Low-count PET image reconstruction with Bayesian inference over a Deep Prior

Hernan Carrillo; Maël Millardet; Thomas Carlier; Diana Mateus

doi:10.1117/12.2580169

15 February 2021 Low-count PET image reconstruction with Bayesian inference over a Deep Prior

Hernan Carrillo, Maël Millardet, Thomas Carlier, Diana Mateus

Proceedings Volume 11596, Medical Imaging 2021: Image Processing; 115960V (2021) https://doi.org/10.1117/12.2580169
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

This paper addresses the problem of reconstructing an image from low-count Positron Emission Tomography (PET) data. We build on recent advances combining deep neural networks with expectation-maximization algorithms. More specifically, we extend the recent DIPRecon approach [1] to handle various challenges linked to natively low-count Yttrium 90 data. To this end, we rely on the interpretation of the Deep Image Prior (DIP) in the light of approximate Bayesian inference. By introducing a stochastic gradient Langevin dynamics (SGLD) optimizer, we reduce the tendency of the algorithm to overfit the noisy maximum likelihood estimate while improving the contrast recovery figures. Moreover, as a by-product of the SGLD optimization, the method recovers an uncertainty value associated with every voxel in the estimated image. We qualitatively and quantitatively evaluate the proposed method on data acquired with the NEMA IEC body phantom achieving high-quality results.

Conference Presentation

Citation Download Citation

Hernan Carrillo, Maël Millardet, Thomas Carlier, and Diana Mateus "Low-count PET image reconstruction with Bayesian inference over a Deep Prior", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115960V (15 February 2021); https://doi.org/10.1117/12.2580169

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available