Automatic Medical Image Segmentation Based On Finite Skew Gaussian Mixture Model

Nagesh Vadaparthi¹, Srinivas Y², SureshVarma P³, Sitharama Raju P⁴

¹Department of I.T, MVGR College of Engineering, Vizianagaram, India.

²Department of I.T., GIT, GITAM University, Visakhapatnam. India.

³Dept. of Computer Science, Adikavi Nannayya University, Rajahmundry, India

⁴Department of CSE, MVGR College of Engineering, Vizianagaram, India.

 Abstract: A novel methodology for segmenting the brain MRI images using the finite skew Gaussian mixture model has been proposed for improving the effectiveness of the segmentation process. This model includes Gaussian mixture model as a limiting case and we believe does more effective segmentation of both symmetric and asymmetric nature of brain tissues as compared to the existing models. The segmentation is carried out by identifying the initial parameters and utilizing the EM algorithm for fine tuning the parameters. For effective segmentation, hierarchical clustering technique is utilized. The proposed model has been evaluated on the brain images extracted from the brainweb image database using8sub-images of 2 brain images. The segmentation evaluation is carried out using objective evaluation criterion viz. Jacquard Coefficient (JC) and Volumetric Similarity (VS). The performance evaluation of reconstructed images is carried out using image quality metrics. The experimentation is carried out using T₁ weighted images and the results are presented. We infer from the results that the proposed model achieves good segmentation results when used in brain image processing.

Keywords: Segmentation, Skew Gaussian Mixture Model, Objective Evaluation, Image Quality Metrics, EM algorithm.

Full Text