MFA-UNet: a vessel segmentation method based on multi-scale feature fusion and attention module.

Introduction: The accurate segmentation of retinal vessels is of utmost importance in the diagnosis of retinal diseases. However, the complex vessel structure often leads to poor segmentation performance, particularly in the case of microvessels. Methods: To address this issue, we propose a vessel segmentation method composed of preprocessing and a multi-scale feature attention network (MFA-UNet). The preprocessing stage involves the application of gamma correction and contrast-limited adaptive histogram equalization to enhance image intensity and vessel contrast. The MFA-UNet incorporates the Multi-scale Fusion Self-Attention Module(MSAM) that adjusts multi-scale features and establishes global dependencies, enabling the network to better preserve microvascular structures. Furthermore, the multi-branch decoding module based on deep supervision (MBDM) replaces the original output layer to achieve targeted segmentation of macrovessels and microvessels. Additionally, a parallel attention mechanism is embedded into the decoder to better exploit multi-scale features in skip paths. Results: The proposed MFA-UNet yields competitive performance, with dice scores of 82.79/83.51/84.17/78.60/81.75/84.04 and accuracies of 95.71/96.4/96.71/96.81/96.32/97.10 on the DRIVE, STARE, CHASEDB1, HRF, IOSTAR and FIVES datasets, respectively. Discussion: It is expected to provide reliable segmentation results in clinical diagnosis.

Attentional Mechanisms and Improved Residual Networks for Diabetic Retinopathy Severity Classification.

Diabetic retinopathy is a main cause of blindness in diabetic patients; therefore, detection and treatment of diabetic retinopathy at an early stage has an important effect on delaying and avoiding vision loss. In this paper, we propose a feasible solution for diabetic retinopathy classification using ResNet as the backbone network. By modifying the structure of the residual blocks and improving the downsampling level, we can increase the feature information of the hidden layer feature maps. In addition, attention mechanism is utilized to enhance the feature extraction effect. The experimental results show that the proposed model can effectively detect and classify diabetic retinopathy and achieve better results than the original model.