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

Journal: Physics in medicine and biology
Published Date:

Abstract

OBJECTIVE: 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.

Authors

  • Rui Hu
    School of Automation and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan, 430074, China.
  • Chenxu Li
    Zhejiang University, 38 Zheda Road, Xihu District, Hangzhou, Hang Zhou, Zhejiang, 314000, CHINA.
  • Kun Tian
    Zhejiang University College of Optical Science and Engineering, Zheda Road 38, Yuquan Campus, Zhejiang University, Hangzhou, Zhejiang, 310058, CHINA.
  • Jianan Cui
    State Key Laboratory of Modern Optical Instrumentation, Department of Optical Engineering, Zhejiang University, Hangzhou, China.
  • Yunmei Chen
    Department of Mathematics, University of Florida, Gainesville, FL 32611-8105, USA, Florida, 32611, UNITED STATES.
  • Huafeng Liu
    State Key Laboratory of Modern Optical Instrumentation, Department of Optical Engineering, Zhejiang University, Hangzhou, China.

Keywords

No keywords available for this article.