BRAIN TUMOR IDENTIFICATION AND ANALYSIS USING FEED FORWARD NEURAL NETWORK METHOD IN MAGNETIC RESONANCE BRAIN IMAGES

Considered the automatic classification of medical images critically and high-resolution analysis and high accurate in the diagnosis of disease and medical interpretation, we proposed in this paper feed forward neural network (supervised method) using segmentation in magnetic resonance brain images in order to identify the region of the tumor and analysis the performance of the method. The advantages of this method give excellent performance and excellent results in terms of accuracy detection, Sensitivity, mean square error (MSE), error histogram, dice overlap index (DOI), specificity, this is confirmed trough the results obtained in this paper.