Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification

TL;DR

This paper introduces MVSC, a novel method that compresses 3D MRI data into 2D features aligned with foundation models, improving Alzheimer's diagnosis accuracy while reducing computational costs.

Contribution

MVSC is the first approach to effectively compress 3D MRI volumes into 2D features using a volume context encoder and adaptive slice fusion, enhancing AD classification.

Findings

MVSC outperforms state-of-the-art methods on large-scale AD benchmarks.

It achieves higher accuracy in both binary and multi-class AD classification.

The method reduces computational costs compared to 3D architectures.

Abstract

High-dimensional structural MRI (sMRI) images are widely used for Alzheimer's Disease (AD) diagnosis. Most existing methods for sMRI representation learning rely on 3D architectures (e.g., 3D CNNs), slice-wise feature extraction with late aggregation, or apply training-free feature extractions using 2D foundation models (e.g., DINO). However, these three paradigms suffer from high computational cost, loss of cross-slice relations, and limited ability to extract discriminative features, respectively. To address these challenges, we propose Multimodal Visual Surrogate Compression (MVSC). It learns to compress and adapt large 3D sMRI volumes into compact 2D features, termed as visual surrogates, which are better aligned with frozen 2D foundation models to extract powerful representations for final AD classification. MVSC has two key components: a Volume Context Encoder that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner. Extensive experiments on three large-scale Alzheimer's disease benchmarks demonstrate our MVSC performs favourably on both binary and multi-class classification tasks compared against state-of-the-art methods.