Ahmed-Selem/Shifaa-Breast-Cancer-UNet-Segmentation

Breast Cancer Segmentation Model

Model Information:

• Architecture: U-Net
• Task: Binary segmentation of breast cancer regions
• Dataset: Breast Cancer Segmentation Dataset
• Input Size: 224×224 RGB images

Performance Metrics:

• Best Dice Score: 0.9179

Usage:

from shifaa.vision import VisionModelFactory

model = VisionModelFactory.create_model(
    model_type="segmentation",
    model_name="Breast_Cancer"
)

results = model.run("breast_scan.png", show_image=True)
image = results["image"]
mask = results["predicted_mask"]

Sample Results:

Architecture Details:

• Custom U-Net with 4 encoder/decoder blocks
• Skip connections for detail preservation
• Sigmoid output for binary masks

Preprocessing:

• Random horizontal flip
• Random rotation ±15°
• Random brightness & contrast adjustment
• Normalize and convert to tensor

Training Details:

• Loss Function: Combined Dice Loss + BCE Loss
• Optimizer: Adam (lr=0.001, weight_decay=1e-5)
• Batch Size: 8
• Epochs: 100 (with early stopping)

---