Automated classification of benign and malignant lesions in F-NaF PET/CT images using machine learning.

Journal: Physics in medicine and biology
PMID:

Abstract

PURPOSE: F-NaF PET/CT imaging of bone metastases is confounded by tracer uptake in benign diseases, such as osteoarthritis. The goal of this work was to develop an automated bone lesion classification algorithm to classify lesions in NaF PET/CT images.

Authors

  • Timothy Perk
    Department of Medical Physics, University of Wisconsin, Madison, WI, United States of America.
  • Tyler Bradshaw
  • Song Chen
    Department of Nuclear Medicine, The First Hospital of China Medical University, Shenyang, China.
  • Hyung-Jun Im
  • Steve Cho
  • Scott Perlman
  • Glenn Liu
    Lauren C. Harshman and Christopher J. Sweeney, Dana-Farber Cancer Institute, Harvard Medical School; Yu-Hui Chen, Dana-Farber Cancer Institute, Eastern Cooperative Oncology Group-American College of Radiology Imaging Network Cancer Research Group, Boston, MA; Glenn Liu and David Jarrard, University of Wisconsin School of Medicine and Public Health and Carbone Cancer Center, Madison, WI; Michael A. Carducci, Noah Hahn, and Mario Eisenberger, Johns Hopkins University, Baltimore, MD; Robert Dreicer, University of Virginia Cancer Center, Charlottesville, VA; Jorge A. Garcia, Cleveland Clinic Taussig Cancer Institute; Matthew Cooney, University Hospitals Cleveland Medical Center, Seidman Cancer Center, Cleveland, OH; Maha Hussain, Robert H. Lurie Comprehensive Cancer Center, Northwestern University Feinberg School of Medicine, Chicago; Daniel Shevrin, NorthShore University Health System, Evanston, IL; Manish Kohli, Mayo Clinic, Rochester, MN; Elizabeth R. Plimack, Fox Chase Cancer Center, Temple Health, Philadelphia, PA; Nicholas J. Vogelzang, Comprehensive Cancer Centers of Nevada, Las Vegas, NV; Joel Picus, Siteman Cancer Center, Washington University School of Medicine, St Louis, MO; and Robert Dipaola, Rutgers Cancer Institute of New Jersey, New Brunswick, NJ.
  • Robert Jeraj