Performance Evaluation of Hmsk and Sqfd Algorithms for Computer Tomography (ct) Image Segmentation of Effective Radiotherapy

Medical Image segmentation plays a significant role in many medical image processing for effective diagnosis. Manual segmentation of medical image by the radiologist is not only a tiresome and time consuming process, also not a very accurate with the increasing medical imaging modalities and unmanageable quantity of medical images. Therefore it is essential to examine current methodologies of image segmentation. Enormous research has been done in medical image segmentation, but it is still difficult to evaluate all the medical images. However the problem remains challenging, with no general and unique solution. In this paper, we present a HMSK (Hybrid Medoid shift and K-Means) algorithm and Signature Quadratic form distance (SQFD) algorithm for Computer tomography image segmentation. The performance of the two algorithms is investigated. Experimental results with real patient images indicate the SQFD algorithm is effective and efficient and reduce the number of fragments. Their pros and cons were analyzed and proposed SQFD algorithm for slices of CT images to give effective radiation therapy.