Medical Image Segmentation Method Based on Texture Character and GRBF Network / 医疗卫生装备

Objective To get a better medical image segmentation result by studing a new image segmentation method. Methods Medical images were segmented using image segmentation method based on texture character and generalized radial basis function neural networks. The texture character parameters were obtained according to gray level co-occurrence matrix. The parameters were input to the generalized radial basis function neural networks to train the network. Results Comparatively, perfect binary images were obtained by using this new image segmentation method. Conclusion The emulational results show that the method is an effective medical image segmentation method.