# AIM-Harvard/pyradiomics

Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks. Support: https://discourse.slicer.org/c/community/radiomics

Repository: https://github.com/AIM-Harvard/pyradiomics
Canonical: https://ross.abutalabs.com/products/pyradiomics
Homepage: http://pyradiomics.readthedocs.io/
Language: Jupyter Notebook
License: BSD-3-Clause
License Family: permissive
Topics: radiomics, cancer-imaging-research, medical-imaging, computational-imaging, nci-qin, tcia-dac, python, radiomics-features, docker, nci-itcr, radiomics-feature-extraction, feature-extraction, ibsi
Last push: 2025-10-27T22:04:28+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 49, release rhythm 8, longevity 100
- inputs: {"age_days": 4005, "days_push": 310, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1441, forks 551 (observed 2026-08-28T04:04:44.344286+00:00)

## What it is
PyRadiomics is an open-source Python package for extracting radiomics features from 2D and 3D medical images and binary masks. It provides a tested, reproducible reference standard for radiomic analysis with segment-based and voxel-based feature computation.

## Use cases
- extract radiomics features from medical images
- compute shape and texture features from tumor segmentations
- reproducible radiomic feature extraction for cancer research
- generate voxel-based feature maps from 3D scans
- apply wavelet and LoG filters before feature extraction
- quantify tumor phenotype from CT or MRI masks

## When to choose
- you need IBSI-compliant radiomic features in Python
- you want reproducible feature extraction with provenance info
- you work with 2D/3D medical images and binary masks
- you need a maintained reference standard for radiomics research

## When to avoid
- you need clinically validated software for patient care
- you need general-purpose image features for natural images
- you need deep-learning-based feature extraction rather than handcrafted features

## Facets
- artifact type: library
- maturity: active
- function: image-processing, data-science, machine-learning
- domain: healthcare, data-science, machine-learning
- platform: python, cross-platform
- tags: radiomics, feature-extraction, medical-imaging, cancer-imaging, ibsi, simpleitk, segmentation, research, docker

## Member repositories
- AIM-Harvard/pyradiomics (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.344286+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:36:26.440247+00:00, confidence not recorded.
  - readme: https://github.com/AIM-Harvard/pyradiomics (fetched 2026-08-28T04:04:44.344286+00:00, sha 2589910ca46d)
- Data as of 2026-08-30T08:39:29.467469+00:00.