Synthesizing Fundus Photographies for Training Segmentation Networks

Jannes Magnusson, Ahmed Afifi, Shengjia Zhang, Andreas Ley, Olaf Hellwich

2021

Abstract

Automated semantic segmentation of medical imagery is a vital application using modern Deep Learning methods as they can support clinicians in their decision-making processes. However, training these models requires a large amount of training data which can be especially hard to obtain in the medical field due to ethical and data protection regulations. In this paper, we present a novel method to synthesize realistic retinal fundus images. The process mainly includes the vessel tree generation and synthesis of non-vascular regions (retinal background, fovea, and optic disc). We show that combining the (virtually) unlimited synthetic data with the limited real data during training boosts segmentation performance beyond what can be achieved with real data alone. We test the performance of the proposed method on the DRIVE and STARE databases. The results highlight that the proposed data augmentation technique achieves state-of-the-art performance and accuracy.

Paper Citation

in Harvard Style

Magnusson J., Afifi A., Zhang S., Ley A. and Hellwich O. (2021). Synthesizing Fundus Photographies for Training Segmentation Networks. In Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA, ISBN 978-989-758-526-5, pages 67-78. DOI: 10.5220/0010618100670078

in Bibtex Style

@conference{delta21,
author={Jannes Magnusson and Ahmed Afifi and Shengjia Zhang and Andreas Ley and Olaf Hellwich},
title={Synthesizing Fundus Photographies for Training Segmentation Networks},
booktitle={Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,},
year={2021},
pages={67-78},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010618100670078},
isbn={978-989-758-526-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,
TI - Synthesizing Fundus Photographies for Training Segmentation Networks
SN - 978-989-758-526-5
AU - Magnusson J.
AU - Afifi A.
AU - Zhang S.
AU - Ley A.
AU - Hellwich O.
PY - 2021
SP - 67
EP - 78
DO - 10.5220/0010618100670078