SlicerPySERA integrates the PySERA radiomics engine into 3D Slicer as an interactive extension.
It enables reproducible, IBSI-compliant handcrafted radiomics as well as deep feature extraction directly within the Slicer environment.

1. Overview
2. Repository Structure
3. Key Features
4. Screenshots
5. Installation
6. Usage in 3D Slicer
7. Data & Batch Expectations
8. Parameters
9. Output
10. Troubleshooting
11. Integration Notes
12. Version History
13. Contact
14. Maintenance
15. Authors
16. Citation
17. License
18. Support
19. Acknowledgment

SlicerPySERA provides a graphical interface for configuring and running radiomics pipelines on medical images and segmentations within 3D Slicer. It exposes all relevant IBSI (Image Biomarker Standardisation Initiative)-aligned preprocessing and feature extraction settings directly through the GUI.

It leverages the PySERA library for computation, ensuring standardized, reproducible, and validated radiomics results.

Key capabilities:

• IBSI-compliant handcrafted radiomics and deep features
• Multi-format compatibility (NIfTI, DICOM, NRRD, RTSTRUCT, etc.)
• Batch and parallel processing support
• Comprehensive logs and parameter export for reproducibility

• PySera_Ext/ – Main 3D Slicer ScriptedLoadableModule (GUI). Includes vendored parameter files under pysera_lib/.
• PySeraCLI/ – Optional CLI wrapper for headless runs. Includes vendored parameter files under pysera_cli_lib/.
• Data/ – Example datasets for testing and development purposes.
• Resources/ – All non-code assets, including GUI icons, screenshots, configuration files, and templates for reports.

Note: The core pysera library is installed into Slicer’s Python using slicer.util.pip_install("pysera") at runtime.

• Fully integrated with 3D Slicer – no external scripts required
• IBSI-compliant handcrafted features (morphological, texture, statistical, etc.)
• Deep-learning feature extraction with pretrained models (ResNet50, VGG16, DenseNet121)
• Advanced configurability – bin size, discretization, resampling, intensity rounding
• High reproducibility – parameter snapshot and structured report export

The following screenshots illustrate the main workflows and tabs of the SlicerPySERA module.
All images are located in Resources/Screenshots/.

Title & Feature Categories

Input / Output Settings

Handcrafted Feature Extraction Mode

Deep Feature Extraction Mode

Setting Parameters

Feature Subset Selection

Run & Show Results

1. Clone or download this repository.
2. In 3D Slicer, navigate to:
   Edit → Application Settings → Modules → Additional Module Paths
   Add the path to the PySera/ directory, then restart Slicer.
3. Ensure pysera is available to Slicer’s Python:
   • Simplest: copy pysera/ into PySera/lib/pysera/
   • Alternatively: install pysera into Slicer’s Python interpreter.
4. After restarting, PySERA appears under the Radiomics module category.

Note: The PySERA library can also be used independently in Python.

1. Load an image and segmentation (mask) into Slicer.
2. Open Modules → Radiomics → PySERA.
3. Select image and mask inputs, and specify output directories.
4. Choose Handcrafted or Deep feature extraction mode.
5. Adjust IBSI parameters (for handcrafted mode).
6. Select categories/dimensions for feature subsets.
7. Click Apply to start feature extraction.

• Compatible with NIfTI, NRRD, DICOM, and RTSTRUCT inputs.
• Ensure image/mask folder structures are mirrored and contain no extra nesting.
• RTSTRUCT processing uses a temporary cache folder (temporary_files_path).

• Excel Report with:
  • Radiomics_Features: All extracted features
  • Parameters: Run configuration
  • Report: Warnings or extraction issues
• In-Slicer summary log after each run.

• Implemented as a ScriptedLoadableModule using Qt/CTK.
• Parameters are grouped for Handcrafted and Deep extraction modes.
• Synchronization maintained between selected categories and dimensions.

v1
└─ v1.0
   └─ v1.0.0 — Initial stable release

For general inquiries or academic collaboration:

Dr. Mohammad R. Salmanpour (Team Lead)
📧 [email protected] · [email protected] · [email protected]

For technical support and maintenance inquiries:

Dr. Mohammad R. Salmanpour (Team Lead)
[email protected] · [email protected] · [email protected]

Sirwan Barichin

• Dr. Mohammad R. Salmanpour (Team Lead, Fund Provider, Evaluator, Medical Imaging Expert, Backend, Refactoring, Debugging, Library Management, IBSI Standardization, Slicer GUI) – [email protected], [email protected], [email protected]
• Sirwan Barichin (IBSI Standardization, Backend, Refactoring, Debugging, Library Management, Activation of PySERA Library, Slicer GUI)
• Dr. Mehrdad Oveisi (Evaluator, Software Engineer, Advisor)
• Dr. Arman Rahmim (Fund Provider, Medical Imaging Expert, Evaluator, Advisor)

If you use this extension or PySERA in your research, please cite the following paper:

@misc{salmanpour2025pyseraopensourcestandardizedpython,
      title={PySERA: Open-Source Standardized Python Library for Automated, Scalable, and Reproducible Handcrafted and Deep Radiomics}, 
      author={Mohammad R. Salmanpour and Amir Hossein Pouria and Sirwan Barichin and Yasaman Salehi and Sonya Falahati and Isaac Shiri and Mehrdad Oveisi and Arman Rahmim},
      year={2025},
      eprint={2511.15963},
      archivePrefix={arXiv},
      primaryClass={physics.med-ph},
      url={https://arxiv.org/abs/2511.15963}, 
}

Released under the MIT License.
See LICENSE for details.

• Issues: GitHub Issues
• Documentation: This README and module help
• Examples: See PySERA Examples

Supported by:

• Quantitative Radiomolecular Imaging and Therapy (Qurit) Lab, UBC, BC, Canada
• BC Cancer Research Institute, Vancouver, BC, Canada
• Virtual Collaboration (VirCollab) Group, BC, Canada
• Technological Virtual Collaboration Corporation (TECVICO Corp.), Bc, Canada

Funding provided by the Natural Sciences and Engineering Research Council of Canada (NSERC) —
Idea to Innovation (I2I) Grant GR034192.

This repository provides the SlicerPySERA extension for 3D Slicer.
The PySERA core library is maintained separately for standalone Python usage.