Home · Fyron

BashPython 3.11+

uv add "fyron @ https://github.com/BitsandFlames/Fyron/releases/download/v0.3.20b4/fyron-0.3.20b4-py3-none-any.whl"

Fyron is a modular Python toolkit for healthcare data, medical imaging, and scientific analysis. Work with familiar DataFrames, arrays, and file paths to build workflows whose inputs, assumptions, and results remain inspectable.

Start Here

Get startedInstall Fyron, choose the extras you need, and run your first workflow. Explore examplesLearn from synthetic workflows before adapting them to your own research. Find an APILook up function signatures, parameters, return values, and examples.

Choose Your Workflow

Work with clinical dataQuery FHIR endpoints and SQL tables, build resources, and map reviewed data to bundles. Prepare medical imagesRead DICOM and NIfTI volumes, check geometry, and evaluate segmentation alignment. Curate image datasetsReview images locally, record selection decisions, and export curated datasets. Extract BOA featuresBuild body-composition and radiomics tables from existing BOA outputs. Analyze and validateConnect cohort preparation, statistical analysis, survival models, and model validation. Create scientific figuresExplore plots for cohort summaries, survival, model performance, and imaging quality.

See the Modules Overview for the full toolkit, use the Unified CLI for repeatable terminal jobs, or install the Fyron skill for your AI assistant.

The Scientific Workflow

Stage	Fyron modules	Output
Connect	`fhir`, `dicom`, `documents`, `core`	resources, files, and tables
Structure	`cohort`, `phenotyping`, `preprocessing`	analysis tables with explicit cohort and feature definitions
Extract	`imaging`, `boa_extraction`, `boa_radiomics`	imaging-derived measurements and feature tables
Analyze	`descriptive`, `statistics`, `survival`, `ml`, `feature_selection`	estimates, models, and summaries
Validate	`validation`, `explainability`, `imaging.segmentation`	model evaluation, explanations, and segmentation metrics
Report	`plotting`, `reporting`, `audit`	figures, tables, and provenance manifests

The Workflow Guide explains how these steps fit together. Each module documents its inputs, outputs, assumptions, and common pitfalls.

Research Use

Fyron is in public beta. Pin the version used for a study, preserve the analysis parameters, and review Release History before upgrading. Research Reliability describes the available verification evidence and its limits.

Fyron supports research; it does not replace clinical validation, privacy review, or institutional approval. See Using Fyron in Research for reproducibility, data handling, and citation guidance, and About Fyron for the project's purpose.

Citation

Please cite the version used in your work, including studies using Fyron Curate.

René Hosch, Katarzyna Borys, Sina Warmer, Jannis Straus, Kamyar Hartmann, and Justin Woolley (2026). Fyron: An Open Research Companion for Healthcare Interoperability, Data Science and AI. Version 0.3.20b4 [Computer software].

BibTeX

bibtex

@software{hosch_fyron_2026,
  author = {Hosch, Ren{\'e} and Borys, Katarzyna and Warmer, Sina and Straus, Jannis and Hartmann, Kamyar and Woolley, Justin},
  title = {Fyron: An Open Research Companion for Healthcare Interoperability, Data Science and AI},
  year = {2026},
  version = {0.3.20b4},
  url = {https://github.com/bitsandflames/fyron}
}

Citation metadata · Research and citation guidance

Citation is appreciated, not a license requirement.