Under-representation for Female Pelvis Cancers in Commercial Auto-segmentation Solutions and Open-source Imaging Datasets.

Journal: Clinical oncology (Royal College of Radiologists (Great Britain))
PMID: 39837727

Abstract

AIM: Artificial intelligence (AI) based auto-segmentation aids radiation therapy (RT) workflows and is being adopted in clinical environments facilitated by the increased availability of commercial solutions for organs at risk (OARs). In addition, open-source imaging datasets support training for new auto-segmentation algorithms. Here, we studied if the female and male anatomies are equally represented among these solutions.

Authors

  • M Thor
    Memorial Sloan Kettering Cancer Center, New York, New York, USA.
  • V Williams
    Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, USA.
  • C Hajj
    Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, USA.
  • L Cervino
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, USA.
  • H Veeraraghavan
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, USA.
  • S Elguindi
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, USA.
  • N Tyagi
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, USA.
  • A Shukla-Dave
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, USA; Department of Radiology, Memorial Sloan Kettering Cancer Center, USA.
  • J M Moran
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, USA.

Keywords

External Resources

Popular Topics
Recent Journals