Download PDFOpen PDF in browser

Deep learning-based detection of domain-specific retinal landmarks for color fundus image registration

3 pagesPublished: February 16, 2023

Abstract

Retinal imaging is widely used to diagnose and monitor eye-specific pathologies as well as some systemic diseases. Registering retinal images is crucial to compare the relevant structures within the eye. In this work, we propose a deep learning-based method to register color fundus images using domain-specific landmarks. We employ a deep neural network to detect bifurcations and crossovers of the retinal arterio-venous vessel tree. Then, these keypoints are directly matched using RANSAC. Our method was tested using the public FIRE dataset obtaining a registration score of 0.657, which is comparable to the best state of the art methods although our proposal is comparably much faster. Furthermore, our method improves the results of the state of the art deep learning methods.

Keyphrases: Color Fundus Images, deep learning, Domain-specific keypoints, medical image registration, Medical Imaging

In: Alvaro Leitao and Lucía Ramos (editors). Proceedings of V XoveTIC Conference. XoveTIC 2022, vol 14, pages 127--129

Links:
BibTeX entry
@inproceedings{XoveTIC2022:Deep_learning_based_detection_of,
  author    = {David Rivas-Villar and \textbackslash{}'Alvaro S. Hervella and Jos\textbackslash{}'e Rouco and Jorge Novo},
  title     = {Deep learning-based detection of domain-specific retinal landmarks for color fundus image registration},
  booktitle = {Proceedings of V XoveTIC Conference. XoveTIC 2022},
  editor    = {Alvaro Leitao and Luc\textbackslash{}'ia Ramos},
  series    = {Kalpa Publications in Computing},
  volume    = {14},
  pages     = {127--129},
  year      = {2023},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2515-1762},
  url       = {https://easychair.org/publications/paper/dZKs},
  doi       = {10.29007/lmk4}}
Download PDFOpen PDF in browser