Tissue characterization of brain using MRI

Abstract

In the evaluation of healthcare services, there is an increasing need for effective use of imaging data in medical diagnosis, the analysis and study of the brain is of great interest due to its potential for studying early growth tumor which is an abnormal mass of tissue found in the brain. The purpose of the project is to characterize an abnormal tissue of brain MRI Imaging, especially the brain tumor. For that, we have firstly used different methods of segmentation which are thresholding, K-means and fuzzy K-means in order to extract the tumor, secondly 3D reconstruction of the tumor has been involved by applying the pre-processing and post-processing steps to get the better image’s results which are inputted as a 2D parallel slices in the marching cube algorithm to form a 3D tumor’s volume. After that the texture analysis is presented as a useful computational method for discriminating between pathologically different regions on medical images because it has been proven to perform better than human eyesight at discriminating certain classes of texture. Finally, an experimental part has been done on where the results of the extraction’s segmentation and texture analysis are discussed, in addition 3D reconstruction is implemented.