Transparent Machine Learning Models to Diagnose Suspicious Thoracic Lesions Leveraging CT Guided Biopsy Data.

Journal: Academic radiology
Published Date: Feb 1, 2022

Abstract

RATIONALE AND OBJECTIVES: To train and validate machine learning models capable of classifying suspicious thoracic lesions as benign or malignant and to further classify malignant lesions by pathologic subtype while quantifying feature importance for each classification.

Authors

  • William D Lindsay
    Oncora Medical, Philadelphia, Pennsylvania.
  • Nicholas Sachs
    Perelman School of Medicine, University of Pennsylvania Health System, Philadelphia, Pennsylvania.
  • James C Gee
    Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
  • Eduardo J Mortani Barbosa
    Department of Bioengineering, School of Applied Sciences, University of Pennsylvania, Philadelphia, Pennsylvania. Electronic address: Eduardo.Barbosa@pennmedicine.upenn.edu.

Keywords

External Resources

Popular Topics
Recent Journals