Abstract:Aiming at the difficulties of formulating fusion strategies and incomplete preservation of modal information in medical image fusion tasks, a multiscale residual attention UnetLike network is proposed for medical image fusion, namely MRAUnet (Multiscale Residual Attention Unetlike Network). Firstly, most traditional fusion algorithms cannot extract sufficient complementary information from multimodal medical images. To enhance the feature extraction ability and stability of the model, MRAUnet employs residual attention mechanism in the feature extraction processing. Secondly, the Unet structure has great advantages in the semantic perception of medical images, and its Ushaped structure enables Unet to have stronger perception and reuse capabilities for shallow simple features and deep abstract features. Therefore, MRAUnet adopts the Unet architecture to enhance the semantic perception ability and feature reuse of the model, while the overall network adopts a multiscale fashion for feature processing to enhance the feature extraction ability of the Unet architecture. In addition, to capture more modal information, a loss function based on structural information and detail information retention is designed to train MRAUnet. Finally, MRAUnet is an endtoend fusion network with no need to manually design fusion strategies. The proposed network can effectively capture the shallow structural features and deep abstract features from the source image, effectively balancing the anatomical and functional information in the fused image, while maintaining high clarity and displaying functional features such as element radiation and blood flow. The experimental results on the Harvard Medical School Whole Brain Atlas dataset indicate that the MRAUnet has significant improvements in both subjective and objective evaluation compared to some recent advanced algorithms, which has great advantages in terms of VIF based on human visual fidelity, and MI based on feature retention and other metrics.