Abstract:

The growing use of image-guided minimally-invasive surgical procedures is confronting clinicians and surgical staff to new radiation exposure risks from X-ray imaging devices. Furthermore, the current surgical practice of wearing a single dosimeter at chest level to measure radiation exposure does not provide a sufficiently accurate estimation of radiation absorption throughout the body. Therefore, our aim is to develop a global radiation awareness system that can more accurately estimate intra-operative radiation exposure, thereby increasing staff awareness of radiation exposure risks and enabling the implementation of well-adapted safety measures.
In this talk, I will present our work towards the development of such a system. I will first present a computer vision approach that combines data from wireless dosimeters with the simulation of radiation propagation in order to compute a global radiation risk map in the area near the X-ray device. A multi-camera RGBD system is used to estimate the layout of the room and display the estimated risk map using augmented reality. By using real-time wireless dosimeters in our system, we can both calibrate the simulation and validate its accuracy at specific locations in real-time.
I will then describe our recent work on human pose estimation and activity recognition using RGBD data recorded during real X-ray guided interventions. Among other applications, the pose estimation of the persons present in the room will allow the computation of the radiation exposure per body part over time and the recognition of surgical activities will permit the correlation of these activities with the radiation risk they pose to staff and clinicians.

Bio:

Nicolas Padoy is an Assistant Professor at the University of Strasbourg, holding a Chair of Excellence in medical robotics within the ICube laboratory. He leads the research group CAMMA on Computational Analysis and Modeling of Medical Activities, which focuses on computer vision, activity recognition and the applications thereof to surgical workflow analysis and human-machine cooperation during surgery. He graduated with a Maîtrise in Computer Science from the Ecole Normale Supérieure de Lyon in 2003 and with a Diploma in Computer Science from the Technische Universität München (TUM), Munich, in 2005. He completed his PhD jointly between the Chair for Computer Aided Medical Procedures at TUM and the INRIA group MAGRIT in Nancy. Subsequently, he was a postdoctoral researcher and later an Assistant Research Professor in the Laboratory for Computational Sensing and Robotics at the Johns Hopkins University, USA.