Skip to main content

Towards Adversarial Retinal Image Synthesis.

Costa, P., Galdran, A., Meyer, M.I., Abràmoff, M.D., Niemeijer, M., Mendonça, A.M. and Campilho, A., 2017. Towards Adversarial Retinal Image Synthesis. The Computing Research Repository (CoRR).

Full text available as:

[img]
Preview
PDF
1701.08974v1.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial.

6MB

Official URL: https://dblp.org/rec/journals/corr/CostaGMANMC17

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.

Item Type:Article
Additional Information:https://arxiv.org/abs/1701.08974
Uncontrolled Keywords:Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Machine Learning (stat.ML)
Group:Faculty of Science & Technology
ID Code:33033
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:13 Nov 2019 11:24
Last Modified:13 Nov 2019 11:24

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -