Deep learning approaches using 2D and 3D convolutional neural networks for generating male pelvic synthetic computed tomography from magnetic resonance imaging.

Journal: Medical physics
Published Date: Jul 26, 2019

Abstract

PURPOSE: The improved soft tissue contrast of magnetic resonance imaging (MRI) compared to computed tomography (CT) makes it a useful imaging modality for radiotherapy treatment planning. Even when MR images are acquired for treatment planning, the standard clinical practice currently also requires a CT for dose calculation and x-ray-based patient positioning. This increases workloads, introduces uncertainty due to the required inter-modality image registrations, and involves unnecessary irradiation. While it would be beneficial to use exclusively MR images, a method needs to be employed to estimate a synthetic CT (sCT) for generating electron density maps and patient positioning reference images. We investigated 2D and 3D convolutional neural networks (CNNs) to generate a male pelvic sCT using a T1-weighted MR image and compare their performance.

Authors

  • Jie Fu
    David Geffen School of Medicine, University of California, Los Angeles, 10833 Le Conte Ave, Los Angeles, 90095, CA, USA.
  • Yingli Yang
    Biomedical Physics Inter-Departmental Graduate Program, University of California, Los Angeles, CA, USA.
  • Kamal Singhrao
    David Geffen School of Medicine, University of California, Los Angeles, 10833 Le Conte Ave, Los Angeles, 90095, CA, USA.
  • Dan Ruan
    Departments of Radiation Oncology, Biomedical Physics and Bioengineering, UCLA, Los Angeles, CA, 90095, USA.
  • Fang-I Chu
    Department of Radiation Oncology, University of California, Los Angeles, 200 Suite B265, Medical Plaza Driveway, Los Angeles, 90095, CA, USA.
  • Daniel A Low
    Department of Radiation Oncology, UCLA, 200 Medical Plaza, Suite B265, Los Angeles, CA, 90095, USA.
  • John H Lewis
    Department of Radiation Oncology, University of California, Los Angeles, 200 Suite B265, Medical Plaza Driveway, Los Angeles, 90095, CA, USA.

Keywords

External Resources

Popular Topics
Recent Journals