Ahmed Emad El-Din Fakhry <br/><br/>
Medical Image Registration Using Modified Mutual Information And Partical Swarm Optimization / 
 مطابقة الصور بإستخدام المعلومات المتبادلة و امثلة أسراب الجسيمات . 
Submitted By :Ahmed Emad El-Din Fakhry ; Supervised By Prof.Essam Hamed Atta , Prof.Ibraheem El-Emam. 
 - [Cairo ] ;  [Arab Academy For Sciemce And Technology & Maritime Transport] ;  2014. 
 - 68 P ;  Ill ;  30 Cm +  CD. 
<br/><br/> Faculty Of Computer science. 
<br/><br/>A Thesis Submitted to The Collegy Of Computing & Information Technology In Partial Fulifillment Of The Requirements For The Award O Degree Of MASTER Of Science In Computer science 
<br/><br/>Includes Bibliographic Referances.P 62 : 68. 
<br/><br/> an important aspect in medical image analysis, and is used in a variety of medical applications. Examples include diagnosis, pre/post surgery guidance, comparing/merging/integrating images from different modalities such as Magnetic Resonance Imaging (MRI), and Computed Tomography (CT). Whether registering images across modalities for a single patient or registering across patients for a single modality, registration is an effective way to combine information from different images into a normalized frame of reference. Registered datasets can be used to provide information about the structure, function, and pathology of the organ or individual being imaged.<br/>  In this thesis a hybrid approach for medical images registration is developed. It employs a modified Mutual Information (MI) as a similarity metric and Particle Swarm Optimization (PSO) method. Computation of mutual information is modified by using a weighted linear combination of image intensity and image gradient vector flow (GVF) intensity. In this manner, statistical as well as spatial image information is included into the image registration process. Maximization of the modified mutual information is implemented by using the versatile Particle Swarm Optimization which is easy to implement and contains few parameters to adjust.<br/>The developed approach has been tested and verified successfully on a number of medical image data sets that include images with missing parts, noise contamination, and/or of different modalities (CT, MRI). The registration results indicate that the proposed approach is accurate and effective, and show that the inclusion of both statistical and spatial image data improves the registration results obtained using only image intensity data. 
<br/><br/>
<br/><br/><br/>Includes Abstract in Arabic 
<br/><br/><label>Subjects--Topical Terms: </label><br/>Medical Image <br/>Computing & Information Technology ---Computer Science
<br/><br/><label>Dewey Class. No.: </label>004.67  / A M