Data

Tools

Indexes

Applications

Experiments

Open Source Science

hipas_av_segmentation

The supplementary code for the pulmonary artery-vein segmentation with various inter-slice thickness

https://github.com/arturia-pendragon-iris/hipas_av_segmentation

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

The supplementary code for the pulmonary artery-vein segmentation with various inter-slice thickness

Basic Info
  • Host: GitHub
  • Owner: Arturia-Pendragon-Iris
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 25.3 MB
Statistics
  • Stars: 24
  • Watchers: 2
  • Forks: 3
  • Open Issues: 4
  • Releases: 1
Created over 3 years ago · Last pushed 12 months ago
Metadata Files
Readme License Citation

README.md

Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differences

Overview

This repository provides the method described in the paper: “Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differences”

King Abdullah University of Science and Technology, KAUST

Our manuscript has been accepted by Nature Communication and is now in publication. Congratulation!!!!! We will update any information timely.

If you have any questions about the code, paper, or datasets, please email yuetan.chu@kaust.edu.sa.

Installation

conda create -n HiPaS python=3.8 conda activate HiPaS pip install -r requirements.txt Here we include all the packages used in our whole platform. However, some packages are not used in this project. You can install some of these packages according to your situation.

Datasets

We have released ~250 cases of chest CT scans with artery-vein annotations. You can download the datasets using this Google drive link or the Zenodo link. To open the CT data and annotation, you can use the following code

ct = np.load(".\ct_scan\001.npz", allow_pickle=True)["data"] artery = np.load(".\annotation\artery\001.npz", allow_pickle=True)["data"] vein = np.load(".\annotation\vein\001.npz", allow_pickle=True)["data"]

Due to the consideration of the project commercialization, the released annotations keep the same as the segmentation standard in the PARSE22 challenge, as shown in Supplementary Figure 6 (Stage 2) in our Supplementary Information. This can satisfy most clinical requirements.

Train

You can use the 3D UNet as the training process for the segmentation model and replace the default 3DUNet with our proposed network. We also provide our training framework in HiPaS. The input data should be stored in HDF5 files. The HDF5 files for training should contain two datasets: raw and label. The "raw" dataset contains CT scans, while the "label" dataset is the artery-vein segmentation. The segmentation of different vessel levels should be trained separately. In order to train on your own data, you can provide the paths to your HDF5 training and validation datasets in the YAML file, and run HiPaS/train.py.

Predict

To predict on your own data, you can provide the checkpoint path as well as paths of the CT volume, and run HiPaS/predict_av.py. It may take about 2 minutes to achieve the prediction result for one CT volume. To run the program on your own data, you can just replace the default path too your own file path.

Workflow

image

Performance evaluation

image

Clinical evaluation

image

Anatomical study

image

Cite

Chu, Y., Luo, G., Zhou, L. et al. Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differences. Nat Commun 16, 2262 (2025). https://doi.org/10.1038/s41467-025-56505-6

Owner

  • Name: Yuetan Chu
  • Login: Arturia-Pendragon-Iris
  • Kind: user
  • Location: Thwual; Jeddah; Saudi Arabria
  • Company: King Abdullah University of Science and Technology

Citation (CITATION.cff) 

cff-version: 2.0.1
message: "If you use this software, please cite it as below."
authors:
- family-names: Chu
  given-names: Yuetan
orcid: https://orcid.org/0000-0003-1729-831X
title: HiPaS Artery-vein Segmentation
version: v2.0.1
date-released: 2024-12-09

GitHub Events

Total
  • Create event: 1
  • Issues event: 5
  • Release event: 1
  • Watch event: 27
  • Issue comment event: 6
  • Push event: 20
  • Fork event: 2
Last Year
  • Create event: 1
  • Issues event: 5
  • Release event: 1
  • Watch event: 27
  • Issue comment event: 6
  • Push event: 20
  • Fork event: 2

