Deep learning-based image domain reconstruction enhances image quality and pulmonary nodule detection in ultralow-dose CT with adaptive statistical iterative reconstruction-V.

Journal: European radiology
Published Date: Jan 10, 2025

Abstract

OBJECTIVES: To evaluate the image quality and lung nodule detectability of ultralow-dose CT (ULDCT) with adaptive statistical iterative reconstruction-V (ASiR-V) post-processed using a deep learning image reconstruction (DLIR)-based image domain compared to low-dose CT (LDCT) and ULDCT without DLIR.

Authors

  • Kai Ye
    MandalaT Software Corporation, F5, Wuxi, China.
  • Libo Xu
    Laboratory for Intelligent Medical Imaging, Tsinghua Cross-strait Research Institute, Xiamen, China.
  • Boyang Pan
    RadioDynamic Healthcare, Shanghai, People's Republic of China.
  • Jie Li
    Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Application Technology Research Institute, Shenzhen Polytechnic University, Shenzhen, China.
  • Meijiao Li
    Department of Radiology, The Third Xiangya Hospital of Central South University, Changsha 410013, China.
  • Huishu Yuan
    Department of Radiology, Peking University Third Hospital, Beijing 10019, China.
  • Nan-Jie Gong
    Vector Lab for Intelligent Medical Imaging and Neural Engineering, International Innovation Center of Tsinghua University, Shanghai, China.

Keywords

External Resources

Popular Topics
Recent Journals