Project-MONAI/MONAILabel
MONAI Label is an intelligent open source image labeling and learning tool.
What it solves
Medical image annotation is time-consuming and labor-intensive. MONAI Label reduces this effort by enabling interactive and automated labeling, helping researchers create annotated datasets and build AI models for clinical evaluation more efficiently.
How it works
It operates as a server-client system where a MONAI Label Server hosts labeling applications as services. Users interact with these apps through supported medical imaging viewers (like 3D Slicer, OHIF, or QuPath) to perform tasks like segmentation or classification. The system supports active learning, where the AI continuously learns and improves from user interactions.
Who it’s for
- Developers looking to build and deploy custom labeling applications.
- Researchers needing to create high-quality annotated datasets for medical AI.
- Clinicians and Annotators who benefit from AI-assisted tools to speed up their manual labeling workflows.
Highlights
- Supports radiology (CT/MRI), pathology (WSI), and endoscopy (video).
- Integrates with popular viewers including 3D Slicer, MITK, OHIF, QuPath, and CVAT.
- Includes support for state-of-the-art models like SAM2 for 2D and 3D tasks.
- Provides automated active learning workflows and DICOMWeb connectivity for PACS integration.