Brain Tumour Detection Using Deep Learning Techniques

In recent years the occurrence of brain tumor has exaggerated in large amount among the people. Gliomas are one of the most common types of primary brain tumors that represent 30% of all human brain tumors and 80% of all malevolent tumors. The grading system specified by the World Health Organization (WHO) is deployed as a standard mechanism for medical diagnosis, prognosis, and the existence forecast so far. The main ideology of this paper is to propose and develop reliable and typical methods to detect the brain tumor, extract the characteristic of it and classify the glioma using Magnetic Resonance Imaging (MRI). The developed model helps in the detection of brain tumor automatically and it is implemented using image processing and artificial neural network. The most basic part of image processing is the analysis and manipulation of a digitized image, especially in order to improve its quality. In this proposed system, the Histogram Equalization (HE) technique is used to improve the contrast of the original image. Then the pre-processed image is subjected to feature extraction using Gray Level Co-occurrence Matrix (GLCM). The obtained feature is given to Probabilistic Neural Network (PNN) classifier that is used to train and test the performance accuracy in the perception of tumor location in brain MRI images. By implementing this approach, PNN classifier has procured accuracy of about 90.9%.