While the aortic valve geometry is highly patient-specific, state-of-the-art prostheses are not aiming at reproducing this individual geometry. One challenge in manufacturing personalized prostheses is the mapping from the curved 3D shape extracted from imaging modalities to the planar 2D leaflet shape that is cut out of the fabrication material. To address this problem, a database was set up to evaluate valve leaflet shape models. First, 3D ultrasound images of ex-vivo porcine valves were acquired under physiologically realistic pressure to extract geometric key parameters describing the individual geometry. In a second step, the valves' leaflets were cut out, spread on an illuminated plate and photographed in this state. From these images, the leaflet shape was extracted using edge detection. This database allows the derivation of a data-driven leaflet model utilizing machine learning, i.e. nonlinear Support Vector Regression (SVR). Additionally, an existing geometric leaflet shape model was evaluated on the dataset. The data-driven approach provided an acceptable leaflet shape estimation and clearly outperformed the existing model. This presents an important step towards personalized aortic valve prostheses.
|Title of host publication
|2018 Computing in Cardiology Conference (CinC)
|Published - 09.2018
|45th Computing in Cardiology Conference - Maastricht, Netherlands
Duration: 23.09.2018 → 26.09.2018
Conference number: 149035