Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics

2025-10-17

AI Summary

To address the limited accessibility and high cost of FDG-PET in dementia diagnosis, this paper proposes SiM2P—a 3D diffusion-bridging framework that synthesizes diagnostic-grade FDG-PET images from T1-weighted MRI and basic demographic data (age, sex). Methodologically, SiM2P introduces: (1) probabilistic mapping to explicitly model cross-modal MRI–PET uncertainty; and (2) a lightweight fine-tuning strategy enabling rapid adaptation with only 20 local cases. Evaluated on multicenter data, blinded clinical reading demonstrates that SiM2P improves diagnostic accuracy from 75.0% to 84.7%, significantly enhances inter-rater agreement (Cohen’s κ), and yields higher diagnostic confidence than MRI-only assessment. This work provides an efficient, deployable imaging surrogate for early dementia differential diagnosis in resource-constrained settings.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Positron emission tomography (PET) with 18F-Fluorodeoxyglucose (FDG) is an established tool in the diagnostic workup of patients with suspected dementing disorders. However, compared to the routinely available magnetic resonance imaging (MRI), FDG-PET remains significantly less accessible and substantially more expensive. Here, we present SiM2P, a 3D diffusion bridge-based framework that learns a probabilistic mapping from MRI and auxiliary patient information to simulate FDG-PET images of diagnostic quality. In a blinded clinical reader study, two neuroradiologists and two nuclear medicine physicians rated the original MRI and SiM2P-simulated PET images of patients with Alzheimer's disease, behavioral-variant frontotemporal dementia, and cognitively healthy controls. SiM2P significantly improved the overall diagnostic accuracy of differentiating between three groups from 75.0% to 84.7% (p<0.05). Notably, the simulated PET images received higher diagnostic certainty ratings and achieved superior interrater agreement compared to the MRI images. Finally, we developed a practical workflow for local deployment of the SiM2P framework. It requires as few as 20 site-specific cases and only basic demographic information. This approach makes the established diagnostic benefits of FDG-PET imaging more accessible to patients with suspected dementing disorders, potentially improving early detection and differential diagnosis in resource-limited settings. Our code is available at https://github.com/Yiiitong/SiM2P.

Problem

• Simulating clinical-grade PET from MRI for dementia diagnosis
• Improving diagnostic accuracy for Alzheimer's and frontotemporal dementia
• Making FDG-PET imaging more accessible in resource-limited settings

Innovation

• Simulates clinical-grade PET from MRI
• Uses 3D diffusion bridge-based framework
• Requires only 20 site-specific training cases