Deep learning-based synthetization of real-time in-treatment 4D images using surface motion and pretreatment images: A proof-of-concept study.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: To develop a deep learning model that maps body surface motion to internal anatomy deformation, which is potentially applicable to dose-free real-time 4D virtual image-guided radiotherapy based on skin surface data.

Authors

  • Yuliang Huang
    Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing Cancer Hospital & Institute Beijing, Beijing, China.
  • Zhengkun Dong
    Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital and Institute, Beijing, China.
  • Hao Wu
    Zhejiang Institute of Tianjin University (Shaoxing), Shaoxing, China.
  • Chenguang Li
    Department of Neurology, Guangdong Key Laboratory for Diagnosis and Treatment of Major Neurological Diseases, National Key Clinical Department, National Key Discipline, the First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China.
  • Hongjia Liu
    Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital and Institute, Beijing, China.
  • Yibao Zhang
    Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing Cancer Hospital, Beijing, China.