Brain-Atlas-Guided Generative Counterfactual Attention for Explainable Cognitive Decline Diagnosis Using Multimodal Connectomes
For clinicians and researchers in Alzheimer's disease diagnosis, this work provides an explainable deep learning method that identifies disease-related connectivity changes, though it is an incremental improvement over existing connectome-based models.
The paper proposes GCAN, a generative counterfactual attention network guided by brain atlas knowledge, for explainable diagnosis of mild cognitive impairment and subjective cognitive decline using multimodal connectomes. It achieves competitive classification performance across multiple tasks on hospital-collected and ADNI datasets, with enhanced interpretability through counterfactual attention maps.
Mild cognitive impairment (MCI) and subjective cognitive decline (SCD) are closely associated with the early Alzheimer's disease continuum, where accurate and explainable diagnosis is important for early risk assessment and intervention. Existing connectome-based deep learning models can improve classification performance but often provide limited insight into disease-related functional and structural connectivity changes. This paper proposes an atlas-knowledge-guided Generative Counterfactual Attention-guided Network (GCAN) for explainable cognitive decline diagnosis using multimodal brain connectomes. GCAN formulates diagnosis as a source-to-target counterfactual generation problem, where target-label connectomes are generated from source-label inputs and their differences are used to construct counterfactual attention maps. To preserve connectome topology, an Atlas-aware Bidirectional Transformer (AABT) performs network-level token encoding and decoding under brain-atlas constraints. The framework is further extended from functional connectivity (FC) to joint functional and structural connectivity (SC) modeling, enabling counterfactual analysis of complementary functional reorganization and structural topology changes. Experiments on hospital-collected and ADNI datasets show that GCAN achieves competitive performance across HC vs. SCD, HC vs. MCI, and SCD vs. MCI classification tasks. Visualization, circular connectome analysis, CAM-based comparison, ablation studies, and confidence interval analysis further support the interpretability and reliability of the proposed framework. Modality-specific FC and SC pre-trained classifiers are used to provide target-state priors for counterfactual generation while being separated from the downstream diagnostic classifier to prevent data leakage.