RSAP-Net:Joint Optic Disc And Cup Segmentation With A Residual Spatial Attention Path Module And MSRCR-PT Pre-Processing Algorithm

Background: Glaucoma can cause irreversible blindness to people’s eyesight. Since there are no symptoms inits early stage, it is particularly important to accurately segment the optic disc (OD) and optic cup (OC) fromfundus medical images for the screening and prevention of glaucoma. In recent years, the mainstream methodof OD and OC segmentation is convolution neural network (CNN). However, most existing CNN methodssegment OD and OC separately and ignore the a priori information that OC is always contained inside the ODregion, which makes the segmentation accuracy of most methods not high enough. Methods: : This paper proposes a new encoder-decoder segmentation structure, called RSAP-Net, for jointsegmentation of OD and OC. We first designed an efficient U-shaped segmentation network as the backbone.Considering the spatial overlap relationship between OD and OC, a new Residual spatial attention path isproposed to connect the encoder-decoder to retain more characteristic information. In order to further improvethe segmentation performance, a pre-processing method called MSRCR-PT has been devised. It incorporates amulti-scale Retinex colour recovery algorithm and a polar coordinate transformation, which can help RSAP-Netto produce more refined boundaries of the optic disc and the optic cup. Results: : The experimental results show that our method achieves excellent segmentation performance on theDrishti-GS1 standard dataset. In the OD and OC segmentation effects, the F1 scores are 0.9752 and 0.9012,respectively. The BLE are 6.33 pixels and 11.97 pixels, respectively. Conclusions: : This paper presents a new framework for the joint segmentation of optic discs and optic cups,called RSAP-Net. The framework mainly consists of a U-shaped segmentation skeleton and a residual spaceattention path module. The design of a pre-processing method called MSRCR-PT for the OD/OCsegmentation task can improve segmentation performance. The method was evaluated on the publiclyavailable Drishti-GS standard dataset and proved to be effective.