Logistic Regression-Based Model Is More Efficient Than U-Net Model for Reliable Whole Brain Magnetic Resonance Imaging Segmentation.

Journal: Topics in magnetic resonance imaging : TMRI
Published Date:

Abstract

OBJECTIVES: Automated whole brain segmentation from magnetic resonance images is of great interest for the development of clinically relevant volumetric markers for various neurological diseases. Although deep learning methods have demonstrated remarkable potential in this area, they may perform poorly in nonoptimal conditions, such as limited training data availability. Manual whole brain segmentation is an incredibly tedious process, so minimizing the data set size required for training segmentation algorithms may be of wide interest. The purpose of this study was to compare the performance of the prototypical deep learning segmentation architecture (U-Net) with a previously published atlas-free traditional machine learning method, Classification using Derivative-based Features (C-DEF) for whole brain segmentation, in the setting of limited training data.

Authors

  • Henry Dieckhaus
    qMRI Core Facility, NINDS, National Institutes of Health, Bethesda, MD.
  • Rozanna Meijboom
    Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, UK.
  • Serhat Okar
    Translational Neuroradiology Section, NINDS, National Institutes of Health, Bethesda, MD.
  • Tianxia Wu
    Clinical Trials Unit, NINDS, National Institutes of Health, Bethesda, MD.
  • Prasanna Parvathaneni
  • Yair Mina
    Viral Immunology Section, NINDS, National Institutes of Health, Bethesda, MD; and.
  • Siddharthan Chandran
    Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom.
  • Adam D Waldman
    Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom.
  • Daniel S Reich
  • Govind Nair
    National Institute of Neurological Disorders and Stroke, National Institutes of Health, Maryland, USA.