An interpretable generative multimodal neuroimaging-genomics framework for decoding Alzheimer's disease

Alzheimer's disease (AD) is the most prevalent form of dementia with a progressive decline in cognitive abilities. The AD continuum encompasses a prodromal stage known as MCI, where patients may either progress to AD (MCIc) or remain stable (MCInc). Understanding AD mechanisms requires complementary analyses relying on different data sources, leading to the development of multimodal DL models. We leveraged structural and functional MRI to investigate the disease-induced GM and functional network connectivity changes. Moreover, considering AD's strong genetic component, we introduced SNPs as a third channel. Missing one or more modalities is a typical concern of multimodal methods. We hence propose a novel DL-based classification framework where a generative module employing Cycle GAN was adopted for imputing missing data in the latent space. Additionally, we adopted an XAI method, Integrated Gradients, to extract features' relevance, enhancing our understanding of the learned representations. Two tasks were addressed: AD detection and MCI conversion prediction. Experimental results showed that our framework reached the SOA in the classification of CN/AD with an average test accuracy of $0.926\pm0.02$. For the MCInc/MCIc task, we achieved an average prediction accuracy of $0.711\pm0.01$ using the pre-trained model for CN and AD. The interpretability analysis revealed that significant GM modulations led the classification performance in cortical and subcortical brain areas well known for their association with AD. Impairments in sensory-motor and visual functional network connectivity along AD, as well as mutations in SNPs defining biological processes linked to endocytosis, amyloid-beta, and cholesterol, were identified as contributors to the results. Overall, our integrative DL model shows promise for AD detection and MCI prediction, while shading light on important biological insights.