Deep Learning for Detection of Pneumothorax and Pleural Effusion on Chest Radiographs: Validation Against Computed Tomography, Impact on Resident Reading Time, and Interreader Concordance.

Journal: Journal of thoracic imaging

Published Date: Sep 29, 2023

Abstract

PURPOSE: To study the performance of artificial intelligence (AI) for detecting pleural pathology on chest radiographs (CXRs) using computed tomography as ground truth.

Authors

Ali Tejani

Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX.
Thomas Dowling
Sreeja Sanampudi
Rana Yazdani
Arzu Canan
Elona Malja
Yin Xi

Departments of Radiology (T.J.O., Y.X., E.S., T.B., Y.S.N., R.M.P.) and Health Systems Information Resources (C.B.), University of Texas Southwestern Medical Center at Dallas, Dallas, Texas, 5323 Harry Hines Blvd, Dallas TX 75235.
Suhny Abbara

Department of Radiology, UT Southwestern Medical Center, 5323 Harry Hines Boulevard, Dallas, TX, 75390-9316, USA.
Ron M Peshock
Fernando U Kay

Department of Radiology, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390.

Keywords

Artificial Intelligence Deep Learning Humans Pleural Effusion Pneumothorax Radiography, Thoracic Retrospective Studies Tomography, X-Ray Computed

External Resources

View on PubMed Access via DOI PubMed (37884394)

Deep Learning for Detection of Pneumothorax and Pleural Effusion on Chest Radiographs: Validation Against Computed Tomography, Impact on Resident Reading Time, and Interreader Concordance.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals