MRI brain tumors images by using independent component analysis

Abstract

The magnetic properties of nuclei have significant applications in medical imaging. These applications are possible because the relaxation properties and the resonance frequency for a nucleus depend upon its environment. Factors such as the presence of chemical bonds, paramagnetic ions and the rate of flow of fluids influence the magnetic resonance (MR) signal. Therefore, different regions of a biological sample produce different MR signals for the given imaging parameters. While the reasons for these differences are often so complex that interpretation is difficult, their existence yields an intrinsic subject contrast between tissues. It is possible to capture several images by changing imaging conditions with different contrasting between the tissues. Independent component analysis (ICA) applied to images provides identification of tissues with the similar response in different imaging conditions. In order to identify tumor regions we have used correlation between symmetrical brain regions and image segmentation based on pixel brightness.