DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET

TL;DR

DiaMond is a novel multi-modal vision Transformer framework that effectively integrates MRI and PET data for improved dementia diagnosis, outperforming existing methods in accuracy and robustness.

Contribution

The paper introduces DiaMond, a new multi-modal vision Transformer with bi-attention and normalization for better MRI and PET data integration in dementia diagnosis.

Findings

Achieves 92.4% accuracy in AD diagnosis

Attains 65.2% accuracy in AD-MCI-CN classification

Reaches 76.5% accuracy in differential diagnosis of AD and FTD

Abstract

Diagnosing dementia, particularly for Alzheimer's Disease (AD) and frontotemporal dementia (FTD), is complex due to overlapping symptoms. While magnetic resonance imaging (MRI) and positron emission tomography (PET) data are critical for the diagnosis, integrating these modalities in deep learning faces challenges, often resulting in suboptimal performance compared to using single modalities. Moreover, the potential of multi-modal approaches in differential diagnosis, which holds significant clinical importance, remains largely unexplored. We propose a novel framework, DiaMond, to address these issues with vision Transformers to effectively integrate MRI and PET. DiaMond is equipped with self-attention and a novel bi-attention mechanism that synergistically combine MRI and PET, alongside a multi-modal normalization to reduce redundant dependency, thereby boosting the performance. DiaMond significantly outperforms existing multi-modal methods across various datasets, achieving a balanced accuracy of 92.4% in AD diagnosis, 65.2% for AD-MCI-CN classification, and 76.5% in differential diagnosis of AD and FTD. We also validated the robustness of DiaMond in a comprehensive ablation study. The code is available at https://github.com/ai-med/DiaMond.