Identification of ocular refraction based on deep learning algorithm as a novel retinoscopy method.

Journal: Biomedical engineering online
PMID: 36528597

Abstract

BACKGROUND: The evaluation of refraction is indispensable in ophthalmic clinics, generally requiring a refractor or retinoscopy under cycloplegia. Retinal fundus photographs (RFPs) supply a wealth of information related to the human eye and might provide a promising approach that is more convenient and objective. Here, we aimed to develop and validate a fusion model-based deep learning system (FMDLS) to identify ocular refraction via RFPs and compare with the cycloplegic refraction. In this population-based comparative study, we retrospectively collected 11,973 RFPs from May 1, 2020 to November 20, 2021. The performance of the regression models for sphere and cylinder was evaluated using mean absolute error (MAE). The accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, and F1-score were used to evaluate the classification model of the cylinder axis.

Authors

  • HaoHan Zou
    Tianjin Eye Hospital, Tianjin Eye Institute, Tianjin Key Laboratory of Ophthalmology and Visual Science, Tianjin, China; Clinical College of Ophthalmology, Tianjin Medical University, Tianjin, China.
  • Shenda Shi
    School of Computer Science, School of National Pilot Software Engineering, Beijing University of Posts and Telecommunications, 10 Xitucheng Road, Hai-Dian District, Beijing, 100876, China.
  • Xiaoyan Yang
  • Jiaonan Ma
    Tianjin Key Lab of Ophthalmology and Visual Science, Tianjin Eye Institute, Tianjin Eye Hospital, Nankai University Affiliated Eye Hospital, 4 Gansu Road, He-Ping District, Tianjin, 300020, China.
  • Qian Fan
    Tianjin Key Lab of Ophthalmology and Visual Science, Tianjin Eye Institute, Tianjin Eye Hospital, Nankai University Affiliated Eye Hospital, 4 Gansu Road, He-Ping District, Tianjin, 300020, China.
  • Xuan Chen
    Electrical Engineering Department, University of California, Los Angeles, CA 90095, USA.
  • Yibing Wang
    Department of Radiation Oncology, Erasmus MC Cancer Institute, Rotterdam, the Netherlands.
  • Mingdong Zhang
    Clinical College of Ophthalmology, Tianjin Medical University, Tianjin, China.
  • Jiaxin Song
    Clinical College of Ophthalmology, Tianjin Medical University, Tianjin, China.
  • Yanglin Jiang
    School of Mechanical Engineering, Anhui University of Technology, Ma'anshan 240302, China.
  • Lihua Li
    College of Life Information Science and Instrument Engineering, Hangzhou Dianzi University, Hangzhou 310018, China. Electronic address: lilh@hdu.edu.cn.
  • Xin He
    Department of Nephrology, The Affiliated Hospital of Guizhou Medical, Guizhou, China.
  • Vishal Jhanji
    Department of Ophthalmology, UPMC Eye Center, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.
  • Shengjin Wang
  • Meina Song
    School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, 100876, China; Education Department Information Network Engineering Research Center, Beijing University of Posts and Telecommunications, Beijing, 100876, China. Electronic address: mnsong@bupt.edu.cn.
  • Yan Wang
    College of Animal Science and Technology, Beijing University of Agriculture, Beijing, China.

Keywords

External Resources

Popular Topics
Recent Journals