Performance Analysis of Hybrid Optimization Technique for Segmentation of Medical Images Yogesh S. Bahendwar Dr. R.H.Talwekar Research Scholar Supervisor Electronics & Telecommunication dept. Electronics & Telecommunication dept. Shri Shankaracharya Techincal Campus Government Engineering College, Shri Shankaracharya Engineering College Raipur, India Bhilai, India bahendwar72@gmail.com ursk.talwekar@gmail.com Abstract:- Imaging studies in medical field are crucial in diagnosing various diseases viz. lung cancer, breast cancer, brain tumor etc. In medical field radio graphic imaging is primarily used to differentiate normal and abnormal tissues. Image segmentation plays a vital role in medical research. Digital mammography, computed tomography(CT),magnetic resonance imaging (MRI), X-ray imaging and other modalities provide an effective solution in mapping the anatomy non invasively of the subject. Wide variety of these imaging technologies greatly increased the knowledge of abnormal and normal tissues for medical research and became critically important component in disease diagnosis and treatment. MRF (Markov Random Field) is widely accepted method in segmenting medical images. This paper proposes a Hybrid approach by combining meta heuristic algorithm ACO (Ant Colony Optimization) and HMRF (Hidden Markov Random Field) method for segmentation of X-ray, CT , MRI images and presented its performance analysis. In this paper section – 1 reveal about medical image processing and segmentation, the related work done by various researchers is discussed in section -2, section -3 discuses the proposed approach. Section-4 and section-5 reveal about experimental result and conclusion along with the reference. Keywords—HMRF;MR;MRF;FM; MAP;ACO;EM. I INTRODUCTION: In digital images, abnormal tissue segmentation is a vital task. Use of CAD(Computer Aided Diagnosis) system in identification of different tissues and pathologies are more accurate and clear. While analyzing objects in images, distinguishing object of interest from background is necessary which can be achieved through segmentation, Segmentation of medical image is one of the most promising issues in image processing domain having reach focus of research in past few years. The aim of segmentation of image is to disjoint/ fragment in to series of regions, depending on attribute of image which are almost constant in every region but prominently differ from one region to another. Extracting useful information in medical image analysis, also referred to as segmentation Beginning with Roentgen Rays (X-rays), in medical imaging various modalities are introduced over the past years. Each having their own advantages and disadvantages viz. Ultrasound (US), Magnetic Resonance Imaging (MRI), Computed Tomography (CT), Nuclear Imaging Single Photon Emission Computed Tomography (SPECT) and Position Emission Tomography (PET).The main purpose of mentioning the anatomical localization from the International Journal of Computer Science and Information Security (IJCSIS), Vol. 15, No. 1, January 2017 39 https://sites.google.com/site/ijcsis/ ISSN 1947-5500