Due to the complex background of fundus images, thin and blurred capillaries, and noise interference, traditional retinal vessel segmentation algorithms often experience issues of inaccurate recognition and disconnections. To address these problems, a retinal blood vessel segmentation algorithm based on improved U-Net and attention mechanism (MRAU-Net) is proposed. To resolve the issue of insufficient feature extraction, a multi-scale residual convolution block (MSRCB) is designed to replace the traditional convolution blocks of U-Net. To reduce information loss and noise interference, a dual-dimensional attention optimization module (DAOM) is embedded in the bottleneck layer. To further mitigate information loss during the encoding-decoding process, a new multi-scale dense convolution block (MDCB) is constructed and combined with traditional skip connections. Experiments conducted on two public datasets of DRIVE and CHASE_DB1 yield F1-scores of 82.92% and 83.75%, AUCs of 98.87% and 98.96%, sensitivities of 84.50% and 83.82%, and accuracies of 97.11% and 97.63%, respectively. These results show that MRAU-Net outperforms existing outstanding algorithms.