Fully automatic liver attenuation estimation combing CNN segmentation and morphological operations.

Journal: Medical physics
Published Date: Jul 5, 2019

Abstract

PURPOSE: Manually tracing regions of interest (ROIs) within the liver is the de facto standard method for measuring liver attenuation on computed tomography (CT) in diagnosing nonalcoholic fatty liver disease (NAFLD). However, manual tracing is resource intensive. To address these limitations and to expand the availability of a quantitative CT measure of hepatic steatosis, we propose the automatic liver attenuation ROI-based measurement (ALARM) method for automated liver attenuation estimation.

Authors

  • Yuankai Huo
    Vanderbilt University, Nashville, TN 37212, USA.
  • James G Terry
    Vanderbilt University Medical Center, , Nashville, USA.
  • Jiachen Wang
    Department of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, 37235, USA.
  • Sangeeta Nair
    Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, 37235, USA.
  • Thomas A Lasko
    Vanderbilt University School of Medicine, Nashville, TN.
  • Barry I Freedman
    Department of Internal Medicine-Nephrology, Wake Forest School of Medicine, Winston-Salem, NC, 27157, USA.
  • J Jeffery Carr
    Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, 37235, USA.
  • Bennett A Landman
    Vanderbilt University, Nashville TN 37235, USA.

Keywords

External Resources

Popular Topics
Recent Journals