Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning.

Journal: AJNR. American journal of neuroradiology
PMID: 38453408

Abstract

BACKGROUND AND PURPOSE: Recent developments in deep learning methods offer a potential solution to the need for alternative imaging methods due to concerns about the toxicity of gadolinium-based contrast agents. The purpose of the study was to synthesize virtual gadolinium contrast-enhanced T1-weighted MR images from noncontrast multiparametric MR images in patients with primary brain tumors by using deep learning.

Authors

  • Gowtham Murugesan
    Department of Radiology, UT Southwestern Medical Center, Dallas, TX, United States.
  • Fang F Yu
    Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas frankf.yu@utsouthwestern.edu.
  • Michael Achilleos
    Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas.
  • John DeBevits
    Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas.
  • Sahil Nalawade
    Dana-Farber Cancer Institute, Boston, MA, USA.
  • Chandan Ganesh
    Department of Radiology, UT Southwestern Medical Center, Dallas, Texas, USA.
  • Ben Wagner
    Department of Radiology, UT Southwestern Medical Center, Dallas, Texas, USA.
  • Ananth J Madhuranthakam
    Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas.
  • Joseph A Maldjian
    Department of Radiology, UT Southwestern Medical Center, Dallas, USA.

Keywords

External Resources

Popular Topics
Recent Journals