Abstract: Aiming at the problem of false segmentation caused by the  significant changes in target size due to glaucomatous lesions in the optic disc and optic cup segmentation task, we proposed a lighter encoder-decoder network and introduced pyramid pooling modules to capture more context features, enrich the scale features and make full use of the global information through  more receptive fields of the network.  A number of comparative experiments and evaluations were carried on  the RIM-ONE v.3 dataset, the experimental results show that the mean intersection over union of optic disc segmentation is 0.908, the Dice coefficient is 0.958, and the mean square error is 0.002. Compared with the existing algorithms, the performance of each index is improved.

Key words: optic disc segmentation, optic cup segmentation, pyramid pooling module, color fundus image