Deep Generalized Learning Model for PET Image Reconstruction

doi:10.1109/TMI.2023.3293836

Deep Generalized Learning Model for PET Image Reconstruction

2024-01-01

4

PRE

AI

DOI：10.1109/TMI.2023.3293836

Original

Original request for help

Save

Abstract

En 中文

Low-count positron emission tomography (PET) imaging is challenging because of the ill-posedness of this inverse problem. Previous studies have demonstrated that deep learning (DL) holds promise for achieving improved low-count PET image quality. However, almost all data-driven DL methods suffer from fine structure degradation and blurring effects after denoising. Incorporating DL into the traditional iterative optimization model can effectively improve its image quality and recover fine structures, but little research has considered the full relaxation of the model, resulting in the performance of this hybrid model not being sufficiently exploited. In this paper, we propose a learning framework that deeply integrates DL and an alternating direction of multipliers method (ADMM)-based iterative optimization model. The innovative feature of this method is that we break the inherent forms of the fidelity operators and use neural networks to process them. The regularization term is deeply generalized. The proposed method is evaluated on simulated data and real data. Both the qualitative and quantitative results show that our proposed neural network method can outperform partial operator expansion-based neural network methods, neural network denoising methods and traditional methods.

Keywords:

Positron emission tomography

deep learning

iterative reconstruction

Deep Generalized Learning Model for PET Image Reconstruction

Abstract

Journal

Organization