Multimodal Contrastive Learning and Tabular Attention for Automated Alzheimer's Disease Prediction

TL;DR

This paper introduces a multimodal contrastive learning framework combined with a novel tabular attention module to improve Alzheimer's disease prediction using neuroimaging and tabular data, achieving over 83.8% accuracy.

Contribution

It presents a new generalizable multimodal contrastive learning approach and a novel tabular attention mechanism for enhanced AD prediction.

Findings

Achieved over 83.8% accuracy in AD detection.

Outperformed previous state-of-the-art by nearly 10%.

Provided interpretable feature rankings through attention scores.

Abstract

Alongside neuroimaging such as MRI scans and PET, Alzheimer's disease (AD) datasets contain valuable tabular data including AD biomarkers and clinical assessments. Existing computer vision approaches struggle to utilize this additional information. To address these needs, we propose a generalizable framework for multimodal contrastive learning of image data and tabular data, a novel tabular attention module for amplifying and ranking salient features in tables, and the application of these techniques onto Alzheimer's disease prediction. Experimental evaulations demonstrate the strength of our framework by detecting Alzheimer's disease (AD) from over 882 MR image slices from the ADNI database. We take advantage of the high interpretability of tabular data and our novel tabular attention approach and through attribution of the attention scores for each row of the table, we note and rank the most predominant features. Results show that the model is capable of an accuracy of over 83.8%, almost a 10% increase from previous state of the art.