Ahmed-Selem/Shifaa-Brain-Tumor-ResNet18

Brain Tumor Model

Model Information:

• Architecture: ResNet18
• Task: Multi-class classification (4 tumor types)
• Dataset: Brain Tumor MRI Dataset
• Input Size: 224×224 RGB images

Classes:

1. Glioma
2. Meningioma
3. Pituitary
4. No Tumor

Performance Metrics:

• Accuracy: 98.55%
• Precision: 0.9861
• Recall: 0.9855
• F1-Score: 0.9856

Usage:

from shifaa.vision import VisionModelFactory

model = VisionModelFactory.create_model(
    model_type="classification",
    model_name="Brain_Tumor"
)

result = model.run("brain_mri.jpg", show_image=True)
print(f"Tumor Type: {result['predicted_class']}")
print(f"Confidence: {result['confidence']:.2f}%")

Confusion Matrix:

Preprocessing:

• Resize to 224×224
• Random horizontal flip
• Random rotation ±10°
• ImageNet normalization

Training Details:

• Loss Function: CrossEntropyLoss
• Optimizer: Adam (lr=0.001)
• Epochs: 30
• Batch Size: 64

---