ABSTRACT
Statistical shape modeling is one of the emerging techniques in the computer vision, image analysis and machine-learning domains, which, if applied effectively, could change the future course of how medical diagnosis and subsequent treatment is imparted to the patient. Image-based model building has been in use for a long time now. Manual or automatic segmentation of image slices is the most commonly used method to build 3D bone models. Data from dry bones was collected for both scapula and humerus. Segmentation was performed in a 3D modeling software called Amira v5.4.3. Registration is the process of finding the spatial transform that maps points from one image or shape to the homologous points in another image or shape. The potential applications of Statistical shape models (SSM) and statistical appearance model (SAM) may increase as imaging modalities improve.
