TauAD: MRI-free Tau Anomaly Detection in PET Imaging via Conditioned Diffusion Models

2024-05-21

arXiv.org

AI Summary

Current tau PET analyses predominantly rely on cortical region–based statistics, limiting characterization of inter-individual local pathological heterogeneity and requiring high-resolution MRI for anatomical priors. To address these limitations, we propose the first MRI-free, whole-brain voxel-wise tau abnormality detection framework. Our method leverages a conditional diffusion model that integrates subject-specific structural priors with a dual reconstruction loss—simultaneously reconstructing pseudo-healthy and pseudo-abnormal tau PET volumes—to effectively suppress false positives in subcortical and extracranial regions. Evaluated on the ADNI cohort (n=534) and the A4 preclinical trial cohort (n=447), our approach significantly outperforms conventional Z-score mapping and state-of-the-art generative baselines. The generated abnormality maps robustly differentiate cognitively distinct groups, enabling sensitive early detection of Alzheimer’s disease pathology. This work establishes a novel, MRI-agnostic paradigm for precision neuroimaging biomarker development in Alzheimer’s disease.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: Brain-Sensing and Analysis
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

The emergence of tau PET imaging over the last decade has enabled Alzheimer's disease (AD) researchers to examine tau pathology in vivo and more effectively characterize the disease trajectories of AD. Current tau PET analysis methods, however, typically perform inferences on large cortical ROIs and are limited in the detection of localized tau pathology that varies across subjects. Furthermore, a high-resolution MRI is required to carry out conventional tau PET analysis, which is not commonly acquired in clinical practices and may not be acquired for many elderly patients with dementia due to strong motion artifacts, claustrophobia, or certain metal implants. In this work, we propose a novel conditional diffusion model to perform MRI-free anomaly detection from tau PET imaging data. By including individualized conditions and two complementary loss maps from pseudo-healthy and pseudo-unhealthy reconstructions, our model computes an anomaly map across the entire brain area that allows simply training a support vector machine (SVM) for classifying disease severity. We train our model on ADNI subjects (n=534) and evaluate its performance on a separate dataset from the preclinical subjects of the A4 clinical trial (n=447). We demonstrate that our method outperforms baseline generative models and the conventional Z-score-based method in anomaly localization without mis-detecting off-target bindings in sub-cortical and out-of-brain areas. By classifying the A4 subjects according to their anomaly map using the SVM trained on ADNI data, we show that our method can successfully group preclinical subjects with significantly different cognitive functions, which further demonstrates the effectiveness of our method in capturing biologically relevant anomaly in tau PET imaging.

Problem

• Detects localized tau pathology in PET imaging
• Uses bilateral-guided diffusion for anomaly detection
• Classifies preclinical Alzheimer's disease via anomaly maps

Innovation

• Bilateral-guided deterministic diffusion sampling for anomaly detection
• Voxel-level anomaly maps from pseudo-healthy reconstruction
• CNN classifier on 3D anomaly maps for group classification