Segmentation of Brain MRI Images by Using Modified Robust Fuzzy c Means Algorithm

Image segmentation play a vital role in numerous biomedical imaging applications. Some of them are computer-integrated surgery, study of anatomical structure and quantification of tissue volumes. When compared to all other medical imaging techniques, the Magnetic Resonance Imaging (MRI) has received much attention because of its advantages. The MRI analysis involves a huge amount of data and hence it consumes time, labor when compared with manual segmentation. Further, the manual segmentation requires a high level of expertise in neuro anatomy and sometimes it leads to human error. To produce more robust segmentation in medical images, this paper presents a Modified Robust Fuzzy c-Means with weight Bias Estimation method. Further to reduce the number of iteration of the proposed method, this paper initializes the initial centroids of clusters using dist-max initialization method.