Image segmentation is a process of dividing an image into sub-parts for further analysis. This technique plays an important role in the field of image processing. The aim of this technique is to make the representation of image into precise form and easy to study. Currently there are different techniques for image segmentation. Every technique have its own advantages and disadvantages. Usually segmentation is performed by traditional techniques like thresholding, and edge-based. However, it is liable to some limitations which include sampling artifacts and noise. To remove these artifacts, noise and extra boundaries some post processing is required. The main goal of this research is to examine different techniques of image segmentation and to identify the limitations of traditional image segmentation techniques and to highlight the strengths of new segmentation technique that is Deformable Model in the field of medical imaging by comparing their results. Comparison is done on the basis of mean square error (MSE) and peak signal to noise ratio (PSNR) on different types of medical images like MRI, Heart CT etc. Furthermore, our work addresses the open problems and provides the perspective of the future work for comprehension of automated diagnosis of other diseases.