Create README.md

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+language:
+  - en
+pipeline_tag: image-segmentation
+tags:
+  - unet
+  - segmentation
+  - medical-imaging
+  - covid19
+  - ct-scans
+---
+
+# 🩺 UNet Model for COVID-19 CT Scan Segmentation
+
+## 📌 Model Overview
+This UNet-based segmentation model is designed for **automated segmentation of COVID-19 infected lung regions** in **CT scans**. It enhances the classic **U-Net** with **attention mechanisms** to improve focus on infected regions.
+
+- **Architecture:** UNet + Attention Gates
+- **Dataset:** COVID-19 CT scans from **Coronacases.org, Radiopaedia.org, and Zenodo Repository**
+- **Task:** Image Segmentation (Lung Infection)
+- **Metrics:** Dice Coefficient, IoU, Hausdorff Distance, ASSD
+
+---
+
+## 📊 Training Details
+- **Dataset Size:** 20 CT scans (512 × 512 × 301 slices)
+- **Preprocessing:**
+  - Normalization of pixel intensities `[0,1]`
+  - HU Thresholding: `[-1000, 1500]`
+  - Image resizing to `128 × 128 pixels`
+  - Binarization of masks (0 = background, 1 = infected regions)
+- **Augmentation:**
+  - **Rotations**: ±5 degrees
+  - **Elastic transformations, Gaussian blur**
+  - **Brightness/contrast variations**
+  - Final dataset: **2,252 CT slices**
+- **Training:**
+  - **Optimizer:** Adam (`learning rate = 1e-4`)
+  - **Loss Function:** Weighted BCE-Dice Loss + Surface Loss
+  - **Batch Size:** 16
+  - **Epochs:** 25
+  - **Training Platform:** NVIDIA Tesla T4 (Google Colab Pro)
+
+---
+
+## 🚀 Model Performance
+| Metric                     | Non-Augmented Model | Augmented Model |
+|----------------------------|---------------------|-----------------|
+| **Dice Coefficient**       | 0.8502              | **0.8658**      |
+| **IoU (Mean)**             | 0.7445              | **0.8316**      |
+| **ASSD (Symmetric Distance)** | 0.3907          | **0.3888**      |
+| **Hausdorff Distance**      | 8.4853              | **9.8995**      |
+| **ROC AUC Score**          | 0.91                | **1.00**        |
+
+📌 **Key Findings:**  
+✔ **Augmentation improved segmentation accuracy significantly**  
+✔ **Attention U-Net outperformed other segmentation models**
+
+---
+
+## 📥 **How to Use the Model**
+### **1️⃣ Load the Model**
+#### **TensorFlow/Keras**
+```python
+from huggingface_hub import hf_hub_download
+from tensorflow.keras.models import load_model
+
+model_path = hf_hub_download(repo_id="amal90888/unet-segmentation-model", filename="unet_model.keras")
+unet = load_model(model_path)