Automatic segmentation method for hip joint based on Bayesian Decision Theory / 中国组织工程研究

ABSTRACT

BACKGROUND:Hip segmentation based on CT image has been widely used in computer-assisted surgery planning, prosthesis design and finite element analysis. OBJECTIVE:To explore application effects of automatic segmentation method for hip joint based on Bayesian Decision Theory in computer-assisted hip surgery. METHODS:An accurate outer surface segmentation and extraction remain chal enging due to deformed shapes and extremely narrow inter-bone regions. In this paper, we present an automatic, fast and accurate approach for segmentation of femoral head and proximal acetabulum. The outline of the femur was segmented and extracted by contrast enhancement, thresholding algorithm and region growth algorithm. The boundaries of the bone regions are further refined based on Bayes decision rule. RESULTS AND CONCLUSION:Automatic segmentation method for hip joint based on Bayesian Decision Theory is an accurate segmentation technique for femoral head and proximal acetabulum and it can be applied in computer-assisted hip surgery and prosthesis design.