Medical imaging is the most challenging and emerging field today. MRI image processing is part of this field. The tumor is defined as the abnormal growth of tissues. The brain tumor is an abnormal mass of tissue in which cells grow and multiply uncontrollably, seemingly uncontrolled by the mechanisms that control normal cells. Brain tumors can be primary or metastatic, and either malignant or benign. A metastatic brain tumor is a cancer that has spread from the rest of the body to the brain. Epilepsy is a brain disorder in which groups of nerve cells, or neurons, in the brain sometimes signal abnormally. Neurons normally generate electrochemical impulses that act on other neurons, glands and muscles to produce thoughts, feelings and human actions. In epilepsy, the normal pattern of neuronal activity becomes disturbed, causing strange sensations, emotions and behavior or sometimes convulsions, muscle spasms and loss of consciousness.
The human brain is the most complex and mysterious part of the human body. Many complex functions are controlled by the brain. The brain image is a widely applicable method for diagnosing many brain abnormalities such as brain tumor, stroke, paralysis, etc. Magnetic resonance imaging (MRI) is one of the methods used for obtaining brain images. It is used to analyze the internal structures in detail. The brain tumor is an abnormal mass of tissue in which cells grow and multiply uncontrollably, seemingly uncontrolled by the mechanisms that control normal cells. The objective of this work is to extract the tumor region from the brain magnetic resonance image using the basin algorithm based on different combinations of characteristics such as color, border, orientation and texture. The results are compared to the truth images of the terrain. Here we used the basin-based marker algorithm to extract the tumor region and the Dice and Tanimoto coefficients were used to compare the results. The method proposed here is found to be producing a promising result.
A classification of the brain into the healthy brain or a brain having a tumor is done first which is then followed by further classification into begnin or malignant tumor. The algorithm incorporates steps for preprocessing, segmentation of images, extraction of characteristics and classification of images using techniques of neural networks. Finally, the tumor area is specified by technique region of interest as the confirmation step. An easy-to-use Matlab GUI program has been built to test the proposed algorithm.