2011 | OriginalPaper | Buchkapitel
3D-SSM Based Segmentation of Proximal Femur from Hip Joint CT Data
verfasst von : Weiwei Song, Shukun Cao, Hui Zhang, Wenming Wang, Kaifeng Song
Erschienen in: Advanced Research on Computer Science and Information Engineering
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
A new method based on 3D SSM (statistical shape model) is presented for segmentation of proximal femur from hip joint CT images consisting of the collapsing femoral head caused by ANFH. The main idea of the method is to take the biological variability of anatomical shape as the prior knowledge model to guide the process of segmentation. The processing scheme consisted of the following four steps. First, constructing 3D shape model by statistical analysis from a training set. Next, fitting a 3D model to the object. Then, estimating the location of the landmarks by neighborhood points gray information. Finally, model deformation by an iterative process of searching and registration. Experimental results show that the proposed method is efficient to predict and rehabilitate the morphological shape of the collapsing femoral head from the incomplete information in the hip joint CT data.