The topology-overlap trade-off in retinal arteriole-venule segmentation

Angel Victor Juanco Muller, João F. C. Mota, Keith A. Goatman, Corné Hoogendoorn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

37 Downloads (Pure)

Abstract


Retinal fundus images can be an invaluable diagnosis tool for screening epidemic diseases like hypertension or diabetes. And they become especially useful when the arterioles and venules they depict are clearly identified and annotated. However, manual annotation of these vessels is extremely time demanding and taxing, which calls for automatic segmentation. Although convolutional neural networks can achieve high overlap between predictions and expert annotations, they often fail to produce topologically correct predictions of tubular structures. This situation is exacerbated by the bifurcation versus crossing ambiguity which causes classification mistakes. This paper shows that including a topology preserving term in the loss function improves the continuity of the segmented vessels, although at the expense of artery-vein misclassification and overall lower overlap metrics. However, we show that by including an orientation score guided convolutional module, based on the anisotropic single sided cake wavelet, we reduce such misclassification and further increase the topology correctness of the results. We evaluate our model on public datasets with conveniently chosen metrics to assess both overlap and topology correctness, showing that our model is able to produce results on par with state-of-the-art from the point of view of overlap, while increasing topological accuracy.
Original languageEnglish
Title of host publicationMedical Imaging 2023: Image Processing
EditorsOlivier Colliot, Ivana Isgum
PublisherSPIE
ISBN (Electronic)9781510660342
ISBN (Print)9781510660335
DOIs
Publication statusPublished - 3 Apr 2023
EventSPIE Medical Imaging 2023 - San Diego, United States
Duration: 19 Feb 202323 Feb 2023

Publication series

NameProceedings of SPIE
Volume12464
ISSN (Print)1605-7422
ISSN (Electronic)2410-9045

Conference

ConferenceSPIE Medical Imaging 2023
Country/TerritoryUnited States
CitySan Diego
Period19/02/2323/02/23

Keywords

  • Retinal fundus images
  • convolutional neural networks
  • orientation scores
  • topology loss function

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging
  • Biomaterials

Fingerprint

Dive into the research topics of 'The topology-overlap trade-off in retinal arteriole-venule segmentation'. Together they form a unique fingerprint.

Cite this