Advancing Image-Based Assistive Technologies In Robotic Surgery: Perception, Targeting, and Planning
Robotic surgery, combined with minimally invasive and image-guided interventions, has elevated surgical practice by enhancing precision, reducing trauma, expediting recovery, and mitigating surgeon fatigue. Yet despite numerous innovations, many robotic procedures still face challenges in fusing live medical imaging with intelligent robot motion. This dissertation responds to these challenges across 3 key areas: image-based perception, needle targeting, and treatment planning. Firstly, a markerless 6 DOF needle pose tracking technique was developed by integrating deep learning-based keypoint detection with point-wise registration, enabling robotic suturing. Building on this, the dissertation extends to Magnetic Resonance (MR) Imaging-based needle localization and targeting for Laser Interstitial Thermal Therapy (LITT), employing an MR-compatible robot that takes live intraoperative feedback to improve accuracy. Finally, once the thermal applicator is positioned, a Finite Element Method-based interactive treatment planning toolkit and a Reinforcement Learning agent can assist surgeons for conformal control of directional hyperthermia. Collectively, these methods integrate medical imaging, robotics, and machine learning to enable precise, adaptive interventions, illustrate the synergy of perception, targeting, and planning advances minimally invasive, image-guided robotic surgery, and highlight the promise of automation for effective, personalized treatments and improved outcomes.
Advisor: Professor Gregory Fischer
Committee: Professor Haichong Zhang (WPI, RBE, BME); Professor Yihao Zheng (WPI, MME); Zhanyue Zhao, Ph.D. (AiM Medical Robotics)
Zoom Link: https://wpi.zoom.us/j/91828600349