The morphological changes of retinal vessels are of significant diagnostic value for early ophthalmic diseases and can aid in distinguishing other conditions such as diabetes and cardiovascular diseases. However, precise segmentation poses a challenge due to the complex structure of retinal vessels. To address these issues, we propose a Rough Attention Fusion Module (RAFM). This module employs max-pooling and average-pooling to define the upper and lower bounds of feature significance, introducing upper and lower weight matrices to obtain more reasonable attention coefficients. This enables the model to more accurately focus on important features in retinal images. Additionally, we integrate the RAFM into the GTS U-Net model, a simplified version of the GT U-Net model, which enhances the segmentation accuracy while reducing computational complexity. Ultimately, we construct a retinal vessel segmentation network based on the RAFM along with Group Transformer. Finally, the network structure is tested on the public DRIVE color fundus image dataset, achieving an Accuracy, F1 score, and AUC of 0.9641, 0.8506, and 0.9820, respectively. In contrast to prevalent retinal vessel segmentation networks in the mainstream, our proposed network demonstrates certain strengths.
Read full abstract