Radiology Python Packages

delira

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

kaiko-eva

Evaluation framework for oncology foundation models (FMs)

boa-contrast

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

vids-validator

Reference validator for the VIDS (Verified Imaging Dataset Standard) specification

gaze-vlm

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

frd-score

Official implementation of the Fréchet Radiomic Distance

segauge

The honest, geometrically-correct, DICOM-native evaluation harness for medical image segmentation.

radreport

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

dicomaster

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

radvis

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

osirixgrpc

Source code and documentation for the core OsiriXgrpc plugin

pyosirix

Pythonic interface for interacting with Osirix through gRPC protocol

medigan

medigan is a modular open-source Python library that provides an interface to multiple generative models and automates synthetic dataset generation.

medip

DICOM-standard medical image preprocessing toolkit — profile-driven, modality-extensible

radiology-swarm

RadiologySwarm - TGSC

radreport-parser

Parse, structure, and export radiology free-text reports to FHIR