PM.20.047 – 4D skeletal surgery twin
The project ‘4D skeletal surgery twin’ aims at the improvement of personalized skeletal health. Degenerative diseases such as cancer, rheumatic inflammation and arthritis ask for multidisciplinary and patient specific treatment. This can be surgery of spine, knee, hand, hip and other skeletal parts, sometimes in combination with (radio) therapy and immunotherapy. Output of this project is digitalization of the planning and evaluation of skeletal surgery, including the design and use of the patient ‘Digital Twin’. The Digital twin combines generic disease models and patient-specific data including a full 4D-model of the surgical area. In addition it includes clinical outcome analyses and known patient outcomes from the past. The design of this Digital Twin is determined by the patient needs, surgical requirements and by the interface with other parts of the treatment. Planning of surgery and verification of the clinical outcome will be with respect to dynamical (4D) parameters of motion, load bearing, breathing and blood. It is based on automated analysis of image and motion parameters. New protocols and 4D visualization will enable shared decision making between patient and healthcare professional. Clinical quality improvement comes by the consultation of other clinical outcomes and a seamless integration of treatment (plans). The use of virtual simulation for education of doctors, students (and patients) brings a huge economic benefit to the current way of working. Other economic benefits are a consequence of higher accuracy (less reoperations, higher patient satisfaction) and of time savings for outpatient visits, planning and treatment time. Clinics with high turn-over will benefit most so immediate implementation and testing in academic and collaborating peripheral clinical centers is taken in the project. These centers will be providing data for machine/deep learning algorithms to the project in return. This creates an even more steep learning curve in an efficient and scalable setting.
deep learning algorithms
Eindhoven University of Technology (TU/e), University of Applied Science Utrecht
|Organisation||UMC Utrecht (UMCU)|
|Name||Prof. dr. R.J.B. (Ralph) Sakkers|