Automatic segmentation of brain tumor in mr images

Abnormal cell growth leads to tumour in the brain cells. Earlier detection,
diagnosis and proper treatment of brain tumour are essential to prevent human death.
An effective brain tumour segmentation of MR image is an essential task in medical
field. Extracting or grouping of pixels in an image based on intensity values is called
segmentation. Image segmentation can be achieved in different ways those are
thresholding, region growing, water sheds and contours. The drawbacks of previous
methods can be overcome through proposed method. To extract information regarding
tumour, at first in the pre-processing level, the extra parts which are outside the skull
and don't have any helpful information are removed and then anisotropic diffusion
filter is applied to the MRI images to remove noise. By applying the fast bounding
box (FBB) algorithm, the tumour area is displayed on the MRI image with a bounding
box and the central part is selected as sample points for training of a One Class SVM
classifier. Then Support Vector Machine classifies the boundary and extracts the
tumour. This method can be implemented by MATLAB. Experimental results show
high precision and dependability of the proposed algorithm. The results are also
highly helpful for specialists and radiologists to easily estimate the size and position
of a tumour.