Development and validation of a CT-based deep learning algorithm to augment non-invasive diagnosis of idiopathic pulmonary fibrosis.

Journal: Respiratory medicine
Published Date: Oct 13, 2023

Abstract

RATIONALE: Non-invasive diagnosis of idiopathic pulmonary fibrosis (IPF) involves identification of usual interstitial pneumonia (UIP) pattern by computed tomography (CT) and exclusion of other known etiologies of interstitial lung disease (ILD). However, uncertainty in identification of radiologic UIP pattern leads to the continued need for invasive surgical biopsy. We thus developed and validated a machine learning algorithm using CT scans alone to augment non-invasive diagnosis of IPF.

Authors

  • Manoj V Maddali
    Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Stanford University, Stanford, CA, USA. Electronic address: manoj.maddali@stanford.edu.
  • Angad Kalra
    Department of Computer Science, University of Toronto, Toronto, Ontario, Canada. Electronic address: angadk@cs.toronto.edu.
  • Michael Muelly
    Imvaria, Inc, USA.
  • Joshua J Reicher
    Stanford Health Care and Palo Alto Veterans Affairs, Palo Alto, CA, USA.

Keywords

External Resources

Popular Topics
Recent Journals