Evaluation of the dataset quality in gamma passing rate predictions using machine learning methods.

Journal: The British journal of radiology
Published Date:

Abstract

OBJECTIVE: Gamma passing rate (GPR) predictions using machine learning methods have been explored for treatment verification of radiotherapy plans. However, these methods presented datasets with unbalanced number of plans having different treatment conditions (heterogeneous datasets), such as anatomical sites or dose per fractions, leading to lower model interpretability and prediction performance.

Authors

  • Paulo Quintero
    Faculty of Science and Engineering, University of Hull, Hull, United Kingdom.
  • David Benoit
    Faculty of Science and Engineering, University of Hull, Hull, United Kingdom.
  • Yongqiang Cheng
    School of Electronic Science, National University of Defense Technology, Changsha 410073, China. yqcheng@nudt.edu.cn.
  • Craig Moore
    Medical Physics Department, Queen's Centre for Oncology, Hull University Teaching Hospitals NHS Trust, Cottingham, United Kingdom.
  • Andrew Beavis
    Medical Physics Department, Queen's Centre for Oncology, Hull University Teaching Hospitals NHS Trust, Cottingham, United Kingdom.