Home

qradiomics

Radiomics research CLI + atomic Python core for lung-cancer imaging studies. qr does two things equally well:

1. Atomic tasks — convert DICOM, extract features, merge clinical, fit a model. Each is a single command, files in / files out.
2. Workflow assembly — generate, scaffold, and run multi-step pipelines from those atomic tasks (Nextflow / Prefect / inline executors).

The canonical radiomics data flow has four stages — data → image → features → modeling — and one qr workflow plan call instantiates the whole chain.

Active successor of three earlier Choi Lab radiomics codebases (taznux/radiomics-tools, taznux/lung-image-analysis, LungCancerScreeningRadiomics). The feature extractors are now in qradiomics (Python/ITK port). New work lands here.

Start here

You want to…	Page
Install the CLI + library	Installation
Run an end-to-end example from scratch	Quick Start
Look up a command	CLI Reference
Use the Python atomic core	Python API
Run a published-cohort pipeline	Pipelines
Reproduce a Choi paper	Reproducibility
Compute shape descriptors (AHSN / spiculation)	Shape Analysis
Find a public dataset	Datasets
Cite qradiomics	Citations

One-liner kick-off

curl -sSL https://raw.githubusercontent.com/choilab-jefferson/qradiomics/main/scripts/kickoff.sh | bash

Clones the repo, creates a .venv, pip install -e ., runs qr info, and runs the smoke tests.

Headline result

On TCIA NSCLC-Radiomics (LUNG1), original_ngtdm_Busyness ranks at the top of the univariate Cox PH (HR ≈ 1.23, p < 1e-4) — replicating the headline finding of Aerts et al., Nature Communications 2014. Full reproduction numbers across Choi 2014 / 2018 / 2021 / CIR 2022: Reproducibility.

License

MIT. See the repo LICENSE.