Towards Adversarial Retinal Image Synthesis
This work addresses the problem of generating realistic retinal images for medical imaging applications, but it is incremental as it applies an existing image-to-image translation technique to a specific domain.
The paper tackled the challenge of synthesizing eye fundus images by learning a mapping from binary vessel trees to retinal images using adversarial learning, resulting in synthetic images that retain a high proportion of the true image set quality.
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.