An interpretable generative multimodal neuroimaging-genomics framework for decoding alzheimer’s disease

2024-06-19

arXiv.org

AI Summary

This study addresses the challenges of early Alzheimer’s disease (AD) identification and predicting conversion from mild cognitive impairment (MCI) to AD. We propose an interpretable generative multimodal deep learning framework integrating structural/functional MRI and single-nucleotide polymorphism (SNP) genomic data. Methodologically, we introduce a latent-space Cycle-GAN for robust imputation under modality dropout and employ Integrated Gradients for cross-modal biological interpretability. Our key contribution is the first systematic elucidation of synergistic discriminative mechanisms linking gray-matter atrophy, resting-state network abnormalities, and SNP pathways related to endocytosis, amyloid-β processing, and cholesterol metabolism. Experiments demonstrate strong performance: 0.926 ± 0.02 accuracy in AD vs. healthy control classification, 0.711 ± 0.01 accuracy in MCI-to-AD conversion prediction, and precise localization of discriminative brain regions and pathogenic biological pathways.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Alzheimer’s disease (AD) is the most prevalent form of dementia, affecting millions worldwide with a progressive decline in cognitive abilities. The AD continuum encompasses a prodromal stage known as Mild Cognitive Impairment (MCI), where patients may either progress to AD (MCIc) or remain stable (MCInc). Understanding the underlying mechanisms of AD requires complementary analyses relying on different data sources, leading to the development of multimodal deep learning models. In this study, we leveraged structural and functional Magnetic Resonance Imaging (sMRI/fMRI) to investigate the disease-induced grey matter and functional network connectivity changes. Moreover, considering AD’s strong genetic component, we introduced Single Nucleotide Polymorphisms (SNPs) as a third channel. Given such diverse inputs, missing one or more modalities is a typical concern of multimodal methods. We hence propose a novel deep learning-based classification framework where a generative module employing Cycle Generative Adversarial Networks (cGAN) was adopted for imputing missing data within the latent space. Additionally, we adopted an Explainable Artificial Intelligence (XAI) method, Integrated Gradients (IG), to extract input features’ relevance, enhancing our understanding of the learned representations. Two critical tasks were addressed: AD detection and MCI conversion prediction. Experimental results showed that our framework was able to reach the state-of-the-art in the classification of CN vs AD with an average test accuracy of 0.926 ± 0.02. For the MCInc vs MCIc task, we achieved an average prediction accuracy of 0.711 ± 0.01 using the pre-trained model for CN and AD. The interpretability analysis revealed that the classification performance was led by significant grey matter modulations in cortical and subcortical brain areas well known for their association with AD. Moreover, impairments in sensory-motor and visual resting state network connectivity along the disease continuum, as well as mutations in SNPs defining biological processes linked to endocytosis, amyloid-beta, and cholesterol, were identified as contributors to the achieved performance. Overall, our integrative deep learning approach shows promise for AD detection and MCI prediction, while shading light on important biological insights.

Problem

• Decoding Alzheimer's disease using neuroimaging and genomics
• Classifying AD patients and detecting MCI converters
• Handling missing data in multimodal MRI and SNP analysis

Innovation

• Generative module imputes missing multimodal data.
• Explainable AI enhances learned representations' interpretability.
• Multimodal DL framework achieves state-of-the-art accuracy.