Issues and Pull Requests

Last synced: almost 2 years ago

All Time
  • Total issues: 3
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 3
  • Total pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • AlphonsG (1)
  • JiahaoHuang99 (1)
  • zhenhua2023 (1)
  • RosieFerr (1)
  • samn546 (1)
  • praveenrp295 (1)
  • id-b3 (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirement.txt pypi
  • abseil-cpp =20230802.0=h6a678d5_2
  • absl-py =1.4.0=py38h06a4308_0
  • aiohttp =3.9.0=py38h5eee18b_0
  • aiosignal =1.2.0=pyhd3eb1b0_0
  • alembic =1.13.1=pypi_0
  • aom =3.6.0=h6a678d5_0
  • asciitree =0.3.3=pypi_0
  • astor =0.8.1=pypi_0
  • async-timeout =4.0.3=py38h06a4308_0
  • attrs =23.1.0=py38h06a4308_0
  • beautifulsoup4 =4.12.2=pypi_0
  • blas =1.0=mkl
  • blinker =1.6.2=py38h06a4308_0
  • blosc =1.21.3=h6a678d5_0
  • brotli =1.0.9=h5eee18b_7
  • brotli-bin =1.0.9=h5eee18b_7
  • brotli-python =1.0.9=py38h6a678d5_7
  • brunsli =0.1=h2531618_0
  • bzip2 =1.0.8=h7b6447c_0
  • c-ares =1.19.1=h5eee18b_0
  • ca-certificates =2023.12.12=h06a4308_0
  • cachetools =4.2.2=pyhd3eb1b0_0
  • certifi =2023.11.17=py38h06a4308_0
  • cffi =1.16.0=py38h5eee18b_0
  • cfitsio =3.470=h5893167_7
  • charls =2.2.0=h2531618_0
  • charset-normalizer =2.0.4=pyhd3eb1b0_0
  • clearml =1.13.3rc1=pypi_0
  • click =8.1.7=py38h06a4308_0
  • cloudpickle =2.2.1=py38h06a4308_0
  • cmaps =2.0.1=pypi_0
  • colorama =0.4.6=pyhd8ed1ab_0
  • coloredlogs =15.0.1=pypi_0
  • colorlog =6.8.0=pypi_0
  • contextlib2 =21.6.0=pypi_0
  • contourpy =1.1.1=pypi_0
  • cryptography =41.0.3=py38hdda0065_0
  • cucim =23.10.0=pypi_0
  • cuda-cudart =11.8.89=0
  • cuda-cupti =11.8.87=0
  • cuda-libraries =11.8.0=0
  • cuda-nvrtc =11.8.89=0
  • cuda-nvtx =11.8.86=0
  • cuda-runtime =11.8.0=0
  • cycler =0.12.1=pypi_0
  • cytoolz =0.12.0=py38h5eee18b_0
  • dask-core =2023.4.1=py38h06a4308_0
  • databricks-cli =0.18.0=pypi_0
  • dataclasses =0.8=pyh6d0b6a4_7
  • dav1d =1.2.1=h5eee18b_0
  • docker =6.1.3=pypi_0
  • eigen =3.4.0=h00ab1b0_0
  • einops =0.7.0=pypi_0
  • entrypoints =0.4=pypi_0
  • enum34 =1.1.10=py38h32f6830_2
  • expat =2.5.0=hcb278e6_1
  • fasteners =0.19=pypi_0
  • ffmpeg =4.3=hf484d3e_0
  • fftw =3.3.10=nompi_hc118613_108
  • filelock =3.11.0=pypi_0
  • fire =0.5.0=pypi_0
  • flask =3.0.0=pypi_0
  • flatbuffers =23.5.26=pypi_0
  • fonttools =4.45.1=pypi_0
  • freetype =2.12.1=h4a9f257_0
  • frozenlist =1.4.0=py38h5eee18b_0
  • fsspec =2023.10.0=py38h06a4308_0
