Joint Optic Disc and Dup Segmentation Based on Densely Connected Depthwise Separable Convolution Deep Network

Abstract

Background: Glaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio is the main indicator used to screen and diagnose glaucoma, optic disc and optic cup segmentation can assist computer in diagnosing glaucoma.Therefore, accurate segmentation of optic disc and optic cup is beneficial to the screening and diagnosis of glaucoma and helps patients diagnose and treat early. Method: In this paper, we consider the segmentation of the optic disc and the optic cup as a multi-category semantic segmentation task, and proposed a deep learning-based model model named DDSC-Net(densely connected depthwise separable convolution network) to extract the optic disc and the optic cup. The backbone network is composed of densely connected deep separable convolution blocks to form a deeper network and the image pyramid input is introduce into the input layer to widen the network. In the post-process, we apply the morphological method to refine the output segmentation results. Result: The proposed method is evaluated on two publicly available datasets, DRISHTI-GS dataset and REFUGE dataset. And the experiment results show that our DDSC-Net outperforms state-of-the-art optic disc and cup segmentation methods in terms of disc coefficients and Jaccard score. Furthermore,our method achieves the best result on the more challenging optic cup segmentation task. Conclusion: The promising segmention performances reveal that our method has potential in assisting the screening and diagnosis of the glaucoma.