Arthroscopy is a minimally invasive joint surgery where a camera and surgical tools are inserted through small incisions. This can be used, for example, to replace a torn ligament in the knee. For the replacement, the surgeon has to drill holes through the bones of the knee joint to be able to insert a tendon graft later. Navigation is performed based on the camera image. This requires substantial spatial visualization abilities.
By tracking the camera and the surgical tools, Augmented Reality (AR) can be used to provide the surgeon with X-ray-vision like capabilities. In our proposed setup, an external tracking system is used to track the position and orientation of the camera and the surgical tools. This makes it possible to locate the position of features such as the planned entry and exit-point of the tunnel needed for the reconstruction.
Arthroscopy is a minimally invasive joint surgery where a camera and surgical tools are inserted through small incisions. This can be used, for example, to replace a torn ligament in the knee. For the replacement, the surgeon has to drill holes through the bones of the knee joint to be able to insert a tendon graft later. Navigation is performed based on the camera image. This requires substantial spatial visualization abilities. By tracking the camera and the surgical tools, Augmented Reality (AR) can be used to provide the surgeon with X-ray-vision like capabilities. In our proposed setup, an external tracking system is used to track the position and orientation of the camera and the surgical tools. This makes it possible to locate the position of features such as the planned entry and exit-point of the tunnel needed for the reconstruction.
The goal of this project is to improve the overall process of arthroscopy by introducing Machine Learning (ML) and Augmented Reality (AR) algorithms. In this master's thesis, you will develop a method for planning drill trajectories based on the live feed from the arthroscopic camera and its pose information. You will familiarize yourself with technologies suitable for solving this task, including but not limited to automatic detection of key points and 3D reconstruction based on video feeds. In a second phase, you will be responsible for designing and implementing the planned pipeline and evaluating its accuracy. Depending on your progress, there is the possibility to implement the entire AR system on a HoloLens device. Although you will be expected to work independently, you can count on a network of experienced researchers to support you along the way.
The goal of this project is to improve the overall process of arthroscopy by introducing Machine Learning (ML) and Augmented Reality (AR) algorithms. In this master's thesis, you will develop a method for planning drill trajectories based on the live feed from the arthroscopic camera and its pose information. You will familiarize yourself with technologies suitable for solving this task, including but not limited to automatic detection of key points and 3D reconstruction based on video feeds. In a second phase, you will be responsible for designing and implementing the planned pipeline and evaluating its accuracy. Depending on your progress, there is the possibility to implement the entire AR system on a HoloLens device. Although you will be expected to work independently, you can count on a network of experienced researchers to support you along the way.
Prof. Philipp Fürnstahl, Head of ROCS Group, University Hospital Balgrist, Zurich, Switzerland; philipp.fuernstahl@balgrist.ch
Sascha Jecklin, PhD Student ROCS Group, University Hospital Balgrist, University of Zurich, Balgrist CAMPUS; sascha.jecklin@balgrist.ch
Prof. Philipp Fürnstahl, Head of ROCS Group, University Hospital Balgrist, Zurich, Switzerland; philipp.fuernstahl@balgrist.ch
Sascha Jecklin, PhD Student ROCS Group, University Hospital Balgrist, University of Zurich, Balgrist CAMPUS; sascha.jecklin@balgrist.ch
