Project Background
The knee is a complex 3D structure, commonly injured or damaged through sport or repetitive stress. By understanding the knee’s cartilage geometry through the use of MRI, optimised treatments are possible.
Project Goals
The aim of this project is to develop a 3D map of the knee.
MR image decision support
The Knee Cartilage Map project will assist doctors and clinicians to make decisions about surgery via interactive MR visualisation.
Knee scan and slice.
Automatic MR cartilage analysis
State-of-the art algorithms for segmentation and analysis are employed to help objectively measure the health and condition of cartilage tissue.
Segmented knee
Statistical Shape Model
The thin cartilages in the knee are prone to injury and disease. MRI allows accurate and non-invasive imaging of the cartilages. Longitudinal studies of osteoarthritis require the cartilages to be segmented. This is difficult, so current approaches are either manual or semi-automated.
Automatic segmentation may be allowed by using more advanced modeling and analysis techniques, including statistical shape models.
Towards this goal we have developed a parametric deformable model based surface extraction algorithm.
Statistical shape models
