Joint optic disc and cup segmentation using semi-supervised conditional GANs

doi:10.1016/j.compbiomed.2019.103485

Joint optic disc and cup segmentation using semi-supervised conditional GANs

2019-12-01

54

PRE

AI

DOI：10.1016/j.compbiomed.2019.103485

Original

Original request for help

Save

Abstract

En 中文

Glaucoma is a chronic and widespread eye disease threatening humans' irreversible vision loss. The cup-to-disc ratio (CDR), one of the most important measurements used for glaucoma screening and diagnosis, requires accurate segmentation of optic disc and cup from fundus images. However, most existing techniques fail to obtain satisfactory segmentation performance because a significant number of pixel-level annotated data are often unavailable during training. To cope with this limitation, in this paper, we propose an effective joint optic disc and cup segmentation method based on semi-supervised conditional Generative Adversarial Nets (GANs). Our architecture consists of a segmentation net, a generator and a discriminator, to learn a mapping between the fundus images and the corresponding segmentation maps. Additionally, we employ both labeled and unlabeled data to improve the segmentation performance. The extensive experiments show that our method achieves state-of-the-art optic disc and cup segmentation results on both ORIGA and REFUGE datasets.

Keywords:

Medical image

Deep learning

General adversarial nets

Semi-supervised learning

Glaucoma screening

Joint optic disc and cup segmentation using semi-supervised conditional GANs

Abstract

AI Summary

Journal

Organization