Bayesian deep learning outperforms clinical trial estimators of intracerebral and intraventricular hemorrhage volume.

Journal: Journal of neuroimaging : official journal of the American Society of Neuroimaging
PMID: 35434846

Abstract

BACKGROUND AND PURPOSE: Intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) clinical trials rely on manual linear and semi-quantitative (LSQ) estimators like the ABC/2, modified Graeb and IVH scores for timely volumetric estimation from CT. Deep learning (DL) volumetrics of ICH have recently approached the accuracy of gold-standard planimetry. However, DL and LSQ strategies have been limited by unquantified uncertainty, in particular when ICH and IVH estimates intersect. Bayesian deep learning methods can be used to approximate uncertainty, presenting an opportunity to improve quality assurance in clinical trials.

Authors

  • Matthew F Sharrock
    Division of Neurocritical Care, Department of Neurology, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. sharrock@unc.edu.
  • W Andrew Mould
    Division of Brain Injury Outcomes, Johns Hopkins University, Baltimore, MD, USA.
  • Meghan Hildreth
    Division of Brain Injury Outcomes, Johns Hopkins University, Baltimore, MD, USA.
  • E Paul Ryu
    Division of Brain Injury Outcomes, Department of Neurology, Johns Hopkins University, Baltimore, Maryland, USA.
  • Nathan Walborn
    Division of Brain Injury Outcomes, Department of Neurology, Johns Hopkins University, Baltimore, Maryland, USA.
  • Issam A Awad
    Neurovascular Surgery Program, Section of Neurosurgery, Department of Surgery, University of Chicago Medicine and Biological Sciences, Chicago, IL, USA.
  • Daniel F Hanley
    Division of Brain Injury Outcomes, Johns Hopkins University, Baltimore, MD, USA.
  • John Muschelli
    Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA.

Keywords

External Resources

Popular Topics
Recent Journals