Skip to main navigation Skip to search Skip to main content

Learning to Address Intra-segment Misclassification in Retinal Imaging

  • Yukun Zhou*
  • , Moucheng Xu
  • , Yipeng Hu
  • , Hongxiang Lin
  • , Joseph Jacob
  • , Pearse A. Keane
  • , Daniel C. Alexander
  • *Corresponding author for this work
  • University College London
  • Moorfields Eye Hospital NHS Foundation Trust
  • Zhejiang Lab

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Accurate multi-class segmentation is a long-standing challenge in medical imaging, especially in scenarios where classes share strong similarity. Segmenting retinal blood vessels in retinal photographs is one such scenario, in which arteries and veins need to be identified and differentiated from each other and from the background. Intra-segment misclassification, i.e. veins classified as arteries or vice versa, frequently occurs when arteries and veins intersect, whereas in binary retinal vessel segmentation, error rates are much lower. We thus propose a new approach that decomposes multi-class segmentation into multiple binary, followed by a binary-to-multi-class fusion network. The network merges representations of artery, vein, and multi-class feature maps, each of which are supervised by expert vessel annotation in adversarial training. A skip-connection based merging process explicitly maintains class-specific gradients to avoid gradient vanishing in deep layers, to favor the discriminative features. The results show that, our model respectively improves F1-score by 4.4%, 5.1%, and 4.2% compared with three state-of-the-art deep learning based methods on DRIVE-AV, LES-AV, and HRF-AV data sets. Code: https://github.com/rmaphoh/Learning-AVSegmentation

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2021 - 24th International Conference, Proceedings
EditorsMarleen de Bruijne, Marleen de Bruijne, Philippe C. Cattin, Stéphane Cotin, Nicolas Padoy, Stefanie Speidel, Yefeng Zheng, Caroline Essert
PublisherSpringer Science and Business Media Deutschland GmbH
Pages482-492
Number of pages11
ISBN (Print)9783030871925
DOIs
StatePublished - 2021
Externally publishedYes
Event24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021 - Virtual, Online
Duration: 27 Sep 20211 Oct 2021

Publication series

NameLecture Notes in Computer Science
Volume12901 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021
CityVirtual, Online
Period27/09/211/10/21

Keywords

  • Binary-to-multi-class fusion network
  • Intra-segment misclassification
  • Multi-class segmentation
  • Retinal vessel

Fingerprint

Dive into the research topics of 'Learning to Address Intra-segment Misclassification in Retinal Imaging'. Together they form a unique fingerprint.

Cite this