An Employment of Probabilistic Neural Network in Magnetic Resonance Imaging For Early Brain Cancer Detection

Given the circumstances of countries in which wars, political instability, and other uncertainties are passing that make atmosphere impure, have caused many diseases, one these diseases has spread widely is cancer. Cancer a very common disease, them affect person lead him or her to death. Among been recent years specifically brain tumors they need early diagnosis do not cause death person. Furthermore, studies field cancer detection done, but best solution still missing. Therefore, this paper, reliable method proposed detect tumors, extract its properties, classify tumor using Magnetic Resonance Imaging (MRI) through artificial neural network. In system, an essential part image processing analysis digital images, especially improve their quality, Bilateral Filter used improving clarity any noise preserves edges. After that, distinctive properties extracted Histogram Oriented Gradient (HOG) method. Thus, features strong can be classified as Probabilistic Neural Network (PNN), what distinguishes our work from previous works. The advantage obtained granted PNN Classifier, train test accuracy performance perceiving location tumour MRI images it resolves 99.5%.