Using deep feature distances for evaluating the perceptual quality of MR image reconstructions.

Journal: Magnetic resonance in medicine
Published Date: Feb 8, 2025

Abstract

PURPOSE: Commonly used MR image quality (IQ) metrics have poor concordance with radiologist-perceived diagnostic IQ. Here, we develop and explore deep feature distances (DFDs)-distances computed in a lower-dimensional feature space encoded by a convolutional neural network (CNN)-as improved perceptual IQ metrics for MR image reconstruction. We further explore the impact of distribution shifts between images in the DFD CNN encoder training data and the IQ metric evaluation.

Authors

  • Philip M Adamson
    Varian Medical Systems, Palo Alto, CA, USA. Electronic address: padamson@stanford.edu.
  • Arjun D Desai
    Department of Radiology, Stanford University, Stanford, California, USA.
  • Jeffrey Dominic
    Department of Electrical Engineering, Stanford University, Stanford, California, USA.
  • Maya Varma
    Department of Computer Science, Stanford University, Stanford, California.
  • Christian Bluethgen
    Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI), Stanford University, Sheffield, USA.
  • Jeff P Wood
    Austin Radiological Association, Austin, Texas, USA.
  • Ali B Syed
    Divison of Musculoskeletal Imaging and Intervention, Department of Radiology, Thomas Jefferson University Hospital, Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, Pennsylvania.
  • Robert D Boutin
    Department of Radiology, University of California, Davis, School of Medicine, Sacramento, California.
  • Kathryn J Stevens
    Department of Radiology, Stanford University, Stanford, California.
  • Shreyas Vasanawala
    Department of Radiology, Stanford University, Stanford, California, USA.
  • John M Pauly
    Department of Electrical Engineering, Stanford University, Stanford, California, USA.
  • Beliz Gunel
    Department of Electrical Engineering, Stanford University, Stanford, California, USA.
  • Akshay S Chaudhari
    Department of Radiology, Stanford University, Stanford, California.

Keywords

External Resources

Popular Topics
Recent Journals