Radiogenomic Bipartite Graph Representation Learning for Alzheimer's Disease Detection
This work addresses Alzheimer's disease diagnosis for medical applications by integrating multi-modal data, though it appears incremental as it builds on existing radiogenomic and graph learning approaches.
The study tackled Alzheimer's disease detection by integrating MRI images and gene expression data using a bipartite graph representation learning method, achieving classification into three stages (AD, MCI, CN) and identifying key genes, with performance evaluated via accuracy, recall, precision, and F1 score.
Imaging and genomic data offer distinct and rich features, and their integration can unveil new insights into the complex landscape of diseases. In this study, we present a novel approach utilizing radiogenomic data including structural MRI images and gene expression data, for Alzheimer's disease detection. Our framework introduces a novel heterogeneous bipartite graph representation learning featuring two distinct node types: genes and images. The network can effectively classify Alzheimer's disease (AD) into three distinct stages:AD, Mild Cognitive Impairment (MCI), and Cognitive Normal (CN) classes, utilizing a small dataset. Additionally, it identified which genes play a significant role in each of these classification groups. We evaluate the performance of our approach using metrics including classification accuracy, recall, precision, and F1 score. The proposed technique holds potential for extending to radiogenomic-based classification to other diseases.