Iterative PET Image Reconstruction Using Convolutional Neural Network Representation
This work addresses PET image reconstruction for medical imaging by proposing an incremental improvement that integrates neural networks into the iterative process.
The paper tackled the challenge of PET image reconstruction by embedding a deep residual convolutional neural network within an iterative reconstruction framework, rather than using it for post-processing, and demonstrated that this method outperforms neural network denoising and conventional penalized maximum likelihood methods in simulation and hybrid real data evaluations.
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.