External Validation of a CT-Based Radiogenomics Model for the Detection of EGFR Mutation in NSCLC and the Impact of Prevalence in Model Building by Using Synthetic Minority Over Sampling (SMOTE): Lessons Learned.

Journal: Academic radiology
Published Date:

Abstract

RATIONALE AND OBJECTIVES: Radiogenomics holds promise in identifying molecular alterations in nonsmall cell lung cancer (NSCLC) using imaging features. Previously, we developed a radiogenomics model to predict epidermal growth factor receptor (EGFR) mutations based on contrast-enhanced computed tomography (CECT) in NSCLC patients. The current study aimed to externally validate this model using a publicly available National Institutes of Health (NIH)-based NSCLC dataset and assess the effect of EGFR mutation prevalence on model performance through synthetic minority oversampling technique (SMOTE).

Authors

  • Andres A Kohan
    Joint Department of Medical Imaging, Princess Margaret Hospital, University Health Network, University of Toronto, Toronto, ON, Canada (A.A.K., S.A.M., R.H., R.K., C.O., U.M., P.V.-H.); Joint Department of Medical Imaging, University Health Network, 263 McCaul St 4th Floor, Toronto, ON M5T 1W7, Canada (A.A.K.). Electronic address: Andres.Kohan@uhn.ca.
  • S A Mirshahvalad
    Joint Department of Medical Imaging, Princess Margaret Hospital, University Health Network, University of Toronto, Toronto, ON, Canada (A.A.K., S.A.M., R.H., R.K., C.O., U.M., P.V.-H.).
  • R Hinzpeter
    Joint Department of Medical Imaging, Princess Margaret Hospital, University Health Network, University of Toronto, Toronto, ON, Canada (A.A.K., S.A.M., R.H., R.K., C.O., U.M., P.V.-H.); Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Zurich, Switzerland (R.H.).
  • R Kulanthaivelu
    Joint Department of Medical Imaging, Princess Margaret Hospital, University Health Network, University of Toronto, Toronto, ON, Canada (A.A.K., S.A.M., R.H., R.K., C.O., U.M., P.V.-H.); Department of Diagnostics Radiology, Queen's University, Kingston, ON, Canada (R.K.).
  • L Avery
    Department of Biostatistics, Princess Margaret Cancer Centre, University Health Network, University of Toronto, Toronto, ON, Canada (L.A.).
  • C Ortega
    Joint Department of Medical Imaging, Princess Margaret Hospital, University Health Network, University of Toronto, Toronto, ON, Canada (A.A.K., S.A.M., R.H., R.K., C.O., U.M., P.V.-H.).
  • U Metser
    Joint Department of Medical Imaging, Princess Margaret Hospital, University Health Network, University of Toronto, Toronto, ON, Canada (A.A.K., S.A.M., R.H., R.K., C.O., U.M., P.V.-H.).
  • A Hope
    Department of Radiation Oncology, University Health Network, University of Toronto, Toronto, ON, Canada (A.H.).
  • P Veit-Haibach
    Joint Department of Medical Imaging, Princess Margaret Hospital, University Health Network, University of Toronto, Toronto, ON, Canada (A.A.K., S.A.M., R.H., R.K., C.O., U.M., P.V.-H.).

Keywords

No keywords available for this article.