Brain Tumor Classification Using Four Versions of EfficientNet

Abstract

Medical image processing approaches for detecting brain cancers are still primarily done manually, with low accuracy and taking a long period. Furthermore, this task can only be done by professionals with a high degree of medical competence, and the number of experts is obviously restricted in comparison to the large number of patients who need to be treated. With the growth of artificial intelligence and the rapid development of computers in terms of processing speed and storage capacity, it is feasible to assist doctors in classifying the existence of tumors in the head. This study employs four variations of the EfficientNet architecture to train a model on a variety of MRI imaging data. The model version B1 was shown to be the best in this investigation, with 98% accuracy, 99% precision, 95% recall, and 97% f1 score from versions B0 to B3 (4 versions). These results are excellent, but they do not rule out additional study utilizing various forms of design.