Geometric and dosimetric evaluation of deep learning based auto-segmentation for clinical target volume on breast cancer.

Journal: Journal of applied clinical medical physics
PMID:

Abstract

BACKGROUND: Recently, target auto-segmentation techniques based on deep learning (DL) have shown promising results. However, inaccurate target delineation will directly affect the treatment planning dose distribution and the effect of subsequent radiotherapy work. Evaluation based on geometric metrics alone may not be sufficient for target delineation accuracy assessment. The purpose of this paper is to validate the performance of automatic segmentation with dosimetric metrics and try to construct new evaluation geometric metrics to comprehensively understand the dose-response relationship from the perspective of clinical application.

Authors

  • Yang Zhong
    Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China.
  • Ying Guo
    National Institutes for Food and Drug Control, Beijing, 100050, China.
  • Yingtao Fang
    Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, People's Republic of China.
  • Zhiqiang Wu
    Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China.
  • Jiazhou Wang
    Department of radiation oncology, Fudan University Shanghai Cancer Center, Shanghai, China.
  • Weigang Hu
    Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China.