PADU-Net: Parallel Attention-based Dual U-Net for Retinal Vessel Segmentation

Retinal vessel segmentation is a key step for the early diagnosis of fundus diseases. Deep learning-based retinal vessel segmentation has shown the potential to achieve better performance than traditional methods. However, most deep learning-based methods still suffer from insufficiently capturing global and local features simultaneously from fundus images. This may degrade the segmentation performance, resulting in infeasible diagnosis for fundus diseases. To solve this problem, this paper introduces the PADU-Net, a parallel attention-based dual U-Net architecture for retinal vessel segmentation. The key is to integrate two parallel U-Net modules, i.e., encoder-decoder architectures, equipped with local and global attention modules, respectively, used for extracting local and global features. Then the features are decoded and fused for generating the segmentation map for the input fundus image. The experiments conducted on the well-known dataset, DRIVE (digital retinal images for vessel extraction), has verified the performance of the proposed framework, outperforming the SOTA (state-of-the-art) methods.