KIKI-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images.

Journal: Magnetic resonance in medicine
Published Date:

Abstract

PURPOSE: To demonstrate accurate MR image reconstruction from undersampled k-space data using cross-domain convolutional neural networks (CNNs) METHODS: Cross-domain CNNs consist of 3 components: (1) a deep CNN operating on the k-space (KCNN), (2) a deep CNN operating on an image domain (ICNN), and (3) an interleaved data consistency operations. These components are alternately applied, and each CNN is trained to minimize the loss between the reconstructed and corresponding fully sampled k-spaces. The final reconstructed image is obtained by forward-propagating the undersampled k-space data through the entire network.

Authors

  • Taejoon Eo
    School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea.
  • Yohan Jun
    School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea.
  • Taeseong Kim
    School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea.
  • Jinseong Jang
    School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea.
  • Ho-Joon Lee
    Department of Radiology and Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea.
  • Dosik Hwang
    School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea. dosik.hwang@yonsei.ac.kr.