Bayesian Posterior Distribution Estimation of Kinetic Parameters in Dynamic Brain PET Using Generative Deep Learning Models

Positron Emission Tomography (PET) is a valuable imaging method for studying molecular-level processes in the body, such as hyperphosphorylated tau (ptau) protein aggregates, a hallmark of several neurodegenerative diseases including Alzheimer's disease. P-tau density and cerebral perfusion can...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging Vol. PP; p. 1
Main Authors: Djebra, Yanis, Liu, Xiaofeng, Marin, Thibault, Tiss, Amal, Dhaynaut, Maeva, Guehl, Nicolas, Johnson, Keith, Fakhri, Georges El, Ma, Chao, Ouyang, Jinsong
Format: Journal Article
Language:English
Published: United States IEEE 15.07.2025
Subjects:
Conditional Variational Autoencoder
Data models
Deep learning
Diffusion models
Diffusion processes
Dynamic PET imaging
Estimation
Imaging
Kinetic modeling
Kinetic theory
Noise
Positron emission tomography
Posterior distribution
Radiotracer
Training
ISSN:0278-0062, 1558-254X, 1558-254X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Positron Emission Tomography (PET) is a valuable imaging method for studying molecular-level processes in the body, such as hyperphosphorylated tau (ptau) protein aggregates, a hallmark of several neurodegenerative diseases including Alzheimer's disease. P-tau density and cerebral perfusion can be quantified from dynamic PET images using tracer kinetic modeling techniques. However, noise in PET images leads to uncertainty in the estimated kinetic parameters, which can be quantified by estimating the posterior distribution of kinetic parameters using Bayesian inference (BI). Markov Chain Monte Carlo (MCMC) techniques are commonly used for posterior estimation but with significant computational needs. This work proposes an Improved Denoising Diffusion Probabilistic Model (iDDPM)-based method to estimate the posterior distribution of kinetic parameters in dynamic PET, leveraging the high computational efficiency of deep learning. The performance of the proposed method was evaluated on a [18F]MK6240 study and compared to a Conditional Variational Autoencoder with dual decoder (CVAE-DD)-based method and a Wasserstein GAN with gradient penalty (WGAN-GP)-based method. Posterior distributions inferred from Metropolis-Hasting MCMC were used as reference. Our approach consistently outperformed the CVAE-DD and WGAN-GP methods and offered significant reduction in computation time than the MCMC method (over 230 times faster), inferring accurate (< 0.67% mean error) and precise (< 7.23% standard deviation error) posterior distributions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0278-0062
1558-254X
1558-254X
DOI:10.1109/TMI.2025.3588859