Spatial fuzzy C-means clustering based segmentation on CT images

Image processing and Pattern Recognition are very much important in the extraction of clinical information from images. A hybrid image processing method is presented based on spatial fuzzy C means clustering combined with parametric deformable model for CT liver images. The Spatial fuzzy c-means using pixel classification and parametric deformable models are utilizing dynamic variational boundaries for image segmentation. The controlling parameters of parametric deformable model evolution are also estimated from the results of clustering. Thus we can improve the segmentation of liver image thereby increasing the detection of tumour effectively. Also we can segment out the liver and the tumor with increased efficiency and robustness.