Interpretable multi-view fusion network via multi-view dual alignment and private bias filtering for Alzheimer's disease analysis

Structural magnetic resonance imaging (sMRI) combined with multi-view learning has been preliminarily explored in Alzheimer's disease (AD) analysis. However, existing methods usually face two key limitations: (i) they fail to fully exploit the inherent consistency of multiple views to design constraints for alignment and feature normalization; (ii) they lack effective mechanisms to separate discriminative information from view-specific noise. Hence, the fused representation may fail to effectively preserve cross-view complementary information, or even contain redundant noise, which often limits the performance of the final model. To address these challenges, we propose an innovative Alignment-Filtering-Fusion Network (AFFNet), which consists of four collaborative modules. Specifically, the multi-view feature extraction module integrates 3D and 2D convolutional networks to capture spatial structural information and extract multi-view features. The multi-view dual alignment module fully exploits the inherent supervision in multi-view data by introducing dual constraints of semantic and attention alignment, ensuring the regularization of complementary multi-view information while enhancing cross-view consistency. The private bias filtering module employs cross-view contrastive loss, orthogonal decomposition, and semantic regularization to identify and separate view-specific noise unrelated to the classification task, improving feature discriminability and laying the foundation for subsequent fusion. Finally, the multi-view fusion and classification module performs mean fusion on the aligned and filtered multi-view features to achieve complementary information integration for AD classification. Extensive experiments on widely used ADNI and AIBL datasets demonstrate that AFFNet significantly outperforms existing methods in AD classification accuracy and model interpretability. All data list and source codes are available at: https://github.com/nollexu/AFFNet.