Update README.md

README.md

@@ -11,15 +11,19 @@ metrics:
 
 # Knee Bone & Cartilage Segmentation Models
 
-This repository contains trained models for 3D MRI Knee Bone and Cartilage Segmentation on the SKI10 dataset, using the `kneeseg` Python package.
+This repository contains trained models for 3D MRI Knee Bone and Cartilage Segmentation on the [SKI10 dataset](https://ski10.grand-challenge.org/), using the `kneeseg` Python package.
+
+- GitHub: https://github.com/wq2012/kneeseg
+- PyPI: https://pypi.org/project/kneeseg/
 
 ## Model Details
 
 - **Architecture**: Dense Random Forest with Auto-Context (2 Passes for Bones, 2 Passes for Cartilage).
-- **Dataset**: Trained on all **100 cases** from the `SKI10/TrainingData` folder.
+- **Dataset**:
+  - **Training**: The models are trained on all **100 cases** from the `SKI10/TrainingData` folder.
+  - **Evaluation**: The evaluations are performed on a subset of 20 cases of `SKI10/TrainingData`. Note that in this setup, the 20 evaluation cases are **included** in the training set, so there is train-eval overlap. For a non-overlap eval, see [GitHub](https://github.com/wq2012/kneeseg) for a 80%-20% split experiment.
+  - **Inference**: We have included the predicted labels for the 50 official **SKI10 TestData** cases in the `TestData_labels/` directory. These were generated using the fully trained models but were **not evaluated** due to the lack of ground truth.
 - **Performance** (evaluated on a subset of 20 cases):
-  > **Note**: These 20 cases are **included** in the training set (overlap). We evaluate on them because the official `SKI10/TestData` (50 cases) does not have public ground truth labels.
-  > **Test Data**: We have included the predicted labels for the 50 official **SKI10 TestData** cases in the `TestData_labels/` directory. These were generated using the fully trained models but were **not evaluated** due to the lack of ground truth.
   - **Femur Bone**: 0.9155 DSC (+/- 0.0303)
   - **Tibia Bone**: 0.9383 DSC (+/- 0.0194)
   - **Femoral Cartilage**: 0.7095 DSC (+/- 0.0478)
@@ -50,6 +54,7 @@ bone_p1.load("bone_rf_p1.joblib")
 - `bone_rf_p2.joblib`: Bone Segmentation Pass 2 (Auto-Context Refinement)
 - `cartilage_rf_p1.joblib`: Cartilage Segmentation Pass 1 (Semantic Context Forest)
 - `cartilage_rf_p2.joblib`: Cartilage Segmentation Pass 2 (Auto-Context Refinement)
+- `TestData_labels`: Predicted labels of the SKI10 official TestData using our models.
 
 ## Citation