MR Protocol Optimization With Deep Learning: A Proof of Concept.

Journal: Current problems in diagnostic radiology
Published Date:

Abstract

PURPOSE: This study was performed to demonstrate that a properly trained convolutional neural net (CNN) can provide an acceptable surrogate for human readers when performing a protocol optimization study. Tears of the anterior cruciate ligament (ACL) were used as a proof of concept for this study.

Authors

  • Michael L Richardson
    Department of Radiology, University of Washington, Seattle, WA. Electronic address: mrich@uw.edu.