Restore deleted unit test: test_brain_image_synthesis_latent_diffusion_model.py

Author: Foxconn-bgroup-aidd

ci/unit_tests/test_brain_image_synthesis_latent_diffusion_model.py

@@ -83,4 +83,4 @@ def test_infer_config(self, override):
 if __name__ == "__main__":
     loader = unittest.TestLoader()
     loader.sortTestMethodsUsing = test_order
-    unittest.main(testLoader=loader)
+    unittest.main(testLoader=loader)

ci/unit_tests/test_coronaryArtery_ct_segmentation.py

@@ -20,4 +20,27 @@
   "network_def": {},
 
   "run": ["[email protected]()"]
+    "imports": [
+        "$import glob"
+    ],
+    "bundle_root": ".",
+    "ckpt_dir": "$@bundle_root + '/models'",
+    "dataset_dir": "",
+    "data": "$list(sorted(glob.glob(@dataset_dir + '/*.nii.gz')))",
+    "output_ext": ".usd",
+    "output_dir": "$@bundle_root + '/Output'",
+    "device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')",
+    "inferer": {
+        "_target_": "scripts.heart_digital_twin.CoroSegmentator_Pipeline",
+        "input_params": {
+            "inputFile": "$@data[0]",
+            "outputDir": "$@output_dir"
+        }
+    },
+    "dataset": {},
+    "evaluator": {},
+    "network_def": {},
+    "run": [
+        "[email protected]()"
+    ]
 }

models/CoronSegmentator/configs/inference.json

@@ -18,4 +18,8 @@ formatter=fullFormatter
 args=(sys.stdout,)
 
 [formatter_fullFormatter]
-format=%(asctime)s - %(name)s - %(levelname)s - %(message)s
+<<<<<<< HEAD
+format=%(asctime)s - %(name)s - %(levelname)s - %(message)s
+=======
+format=%(asctime)s - %(name)s - %(levelname)s - %(message)s
+>>>>>>> c8b3ad0a5842cf425f0ffb9355bfcb67ce994382

models/CoronSegmentator/configs/logging.conf

@@ -1,4 +1,5 @@
 {
+<<<<<<< HEAD
   "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
   "name": "coronaryArtery_ct_segmentation",
   "version": "1.0.0",
@@ -71,4 +72,92 @@
         "numpy": "2.3.1"
     }
   }
-}
+}
+=======
+    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
+    "name": "coronaryArtery_ct_segmentation",
+    "version": "1.0.0",
+    "monai_version": "1.4.0",
+    "pytorch_version": "1.4.0",
+    "numpy_version": "2.3.1",
+    "required_packages_version": {
+        "fire": "0.7.0",
+        "PyYAML": "6.0.2",
+        "gdown": "5.2.0",
+        "nnunetv2": "2.6.0",
+        "nibabel": "5.3.2",
+        "numpy_stl": "3.2.0",
+        "pynrrd": "1.1.3",
+        "scipy": "1.16.0",
+        "simpleitk": "2.5.0",
+        "scikit-image": "0.25.2",
+        "torch": "2.7.0+cu126",
+        "trimesh": "4.6.10",
+        "usd_core": "25.5.1",
+        "numpy-stl": "3.2.0"
+    },
+    "task": "Coronary artery ct segmentation",
+    "description": "Coronsegmentator is an automated pipeline that performs dual-task segmentation on cardiac CT images, focusing on both whole-heart and coronary artery structures. It integrates MONAI Auto3DSeg for general cardiac segmentation and a custom nnU-Net model for detailed coronary artery segmentation. The pipeline further converts segmentation results (in STL format) into USD files for downstream 3D visualization and digital twin simulation using NVIDIA Omniverse.",
+    "authors": "Y. Ke, MC. Chen, TY. Lin, YC. Chan Foxconn Digital Health AI Team",
+    "copyright": "Copyright \u00a9 2025 Hon Hai Precision Industry Co.,Ltd. All rights reserved",
+    "data_source": "The ImageCAS dataset is publicly available at: https://github.com/XiaoweiXu/ImageCAS-A-Large-Scale-Dataset-and-Benchmark-for-Coronary-Artery-Segmentation-based-on-CT.git",
+    "data_type": "nifti",
+    "image_classes": "3D volume data",
+    "label_classes": "single channel data, 1 is coronary artery, 0 is background",
+    "pred_classes": "2 channels OneHot data, channel 1 is coronary artery, channel 0 is background",
+    "intended_use": "This is an example, not to be used for diagnostic purposes",
+    "references": [
+        "Zeng, An, et al. ImageCAS: A large-scale dataset and benchmark for coronary artery segmentation based on computed tomography angiography images. Computerized Medical Imaging and Graphics 109 (2023): 102287.",
+        "Isensee, Fabian, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18.2 (2021): 203-211."
+    ],
+    "network_data_format": {
+        "inputs": {
+            "image": {
+                "type": "image",
+                "format": "hounsfield",
+                "modality": "CT",
+                "num_channels": 1,
+                "spatial_shape": [
+                    512,
+                    512,
+                    256
+                ],
+                "dtype": "float32",
+                "value_range": [
+                    0,
+                    1
+                ],
+                "is_patch_data": true,
+                "channel_def": {
+                    "0": "image"
+                }
+            }
+        },
+        "outputs": {
+            "pred": {
+                "type": "usd",
+                "format": "segmentation",
+                "num_channels": 1,
+                "spatial_shape": [
+                    512,
+                    512,
+                    256
+                ],
+                "dtype": "float32",
+                "value_range": [
+                    0,
+                    1
+                ],
+                "channel_def": {
+                    "0": "Coronary Artery (1 = target, 0 = background)"
+                }
+            }
+        },
+        "optional_packages_version": {
+            "monai": "1.3.2",
+            "torch": "2.7.0+cu126",
+            "numpy": "2.3.1"
+        }
+    }
+}
+>>>>>>> c8b3ad0a5842cf425f0ffb9355bfcb67ce994382

