Radiology Python Packages

radiowriter

Search PubMed, screen the results and write a Radiopaedia article from them. Journal quartiles from SCImago and open access from Unpaywall. Unofficial.

kaiko-eva

Evaluation framework for oncology foundation models (FMs)

mlx-reason-ct

Native MLX port of NVIDIA NV-Reason-CT for 3D CT reasoning on Apple Silicon

radmatch

RadMatch: an auditable, finding-by-finding framework for radiology report generation

boa-contrast

Computes CT contrast phase and GI tract contrast using TotalSegmentator and ML

dicom-ai-router

DICOM router for imaging AI: receives studies, routes by rules, de-identifies (PS3.15 subset), calls the model, returns SR + key image to PACS. Audited end to end.

hl7v2-fhir-bridge

HL7 v2 to FHIR R4 bridge for the radiology workflow: ADT, orders and results over MLLP become validated, idempotent FHIR transaction bundles with provenance and actionable ACKs.

delira

Lightweight framework for fast prototyping and training deep neural networks with PyTorch and TensorFlow

radvis

RadVis (Radiology Visualization) is a visualization tool for medical images.

radgraph-it

Italian NLP package for extracting clinical entities and relations from free-text radiology reports.

frd-score

Official implementation of the Fréchet Radiomic Distance

osirixgrpc

Source code and documentation for the core OsiriXgrpc plugin

dicomaster

Secure, High-performance DICOM anonymization and metadata extraction for research and healthcare.

radiology-swarm

A powerful, enterprise-grade multi-agent system for advanced radiological analysis, diagnosis, and treatment planning. This system leverages specialized AI agents working in concert to provide comprehensive medical imaging analysis and care recommendations.

gaze-vlm

Grounded agentic framework for medical vision-language models: viewer-level image tools, multi-turn tool use, and PubMed/Open-i literature retrieval

vids-validator

Open standard for structuring, validating, and delivering annotated medical imaging datasets for AI/ML

medigan

medigan - A Python Library of Pretrained Generative Models for Medical Image Synthesis

medip

DICOM-standard medical image preprocessing toolkit with profile-driven workflows and built-in mammography support.

radreport

Parse radiology free-text reports into structured data. No ML. No GPU. No dependencies.

segauge

Geometrically-correct, DICOM-native evaluation metrics for medical image segmentation in Python: Dice, IoU, HD95, ASSD, Normalized Surface Dice, per-lesion detection F1, with bootstrap confidence intervals and subgroup/fairness slicing.

radreport-parser

Parse radiology free-text reports into structured data. No ML. No GPU. No dependencies.