Conference Proceeding

Multiple ocular diseases detection by graph regularized multi-label learning

Authors
  • Xiangyu Chen (Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore)
  • Yanwu Xu (Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore)
  • Lixin Duan (Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore)
  • Zhuo Zhang (Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore)
  • Damon Wing Kee Wong (Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore)
  • Jiang Liu (Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore)

Abstract

We develop a general framework for multiple ocular diseases diagnosis, based on Graph Regularized Multi-label Learning (GRML). Glaucoma, Pathological Myopia (PM), and Age-related Macular Degeneration (AMD) are three leading ocular diseases in the world. By exploiting the correlations among these three diseases, a novel GRML scheme is investigated for a simultaneous detection of these three leading ocular diseases for a given fundus image. We validate our GRML framework by conducting extensive experiments on SiMES dataset. The results show area under curve (AUC) of the receiver operating characteristic curve in multiple ocular diseases detection are much better than traditional popular algorithms. The method could be used for glaucoma, PM, and AMD diagnosis.

How to Cite:

Chen, X. & Xu, Y. & Duan, L. & Zhang, Z. & Wong, D. W. & Liu, J., (2014) “Multiple ocular diseases detection by graph regularized multi-label learning”, Proceedings of the Ophthalmic Medical Image Analysis International Workshop 1(2014), 17-24. doi: https://doi.org/10.17077/omia.1004

Rights: Copyright © 2014, Xiangyu Chen, Yanwu Xu, Lixin Duan, Zhuo Zhang, Damon Wing Kee Wong, and Jiang Liu.

Downloads:
Download pdf
View PDF

246 Views

86 Downloads

Published on
14 Sep 2014
Peer Reviewed