An Efficient Hybrid Segmentation Algorithm for Computer Tomography Image Segmentation

Abstract

Medical Image segmentation plays a major role in medical image processing. During last decades, developing robust and efficient algorithms for medical image segmentation has been a demanding area of growing research interest. Extensive research has been done in creating many different approaches and algorithms for image segmentation, but it is still difficult to assess whether one algorithm produces more accurate segmentations than the other. The proposed method utilizes clustering with distance based segmentation approach for Computer tomography image segmentation. This paper provides new hybrid segmentation method based on K-Means, Medoid shift and Signature Quadratic Form Distance algorithm for computer tomography images. We validate the Hybrid segmentation approach with the parameters in terms of sensitivity, specificity, accuracy and number of fragments. The Real time dataset is used to evaluate the performance of the proposed method. The results obtained from the experimentation show that the proposed approach attains reliable segmentation accuracy and also clear that it is more efficient, robust and more appropriate for organ classification.