Answers are grounded in this paper and cite their sources.
Comparative analysis shows EfficientNetV2 enhances brain tumor classification accuracy using MRI data.
Identifying and classifying brain tumors play a pivotal role in gaining insights into their underlying mechanisms. In contemporary medical practice, the integration of Computer-assisted Diagnosis (CAD) and machine learning, particularly deep learning, has significantly enhanced the radiologist's ability to accurately identify brain tumors. Unlike traditional machine learning methods, which often rely on manual feature engineering for classification, deep learning models can be structured to prevent the need for manual feature extraction, yielding highly accurate classification outcomes. This paper customizes advanced deep learning models including VGG19, ResNet50, InceptionV3, and EfficientNetV2 as the most powerful deep learning models aimed at the identification of both binary (normal and abnormal) and multiclass: 17 classes including Glioma, Meningioma, Neurocytoma, and other types of injuries such as Abscesses and Cysts. We utilize a publicly available dataset containing 4449 MRI images. Subsequently, we conduct a comprehensive comparative analysis of our proposed models against existing models in the literature. Our experimental findings indicates that EfficientNetV2 outperforms other state-of-the-art deep-learning models.
No takes yet. Share an insight, caveat, or question.
Golkarieh et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: