Iterative PET Image Reconstruction Using Convolutional Neural Network Representation

TL;DR

This paper introduces an iterative PET image reconstruction method that embeds a deep residual CNN within the reconstruction process, improving image quality by leveraging inter-patient information and optimizing via ADMM.

Contribution

The novel integration of a residual CNN into the iterative reconstruction framework for PET imaging enhances image quality beyond traditional methods.

Findings

Outperforms neural network denoising techniques

Outperforms conventional penalized maximum likelihood methods

Effective on both simulation and real data

Abstract

PET image reconstruction is challenging due to the ill-poseness of the inverse problem and limited number of detected photons. Recently deep neural networks have been widely and successfully used in computer vision tasks and attracted growing interests in medical imaging. In this work, we trained a deep residual convolutional neural network to improve PET image quality by using the existing inter-patient information. An innovative feature of the proposed method is that we embed the neural network in the iterative reconstruction framework for image representation, rather than using it as a post-processing tool. We formulate the objective function as a constraint optimization problem and solve it using the alternating direction method of multipliers (ADMM) algorithm. Both simulation data and hybrid real data are used to evaluate the proposed method. Quantification results show that our proposed iterative neural network method can outperform the neural network denoising and conventional penalized maximum likelihood methods.