Multi-modal Imputation for Alzheimer's Disease Classification

TL;DR

This paper introduces a conditional denoising diffusion model to impute missing DWI scans from T1 MRI data, enhancing Alzheimer's disease classification accuracy when multimodal data is incomplete.

Contribution

It presents a novel diffusion-based imputation method for missing MRI modalities, improving diagnostic performance in Alzheimer's disease classification tasks.

Findings

Imputation improves classification metrics, especially for minority classes.

The method enhances both uni-modal and bi-modal deep learning models.

Experimental results show significant performance gains with the proposed approach.

Abstract

Deep learning has been successful in predicting neurodegenerative disorders, such as Alzheimer's disease, from magnetic resonance imaging (MRI). Combining multiple imaging modalities, such as T1-weighted (T1) and diffusion-weighted imaging (DWI) scans, can increase diagnostic performance. However, complete multimodal datasets are not always available. We use a conditional denoising diffusion probabilistic model to impute missing DWI scans from T1 scans. We perform extensive experiments to evaluate whether such imputation improves the accuracy of uni-modal and bi-modal deep learning models for 3-way Alzheimer's disease classification-cognitively normal, mild cognitive impairment, and Alzheimer's disease. We observe improvements in several metrics, particularly those sensitive to minority classes, for several imputation configurations.