A Convolutional Neural Network for Automatic Brain Tumor Detection

Magnetic resonance imaging (MRI) combined with artificial intelligence (AI) algorithms to detect brain tumors is one of the important medical applications. In this study, a Convolutional neural network (CNN) model proposed meningioma and pituitary, which was tested dataset consisting two categories 1,800 MRI images from several persons. The CNN trained via Python library, namely TensorFlow, an automatic tuning approach obtain highest testing accuracy tumor detection. used programming language in Google Colab sensitivity, precision, area under PR receiver operating characteristic (ROC), error matrix, accuracy. results show that has high performance detection tumors. It achieves 95.78% weighted average precision 95.82%.