[](https://github.com/imagingdatacommons/highdicom/actions)
[](https://highdicom.readthedocs.io/en/latest/?badge=latest)
[](https://pypi.python.org/pypi/highdicom/)
[](https://pypi.org/project/highdicom/)
[](https://pepy.tech/project/highdicom)
[](code_of_conduct.md)
# Highdicom
`highdicom` is a pure Python package built on top of `pydicom` to provide a higher-level application programming interface (API) for working with DICOM files. Its focus is on common operations required for machine learning, computer vision, and other similar computational analyses. Broadly speaking, the package helps with three types of task:
1. Reading existing DICOM image files of a wide variety of modalities (covering radiology, pathology, and more) and selecting and formatting its frames for computational analysis. This includes considerations such as spatial arrangements of frames, and application of pixel transforms, which are not handled by `pydicom`.
2. Storing image-derived information, for example from computational analyses or human annotation, in derived DICOM objects for communication and storage. This includes:
* Annotations
* Parametric Map images
* Segmentation images
* Structured Report documents (containing numerical results, qualitative evaluations, and/or vector graphic annotations)
* Secondary Capture images
* Key Object Selection documents
* Legacy Converted Enhanced CT/PET/MR images (e.g., for single frame to multi-frame conversion)
* Softcopy Presentation State instances (including Grayscale, Color, and Pseudo-Color)
3. Reading existing derived DICOM files of the above types and filtering and accessing the information contained within them.
## Documentation
Please refer to the online documentation at [highdicom.readthedocs.io](https://highdicom.readthedocs.io), which includes installation instructions, a user guide with examples, a developer guide, and complete documentation of the application programming interface of the `highdicom` package.
## Citation
For more information about the motivation of the library and the design of highdicom's API, please see the following article:
> [Highdicom: A Python library for standardized encoding of image annotations and machine learning model outputs in pathology and radiology](https://link.springer.com/article/10.1007/s10278-022-00683-y)
> C.P. Bridge, C. Gorman, S. Pieper, S.W. Doyle, J.K. Lennerz, J. Kalpathy-Cramer, D.A. Clunie, A.Y. Fedorov, and M.D. Herrmann.
> Journal of Digital Imaging, August 2022
If you use highdicom in your research, please cite the above article.
## Support
The developers gratefully acknowledge their support:
* The [Alliance for Digital Pathology](https://digitalpathologyalliance.org/)
* The [MGH & BWH Center for Clinical Data Science](https://www.ccds.io/)
* [Quantitative Image Informatics for Cancer Research (QIICR)](https://qiicr.org/)
* [Radiomics](https://www.radiomics.io/)
This software is maintained in part by the [NCI Imaging Data Commons](https://imaging.datacommons.cancer.gov/) project,
which has been funded in whole or in part with Federal funds from the NCI, NIH, under task order no. HHSN26110071
under contract no. HHSN261201500003l.
Raw data
{
"_id": null,
"home_page": null,
"name": "highdicom",
"maintainer": "Markus D. Herrmann, Christopher P. Bridge",
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Markus D. Herrmann, Christopher P. Bridge",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/7e/44/d8b353560fb248ff79a6ca5e7aae2d48c015438d943f903fa509b69a7d8e/highdicom-0.26.1.tar.gz",
"platform": null,
"description": "[](https://github.com/imagingdatacommons/highdicom/actions)\n[](https://highdicom.readthedocs.io/en/latest/?badge=latest)\n[](https://pypi.python.org/pypi/highdicom/)\n[](https://pypi.org/project/highdicom/)\n[](https://pepy.tech/project/highdicom)\n[](code_of_conduct.md)\n\n# Highdicom\n\n`highdicom` is a pure Python package built on top of `pydicom` to provide a higher-level application programming interface (API) for working with DICOM files. Its focus is on common operations required for machine learning, computer vision, and other similar computational analyses. Broadly speaking, the package helps with three types of task:\n\n1. Reading existing DICOM image files of a wide variety of modalities (covering radiology, pathology, and more) and selecting and formatting its frames for computational analysis. This includes considerations such as spatial arrangements of frames, and application of pixel transforms, which are not handled by `pydicom`.