PyRadiomics addresses a core need in precision oncology: systematically extracting quantitative features from medical images. This open-source Python package pulls hundreds of radiomic features — shape, texture, first-order statistics — from 2D and 3D images and binary masks, supporting both region-of-interest (“segment-based”) and voxel-based feature maps. It’s a natural fit for studies linking imaging phenotypes to tumor heterogeneity, metastatic behavior, or treatment response.
Sustainability Snapshot via Cancer Complexity Toolkit:
📚 Comprehensive documentation with README, dependency tracking, and user manual on ReadTheDocs
🔧 Active development on GitHub (Radiomics/pyradiomics)
✅ Quality indicators: JOSS Score 0.56 | Almanack 0.55
🌱 All four Almanack checks pass
Why this matters: PyRadiomics earns a “Developing” Almanack grade (0.55) with a notable distinction: it’s one of the only tools in the CCKP registry where all four sustainability checks pass (with complete README, dependency presence, test coverage). For labs integrating imaging data into cancer research workflows, it provides a reproducible, well-tested path from raw scans to quantitative phenotypic features.
Attribution: Developed by the Computational Imaging & Bioinformatics Laboratory at Harvard Medical School / Dana-Farber Cancer Institute (Radiomics/pyradiomics).
