Development and Assessing a Competitive Deep Learning Framework forBrain Tumor classification Based on MRI Images

The objective of this study is to introduce a model with the same number of layers as AlexNet andZFNet models with less training data in order to be competitive in the development of automatedmedical image analysis and brain tumor classification using a set of brain MRI images. A total of۳۰۰۰ brain magnetic resonance (MR) images, both with and without tumor presence, were sourcedfrom the Kaggle site. This dataset was divided into ۲۴۰۰ images for training and ۶۰۰ for testing.The model, implemented using the Python programming language with TensorFlow and Keraslibraries, competes against AlexNet, ZFNet, and VGG۱۶. Performance was evaluated on the basisof several experimental criteria, including accuracy, recall, F۱ score, precision, area under thereceiver operating characteristic curve (AUC), and training time. A comparative analysis amongthe models was conducted based on these metrics. The proposed model demonstrated competitiveperformance, ranking after AlexNet and ZFNet but outperforming VGG۱۶. This study contributedto the evolution of efficient deep learning models for medical image analysis, particularly for braintumor classification

Keywords:

brain , tumor , deep learning , algorithm , classification