Efficient detection of Brain Tumor in MRI using Non Intelligent based techniques

Brain Tumor is a fatal disease which cannot be confidently determined without MRI. Earlier detection, diagnosis and proper treatment of brain tumor are essential to prevent health. Abnormal cell growth leads to a tumor are essential to prevent human death. An effective brain tumor 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 like thresholding, region growing, water sheds and contours. The drawbacks of previous methods can be overcome through proposed method. To extract the information regarding tumor, at first in the pre-processing level, the image was filtered using Anisotropic Diffusion filter to remove noise and then the extra parts which are outside the skull and the area that does not have any helpful information are removed. After that a difference image is found to highlight the tumor. Then the image is resized and the image was converted to a threshold image. On this semi processed image morphological operations have been applied and information on solidity and areas of the plausible locations was determined. Then it was used to detect the tumor. 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 tumor