Classification performance bias between training and test sets in a limited mammography dataset.

Journal: PloS one
Published Date: Feb 7, 2024

Abstract

OBJECTIVES: To assess the performance bias caused by sampling data into training and test sets in a mammography radiomics study.

Authors

  • Rui Hou
    Guangzhou KangRui Biological Pharmaceutical Technology Company, 510005 Guangzhou, China.
  • Joseph Y Lo
    Carl E. Ravin Advanced Imaging Laboratories, Department of Radiology, Duke University School of Medicine, Durham, North Carolina.
  • Jeffrey R Marks
    Department of Surgery, Duke University School of Medicine, Durham, North Carolina.
  • E Shelley Hwang
    Department of Surgery, Duke University School of Medicine, Durham, North Carolina.
  • Lars J Grimm

Keywords

External Resources

Popular Topics
Recent Journals