Fully Automated Segmentation of Globes for Volume Quantification in CT Images of Orbits using Deep Learning.

Journal: AJNR. American journal of neuroradiology
Published Date: May 21, 2020

Abstract

BACKGROUND AND PURPOSE: Fast and accurate quantification of globe volumes in the event of an ocular trauma can provide clinicians with valuable diagnostic information. In this work, an automated workflow using a deep learning-based convolutional neural network is proposed for prediction of globe contours and their subsequent volume quantification in CT images of the orbits.

Authors

  • L Umapathy
    From the Departments of Electrical and Computer Engineering (L.U., A.B.).
  • B Winegar
    Medical Imaging (L.U., B.W., L.M., M.H., M.I.A., A.B.).
  • L MacKinnon
    Medical Imaging (L.U., B.W., L.M., M.H., M.I.A., A.B.).
  • M Hill
    Medical Imaging (L.U., B.W., L.M., M.H., M.I.A., A.B.).
  • M I Altbach
    Medical Imaging (L.U., B.W., L.M., M.H., M.I.A., A.B.).
  • J M Miller
    Ophthalmology and Vision Science (J.M.M.).
  • A Bilgin
    From the Departments of Electrical and Computer Engineering (L.U., A.B.) bilgin@email.arizona.edu.

Keywords

External Resources

Popular Topics
Recent Journals