Metadata-Version: 2.4
Name: PREDICT
Version: 3.2.0
Summary: Predict: a Radiomics Extensive Digital Interchangable Classification Toolkit.
Author-email: "Martijn P. A. Starmans" <m.starmans@erasmusmc.nl>, "Sebastian R. van der Voort" <s.vandervoort@erasmusmc.nl>
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/Svdvoort/PREDICTFastr
Keywords: bioinformatics,radiomics,features
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Healthcare Industry
Classifier: Intended Audience :: Information Technology
Classifier: Intended Audience :: Education
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: System :: Distributed Computing
Classifier: Topic :: System :: Logging
Classifier: Topic :: Utilities
Requires-Python: >=3.11
Description-Content-Type: text/x-rst
License-File: LICENSE
Requires-Dist: numpy==1.26.3
Requires-Dist: configparser
Requires-Dist: joblib
Requires-Dist: natsort
Requires-Dist: pandas
Requires-Dist: phasepack
Requires-Dist: pyradiomics==3.0.1
Requires-Dist: scipy
Requires-Dist: scikit-image
Requires-Dist: SimpleITK
Requires-Dist: tables
Requires-Dist: pydicom
Dynamic: license-file

PREDICT v3.2.0
==============

PREDICT: a Radiomics Extensive Digital Interchangable Classification Toolkit
----------------------------------------------------------------------------

This is an open-source python package supporting radiomics image feature extraction.

Documentation
~~~~~~~~~~~~~

For more information, see the sphinx generated documentation available in the docs folder. PREDICT is mostly used through `the WORC toolbox <https://github.com/MStarmans91/WORC>`__, in which further documentation on the features computed is also available, see https://worc.readthedocs.io/en/latest/static/features.html.

Alternatively, you can generate the documentation by checking out the master branch and running from the root directory:

.. code:: python

   python setup.py build_sphinx

The documentation can then be viewed in a browser by opening ``PACKAGE_ROOT\build\sphinx\html\index.html``.

Installation
~~~~~~~~~~~~

PREDICT has currently been tested on Ubuntu 24.04, and Windows 10 using Python 3.11.5 and higher.

The package can be installed through pip :

.. code:: python

   pip install PREDICT

Alternatively, you can use the provided setup.py file:

.. code:: python

   python setup.py install

Make sure you first install the required packages:

.. code:: python

   pip install -r requirements.txt

Configuration and usage
~~~~~~~~~~~~~~~~~~~~~~~

We recommend using PREDICT through `the WORC toolbox <https://github.com/MStarmans91/WORC>`__, as WORC provides easy execution, good default configurations, and additional functionality such as preprocessing. If you want to use PREDICT as standalone package, we have included the default config for PREDICT from WORC in the ``tests`` folder. The main function of PREDICT is the ``PREDICT.CalcFeatures.CalcFeatures`` function, see tests.py in the test folder on the usage.

3rd-party packages used in PREDICT:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

We mainly rely on the following packages:

- SimpleITK (Image loading and preprocessing)
- numpy (Feature computation)
- scikit-image
- pandas (Storage)
- PyRadiomics
- pydicom

See also the `requirements file <requirements.txt>`__.

License
~~~~~~~

This package is covered by the open source `APACHE 2.0 License <APACHE-LICENSE-2.0>`__. When using PREDICT, please cite the following DOI: |DOI|.

Contact
~~~~~~~

We are happy to help you with any questions: please send us a message or create an issue on Github.

.. |DOI| image:: https://zenodo.org/badge/doi/10.5281/zenodo.3854839.svg
   :target: https://zenodo.org/badge/latestdoi/92298822
