Image domain dual material decomposition for dual-energy CT using butterfly network.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: Dual-energy CT (DECT) has been increasingly used in imaging applications because of its capability for material differentiation. However, material decomposition suffers from magnified noise from two CT images of independent scans, leading to severe degradation of image quality. Existing algorithms exhibit suboptimal decomposition performance because they fail to fully depict the mapping relationship between DECT images and basis materials under noisy conditions. Convolutional neural network exhibits great promise in the modeling of data coupling and has recently become an important technique in medical imaging application. Inspired by its impressive potential, we developed a new Butterfly network to perform the image domain dual material decomposition.

Authors

  • Wenkun Zhang
    National Digital Switching System Engineering and Technological Research Center, Zhengzhou, Henan, 450002, China.
  • Hanming Zhang
    National Digital Switching System Engineering and Technological Research Center, Zhengzhou, Henan, 450002, China.
  • Linyuan Wang
    National Digital Switching System Engineering and Technological Research Centre, Zhengzhou, China.
  • Xiaohui Wang
    School of Kinesiology, Shanghai University of Sport, Shanghai 200438, China.
  • Xiuhua Hu
    Department of Radiology, School of Medicine, Sir Run Run Shaw Hospital, Zhejiang University, 3 East Qingchun Road, Hangzhou, 310006, Zhejiang, People's Republic of China. huxiuhua_srrsh@zju.edu.cn.
  • Ailong Cai
    National Digital Switching System Engineering and Technological Research Center, Zhengzhou, Henan, 450002, China.
  • Lei Li
    Department of Thoracic Surgery, The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University, Huai'an, China.
  • Tianye Niu
    Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
  • Bin Yan
    National Digital Switching System Engineering and Technological Research Centre, Zhengzhou, China.