  • furl =2.1.3=pypi_0
  • gdown =4.7.1=pypi_0
  • gggenshinpy =0.1.0=pypi_0
  • giflib =5.2.1=h5eee18b_3
  • gitdb =4.0.11=pypi_0
  • gitpython =3.1.40=pypi_0
  • gmp =6.2.1=h295c915_3
  • gmpy2 =2.1.2=py38heeb90bb_0
  • gnutls =3.6.15=he1e5248_0
  • google-auth =2.22.0=py38h06a4308_0
  • google-auth-oauthlib =0.5.2=py38h06a4308_0
  • greenlet =3.0.3=pypi_0
  • grpc-cpp =1.48.2=he1ff14a_4
  • grpcio =1.48.2=py38he1ff14a_4
  • gtest =1.14.0=hdb19cb5_0
  • gunicorn =21.2.0=pypi_0
  • h5py =3.10.0=pypi_0
  • hausdorff =0.2.6=pypi_0
  • hdf5 =1.14.2=nompi_h4f84152_100
  • huggingface-hub =0.20.1=pypi_0
  • huggingface_hub =0.20.2=py_0
  • humanfriendly =10.0=pypi_0
  • icu =73.2=h59595ed_0
  • idna =3.4=py38h06a4308_0
  • imagecodecs =2023.3.16=pypi_0
  • imagecodecs-lite =2019.12.3=py38h7f0c24c_7
  • imageio =2.31.4=py38h06a4308_0
  • importlib-metadata =6.0.0=py38h06a4308_0
  • importlib-resources =6.1.1=pypi_0
  • imutils =0.5.4=pypi_0
  • intel-openmp =2023.1.0=hdb19cb5_46306
  • itk =5.3.0=pypi_0
  • itk-core =5.3.0=pypi_0
  • itk-filtering =5.3.0=pypi_0
  • itk-io =5.3.0=pypi_0
  • itk-numerics =5.3.0=pypi_0
  • itk-registration =5.3.0=pypi_0
  • itk-segmentation =5.3.0=pypi_0
  • itsdangerous =2.1.2=pypi_0
  • jinja2 =3.1.2=py38h06a4308_0
  • joblib =1.3.2=pypi_0
  • json-tricks =3.17.3=pypi_0
  • jsonschema =4.20.0=pypi_0
  • jsonschema-specifications =2023.12.1=pypi_0
  • jxrlib =1.1=h7b6447c_2
  • kiwisolver =1.4.5=pypi_0
  • krb5 =1.20.1=h143b758_1
  • lame =3.100=h7b6447c_0
  • lazy-loader =0.3=pypi_0
  • lcms2 =2.15=h7f713cb_2
  • ld_impl_linux-64 =2.38=h1181459_1
  • lerc =4.0.0=h27087fc_0
  • libaec =1.1.2=h59595ed_1
  • libavif =0.11.1=h5eee18b_0
  • libbrotlicommon =1.0.9=h5eee18b_7
  • libbrotlidec =1.0.9=h5eee18b_7
  • libbrotlienc =1.0.9=h5eee18b_7
  • libcublas =11.11.3.6=0
  • libcufft =10.9.0.58=0
  • libcufile =1.8.1.2=0
  • libcurand =10.3.4.101=0
  • libcurl =8.4.0=h251f7ec_0
  • libcusolver =11.4.1.48=0
  • libcusparse =11.7.5.86=0
  • libdeflate =1.19=hd590300_0
  • libedit =3.1.20221030=h5eee18b_0
  • libev =4.33=h7f8727e_1
  • libexpat =2.5.0=hcb278e6_1
  • libffi =3.4.4=h6a678d5_0
  • libgcc-ng =13.2.0=h807b86a_3
  • libgfortran-ng =13.2.0=h69a702a_3
  • libgfortran5 =13.2.0=ha4646dd_3
  • libhwloc =2.9.3=default_h554bfaf_1009
  • libiconv =1.17=h166bdaf_0
  • libidn2 =2.3.4=h5eee18b_0
  • libitk =5.3.0=h0dad300_7
  • libjpeg-turbo =2.1.5.1=hd590300_1
  • libnghttp2 =1.57.0=h2d74bed_0
