一种各向异性Wells算法脑核磁共振图像分割模型.pdfVIP

ISSNN 111777TP Journal of Computer Research and Development 7( 11) : 1878 1885, 2010 Wells 1 2 2 3 陈允杰 张建伟 王顺凤 詹天明 1 ( 2100 ) 2 ( 2100 ) 3 ( 21009 ) ( generalcyj@ yahoo. com. cn) Brain MR Image Segmentation Based on Anisotropic Wells Model 1 2 2 3 Chen Yunjie , Zhang Jianw ei , Wang Shunfeng , and Zhan Tianming 1 ( School of M ath and Physics, Nanj ing Univers ity of Inf ormation Science and T echnology , Nanj ing 2100 ) 2 ( Binj iang School, N anj ing University of Inf ormation Science and Technolog y, Nanj ing 2100 ) 3 ( School of Comp ter S cience and Technology , N anj ing University of S cience and Technology , N anj ing 21009 ) Abstract Nuclear magnetic resonance ( MR) image analysis has become a major means of the auxiliary medical services. However, intensity inhomogeneity, w hich is usually named as bias field, causes considerable difficulty in the quantitative analysis of M R images. T hus bias field estimation is a necessary preprocessing step before quantitative analysis of MR data. T he Wells model, one of the w idely used methods, uses know ledge of tissue intensity properties and intensity inhomogeneities to correct and segment M R images. How ever, the classical W ells model only uses the intensity information and no spatial information is taken into account, so it is sensitive to the noise. In order to overcome this limitation, the Gibbs theory and the image structure information are used to construct anisotropic Gibbs random field. T he traditional Gibbs theory usually loses the information of the beam structure regions and the corner regions. With the spatial information, the anisotropic Gibbs random field can reduce the effect of the noise and contain the informa