{"id":15109175,"url":"https://github.com/aim-harvard/pyradiomics","last_synced_at":"2025-05-14T03:07:03.561Z","repository":{"id":38344545,"uuid":"42527304","full_name":"AIM-Harvard/pyradiomics","owner":"AIM-Harvard","description":"Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks. Support: https://discourse.slicer.org/c/community/radiomics","archived":false,"fork":false,"pushed_at":"2024-10-21T16:31:16.000Z","size":55840,"stargazers_count":1156,"open_issues_count":146,"forks_count":499,"subscribers_count":47,"default_branch":"master","last_synced_at":"2024-10-29T15:38:09.915Z","etag":null,"topics":["cancer-imaging-research","computational-imaging","docker","feature-extraction","ibsi","medical-imaging","nci-itcr","nci-qin","python","radiomics","radiomics-feature-extraction","radiomics-features","tcia-dac"],"latest_commit_sha":null,"homepage":"http://pyradiomics.readthedocs.io/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AIM-Harvard.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGES.rst","contributing":"CONTRIBUTING.rst","funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2015-09-15T15:11:28.000Z","updated_at":"2024-10-29T12:33:29.000Z","dependencies_parsed_at":"2023-07-17T20:41:57.138Z","dependency_job_id":"c906e5de-ee9e-44ff-9686-5f08999bdd15","html_url":"https://github.com/AIM-Harvard/pyradiomics","commit_stats":{"total_commits":912,"total_committers":33,"mean_commits":"27.636363636363637","dds":0.4714912280701754,"last_synced_commit":"6a761c4eb01905cfcb1139b0b158547c55edd4df"},"previous_names":["radiomics/pyradiomics"],"tags_count":35,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIM-Harvard%2Fpyradiomics","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIM-Harvard%2Fpyradiomics/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIM-Harvard%2Fpyradiomics/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIM-Harvard%2Fpyradiomics/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AIM-Harvard","download_url":"https://codeload.github.com/AIM-Harvard/pyradiomics/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248261932,"owners_count":21074225,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cancer-imaging-research","computational-imaging","docker","feature-extraction","ibsi","medical-imaging","nci-itcr","nci-qin","python","radiomics","radiomics-feature-extraction","radiomics-features","tcia-dac"],"created_at":"2024-09-25T23:01:00.209Z","updated_at":"2025-05-14T03:07:03.554Z","avatar_url":"https://github.com/AIM-Harvard.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pyradiomics v3.1.0\n\n\u003c-- ## Build Status\n\n| Linux / MacOS                 | Windows                       |\n| ----------------------------- | ----------------------------- |\n|                               |                               |\n--\u003e\n\n## Radiomics feature extraction in Python\n\nThis is an open-source python package for the extraction of Radiomics features\nfrom medical imaging.\n\nWith this package we aim to establish a reference standard for Radiomic\nAnalysis, and provide a tested and maintained open-source platform for easy and\nreproducible Radiomic Feature extraction. By doing so, we hope to increase\nawareness of radiomic capabilities and expand the community.\n\nThe platform supports both the feature extraction in 2D and 3D and can be used\nto calculate single values per feature for a region of interest\n(\"segment-based\") or to generate feature maps (\"voxel-based\").\n\n**Not intended for clinical use.**\n\n**If you publish any work which uses this package, please cite the following\npublication:** _van Griethuysen, J. J. M., Fedorov, A., Parmar, C., Hosny, A.,\nAucoin, N., Narayan, V., Beets-Tan, R. G. H., Fillion-Robin, J. C., Pieper, S.,\nAerts, H. J. W. L. (2017). Computational Radiomics System to Decode the\nRadiographic Phenotype. Cancer Research, 77(21), e104–e107.\nhttps://doi.org/10.1158/0008-5472.CAN-17-0339_\n\n### Join the Community!\n\nPlease join the\n[Radiomics community section of the 3D Slicer Discourse](https://discourse.slicer.org/c/community/radiomics/23).\n\n### Feature Classes\n\nCurrently supports the following feature classes:\n\n- First Order Statistics\n- Shape-based (2D and 3D)\n- Gray Level Co-occurrence Matrix (GLCM)\n- Gray Level Run Length Matrix (GLRLM)\n- Gray Level Size Zone Matrix (GLSZM)\n- Gray Level Dependece Matrix (GLDM)\n- Neighboring Gray Tone Difference Matrix (NGTDM)\n\n### Filter Classes\n\nAside from the feature classes, there are also some built-in optional filters:\n\n- Laplacian of Gaussian (LoG, based on SimpleITK functionality)\n- Wavelet (using the PyWavelets package)\n- Square\n- Square Root\n- Logarithm\n- Exponential\n- Gradient (Magnitude)\n- Local Binary Pattern (LBP) 2D / 3D\n\n### Supporting reproducible extraction\n\nAside from calculating features, the pyradiomics package includes provenance\ninformation in the output. This information contains information on used image\nand mask, as well as applied settings and filters, thereby enabling fully\nreproducible feature extraction.\n\n### Documentation\n\nFor more information, see the sphinx generated documentation available\n[here](http://pyradiomics.readthedocs.io/).