models/CoronSegmentator/configs/metadata.json

@@ -126,7 +126,7 @@ def initialize_vertex_map(self):
         """
         if self.num_triangles == 0:
             return
-        
+
         vectors = self.original_mesh.vectors
         # Process in batches to reduce memory pressure
         batch_size = min(10000, self.num_triangles)  # Adjust batch size based on available memory

models/CoronSegmentator/scripts/coronaryArtery_segmentation/coronaryArtery_seg.py

@@ -12,7 +12,7 @@ def _calculate_md5(filepath: Path, block_size: int = 65536) -> str:
     Calculate md5 value of file
     """
     md5 = hashlib.md5()
-    
+
     with open(filepath, 'rb') as f:
         for block in iter(lambda: f.read(block_size), b''):
             md5.update(block)
@@ -30,7 +30,7 @@ def download_and_verify():
     """
     with open(DOWNLOAD_CONFIG, 'r') as file:
         downloadConfig = yaml.safe_load(file)
-    
+
     for fileInfo in downloadConfig['large_files']:
         rel_path = fileInfo.get("path")
         url = fileInfo.get("url")
@@ -52,4 +52,4 @@ def download_and_verify():
 
         final_hash = _calculate_md5(destination_path)
         if final_hash != expected_hash:
-            raise RuntimeError(f"final_hash donesn't match expected_hash")
+            raise RuntimeError(f"final_hash donesn't match expected_hash")

models/CoronSegmentator/scripts/download.py

@@ -86,17 +86,17 @@ def convert_nrrd_to_stl(nrrd_file_path, stl_file_path, gaussian_sigma=1.0):
                 raise RuntimeError(f"Failed during image smoothing: {str(e)}")
 
             logger.debug("Converting image to numpy array")
-            
+
             volume_data = sitk.GetArrayFromImage(smoothed_image)
             del smoothed_image
             logger.debug("Generating mesh using marching cubes algorithm")
 
             if np.all(volume_data == 0):
-                
+
                 dummy_vertices = [[0.0, 0.0, 0.0], [0.0, 0.0, 0.0], [0.0, 0.0, 0.0]]
                 dummy_faces = [[0, 1, 2]]
                 mesh_obj = trimesh.Trimesh(vertices=dummy_vertices, faces=dummy_faces)
-        
+
             else:
                 verts, faces, _, _ = marching_cubes(volume_data, level=0.5)
                 del volume_data