Add 2nd pass models

README.md

@@ -11,18 +11,19 @@ metrics:
 
 # Knee Bone & Cartilage Segmentation Models
 
-This repository contains trained models for 3D MRI Knee Bone and Cartilage Segmentation using the `kneeseg` Python package.
+This repository contains trained models for 3D MRI Knee Bone and Cartilage Segmentation on the SKI10 dataset, using the `kneeseg` Python package.
 
 ## Model Details
-- **Architecture**: Dense Random Forest with Auto-Context (2 Passes for Bones, 1 Pass for Cartilage).
+
+- **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.
 - **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**: ~0.916 DSC (+1.2%)
-  - **Tibia Bone**: ~0.939 DSC (+1.0%)
-  - **Femoral Cartilage**: ~0.622 DSC (+2.8%)
-  - **Tibial Cartilage**: ~0.616 DSC (+3.5%)
+  - **Femur Bone**: 0.9155 DSC (+/- 0.0303)
+  - **Tibia Bone**: 0.9383 DSC (+/- 0.0194)
+  - **Femoral Cartilage**: 0.7095 DSC (+/- 0.0478)
+  - **Tibial Cartilage**: 0.6799 DSC (+/- 0.0429)
 
 ## Usage
 These models are designed to be used with the `kneeseg` library.
@@ -47,8 +48,8 @@ bone_p1.load("bone_rf_p1.joblib")
 ## Files
 - `bone_rf_p1.joblib`: Bone Segmentation Pass 1 (Voxel Classifier)
 - `bone_rf_p2.joblib`: Bone Segmentation Pass 2 (Auto-Context Refinement)
-- `cartilage_rf.joblib`: Cartilage Segmentation (Semantic Context Forest)
-- `TestData_labels/`: Contains segmentation masks for the SKI10 Test Data (50 cases), generated using these models.
+- `cartilage_rf_p1.joblib`: Cartilage Segmentation Pass 1 (Semantic Context Forest)
+- `cartilage_rf_p2.joblib`: Cartilage Segmentation Pass 2 (Auto-Context Refinement)
 
 ## Citation
 

bone_rf_p1.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5e4c468262beee76751d01d72e0ab62ef952f39f2e45873fa926b6ee2d3df0
-size 3210389441
+oid sha256:538d814808049d1ad5583b1d607ce70b8b91573a946863b9cb0a5517dfcdb38e
+size 3704942225

bone_rf_p2.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c52e33783035bdac1c0c5431b6f122233c06dd5c47a625528ed3e4575c0f28
-size 538649777
+oid sha256:ad6a21b4e64f4ba89cdfee15cd886f630969ae2b47f9d4a877903577c6579e28
+size 734223089

cartilage_rf.joblib → cartilage_rf_p1.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3ffe79c33bb4042db51bcdfdf5dfecc901795afb6a42c6a5340edccc5dffcb
-size 827343265
+oid sha256:bacf70cba4f8c6a7932b7f516656d8f80c8e05d8d4b02632b0728faf64491703
+size 923730257

cartilage_rf_p2.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6562cb124a6191401e6cf49c8becff1f4ee66f8642813315625a3208f5b36e
+size 305168625