Skip to content

Commit ebde3a9

Browse files
pre-commit-ci[bot]pre-commit-ci[bot]
committed
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
1 parent f34535c commit ebde3a9

File tree

2 files changed

+100
-82
lines changed

2 files changed

+100
-82
lines changed

‎models/CoronSegmentator/configs/inference.json‎

Lines changed: 23 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -1,21 +1,25 @@
11
{
2-
"imports": ["$import glob"],
3-
"bundle_root": ".",
4-
"ckpt_dir": "$@bundle_root + '/models'",
5-
"dataset_dir": "",
6-
"data": "$list(sorted(glob.glob(@dataset_dir + '/*.nii.gz')))",
7-
"output_ext": ".usd",
8-
"output_dir": "$@bundle_root + '/Output'",
9-
"device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')",
10-
"inferer": {
11-
"_target_": "scripts.heart_digital_twin.CoroSegmentatorPipeline",
12-
"input_params": {
13-
"inputFile": "$@data[0]",
14-
"outputDir": "$@output_dir"
15-
}
16-
},
17-
"dataset": {},
18-
"evaluator": {},
19-
"network_def": {},
20-
"run": ["[email protected]()"]
2+
"imports": [
3+
"$import glob"
4+
],
5+
"bundle_root": ".",
6+
"ckpt_dir": "$@bundle_root + '/models'",
7+
"dataset_dir": "",
8+
"data": "$list(sorted(glob.glob(@dataset_dir + '/*.nii.gz')))",
9+
"output_ext": ".usd",
10+
"output_dir": "$@bundle_root + '/Output'",
11+
"device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')",
12+
"inferer": {
13+
"_target_": "scripts.heart_digital_twin.CoroSegmentatorPipeline",
14+
"input_params": {
15+
"inputFile": "$@data[0]",
16+
"outputDir": "$@output_dir"
17+
}
18+
},
19+
"dataset": {},
20+
"evaluator": {},
21+
"network_def": {},
22+
"run": [
23+
"[email protected]()"
24+
]
2125
}

‎models/CoronSegmentator/configs/metadata.json‎

Lines changed: 77 additions & 63 deletions
Original file line numberDiff line numberDiff line change
@@ -1,68 +1,82 @@
11
{
2-
"schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
3-
"name": "coronaryArtery_ct_segmentation",
4-
"version": "1.0.0",
5-
"monai_version": "1.3.2",
6-
"pytorch_version": "2.7.0",
7-
"numpy_version": "2.3.1",
8-
"required_packages_version": {
9-
"fire": "0.7.0",
10-
"monai": " 1.4.0",
11-
"nnunetv2": "2.6.0",
12-
"nibabel": "5.3.2",
13-
"numpy": "2.3.1",
14-
"numpy_stl": "3.2.0",
15-
"pynrrd": "1.1.3",
16-
"scipy": "1.16.0",
17-
"simpleitk": "2.5.0",
18-
"scikit-image": "0.25.2",
19-
"torch": "2.7.0+cu126",
20-
"trimesh": "4.6.10",
21-
"usd_core": "25.5.1",
22-
"numpy-stl": "3.2.0"
23-
},
24-
"task": "Coronary artery ct segmentation",
25-
"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.",
26-
"authors": "Y. Ke, MC. Chen, TY. Lin, YC. Chan Foxconn Digital Health AI Team",
27-
"copyright": "Copyright \u00a9 2025 Hon Hai Precision Industry Co.,Ltd. All rights reserved",
28-
"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",
29-
"data_type": "nifti",
30-
"image_classes": "3D volume data",
31-
"label_classes": "single channel data, 1 is coronary artery, 0 is background",
32-
"pred_classes": "2 channels OneHot data, channel 1 is coronary artery, channel 0 is background",
33-
"intended_use": "This is an example, not to be used for diagnostic purposes",
34-
"references": [
35-
"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.",
36-
"Isensee, Fabian, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18.2 (2021): 203-211."
37-
],
38-
"network_data_format": {
39-
"inputs": {
40-
"image": {
41-
"type": "image",
42-
"format": "hounsfield",
43-
"modality": "CT",
44-
"num_channels": 1,
45-
"spatial_shape": [512, 512, 256],
46-
"dtype": "float32",
47-
"value_range": [0, 1],
48-
"is_patch_data": true,
49-
"channel_def": {
50-
"0": "image"
51-
}
52-
}
2+
"schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
3+
"name": "coronaryArtery_ct_segmentation",
4+
"version": "1.0.0",
5+
"monai_version": "1.3.2",
6+
"pytorch_version": "2.7.0",
7+
"numpy_version": "2.3.1",
8+
"required_packages_version": {
9+
"fire": "0.7.0",
10+
"monai": " 1.4.0",
11+
"nnunetv2": "2.6.0",
12+
"nibabel": "5.3.2",
13+
"numpy": "2.3.1",
14+
"numpy_stl": "3.2.0",
15+
"pynrrd": "1.1.3",
16+
"scipy": "1.16.0",
17+
"simpleitk": "2.5.0",
18+
"scikit-image": "0.25.2",
19+
"torch": "2.7.0+cu126",
20+
"trimesh": "4.6.10",
21+
"usd_core": "25.5.1",
22+
"numpy-stl": "3.2.0"
5323
},
54-
"outputs": {
55-
"pred": {
56-
"type": "usd",
57-
"format": "segmentation",
58-
"num_channels": 1,
59-
"spatial_shape": [512, 512, 256],
60-
"dtype": "float32",
61-
"value_range": [0, 1],
62-
"channel_def": {
63-
"0": "Coronary Artery (1 = target, 0 = background)"
24+
"task": "Coronary artery ct segmentation",
25+
"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.",
26+
"authors": "Y. Ke, MC. Chen, TY. Lin, YC. Chan Foxconn Digital Health AI Team",
27+
"copyright": "Copyright \u00a9 2025 Hon Hai Precision Industry Co.,Ltd. All rights reserved",
28+
"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",
29+
"data_type": "nifti",
30+
"image_classes": "3D volume data",
31+
"label_classes": "single channel data, 1 is coronary artery, 0 is background",
32+
"pred_classes": "2 channels OneHot data, channel 1 is coronary artery, channel 0 is background",
33+
"intended_use": "This is an example, not to be used for diagnostic purposes",
34+
"references": [
35+
"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.",
36+
"Isensee, Fabian, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18.2 (2021): 203-211."
37+
],
38+
"network_data_format": {
39+
"inputs": {
40+
"image": {
41+
"type": "image",
42+
"format": "hounsfield",
43+
"modality": "CT",
44+
"num_channels": 1,
45+
"spatial_shape": [
46+
512,
47+
512,
48+
256
49+
],
50+
"dtype": "float32",
51+
"value_range": [
52+
0,
53+
1
54+
],
55+
"is_patch_data": true,
56+
"channel_def": {
57+
"0": "image"
58+
}
59+
}
60+
},
61+
"outputs": {
62+
"pred": {
63+
"type": "usd",
64+
"format": "segmentation",
65+
"num_channels": 1,
66+
"spatial_shape": [
67+
512,
68+
512,
69+
256
70+
],
71+
"dtype": "float32",
72+
"value_range": [
73+
0,
74+
1
75+
],
76+
"channel_def": {
77+
"0": "Coronary Artery (1 = target, 0 = background)"
78+
}
79+
}
6480
}
65-
}
6681
}
67-
}
6882
}

0 commit comments

Comments
 (0)