  • libnpp =11.8.0.86=0
  • libnvjpeg =11.9.0.86=0
  • libpng =1.6.39=h5eee18b_0
  • libprotobuf =3.20.3=he621ea3_0
  • libssh2 =1.10.0=hdbd6064_2
  • libstdcxx-ng =13.2.0=h7e041cc_3
  • libtasn1 =4.19.0=h5eee18b_0
  • libtiff =4.6.0=h29866fb_1
  • libunistring =0.9.10=h27cfd23_0
  • libwebp-base =1.3.2=h5eee18b_0
  • libxcb =1.15=h0b41bf4_0
  • libxml2 =2.11.6=h232c23b_0
  • libzlib =1.2.13=hd590300_5
  • libzopfli =1.0.3=he6710b0_0
  • llvm-openmp =14.0.6=h9e868ea_0
  • llvmlite =0.41.1=pypi_0
  • lmdb =1.4.1=pypi_0
  • locket =1.0.0=py38h06a4308_0
  • lpips =0.1.4=pypi_0
  • lz4-c =1.9.4=h6a678d5_0
  • mako =1.3.0=pypi_0
  • markdown =3.4.1=py38h06a4308_0
  • markupsafe =2.1.1=py38h7f8727e_0
  • matplotlib =3.7.4=pypi_0
  • medpy =0.4.0=pypi_0
  • mkl =2023.1.0=h213fc3f_46344
  • mkl-service =2.4.0=py38h5eee18b_1
  • mkl_fft =1.3.8=py38h5eee18b_0
  • mkl_random =1.2.4=py38hdb19cb5_0
  • mlflow =2.9.2=pypi_0
  • monai =1.3.0=pyhd8ed1ab_0
  • mpc =1.1.0=h10f8cd9_1
  • mpfr =4.0.2=hb69a4c5_1
  • mpmath =1.3.0=py38h06a4308_0
  • multidict =6.0.4=py38h5eee18b_0
  • ncurses =6.4=h6a678d5_0
  • nettle =3.7.3=hbbd107a_1
  • networkx =3.1=py38h06a4308_0
  • nibabel =5.1.0=pypi_0
  • ninja =1.11.1.1=pypi_0
  • nni =3.0=pypi_0
  • nptyping =2.5.0=pypi_0
  • numba =0.58.1=pypi_0
  • numcodecs =0.12.1=pypi_0
  • numpy =1.24.3=py38hf6e8229_1
  • numpy-base =1.24.3=py38h060ed82_1
  • nvidia-ml-py =12.535.133=pypi_0
  • oauthlib =3.2.2=py38h06a4308_0
  • onnx =1.15.0=pypi_0
  • onnxruntime =1.16.3=pypi_0
  • opencv-python =4.8.1.78=pypi_0
  • openh264 =2.1.1=h4ff587b_0
  • openjpeg =2.5.0=h488ebb8_3
  • openslide-python =1.1.2=pypi_0
  • openssl =3.2.0=hd590300_1
  • optuna =3.5.0=pypi_0
  • orderedmultidict =1.0.1=pypi_0
  • packaging =23.1=py38h06a4308_0
  • pandas =2.0.3=pypi_0
  • partd =1.4.1=py38h06a4308_0
  • pathlib =1.0.1=py38h578d9bd_7
  • pathlib2 =2.3.7.post1=pypi_0
  • pillow =10.0.1=py38h71741d6_1
  • pip =23.3.1=py38h06a4308_0
  • pkgutil-resolve-name =1.3.10=pypi_0
  • platformdirs =3.10.0=py38h06a4308_0
  • pooch =1.7.0=py38h06a4308_0
  • prettytable =3.9.0=pypi_0
  • protobuf =3.20.3=py38h6a678d5_0
  • psutil =5.9.7=pypi_0
  • pthread-stubs =0.4=h36c2ea0_1001
  • pyarrow =14.0.2=pypi_0
  • pyasn1 =0.4.8=pyhd3eb1b0_0
  • pyasn1-modules =0.2.8=py_0
  • pycparser =2.21=pyhd3eb1b0_0
  • pydicom =2.4.3=pypi_0
  • pyjwt =2.4.0=py38h06a4308_0
  • pynrrd =1.0.0=pypi_0
  • pyopenssl =23.2.0=py38h06a4308_0
  • pyparsing =3.1.1=pypi_0
