Detection of the failed-tolerance causes of electronic-portal-imaging-device-based dosimetry using machine learning for volumetric-modulated arc therapy: A feasibility study.

Journal: Physics and imaging in radiation oncology
Published Date: May 17, 2025

Abstract

BACKGROUND AND PURPOSE: When electronic-portal-imaging-device (EPID)-based dosimetry (IVD) identifies dose tolerance failures, the cause of the failures should be evaluated. This study aimed to develop a machine-learning (ML) model to classify the cause of EPID-based IVD failures in volumetric-modulated arc therapy (VMAT) treatment.

Authors

  • Nipon Saiyo
    Department of Quantum Medical Technology, Graduate Course of Medical Sciences and Technology, Division of Health Sciences, Graduate School of Medical Sciences, Kanazawa University, Ishikawa, Japan.
  • Hironori Kojima
    Department of Radiology, Kanazawa University Hospital, Kanazawa University, Ishikawa, Japan.
  • Kimiya Noto
    Department of Radiology, Kanazawa University Hospital, Kanazawa University, Ishikawa, Japan.
  • Naoki Isomura
    Department of Radiology, Kanazawa University Hospital, Kanazawa University, Ishikawa, Japan.
  • Kosuke Tsukamoto
    Department of Radiology, Kanazawa University Hospital, Kanazawa University, Ishikawa, Japan.
  • Shotaro Yamaguchi
    Department of Quantum Medical Technology, Graduate Course of Medical Sciences and Technology, Division of Health Sciences, Graduate School of Medical Sciences, Kanazawa University, Ishikawa, Japan.
  • Yuto Segawa
    Department of Quantum Medical Technology, Graduate Course of Medical Sciences and Technology, Division of Health Sciences, Graduate School of Medical Sciences, Kanazawa University, Ishikawa, Japan.
  • Junya Kohigashi
    Department of Quantum Medical Technology, Graduate Course of Medical Sciences and Technology, Division of Health Sciences, Graduate School of Medical Sciences, Kanazawa University, Ishikawa, Japan.
  • Akihiro Takemura
    Faculty of Health Sciences, Institute of Medical, Pharmaceutical and Health Sciences, Kanazawa University, Ishikawa, Japan.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals