MONAI Label — Intelligent Medical Image Labeling
Active-learning annotation server for medical images: auto-segmentation, interactive refinement, OHIF/3D Slicer integration.
MONAI Label — Intelligent Medical Image Labeling
MONAI Label is an intelligent open-source medical image annotation tool (distinct from the MONAI training framework). It runs as a server, exposing REST APIs that OHIF Viewer, 3D Slicer, and QuPath call to get AI-generated segmentation suggestions — cutting labeling time by up to 75% through active learning.
Key features
- Active learning loop: model learns from each correction, improves suggestions over time
- Pre-built apps for radiology (CT organs, tumors), pathology (nuclei, tissue), and endoscopy
- REST API makes it embeddable into any DICOM viewer or web app
- Supports NVIDIA GPUs via CUDA; CPU fallback for inference
- Ships with 10+ pre-trained MONAI segmentation models
Quick start
pip install monailabel
# Download a pre-built app
monailabel apps --download --name radiology --output apps/
# Download sample data and start the server
monailabel start_server --app apps/radiology --studies ./studies
# Open http://localhost:8000 in OHIF or 3D Slicer
npx ai-supply add monai-label-active-learning
Curated mirror of the open-source MONAI Label (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/monai-label-active-learning/check). Click a policy:
Consume MONAI Label — Intelligent Medical Image Labeling programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/monai-label-active-learning
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/monai-label-active-learning/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add monai-label-active-learning
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/monai-label-active-learning/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "monai-label-active-learning" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.