Clinical Validation and Extension of an Automated, Deep Learning-Based Algorithm for Quantitative Sinus CT Analysis.

Journal: AJNR. American journal of neuroradiology
PMID: 36538385

Abstract

BACKGROUND AND PURPOSE: Sinus CT is critically important for the diagnosis of chronic rhinosinusitis. While CT is sensitive for detecting mucosal disease, automated methods for objective quantification of sinus opacification are lacking. We describe new measurements and further clinical validation of automated CT analysis using a convolutional neural network in a chronic rhinosinusitis population. This technology produces volumetric segmentations that permit calculation of percentage sinus opacification, mean Hounsfield units of opacities, and percentage of osteitis.

Authors

  • C J Massey
    From the Department of Otolaryngology-Head and Neck Surgery (C.J.M., L.R., V.R.R.), University of Colorado School of Medicine, Aurora, Colorado.
  • L Ramos
    From the Department of Otolaryngology-Head and Neck Surgery (C.J.M., L.R., V.R.R.), University of Colorado School of Medicine, Aurora, Colorado.
  • D M Beswick
    Department of Otolaryngology-Head and Neck Surgery (D.M.B.), University of California-Los Angeles School of Medicine, Los Angeles, California.
  • V R Ramakrishnan
    From the Department of Otolaryngology-Head and Neck Surgery (C.J.M., L.R., V.R.R.), University of Colorado School of Medicine, Aurora, Colorado.
  • S M Humphries
    Quantitative Imaging Laboratory (S.M.H.), Department of Radiology, National Jewish Health, Denver, Colorado humphriess@NJHealth.org.

Keywords

External Resources

Popular Topics
Recent Journals