MSFAN: A Multi-scale Feature Attention Network for Alzheimer’s Disease Diagnosis

Alzheimer’s disease (AD) is a common neurodegenerative disease in the elderly, characterized by progressive memory decline, language impairment, and behavioral abnormalities. MRI has been widely utilized as a non-invasive technique for diagnosing AD. However, traditional cnn have limitations in extracting multi-scale lesion features, making it challenging to fully capture the local information and global dependencies of the lesion area. To overcome this issue, we propose a multi-scale feature attention network (MSFAN), which integrates multi-scale feature extraction (MSF), channel attention mechanism (CAM) and non-local block for AD classification. Specifically, the MSF module extracts local features at different scales through cascaded multi-scale convolution kernels; the CAM module adaptively reweights channel responses to emphasize critical lesion areas; and the non-local block captures long-range dependencies across different brain regions, thereby enhancing global feature representation. Experimental results show that MSFAN performs well compared to other cnn models in AD classification tasks, with accuracy, precision, recall and F1 score all significantly improved.