park; Rajesh S Kumar; David S Friedman; Tin Aung
Journal:  J Glaucoma       Date:  2012-09       Impact factor: 2.503

3.  Artificial Intelligence in Health Care: Will the Value Match the Hype?

Authors:  Ezekiel J Emanuel; Robert M Wachter
Journal:  JAMA       Date:  2019-06-18       Impact factor: 56.272

4.  Deep Learning Classifiers for Automated Detection of Gonioscopic Angle Closure Based on Anterior Segment OCT Images.

Authors:  Benjamin Y Xu; Michael Chiang; Shreyasi Chaudhary; Shraddha Kulkarni; Anmol A Pardeshi; Rohit Varma
Journal:  Am J Ophthalmol       Date:  2019-08-22       Impact factor: 5.258

5.  Correlation between Intraocular Pressure and Angle Configuration Measured by OCT: The Chinese American Eye Study.

Authors:  Benjamin Y Xu; Bruce Burkemper; Juan Pablo Lewinger; Xuejuan Jiang; Anmol A Pardeshi; Grace Richter; Mina Torres; Roberta McKean-Cowdin; Rohit Varma
Journal:  Ophthalmol Glaucoma       Date:  2018-09-29

6.  The anterior chamber angle is different in different racial groups: a gonioscopic study.

Authors:  Y G Oh; S Minelli; G L Spaeth; W C Steinman
Journal:  Eye (Lond)       Date:  1994       Impact factor: 3.775

7.  Laser peripheral iridotomy for the prevention of angle closure: a single-centre, randomised controlled trial.

Authors:  Mingguang He; Yuzhen Jiang; Shengsong Huang; Dolly S Chang; Beatriz Munoz; Tin Aung; Paul J Foster; David S Friedman
Journal:  Lancet       Date:  2019-03-14       Impact factor: 79.321

Review 8.  The pathophysiology and treatment of glaucoma: a review.

Authors:  Robert N Weinreb; Tin Aung; Felipe A Medeiros
Journal:  JAMA       Date:  2014-05-14       Impact factor: 56.272

9.  Agreement between Gonioscopic Examination and Swept Source Fourier Domain Anterior Segment Optical Coherence Tomography Imaging.

Authors:  Mohammed Rigi; Nicholas P Bell; David A Lee; Laura A Baker; Alice Z Chuang; Donna Nguyen; Vandana R Minnal; Robert M Feldman; Lauren S Blieden
Journal:  J Ophthalmol       Date:  2016-11-20       Impact factor: 1.909

10.  A Population-Based Assessment of the Agreement Between Grading of Goniophotographic Images and Gonioscopy in the Chinese-American Eye Study (CHES).

Authors:  Yohko Murakami; Dandan Wang; Bruce Burkemper; Shan C Lin; Rohit Varma
Journal:  Invest Ophthalmol Vis Sci       Date:  2016-08-01       Impact factor: 4.799

View more
  3 in total

1.  Deep learning-based classification of the anterior chamber angle in glaucoma gonioscopy.

Authors:  Quan Zhou; Jingmin Guo; Zhiqi Chen; Wei Chen; Chaohua Deng; Tian Yu; Fei Li; Xiaoqin Yan; Tian Hu; Linhao Wang; Yan Rong; Mingyue Ding; Junming Wang; Xuming Zhang
Journal:  Biomed Opt Express       Date:  2022-08-10       Impact factor: 3.562

2.  Semantic segmentation of gonio-photographs via adaptive ROI localisation and uncertainty estimation.

Authors:  Andrea Peroni; Anna Paviotti; Mauro Campigotto; Luis Abegão Pinto; Carlo Alberto Cutolo; Jacintha Gong; Sirjhun Patel; Caroline Cobb; Stewart Gillan; Andrew Tatham; Emanuele Trucco
Journal:  BMJ Open Ophthalmol       Date:  2021-11-25

3.  Automated Focal Plane Merging From a Stack of Gonioscopic Photographs Using a Focus-Stacking Algorithm.

Authors:  Masato Matsuo; Nana Kozuki; Yuina Inomata; Yoshiki Kumagai; Ryosuke Shiba; Koji Hamaguchi; Masaki Tanito
Journal:  Transl Vis Sci Technol       Date:  2022-04-01       Impact factor: 3.048

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.