Integrating Genetic Information for Alzheimer's Diagnosis through MRI Interpretation

Seungeun Lee; Jaeyoung Lee; Moonhyun Lee; Jintak Choi; Younghoon Kim; Kyungtae Kang

Abstract

Early detection of Alzheimer's disease (AD) is crucial, yet predicting AD in the mild cognitive impairment stage remains challenging. Integrating biological data from genomics and neuroimaging can provide valuable insights into early detection and treatment. Although recent deep learning studies have shown promise in AD prediction tasks, they often lack the interpretation of multimodal data interactions. Therefore, there is a need for further research on deep learning methods that can effectively integrate and interpret multimodal biological data for AD diagnosis and prediction. This study proposes a novel approach for identifying regions where interactions occur in sMRI (structural MRI) and genetic information and for detecting discriminative features in AD progression. Through the use of an attention mechanism and contrastive loss, it effectively models the inter-relationships between these modalities, leading to a more accurate understanding of AD. Our proposed method achieved remarkable performance, with an accuracy of 92%. Additionally, through model interpretation, we were able to identify genetic and brain feature associations in AD progression. This study provides a interpretable approach to AD prediction by integrating imaging and genetic data. By capturing the interplay between imaging and genetic data, the model provides valuable clinical interpretations and enhances its predictive capabilities. This integration also enables the identification of critical biomarkers and signatures for early detection and intervention in AD.

Keywords: Alzheimer's disease; Multi-modal data; Interpretation

Links
[Full text PDF][Bibtex]