A Convolutional Neural Network with The VGG-16 Model for Classifying Human Brain Tumor

Brain cancer is one of the most dangerous diseases if it is not detected early. In recent years, AI technology has been increasingly applied in many different fields, including the medical field. For the purpose of supporting doctors in diagnosis and treatment, this paper proposes a Convolutional Neural Network (CNN) architecture with the VGG-16 model to classify brain tumors. In particular, adjusting the learning rate, sorting, and dividing the appropriate data sets are performed in the classification system to increase the classification performance. The experimental results of the classifier with the VGG-16 model gave an accuracy of 97.3%, with 3000 MRI images, in which there is 50% of the tumor images. For the accuracy evaluation, a confusion matrix is applied to illustrate the effectiveness of the proposed approach. This research can develop for the application to many types of different brain problems with a large number of images.