Ahmed-Selem/Shifaa-COVID-Chest-Xray-ResNet50

COVID-19 Chest X-ray Model

Model Information:

• Architecture: ResNet50
• Task: Multi-class classification (4 conditions)
• Dataset: COVID-19 Radiography Database
• Input Size: 224×224 RGB images

Classes:

1. COVID
2. Lung_Opacity
3. Normal
4. Viral Pneumonia

Performance Metrics:

• Accuracy: 91.6%
• Precision: 0.92
• Recall: 0.91
• F1-Score: 0.91

Usage:

from shifaa.vision import VisionModelFactory

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

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

Confusion Matrix:

Preprocessing:

• Resize to 224×224
• Random horizontal flip
• Random rotation ±10°
• Color jitter (brightness & contrast)
• ImageNet normalization

Training Details:

• Loss Function: CrossEntropyLoss (with class weights)
• Optimizer: Adam (lr=0.0005)
• Epochs: 30
• Batch Size: 32

---