A retinal vessel segmentation method based improved U-Net model

Abstract

There are two problems in retinal blood vessel segmentation, which are the insufficient segmentation of small vessels due to the complex curvature morphology of blood vessels and the segmentation difficulty of blood vessels due to uneven brightness background of lesion fundus images. To solve the problems, a series deformable convolution structure is proposed in this paper, which could improve theadaptive features extraction ability to the blood vessels with various shapes and sizes, enhance feature transmissions and alleviate exploding gradients. On this basis, a retinal vessel segmentation method with series deformable convolution and attention mechanism based on U-Net structure (SDAU-Net) is proposed. In SDAU-Net, the convolution module in U-Net is replaced by series deformable convolution module, the lightweight attention module and dual attention module are applied in the decoder part, which effectively improve the U-Net feature extraction ability for the small vessels with complex morphology and the retinopathy images. To verify the SDAU-Net effect, the comparative experiments are conducted on datasets of DRIVE, STARE, CHASE_DB1 and IOSTAR. The results show that SDAU-Net is superior to comparative methods in accuracy. The Se and Acc on the DRIVE and STARE are 0.8293, 0.9675, 0.8973 and 0.9833 respectively, which indicate that SDAU-Net has more advantages in small vessel segmentation and lesion images. To verify the generalization and extendibility, cross-dataset and cross-modality experiments are conducted on DRIVE, STARE and IOSTAR, the results demonstrate outstanding generalization and extendibility of SDAU-Net.