Tau Anomaly Detection in PET Imaging via Bilateral-Guided Deterministic Diffusion Model

TL;DR

This paper introduces a novel deterministic diffusion model for voxel-level tau anomaly detection in PET imaging, improving localization accuracy and enabling preclinical screening for Alzheimer's disease.

Contribution

The study presents a new bilateral-guided deterministic diffusion sampling method that enhances localized tau anomaly detection in PET scans, outperforming existing baselines.

Findings

Outperforms baseline methods in anomaly localization accuracy.

Successfully groups preclinical subjects by cognitive function.

Demonstrates potential for early Alzheimer's disease screening.

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. In this work, we propose a novel bilateral-guided deterministic diffusion sampling method to perform anomaly detection from tau PET imaging data. By including individualized brain structure and cognitively normal (CN) template conditions, our model computes a voxel-level anomaly map based on the deterministically sampled pseudo-healthy reconstruction. We train our model on ADNI CN subjects (n=380) and evaluate anomaly localization performance on the left MCI/AD subjects (n=154) and the preclinical subjects of the A4 clinical trial (n=447). We further train a CNN classifier on the derived 3D anomaly maps from ADNI, including CN and MCI/AD, to classify subjects into two groups and test classification performance on A4. We demonstrate that our method outperforms baselines in anomaly localization. Additionally, we show that our method can successfully group preclinical subjects with significantly different cognitive functions, highlighting the potential of our approach for application in preclinical screening tests. The code will be publicly available.