Evaluating the relationship between magnetic resonance image quality metrics and deep learning-based segmentation accuracy of brain tumors.

Journal: Medical physics
Published Date: Apr 19, 2024

Abstract

BACKGROUND: Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment-based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal-to-noise, contrast-to-noise) and segmentation accuracy.

Authors

  • Rajarajeswari Muthusivarajan
    Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Adrian Celaya
    Department of Imaging Physics, MD Anderson Cancer Center, The University of Texas, Houston, Texas, USA.
  • Joshua P Yung
    Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • James P Long
    Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Satish E Viswanath
    Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA.
  • Daniel S Marcus
    Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO, USA.
  • Caroline Chung
    The University of Texas MD Anderson Cancer Center, Houston, TX.
  • David Fuentes
    Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, United States.

Keywords

External Resources

Popular Topics
Recent Journals