MIRAGE: Knowledge Graph-Guided Cross-Cohort MRI Synthesis for Alzheimer's Disease Prediction

2026-03-02

AI Summary

This study addresses the challenge of deploying multimodal models for Alzheimer’s disease (AD) diagnosis when structural MRI is unavailable. To this end, the authors propose an anatomy-guided cross-modal latent space distillation framework that leverages biomedical knowledge graphs and electronic health records (EHR) to construct heterogeneous embeddings. By freezing a pre-trained 3D U-Net decoder as an anatomical regularizer and incorporating a cohort-aggregated skip-connection feature compensation mechanism, the method generates transferable diagnostic proxy representations without synthesizing actual 3D MRI scans. Experimental results demonstrate that, on patient cohorts lacking MRI data, the proposed approach improves AD classification accuracy by 13% over single-modality baselines, effectively bridging the performance gap caused by missing imaging modalities.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning 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

Reliable Alzheimer's disease (AD) diagnosis increasingly relies on multimodal assessments combining structural Magnetic Resonance Imaging (MRI) and Electronic Health Records (EHR). However, deploying these models is bottlenecked by modality missingness, as MRI scans are expensive and frequently unavailable in many patient cohorts. Furthermore, synthesizing de novo 3D anatomical scans from sparse, high-dimensional tabular records is technically challenging and poses severe clinical risks. To address this, we introduce MIRAGE, a novel framework that reframes the missing-MRI problem as an anatomy-guided cross-modal latent distillation task. First, MIRAGE leverages a Biomedical Knowledge Graph (KG) and Graph Attention Networks to map heterogeneous EHR variables into a unified embedding space that can be propagated from cohorts with real MRIs to cohorts without them. To bridge the semantic gap and enforce physical spatial awareness, we employ a frozen pre-trained 3D U-Net decoder strictly as an auxiliary regularization engine. Supported by a novel cohort-aggregated skip feature compensation strategy, this decoder acts as a rigorous structural penalty, forcing 1D latent representations to encode biologically plausible, macro-level pathological semantics. By exclusively utilizing this distilled "diagnostic-surrogate" representation during inference, MIRAGE completely bypasses computationally expensive 3D voxel reconstruction. Experiments demonstrate that our framework successfully bridges the missing-modality gap, improving the AD classification rate by 13% compared to unimodal baselines in cohorts without real MRIs.

Problem

• Alzheimer's Disease
• MRI Synthesis
• Missing Modality
• Electronic Health Records
• Cross-Cohort

Innovation

• Knowledge Graph
• Cross-modal Synthesis
• Latent Distillation
• 3D U-Net Regularization
• Missing Modality Imputation