PET image denoising using unsupervised deep learning.

Journal: European journal of nuclear medicine and molecular imaging
Published Date: Aug 29, 2019

Abstract

PURPOSE: Image quality of positron emission tomography (PET) is limited by various physical degradation factors. Our study aims to perform PET image denoising by utilizing prior information from the same patient. The proposed method is based on unsupervised deep learning, where no training pairs are needed.

Authors

  • Jianan Cui
    State Key Laboratory of Modern Optical Instrumentation, Department of Optical Engineering, Zhejiang University, Hangzhou, China.
  • Kuang Gong
  • Ning Guo
  • Chenxi Wu
    Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital, 55 Fruit St, White 427, Boston, MA, 02114, USA.
  • Xiaxia Meng
    Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital, 55 Fruit St, White 427, Boston, MA, 02114, USA.
  • Kyungsang Kim
  • Kun Zheng
    Children's Hospital of Zhejiang University School of Medicine, Hangzhou, 310003.
  • Zhifang Wu
    Department of Nuclear Medicine, First Hospital of Shanxi Medical University, Taiyuan, China.
  • Liping Fu
    Department of Nuclear Medicine, The Chinese PLA General Hospital, Beijing, China.
  • Baixuan Xu
    Department of Nuclear Medicine, The Chinese PLA General Hospital, Beijing, China.
  • Zhaohui Zhu
    Department of Urology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China. zhuzhaohui316@163.com.
  • Jiahe Tian
    Department of Nuclear Medicine, The Chinese PLA General Hospital, Beijing, China.
  • Huafeng Liu
    State Key Laboratory of Modern Optical Instrumentation, Department of Optical Engineering, Zhejiang University, Hangzhou, China.
  • Quanzheng Li
    Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States.

Keywords

External Resources

Popular Topics
Recent Journals