Radiogenomic Bipartite Graph Representation Learning for Alzheimer's Disease Detection

2025-05-14

AI Summary

This study addresses the challenge of improving multi-stage classification (AD/MCI/CN) and identifying stage-specific pathogenic genes in Alzheimer’s disease (AD). We propose the first radiogenomic heterogeneous bipartite graph representation learning framework, which integrates structural MRI and gene expression data to construct a gene–brain-region bipartite graph. The framework incorporates node-type-aware message passing, cross-modal feature alignment, and few-shot classification mechanisms. Evaluated under limited labeled-data conditions, our model achieves high accuracy and F1-score while maintaining interpretability—precisely identifying stage-discriminative genes (e.g., APOE for AD, BIN1 for MCI). This work establishes a novel paradigm for multimodal modeling and mechanistic interpretation of neurodegenerative diseases.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

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.

Problem

• Integrates MRI and gene data for Alzheimer's detection
• Classifies Alzheimer's into three distinct stages
• Identifies significant genes for each disease stage

Innovation

• Heterogeneous bipartite graph for gene-image representation
• Multi-stage AD classification using small dataset
• Identifies significant genes per disease stage