biostudies-literatureChiang MNEI NIH HHSAmerican Glaucoma SocietyResearch to Prevent BlindnessFight for SightNational Institutes of HealthUniversity of Southern California Southern California Clinical and Translational Science Institute100-107https://www.ebi.ac.uk/biostudies/studies/S-EPMC8286291biostudies-literatureUnknown226<h4>Purpose</h4>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.<h4>Design</h4>Retrospective cross-sectional study.<h4>Methods</h4>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. American journal of ophthalmologyGlaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study.PMC8286291K23 EY029763U10 EY017337P30 EY029220Gokoffski KLin SShan MSong BGuth DChiang MWong BJShen ADredge JXu BYPardeshi AARandhawa JNguyen AVarma RfalseGlaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study.<h4>Purpose</h4>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.<h4>Design</h4>Retrospective cross-sectional study.<h4>Methods</h4>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. 2021-01-01T00:00:00Z2021 Jun2025-04-22T21:51:54.415Z2025-04-06T03:53:46.68ZS-EPMC82862913357779110.1016/j.ajo.2021.02.004