Brain Tumor Extraction Using Matlab

Abstract

The brain is the most crucial part of our human body which acts as central coordinating system for all the controlling and all regular functions of our body. The continuous growth of abnormal cells which creates certain mass of tissue is called as tumor. Tumor in the brain can be either formed inside the brain or gets into brain after formed at other part. But there is no clear information regarding the formation of brain tumor till date. Though the formation tumor in brain is not common or regular but the mortality rate of the infected people is very high because the brain is major part of body. So, it is very important get the treatment at the early stages of brain tumor but there is no direct procedure for detection and classification of tumor in the very first step of diagnosis. In actual medical diagnosis, mri images alone can’t be able to determine the detected tumor as either the cancerous or non-cancerous. But the tumor may be sometimes danger to life or may not be danger to life. Tumor inside the brain can be of either the benign(non- cancerous) or the malignant(cancerous). So, we need to detect the tumor from the MRI images through image processing and then to classify the detected tumor as it belongs to either the benign or malignant tumor. We are going to get the brain mri images as our dataset for our proposed method but the images we got may have the noise. So, we need to preprocess the image using the image preprocessing techniques. We are going to use several algorithms like thresholding, clustering to make the detection of tumor by using the image processing and image segmentation and after the detection of tumor we are going do feature extraction. This step involves the extraction of detected objects features using DWT. This extracted features are given as input to classifier algorithms like SVM’s and CNN after reduction of features using the PCA.