Accuracy, uncertainty, and adaptability of automatic myocardial ASL segmentation using deep CNN.

Journal: Magnetic resonance in medicine
Published Date: Nov 14, 2019

Abstract

PURPOSE: To apply deep convolution neural network to the segmentation task in myocardial arterial spin labeled perfusion imaging and to develop methods that measure uncertainty and that adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff.

Authors

  • Hung P Do
    Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, California.
  • Yi Guo
    Department of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China.
  • Andrew J Yoon
    Long Beach Memorial Medical Center, University of California Irvine, Irvine, California.
  • Krishna S Nayak
    Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, California.

Keywords

External Resources

Popular Topics
Recent Journals