TauGenNet: Plasma-Driven Tau PET Image Synthesis via Text-Guided 3D Diffusion Models

2025-09-04

AI Summary

Tau PET imaging is costly and inaccessible, limiting its use in routine Alzheimer’s disease (AD) diagnosis and longitudinal monitoring; meanwhile, structural MRI and plasma p-tau217—though widely available—cannot directly quantify tau pathology. To address this, we propose the first text-guided 3D diffusion model that encodes plasma p-tau217 concentration as a semantic textual prompt and integrates structural MRI as an anatomical prior, enabling multimodal conditional synthesis of tau PET images. Our approach establishes a novel “biomarker → text prompt → image generation” paradigm, overcoming cross-modal mapping bottlenecks. Validated on the ADNI dataset, the model generates high-fidelity, clinically interpretable 3D tau PET volumes across disease stages. It enables noninvasive tau assessment, synthetic data augmentation, and simulation of disease progression stratified by p-tau217 levels.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate quantification of tau pathology via tau positron emission tomography (PET) scan is crucial for diagnosing and monitoring Alzheimer's disease (AD). However, the high cost and limited availability of tau PET restrict its widespread use. In contrast, structural magnetic resonance imaging (MRI) and plasma-based biomarkers provide non-invasive and widely available complementary information related to brain anatomy and disease progression. In this work, we propose a text-guided 3D diffusion model for 3D tau PET image synthesis, leveraging multimodal conditions from both structural MRI and plasma measurement. Specifically, the textual prompt is from the plasma p-tau217 measurement, which is a key indicator of AD progression, while MRI provides anatomical structure constraints. The proposed framework is trained and evaluated using clinical AV1451 tau PET data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results demonstrate that our approach can generate realistic, clinically meaningful 3D tau PET across a range of disease stages. The proposed framework can help perform tau PET data augmentation under different settings, provide a non-invasive, cost-effective alternative for visualizing tau pathology, and support the simulation of disease progression under varying plasma biomarker levels and cognitive conditions.

Problem

• Synthesizing tau PET images from plasma biomarkers and MRI
• Reducing cost and accessibility barriers in tau PET imaging
• Generating realistic 3D tau PET scans across disease stages

Innovation

• Text-guided 3D diffusion model
• Multimodal MRI and plasma conditions
• Synthesizes realistic tau PET images