Densely connected U-Net retinal vessel segmentation algorithm based on multi-scale feature convolution extraction.

Journal: Medical physics
Published Date: Jun 16, 2021

Abstract

PURPOSE: The segmentation results of retinal blood vessels have a significant impact on the automatic diagnosis of various ophthalmic diseases. In order to further improve the segmentation accuracy of retinal vessels, we propose an improved algorithm based on multiscale vessel detection, which extracts features through densely connected networks and reuses features.

Authors

  • Xinfeng Du
    School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, 114051, China.
  • Jiesheng Wang
    School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, 114051, China.
  • Weizhen Sun
    School of Biological Science and Medical Engineering, Southeast University, Nanjing, Jiangsu, 210000, China.

Keywords

External Resources

Popular Topics
Recent Journals