To extract region of interests （ROI） in brain magnetic resonance imaging （MRI） with more than two objects and improve the segmentation accuracy, a hybrid model of a kemel-based fuzzy c-means （KFCM） clustering al...To extract region of interests （ROI） in brain magnetic resonance imaging （MRI） with more than two objects and improve the segmentation accuracy, a hybrid model of a kemel-based fuzzy c-means （KFCM） clustering algorithm and Chan-Vese （CV） model for brain MRI segmentation is proposed. The approach consists of two succes- sive stages. Firstly, the KFCM is used to make a coarse segmentation, which achieves the automatic selection of initial contour. Then an improved CV model is utilized to subdivide the image. Fuzzy membership degree from KFCM clus- tering is incorporated into the fidelity term of the 2-phase piecewise constant CV model to obtain accurate multi-object segmentation. Experimental results show that the proposed model has advantages both in accuracy and in robustness to noise in comparison with fuzzy c-means （FCM） clustering, KFCM, and the hybrid model of FCM and CV on brain MRI segmentation.展开更多
Objective:To probe into the relation between magnetic resonance imaging(MRI) signal classifications and TCM syndromes in femoral head necrosis patients,so as to provide reference for TCM diagnosis of this disease.Meth...Objective:To probe into the relation between magnetic resonance imaging(MRI) signal classifications and TCM syndromes in femoral head necrosis patients,so as to provide reference for TCM diagnosis of this disease.Methods:Refering to the criteria for TCM syndrome types of necrosis of the femoral head described in "The Guiding Principles of Clinical Studies of New Chinese Drugs" and Shimizu and Mitchell's MRI signal classifications,MRI signal classifications between different TCM syndrome types were compared.Results:The Shimizu signal classification of different TCM syndrome types had statistically significant difference(P=0.04);Both T2WI+fs and Mitchell signal classifications of different TCM syndrome types had no statistical by significant differences(P=0.42 or P=0.15).Conclusion:There is a certain correlativity of TCM syndrome types of necrosis of the femoral head with T1WI signal classification of MRI.MRI signal classification may contribute to objectivity in TCM syndrome typing of this disease.展开更多
基金Supported by National Natural Science Foundation of China (No. 60872065)
文摘To extract region of interests （ROI） in brain magnetic resonance imaging （MRI） with more than two objects and improve the segmentation accuracy, a hybrid model of a kemel-based fuzzy c-means （KFCM） clustering algorithm and Chan-Vese （CV） model for brain MRI segmentation is proposed. The approach consists of two succes- sive stages. Firstly, the KFCM is used to make a coarse segmentation, which achieves the automatic selection of initial contour. Then an improved CV model is utilized to subdivide the image. Fuzzy membership degree from KFCM clus- tering is incorporated into the fidelity term of the 2-phase piecewise constant CV model to obtain accurate multi-object segmentation. Experimental results show that the proposed model has advantages both in accuracy and in robustness to noise in comparison with fuzzy c-means （FCM） clustering, KFCM, and the hybrid model of FCM and CV on brain MRI segmentation.
文摘Objective:To probe into the relation between magnetic resonance imaging(MRI) signal classifications and TCM syndromes in femoral head necrosis patients,so as to provide reference for TCM diagnosis of this disease.Methods:Refering to the criteria for TCM syndrome types of necrosis of the femoral head described in "The Guiding Principles of Clinical Studies of New Chinese Drugs" and Shimizu and Mitchell's MRI signal classifications,MRI signal classifications between different TCM syndrome types were compared.Results:The Shimizu signal classification of different TCM syndrome types had statistically significant difference(P=0.04);Both T2WI+fs and Mitchell signal classifications of different TCM syndrome types had no statistical by significant differences(P=0.42 or P=0.15).Conclusion:There is a certain correlativity of TCM syndrome types of necrosis of the femoral head with T1WI signal classification of MRI.MRI signal classification may contribute to objectivity in TCM syndrome typing of this disease.
