Introduction
Radiuma is a Unified Zero-Code Executable Graphical Workflow Generator for Reproducible and Shareable Medical Image Analysis and Machine Learning
It is an open-access platform designed to make advanced medical image analysis, radiomics, and machine learning more accessible, reproducible, and shareable.
Radiuma provides a visual, node-based interface that allows researchers and clinicians to build complete executable workflows without writing code. Individual modules can be used independently or connected to create customized end-to-end pipelines.
More Details
Read more: https://arxiv.org/abs/2605.24201
Key capabilities include:
🔹 Support for CT, MRI, PET, SPECT, ultrasound, X-ray, and multimodal imaging
🔹 DICOM, NIfTI, NRRD, RT-Structure, CSV, and Excel compatibility
🔹 2D, 3D, and multimodal image visualization
🔹 Image segmentation, registration, fusion, filtering, and format conversion
🔹 Standardized handcrafted and deep radiomics feature extraction
🔹 Classification, regression, clustering, feature selection, and model evaluation
🔹 Savable, reusable, and shareable graphical workflows
🔹 Compatibility with Windows, macOS, and Linux
By connecting image processing, radiomics, and machine learning within one unified environment, Radiuma helps reduce fragmented workflows and supports the principles of Usability, Reusability, Reproducibility, and Accessibility (URRA).
Our goal is to empower researchers, radiologists, medical physicists, clinicians and data scientists to develop reliable imaging biomarkers and predictive models, regardless of their programming experience.
Download and Documentation
🌐 Download Radiuma:
https://radiuma.com/products/radiuma/
📘 Documentation and examples:
https://radiuma-documentation.readthedocs.io/en/latest/
🎥 Training videos:
https://www.youtube.com/@Radiuma-software
🔎 To explore more products and solutions, please visit:
https://radiuma.com
🙏 Acknowledgment
We appreciate TECVICO Corp. (tecvico.com) and VirCollab Group (vircollab.com) for their contributions and continued support in the development of Radiuma.
Reference
Please cite the following reference if you publish results with help from SERA:
Salmanpour, M., Oveisi, M., Shiri, I. and Rahmim, A., 2026. Radiuma: A Unified Zero-Code Executable Graphical Workflow Generator for Reproducible and Shareable Medical Image Analysis and Machine Learning. arXiv preprint arXiv:2605.24201.
https://arxiv.org/abs/2605.24201