Robot-assisted flexible needle insertion using universal distributional deep reinforcement learning.

Journal: International journal of computer assisted radiology and surgery
Published Date: Nov 25, 2019

Abstract

PURPOSE: Flexible needle insertion is an important minimally invasive surgery approach for biopsy and radio-frequency ablation. This approach can minimize intraoperative trauma and improve postoperative recovery. We propose a new path planning framework using multi-goal deep reinforcement learning to overcome the difficulties in uncertain needle-tissue interactions and enhance the robustness of robot-assisted insertion process.

Authors

  • Xiaoyu Tan
    Department of Mechanical Engineering, National University of Singapore, Singapore, 117575, Singapore. xiaoyu_tan@u.nus.edu.
  • Yonggu Lee
    Department of Mechanical Engineering, National University of Singapore, Singapore, 117575, Singapore.
  • Chin-Boon Chng
    Department of Mechanical Engineering, National University of Singapore, Singapore, 117575, Singapore.
  • Kah-Bin Lim
    Department of Mechanical Engineering, National University of Singapore, Singapore, 117575, Singapore.
  • Chee-Kong Chui
    Department of Mechanical Engineering, National University of Singapore, Singapore, 117575, Singapore.

Keywords

External Resources

Popular Topics
Recent Journals