MINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening

TL;DR

This paper introduces MINT, a novel framework that transfers neuroimaging biomarkers into speech representations, enabling early Alzheimer's screening without requiring MRI at inference, thus combining biological grounding with practical deployment.

Contribution

MINT is the first method to transfer MRI-derived biomarkers into speech models, improving early Alzheimer's detection and reducing reliance on costly neuroimaging during inference.

Findings

Speech aligned with MRI biomarkers achieves comparable accuracy to MRI-based classifiers.

Multimodal fusion enhances screening performance beyond MRI alone.

MRI-to-speech transfer enables biologically grounded, scalable Alzheimer's screening.

Abstract

Alzheimer's disease is a progressive neurodegenerative disorder in which mild cognitive impairment (MCI) marks a critical transition between aging and dementia. Neuroimaging modalities, such as structural MRI, provide biomarkers of this transition; however, their high costs and infrastructure needs limit their deployment at a population scale. Speech analysis offers a non-invasive alternative, but speech-only classifiers are developed independently of neuroimaging, leaving decision boundaries biologically ungrounded and limiting reliability on the subtle CN-versus-MCI distinction. We propose MINT (Multimodal Imaging-to-Speech Knowledge Transfer), a three-stage cross-modal framework that transfers biomarker structure from MRI into a speech encoder at training time. An MRI teacher, trained on 1,228 subjects, defines a compact neuroimaging embedding space for CN-versus-MCI classification. A residual projection head aligns speech representations to this frozen imaging manifold via a combined geometric loss, adapting speech to the learned biomarker space while preserving imaging encoder fidelity. The frozen MRI classifier, which is never exposed to speech, is applied to aligned embeddings at inference and requires no scanner. Evaluation on ADNI-4 shows aligned speech achieves performance comparable to speech-only baselines (AUC 0.720 vs 0.711) while requiring no imaging at inference, demonstrating that MRI-derived decision boundaries can ground speech representations. Multimodal fusion improves over MRI alone (0.973 vs 0.958). Ablation studies identify dropout regularization and self-supervised pretraining as critical design decisions. To our knowledge, this is the first demonstration of MRI-to-speech knowledge transfer for early Alzheimer's screening, establishing a biologically grounded pathway for population-level cognitive triage without neuroimaging at inference.