Patella – Atlas Based Segmentation

The main aim of this research is to present an automated image segmentation methodology being used in the field of medicine. The paper shows the automatic extraction of patella in the knee joint based on atlas segmentation. This method allows to build a feature vector that automates and streamlines known segmentation methods (e.g. fuzzy c-means (FCM), fuzzy connectedness (FC)). The described methodology has been implemented in MATLAB and tested on clinical computed tomography (CT) slices of the knee joint in transverse plane.