Multi-modal global- and local- feature interaction with attention-based mechanism for diagnosis of Alzheimer's disease

Nana Jia, Tong Jia, Li Zhao, Bowen Ma, Zheyi Zhu

Abstract: Highlights•We propose a multi-model fusion method to perform Alzheimer’s disease classification using 3D MRI and clinical tabular data by learning the global and local fusion information.•We propose an attention-based local fusion strategy to realize the local fusion and then enforce the feature extractor concentrating on areas related to Alzheimer’s disease.•The experimental results demonstrate that our method performs better compared with other state-of-the-art methods.