  • pysocks =1.7.1=py38h06a4308_0
  • python =3.8.18=h955ad1f_0
  • python-dateutil =2.8.2=pypi_0
  • python_abi =3.8=2_cp38
  • pythonwebhdfs =0.2.3=pypi_0
  • pytorch =2.1.1=py3.8_cuda11.8_cudnn8.7.0_0
  • pytorch-cuda =11.8=h7e8668a_5
  • pytorch-ignite =0.4.11=pypi_0
  • pytorch-mutex =1.0=cuda
  • pyttsx3 =2.90=pypi_0
  • pytz =2023.3.post1=pypi_0
  • pywavelets =1.4.1=py38h5eee18b_0
  • pyyaml =6.0.1=py38h5eee18b_0
  • querystring-parser =1.2.4=pypi_0
  • re2 =2022.04.01=h295c915_0
  • readline =8.2=h5eee18b_0
  • referencing =0.32.0=pypi_0
  • regex =2023.12.25=pypi_0
  • requests =2.31.0=py38h06a4308_0
  • requests-oauthlib =1.3.0=py_0
  • responses =0.24.1=pypi_0
  • rpds-py =0.16.2=pypi_0
  • rsa =4.7.2=pyhd3eb1b0_1
  • sacremoses =master=py_0
  • safetensors =0.4.1=pypi_0
  • schema =0.7.5=pypi_0
  • scikit-image =0.19.3=py38h6a678d5_1
  • scikit-learn =1.3.2=pypi_0
  • scipy =1.10.1=py38hf6e8229_1
  • setuptools =68.0.0=py38h06a4308_0
  • simpleitk =2.3.1=py38h17151c0_1
  • simplejson =3.19.2=pypi_0
  • six =1.16.0=pyhd3eb1b0_1
  • smmap =5.0.1=pypi_0
  • snappy =1.1.9=h295c915_0
  • soupsieve =2.5=pypi_0
  • sqlalchemy =2.0.25=pypi_0
  • sqlite =3.41.2=h5eee18b_0
  • sqlparse =0.4.4=pypi_0
  • sympy =1.11.1=py38h06a4308_0
  • tabulate =0.9.0=pypi_0
  • tbb =2021.10.0=h00ab1b0_2
  • tensorboard =2.12.1=py38h06a4308_0
  • tensorboard-data-server =0.7.0=py38h52d8a92_0
  • tensorboard-plugin-wit =1.8.1=py38h06a4308_0
  • tensorboardx =2.6.2.2=pypi_0
  • termcolor =2.4.0=pypi_0
  • threadpoolctl =3.2.0=pypi_0
  • tifffile =2019.7.26.2=py38_0
  • timm =0.9.12=pypi_0
  • tk =8.6.12=h1ccaba5_0
  • tokenizers =0.12.1=pypi_0
  • toolz =0.12.0=py38h06a4308_0
  • torchaudio =2.1.1=py38_cu118
  • torchtriton =2.1.0=py38
  • torchvision =0.16.1=py38_cu118
  • tqdm =4.66.1=pyhd8ed1ab_0
  • transformers =4.21.3=pypi_0
  • typeguard =4.1.2=pypi_0
  • typing-extensions =4.7.1=py38h06a4308_0
  • typing_extensions =4.7.1=py38h06a4308_0
  • tzdata =2023.3=pypi_0
  • urllib3 =1.26.18=py38h06a4308_0
  • wcwidth =0.2.12=pypi_0
  • websocket-client =1.7.0=pypi_0
  • websockets =12.0=pypi_0
  • werkzeug =3.0.1=pypi_0
  • wheel =0.41.2=py38h06a4308_0
  • xorg-libxau =1.0.11=hd590300_0
  • xorg-libxdmcp =1.1.3=h7f98852_0
  • xz =5.4.2=h5eee18b_0
  • yaml =0.2.5=h7b6447c_0
  • yarl =1.9.3=py38h5eee18b_0
  • zarr =2.16.1=pypi_0
  • zfp =1.0.0=h6a678d5_0
  • zipp =3.11.0=py38h06a4308_0
  • zlib =1.2.13=hd590300_5
  • zstd =1.5.5=hc292b87_0