---
license: mit
metrics:
- accuracy
pipeline_tag: image-classification
tags:
- medical
- biology
---
COVID-19 Chest X-ray Model

**Model Information:**
- **Architecture:** ResNet50
- **Task:** Multi-class classification (4 conditions)
- **Dataset:** [COVID-19 Radiography Database](https://www.kaggle.com/datasets/tawsifurrahman/covid19-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:**
```python
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:**

![Confusion Matrix](./Chest_CM.png)

**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

---