Estimating Uncertainty in PET Image Reconstruction via Deep Posterior Sampling
This addresses a critical need for medical practitioners in evaluating brain disorders by providing uncertainty measures to aid decision-making, representing a novel application in PET imaging.
The paper tackles the problem of uncertainty quantification in PET image reconstruction, which is ill-posed and noisy, by proposing a deep learning method based on conditional generative adversarial networks that generates high-quality posterior samples and physically-meaningful uncertainty estimates.
Positron emission tomography (PET) is an important functional medical imaging technique often used in the evaluation of certain brain disorders, whose reconstruction problem is ill-posed. The vast majority of reconstruction methods in PET imaging, both iterative and deep learning, return a single estimate without quantifying the associated uncertainty. Due to ill-posedness and noise, a single solution can be misleading or inaccurate. Thus, providing a measure of uncertainty in PET image reconstruction can help medical practitioners in making critical decisions. This paper proposes a deep learning-based method for uncertainty quantification in PET image reconstruction via posterior sampling. The method is based on training a conditional generative adversarial network whose generator approximates sampling from the posterior in Bayesian inversion. The generator is conditioned on reconstruction from a low-dose PET scan obtained by a conventional reconstruction method and a high-quality magnetic resonance image and learned to estimate a corresponding standard-dose PET scan reconstruction. We show that the proposed model generates high-quality posterior samples and yields physically-meaningful uncertainty estimates.