Low-count PET image reconstruction with Bayesian inference over a Deep Prior - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (1) , (2, 3) , (1)
1
2
3

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.
Not file

Dates and versions

inserm-03546657 , version 1 (28-01-2022)

Identifiers

Cite

Hernan Camilo Carrillo Lindado, Maël Millardet, Thomas Carlier, Diana Mateus. Low-count PET image reconstruction with Bayesian inference over a Deep Prior. Image Processing, Feb 2021, Online Only, United States. pp.24, ⟨10.1117/12.2580169⟩. ⟨inserm-03546657⟩
22 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More