Automatic Detection of Brain tumor using Deep Learning Algorithms

Brain tumor is an abnormal growth of cells which reproduce themselves in an uncontrolled manner. It is diagnosed through Magnetic Resonance Imaging (MRI) which plays an important role in segmenting a tumor region into different ways for surgical and medical planning assessments. But, manual detection may lead to errors, and it is a time-consuming process. To overcome the problem, experts use various algorithms for automatic detection of the tumor region which are based on Deep learning algorithms. They are designed to train and tune millions of images within a short period of time. Further, this paper proposes different types of classification methods with a number of iterations based on CNN architectures such as VggNet, GoogleNet and ResNet 50. For 60 iterations VggNet reports that 89.33% accuracy, GoogleNet 93.45% and ResNet 50 96.50%. Finally, it is proved that ResNet 50 achieves better results than VggNet and GoogleNet do in quicker time and with better accuracy.