Self-relabeling for noise-tolerant retina vessel segmentation through label reliability estimation.

Journal: BMC medical imaging
Published Date: Jan 12, 2022

Abstract

BACKGROUND: Retinal vessel segmentation benefits significantly from deep learning. Its performance relies on sufficient training images with accurate ground-truth segmentation, which are usually manually annotated in the form of binary pixel-wise label maps. Manually annotated ground-truth label maps, more or less, contain errors for part of the pixels. Due to the thin structure of retina vessels, such errors are more frequent and serious in manual annotations, which negatively affect deep learning performance.

Authors

  • Jiacheng Li
    College of Intelligence and Computing, Tianjin University, Tianjin, China.
  • Ruirui Li
    College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China.
  • Ruize Han
    College of Intelligence and Computing, Tianjin University, Tianjin, China.
  • Song Wang
    Key Laboratory of Precision and Intelligent Chemistry, School of Chemistry and Materials Science, University of Science and Technology of China, China.

Keywords

External Resources

Popular Topics
Recent Journals