BrainVAE: Exploring the role of white matter BOLD in preclinical Alzheimer disease classification

Abstract

INTRODUCTIONLike gray matter (GM), white matter (WM) BOLD functional signals change in preclinical AD. However, the potential of WM BOLD for identifying preclinical AD remains underexplored. METHODSWe developed BrainVAE, a transformer-based variational autoencoder with interpretability, to classify preclinical AD and normal controls using resting-state fMRI data. We benchmarked BrainVAE against nine alternative models under three input configurations: WM-only, GM-only, and combined WM+GM. Interpretability analysis was also performed to investigate each brain regions contribution to the classification task. RESULTSBrainVAE outperformed other models and performed well (accuracy = 83.42%, F1-score = 91.62%, AUC = 64.50%) using the combined input compared to WM-only and GM-only. Specific WM bundles--including corpus callosum, fornix, and corticospinal tract--were among the most influential features contributing to the classification. DISCUSSIONIncorporating WM BOLD signals improves the distinction of preclinical AD from controls, underscoring the potential role of WM BOLD features for detecting early-stage AD. HighlightsO_LIBrainVAE integrates white and gray matter BOLD signals for classification of pre-AD and controls. C_LIO_LIBrainVAE achieves high accuracy (83.42%) and F1-score (91.62%) in identifying pre-AD. C_LIO_LIModels using combined WM+GM inputs outperform those using WM-only or GM-only inputs. C_LIO_LIWM regions, such as corpus callosum and fornix, contribute significantly to model predictions. C_LIO_LIResults suggest WM BOLD signals are informative markers for early AD detection. C_LI