Prediction of the position of external markers using a recurrent neural network trained with unbiased online recurrent optimization for safe lung cancer radiotherapy.

Journal: Computer methods and programs in biomedicine
Published Date: May 25, 2022

Abstract

BACKGROUND AND OBJECTIVE: During lung cancer radiotherapy, the position of infrared reflective objects on the chest can be recorded to estimate the tumor location. However, radiotherapy systems have a latency inherent to robot control limitations that impedes the radiation delivery precision. Prediction with online learning of recurrent neural networks (RNN) allows for adaptation to non-stationary respiratory signals, but classical methods such as real-time recurrent learning (RTRL) and truncated backpropagation through time are respectively slow and biased. This study investigates the capabilities of unbiased online recurrent optimization (UORO) to forecast respiratory motion and enhance safety in lung radiotherapy.

Authors

  • Michel Pohl
    The University of Tokyo, Graduate School of Engineering, Department of Bioengineering, Tokyo, Japan. Electronic address: michel.pohl@centrale-marseille.fr.
  • Mitsuru Uesaka
    The University of Tokyo, Graduate School of Engineering, Department of Bioengineering, Tokyo, Japan; The University of Tokyo, Graduate School of Engineering, Department of Nuclear Engineering and Management, Tokyo, Japan.
  • Hiroyuki Takahashi
    Department of Pathology, Jikei University School of Medicine, Tokyo, Japan.
  • Kazuyuki Demachi
    The University of Tokyo, Graduate School of Engineering, Department of Nuclear Engineering and Management, Tokyo, Japan.
  • Ritu Bhusal Chhatkuli
    National Institute for Quantum and Radiological Science and Technology, Chiba, Japan.

Keywords

External Resources

Popular Topics
Recent Journals