Bayesian deep learning-based H-MRS of the brain: Metabolite quantification with uncertainty estimation using Monte Carlo dropout.

Journal: Magnetic resonance in medicine
Published Date:

Abstract

PURPOSE: To develop a Bayesian convolutional neural network (BCNN) with Monte Carlo dropout sampling for metabolite quantification with simultaneous uncertainty estimation in deep learning-based proton MRS of the brain.

Authors

  • Hyeong Hun Lee
    Department of Biomedical Sciences, Seoul National University, Seoul, Korea.
  • Hyeonjin Kim
    Department of Biomedical Sciences, Seoul National University, Seoul, Korea.