Medical Image Segmentation using Modified K Means Clustering

Image segmentation is an important technique for image processing which aims at partitioning the image into different homogeneous regions or clusters.Lots of general-purpose techniques and algorithms have been developed and widely applied in various application areas.For the study of anatomical structures and to identify the region of interest.Magnetic Resonance Images are used to produce images of soft tissue of human body.Noise present in the Brain MRI images are multiplicative noise and reductions of these noise are difficult task.However, accurate Segmentation of the MRI images is very important and crucial for the exact diagnosis by computer aided clinical tools.A large variety of algorithms for segmentation of MRI images had been developed.However most of these have some limitations, to overcome these limitations; modified k means clustering is proposed.The comparison of existing segmentation approaches such as C-Means Clustering, K-Means Clustering with Modified K-Means Clustering is performed then the performance evaluated.Finally generated outcomes of the Fuzzy c-means clustering, k-means clustering and modified k means clustering algorithm for the brain MRI shows that modified kmeans clustering technique gives better results for all performance measuring parameters such as structural similarity index measure, structural content, mean squared error and peak to signal noise ratio.