An Efficient Deep Learning Network for Automatic Detection of Neovascularization in Color Fundus Images.

Journal: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
PMID:

Abstract

Retinopathy screening is a non-invasive method to collect retinal images and neovascularization detection from retinal images plays a significant role on the identification and classification of diabetes retinopathy. In this paper, an efficient deep learning network for automatic detection of neovascularization in color fundus images is proposed. The network employs Feature Pyramid Network and Vovnet as the backbone to detect neovascularization. The network is evaluated with color fundus images from practice. Experimental results show the network has less training and test time than Mask R-CNN while with a high accuracy of 98.6%.

Authors

  • He Huang
  • Xiu Wang
    Department of Functional Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
  • He Ma
    Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang 110819, China and Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University, Shenyang 110819, China.