Deep unrolled primal dual network for TOF-PET list-mode image reconstruction

TL;DR

This paper introduces a deep unrolled primal dual network for TOF-PET list-mode image reconstruction, leveraging deep learning to improve image quality and reduce noise, especially in low-count data scenarios.

Contribution

The study presents a novel deep unrolled primal dual network architecture that efficiently incorporates TOF information and mitigates memory issues, outperforming existing methods.

Findings

Outperforms LM-OSEM, LM-EMTV, LM-SPDHG, and FastPET in quality.

Uses CUDA for efficient parallel computation and memory management.

Demonstrates superior results across different TOF resolutions and count levels.

Abstract

Time-of-flight (TOF) information provides more accurate location data for annihilation photons, thereby enhancing the quality of PET reconstruction images and reducing noise. List-mode reconstruction has a significant advantage in handling TOF information. However, current advanced TOF PET list-mode reconstruction algorithms still require improvements when dealing with low-count data. Deep learning algorithms have shown promising results in PET image reconstruction. Nevertheless, the incorporation of TOF information poses significant challenges related to the storage space required by deep learning methods, particularly for the advanced deep unrolled methods. In this study, we propose a deep unrolled primal dual network for TOF-PET list-mode reconstruction. The network is unrolled into multiple phases, with each phase comprising a dual network for list-mode domain updates and a primal network for image domain updates. We utilize CUDA for parallel acceleration and computation of the system matrix for TOF list-mode data, and we adopt a dynamic access strategy to mitigate memory consumption. Reconstructed images of different TOF resolutions and different count levels show that the proposed method outperforms the LM-OSEM, LM-EMTV, LM-SPDHG,LM-SPDHG-TV and FastPET method in both visually and quantitative analysis. These results demonstrate the potential application of deep unrolled methods for TOF-PET list-mode data and show better performance than current mainstream TOF-PET list-mode reconstruction algorithms, providing new insights for the application of deep learning methods in TOF list-mode data. The codes for this work are available at https://github.com/RickHH/LMPDnet