Developing an Artificial Intelligence Model for Tumor Grading and Classification, Based on MRI Sequences of Human Brain Gliomas

Background: Artificial intelligence (AI) models provide advanced applications to many scientific areas, including the prediction of pathologic grade tumors, utilizing radiology techniques. Gliomas are among malignant brain tumors in human adults, and their efficient diagnosis is high clinical significance. Objectives: Given contribution AI medical diagnoses, we investigated role deep learning differential grading gliomas. Methods: This study developed a new diagnostic model, i.e., EfficientNetB0, classify gliomas, using sequences from magnetic resonance imaging (MRI). Results: We validated standard dataset (BraTS-2019) demonstrated that components, convolutional neural networks transfer learning, provided excellent performance for classifying glioma images at 98.8% accuracy. Conclusions: The proposed capable MRI accuracy, validity, specificity. It can better results than by previous studies.