International Journal of Computational Engineering Research||Vol, 03||Issue, 8|| ||Issn 2250-3005 || ||August||2013|| Page 1 Image Fusion For Medical Image Retrieval Deepali Sale 1 , Dr. Madhuri Joshi 2 , Varsha Patil 3 Pallavi Sonare 4 ,Chaya Jadhav 5 1,3,4,5 Pad. Dr. D.Y. Patil Institute of Engineering and Technology, Pimpri, Pune, India 2 College of Engineering, Pune-411005, India I. INTRODUCTION In health care domain there are many research projects. The medical system is under many pressuring factors to offer the highest services, with efficiency, in the conditions of a growing population. To offer a real support for diagnosis, images have to be processed with different algorithms, for a better accuracy. A fusion based on transforms has some advantages over other simple methods, like: energy compaction, larger SNR, reduced features, etc. The transform coefficients are representative for image pixels. Clinical investigations are based more and more on medical imaging and physicians are faced very often with the difficulty of integrating the great amount of data. The specialists have to visualize and compare images from different medical modalities and to correlate the observed information with the clinical and auxiliary data. A fusion of multimodal images can be very useful for clinical applications such as diagnosis, modeling of the human body or treatment planning. Fusion of images taken at different resolutions, intensity and by different techniques helps physicians to extract the features that may not be normally visible in a single image by different modalities. The usage of fusion in radiotherapy and skull surgery. Here, the information provided by magnetic resonance imaging (MRI) and X-ray computed tomography (CT) is complementary. CT provides best information about denser tissue and MRI offers best information on soft tissue. Normal and pathological soft tissues are better visualized by MRI, while the structure of tissue bone is better visualized by CT. The composite image, not only provides salient information from both images simultaneously, but also reveals the relative position of soft tissue with respect to the bone structure. Fusion of images taken at different resolutions, intensity and by different techniques helps physicians to extract the features that may not be normally visible in a single image by different modalities. This work aims at the fusion of registered CT and MRI Images. ABSTRACT: In medical imaging, various modalities provide different features of the human body because they use different physical principles of imaging. CT and MRI images with high spatial resolution provide the anatomical details, while PET and SPECT show the biochemical and physiological information but their spatial resolutions are not good enough. So it is very useful and important to combine images from multi-modality scanning such that the resulting image can provide both functional and anatomical information with high spatial resolution. In this paper we present a wavelet-based image fusion algorithm. The images to be fused are firstly decomposed into high frequency and low frequency bands. We select four groups of images to simulate, and compare our simulation results with the pixel addition, weighted averaging method and wavelet method based on min-max and subtraction based fusion rule. Then, the low and high frequency components are combined by using different fusion rules. Finally, the fused image is constructed by inverse wavelet transform. The various objective and subjective evaluation metrics and Quality are calculated to compare the results. The wavelet based fusion methods using different fusion rules is compared both subjectively as well as objectively. The experimental results show that the pixel minimum method is giving the better results in respect of MSE, SNR and using edge based quality metrics addition method observed to be better in preserving the edge information. One Image fusion method can be perfect for one particular application but may not for another application. So it depends on which information to extract, enhance, and reconstruct or retrieve to use the particular fusion method. KEYWORDS: Computed Tomography (CT), DWT (Discrete Wavelet Transform), Image fusion, MRI (Magnetic Resonance imaging), Quality.