Brain-Tumor-MRI-Classification-Using-Deep-Learning

Overview

This project presents a comparative evaluation of deep learning models for multiclass brain tumor classification using MRI images.

The study compares:

• Custom CNN
• VGG16
• ResNet50
• EfficientNetB0

using the Brain Tumor MRI Dataset from Kaggle.

Dataset

Brain Tumor MRI Dataset: https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset

Technologies

• Python
• TensorFlow
• Keras
• Google Colab
• NumPy
• Matplotlib
• Scikit-learn

Evaluation Metrics

• Accuracy
• Precision
• Recall
• F1-score
• ROC-AUC
• Confusion Matrix

Best Model

VGG16 achieved the best performance with a test accuracy of 91.19%.

Author

Amantle Maakelo