Training data distribution significantly impacts the estimation of tissue microstructure with machine learning.

Journal: Magnetic resonance in medicine
Published Date: Sep 21, 2021

Abstract

PURPOSE: Supervised machine learning (ML) provides a compelling alternative to traditional model fitting for parameter mapping in quantitative MRI. The aim of this work is to demonstrate and quantify the effect of different training data distributions on the accuracy and precision of parameter estimates when supervised ML is used for fitting.

Authors

  • Noemi G Gyori
    Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK.
  • Marco Palombo
    University College London, London, United Kingdom.
  • Christopher A Clark
    Great Ormond Street Institute of Child Health, University College London, London, UK.
  • Hui Zhang
    Department of Pulmonary Vessel and Thrombotic Disease, Sixth Medical Center, Chinese PLA General Hospital, Beijing, China.
  • Daniel C Alexander
    Centre for Medical Image Computing and Dept of Computer Science, University College London, Gower Street, London WC1E 6BT, UK.

Keywords

External Resources

Popular Topics
Recent Journals