General deep learning model for detecting diabetic retinopathy.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Doctors can detect symptoms of diabetic retinopathy (DR) early by using retinal ophthalmoscopy, and they can improve diagnostic efficiency with the assistance of deep learning to select treatments and support personnel workflow. Conventionally, most deep learning methods for DR diagnosis categorize retinal ophthalmoscopy images into training and validation data sets according to the 80/20 rule, and they use the synthetic minority oversampling technique (SMOTE) in data processing (e.g., rotating, scaling, and translating training images) to increase the number of training samples. Oversampling training may lead to overfitting of the training model. Therefore, untrained or unverified images can yield erroneous predictions. Although the accuracy of prediction results is 90%-99%, this overfitting of training data may distort training module variables.

Authors

  • Ping-Nan Chen
    Department of Biomedical Engineering, National Defense Medical Center, Taipei, 114, Taiwan, ROC. g931310@gmail.com.
  • Chia-Chiang Lee
    Graduate Institute of Applied Science and Technology, National Taiwan University of Science and Technology, Taipei, 106, Taiwan, ROC.
  • Chang-Min Liang
    Department of Ophthalmology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan.
  • Shu-I Pao
    Department of Ophthalmology, Tri-Service General Hospital, National Defense Medical Center, Taipei, 114, Taiwan, ROC.
  • Ke-Hao Huang
    Department of Ophthalmology, Tri-Service General Hospital, National Defense Medical Center, Taipei, 114, Taiwan, ROC.
  • Ke-Feng Lin
    Graduate Institute of Applied Science and Technology, National Taiwan University of Science and Technology, Taipei, 106, Taiwan, ROC.