论文信息 - Segmentation Method of MRI Using Fuzzy Gaussian Basis Neural Network

Segmentation Method of MRI Using Fuzzy Gaussian Basis Neural Network

Considering the features of magnetic resonance imaging (MRI), a segmentation method of MRI based on fuzzy Gaussian basis neural network (FGBNN) is proposed. In proposed method, the fuzzy inference is realized by neural network. Gaussian basis function is used as fuzzy membership function, and error backpropagation (BP) algorithm is used to train the neural network. The experimental results show that the proposed method has higher segmentation precision and faster network learning speed than the segmentation method based on traditional radial basis function neural network (RBFNN). Keywords—Fuzzy neural network, magnetic resonance image, image segmentation

Yaonan Wang | Wei Sun

[1] Javad Alirezaie,et al. Automatic segmentation of cerebral MR images using artificial neural networks , 1996 .

[2] L O Hall,et al. Review of MR image segmentation techniques using pattern recognition. , 1993, Medical physics.

[3] Yoshiki Uchikawa,et al. On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm , 1992, IEEE Trans. Neural Networks.

[4] A. D. Kulkarni,et al. Neural-Fuzzy Models for Multispectral Image Analysis , 1998, Applied Intelligence.

[5] A. Alavi,et al. Analysis of brain and cerebrospinal fluid volumes with MR imaging. Part I. Methods, reliability, and validation. , 1991, Radiology.

[6] Raquel Valdés-Cristerna,et al. Coupling of radial-basis network and active contour model for multispectral brain MRI segmentation , 2004, IEEE Transactions on Biomedical Engineering.