\n2. Storing image-derived information, for example from computational analyses or human annotation, in derived DICOM objects for communication and storage. This includes:\n * Annotations\n * Parametric Map images\n * Segmentation images\n * Structured Report documents (containing numerical results, qualitative evaluations, and/or vector graphic annotations)\n * Secondary Capture images\n * Key Object Selection documents\n * Legacy Converted Enhanced CT/PET/MR images (e.g., for single frame to multi-frame conversion)\n * Softcopy Presentation State instances (including Grayscale, Color, and Pseudo-Color)\n\n3. Reading existing derived DICOM files of the above types and filtering and accessing the information contained within them.\n\n## Documentation\n\nPlease refer to the online documentation at [highdicom.readthedocs.io](https://highdicom.readthedocs.io), which includes installation instructions, a user guide with examples, a developer guide, and complete documentation of the application programming interface of the `highdicom` package.\n\n## Citation\n\nFor more information about the motivation of the library and the design of highdicom's API, please see the following article:\n\n> [Highdicom: A Python library for standardized encoding of image annotations and machine learning model outputs in pathology and radiology](https://link.springer.com/article/10.1007/s10278-022-00683-y)\n> C.P. Bridge, C. Gorman, S. Pieper, S.W. Doyle, J.K. Lennerz, J. Kalpathy-Cramer, D.A. Clunie, A.Y. Fedorov, and M.D. Herrmann.\n> Journal of Digital Imaging, August 2022\n\nIf you use highdicom in your research, please cite the above article.\n\n## Support\n\nThe developers gratefully acknowledge their support:\n* The [Alliance for Digital Pathology](https://digitalpathologyalliance.org/)\n* The [MGH & BWH Center for Clinical Data Science](https://www.ccds.io/)\n* [Quantitative Image Informatics for Cancer Research (QIICR)](https://qiicr.org/)\n* [Radiomics](https://www.radiomics.io/)\n\nThis software is maintained in part by the [NCI Imaging Data Commons](https://imaging.datacommons.cancer.gov/) project,\nwhich has been funded in whole or in part with Federal funds from the NCI, NIH, under task order no. HHSN26110071\nunder contract no. HHSN261201500003l.\n",
"bugtrack_url": null,
"license": "LICENSE",
"summary": "High-level DICOM abstractions.",
"version": "0.26.1",
"project_urls": {
"documentation": "https://highdicom.readthedocs.io/",
"homepage": "https://github.com/imagingdatacommons/highdicom",
"repository": "https://github.com/ImagingDataCommons/highdicom.git"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "fab11450bf5ac786c3519e2915ca0d911e3f9e8b7f41025f8baff0c0b0704862",
"md5": "f7d509f265317e41c73474c010ab73a9",
"sha256": "2b554a661c8ff6d2c6c0ca41df240c29161326066dd4025025b7768a497374df"
},
"downloads": -1,
"filename": "highdicom-0.26.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f7d509f265317e41c73474c010ab73a9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 1106171,
"upload_time": "2025-08-06T23:42:21",
"upload_time_iso_8601": "2025-08-06T23:42:21.245898Z",
"url": "https://files.pythonhosted.org/packages/fa/b1/1450bf5ac786c3519e2915ca0d911e3f9e8b7f41025f8baff0c0b0704862/highdicom-0.26.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7e44d8b353560fb248ff79a6ca5e7aae2d48c015438d943f903fa509b69a7d8e",
"md5": "7cb2ba61f5760491f71a8cef1e89f195",
"sha256": "51c3c311e3f177a21a5a0cbabd4162fc639f2dc00f4bd9f5102f2d26b1ad1920"
},
"downloads": -1,
"filename": "highdicom-0.26.1.tar.gz",
"has_sig": false,
"md5_digest": "7cb2ba61f5760491f71a8cef1e89f195",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 1124699,
"upload_time": "2025-08-06T23:42:23",
"upload_time_iso_8601": "2025-08-06T23:42:23.190183Z",
"url": "https://files.pythonhosted.org/packages/7e/44/d8b353560fb248ff79a6ca5e7aae2d48c015438d943f903fa509b69a7d8e/highdicom-0.26.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-06 23:42:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "imagingdatacommons",
"github_project": "highdicom",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "highdicom"
}