\n\nAlternatively, you can generate the documentation by checking out the master\nbranch and running from the root directory:\n\n    python setup.py build_sphinx\n\nThe documentation can then be viewed in a browser by opening\n`PACKAGE_ROOT\\build\\sphinx\\html\\index.html`.\n\nFurthermore, an instruction video is available\n[here](http://radiomics.io/pyradiomics.html).\n\n### Installation\n\nPyRadiomics is OS independent and compatible with Python \u003e= 3.5. Pre-built\nbinaries are available on PyPi and Conda. To install PyRadiomics, ensure you\nhave python installed and run:\n\n    `python -m pip install pyradiomics`\n\nDetailed installation instructions, as well as instructions for building\nPyRadiomics from source, are available in the\n[documentation](http://pyradiomics.readthedocs.io/en/latest/installation.html).\n\n### Docker\n\nPyRadiomics also supports [Dockers](https://www.docker.com/). Currently, 2\ndockers are available:\n\nThe first one is a [Jupyter notebook](http://jupyter.org/) with PyRadiomics\npre-installed with example Notebooks.\n\nTo get the Docker:\n\n    docker pull radiomics/pyradiomics:latest\n\nThe `radiomics/notebook` Docker has an exposed volume (`/data`) that can be\nmapped to the host system directory. For example, to mount the current\ndirectory:\n\n    docker run --rm -it --publish 8888:8888 -v `pwd`:/data radiomics/notebook\n\nor for a less secure notebook, skip the randomly generated token\n\n    docker run --rm -it --publish 8888:8888 -v `pwd`:/data radiomics/notebook start-notebook.sh --NotebookApp.token=''\n\nand open the local webpage at http://localhost:8888/ with the current directory\nat http://localhost:8888/tree/data.\n\nThe second is a docker which exposes the PyRadiomics CLI interface. To get the\nCLI-Docker:\n\n    docker pull radiomics/pyradiomics:CLI\n\nYou can then use the PyRadiomics CLI as follows:\n\n    docker run radiomics/pyradiomics:CLI --help\n\nFor more information on using docker, see\n[here](https://pyradiomics.readthedocs.io/en/latest/installation.html#use-pyradiomics-docker)\n\n### Usage\n\nPyRadiomics can be easily used in a Python script through the `featureextractor`\nmodule. Furthermore, PyRadiomics provides a commandline script, `pyradiomics`,\nfor both single image extraction and batchprocessing. Finally, a convenient\nfront-end interface is provided as the 'Radiomics' extension for 3D Slicer,\navailable [here](https://github.com/AIM-Harvard/SlicerRadiomics).\n\n### 3rd-party packages used in pyradiomics:\n\n- SimpleITK (Image loading and preprocessing)\n- numpy (Feature calculation)\n- PyWavelets (Wavelet filter)\n- pykwalify (Enabling yaml parameters file checking)\n- scipy (Only for LBP filter, install separately to enable this filter)\n- scikit-image (Only for LBP filter, install separately to enable this filter)\n- trimesh (Only for LBP filter, install separately to enable this filter)\n\nSee also the requirements section of the [pyproject file](pyproject.toml).\n\n### 3D Slicer\n\nPyRadiomics is also available as an\n[extension](https://github.com/AIM-Harvard/SlicerRadiomics) to\n[3D Slicer](slicer.org). Download and install the 3D slicer\n[nightly build](http://download.slicer.org/), the extension is then available in\nthe extension manager under \"SlicerRadiomics\".\n\n### License\n\nThis package is covered by the open source [3-clause BSD License](LICENSE.txt).\n\n### Developers\n\n- [Joost van Griethuysen](https://github.com/JoostJM)\u003csup\u003e1,3,4\u003c/sup\u003e\n- [Andriy Fedorov](https://github.com/fedorov)\u003csup\u003e2\u003c/sup\u003e\n- [Nicole Aucoin](https://github.com/naucoin)\u003csup\u003e2\u003c/sup\u003e\n- [Jean-Christophe Fillion-Robin](https://github.com/jcfr)\u003csup\u003e5\u003c/sup\u003e\n- [Ahmed Hosny](https://github.com/ahmedhosny)\u003csup\u003e1\u003c/sup\u003e\n- [Steve Pieper](https://github.com/pieper)\u003csup\u003e6\u003c/sup\u003e\n- [Hugo Aerts (PI)](https://github.com/hugoaerts)\u003csup\u003e1,2\u003c/sup\u003e\n\n\u003csup\u003e1\u003c/sup\u003eDepartment of Radiation Oncology, Dana-Farber Cancer Institute,\nBrigham and Women's Hospital, Harvard Medical School, Boston, MA,\n\u003csup\u003e2\u003c/sup\u003eDepartment of Radiology, Brigham and Women's Hospital, Harvard\nMedical School, Boston, MA, \u003csup\u003e3\u003c/sup\u003eDepartment of Radiology, Netherlands\nCancer Institute, Amsterdam, The Netherlands, \u003csup\u003e4\u003c/sup\u003eGROW-School for\nOncology and Developmental Biology, Maastricht University Medical Center,\nMaastricht, The Netherlands, \u003csup\u003e5\u003c/sup\u003eKitware, \u003csup\u003e6\u003c/sup\u003eIsomics\n\n### Contact\n\nWe are happy to help you with any questions. Please contact us on the\n[Radiomics community section of the 3D Slicer Discourse](https://discourse.slicer.org/c/community/radiomics/23).\n\nWe welcome contributions to PyRadiomics. Please read the\n[contributing guidelines](CONTRIBUTING.rst) on how to contribute to PyRadiomics.\n\n**This work was supported in part by the US National Cancer Institute grants:\nU24CA194354 - QUANTITATIVE RADIOMICS SYSTEM DECODING THE TUMOR PHENOTYPE and\nU01CA190234 - TUMOR GENOTYPE AND RADIOMIC PHENOTYPE IN LUNG CANCER**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faim-harvard%2Fpyradiomics","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faim-harvard%2Fpyradiomics","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faim-harvard%2Fpyradiomics/lists"}