LITERATURE SURVEY FOR 3D RECONSTRUCTION OF BRAIN MRI IMAGES

Megha Borse, S.B. Patil, B.S.Patil

Abstract: Since Doctors had only the 2D Image Data to visualize the tumors in the MRI images, which never gave the actual feel of how the tumor would exactly look like . The doctors were deprived from the exact visualization of the tumor the amount of the tumor to be removed by operation was not known, which caused a lot of deformation in the faces and structure of the patients face or skull. The diversity and complexity of tumor cells makes it very challenging to visualize tumor present in magnetic resonance image (MRI) data. Hence to visualize the tumor properly 2D MRI image has to be converted to 3D image. With the development of computer image processing technology, three-dimensional (3D) visualization has become an important method of the medical diagnose, it offers abundant and accurate information for medical experts. Three-dimensional (3-D) reconstruction of medical images is widely applied to tumor localization; surgical planning and brain electromagnetic field computation etc. The brain MR images have unique characteristics, i.e., very complicated changes of the gray-scales and highly irregular boundaries. Traditional 3-D reconstruction algorithms are challenged in solving this problem. Many reconstruction algorithms, such as marching cubes and dividing cubes, need to establish the topological relationship between the slices of images. The results of these traditional approaches vary depending on the number of input sections, their positions, the shape of the original body and the applied interpolation technique. These make the task tedious and time-consuming. Moreover, satisfied reconstruction result may not even be obtained when the highly irregular objects such as the encephalic tissues are considered. Due to complexity and irregularity of each encephalic tissue boundary, threedimensional (3D) reconstruction for MRI image is necessary. A Literature survey is done to study different methods of 3D reconstruction of brain images from MRI images

Keywords: 3-D reconstruction, region growing, segmentation method, immune algorithm (IA), one class support vector machine (OCSVM) and sphere shaped support vector machine (SSSVM)

DOI: https://doi.org/10.15623/ijret.2013.0211112