Preprint
Towards Adversarial Retinal Image Synthesis
ArXiv.org
01/31/2017
Abstract
Synthesizing images of the eye fundus is a challenging task that has been
previously approached by formulating complex models of the anatomy of the eye.
New images can then be generated by sampling a suitable parameter space. In
this work, we propose a method that learns to synthesize eye fundus images
directly from data. For that, we pair true eye fundus images with their
respective vessel trees, by means of a vessel segmentation technique. These
pairs are then used to learn a mapping from a binary vessel tree to a new
retinal image. For this purpose, we use a recent image-to-image translation
technique, based on the idea of adversarial learning. Experimental results show
that the original and the generated images are visually different in terms of
their global appearance, in spite of sharing the same vessel tree.
Additionally, a quantitative quality analysis of the synthetic retinal images
confirms that the produced images retain a high proportion of the true image
set quality.
Details
- Title: Subtitle
- Towards Adversarial Retinal Image Synthesis
- Creators
- Pedro CostaAdrian GaldranMaria Inês MeyerMichael David AbràmoffMeindert NiemeijerAna Maria MendonçaAurélio Campilho
- Resource Type
- Preprint
- Publication Details
- ArXiv.org
- ISSN
- 2331-8422
- Number of pages
- 11 pages
- Language
- English
- Date posted
- 01/31/2017
- Academic Unit
- Electrical and Computer Engineering; Ophthalmology and Visual Sciences; Roy J. Carver Department of Biomedical Engineering; Fraternal Order of Eagles Diabetes Research Center
- Record Identifier
- 9984172169202771
Metrics
9 Record Views