Brain Tumor Detection Using Convolution Neural Networks

ABSTRACT Early diagnosis of brain tumors is important for improving patient prognoses; however, traditional diagnostic methods like biopsies require invasive surgical procedures. In this paper, we introduce two deep learning-based methods—a new two-dimensional Convolutional Neural Network (CNN) and a convolutional auto-encoder network—that enable the accurate classification of brain tumors from magnetic resonance imaging (MRI). A data set of 7,000 T1-weighted contrast-enhanced MRI images was utilized, including glioma, meningioma, pituitary gland tumor, and normal brain samples. Preprocessing and augmentation procedures were carried out on the data set in order to enhance the generalization ability of the models. The suggested architecture of the 2D CNN includes eight convolutional layers, four pooling layers, and utilizes batch normalization with a uniform 2×2 kernel across the network. The auto-encoder architecture combines feature extraction and classification by utilizing the last output of the encoder. Experimental results show that the 2D CNN achieved a training accuracy of 96.47% with an average recall of 95%, showing good performance and efficiency in computation. The simplicity and effectiveness of the proposed CNN make it a promising tool for real-time clinical applications, offering a non-surgical and highly reliable tool for the assistance of radiologists in the diagnosis of brain tumors.