Overview - Project-MONAI/MONAILabel Wiki

Original URL: https://github.com/Project-MONAI/MONAILabel/wiki/Overview


The MONAI Label is a server-client system that facilitates interactive medical image annotation by using AI. It is an open-source and easy-to-install ecosystem that can run locally on a machine with one or two GPUs. Both server and client work on the same machine, so initially it doesn't support multiple users or communication with an external database. It shares the same principles with MONAI. This means it is modular, Pythonic, Extensible, Easy to debug, User friendly and Portable (use components/workflows via Python “import”)

MONAI Label is composed of the following key components:

MONAI Label Server

The MONAI Label server allows/serves the integration of functionalities: active learning techniques, DeepEdit, DeepGrow, etc. It has a REST API that allows communication between the MONAI Label server and the client (i.e. Slicer plugin, OHIF plugin, etc).

MONAI Label Sample Apps

The currently available sample apps in MONAI Label are the following.

MONAI Label Sample Datasets

Among other datasets, MONAI Label uses the Medical Segmentation Decathlon datasets to showcase how easy is to create MONAI Label Apps using the three different paradigms: DeepGrow, DeepEdit and automatic segmentation

3DSlicer Viewer

This Slicer module handles calls/events created by the user interaction and MONAI Label server. Current version supports click interaction and allows the user to upload images and labels. Additional interactions such as closed curves, ROI or any other are supported by the MONAI Label server. A researcher can modify this plugin to make it more dynamic or customised to their MONAI Label Apps.

DICOMweb server support

MONAI Label supports the DICOMweb Standard for web-based medical imaging. DICOMweb is a set of RESTful services that enable users to integrate MONAI Label in their Picture Archiving and Communication System (PACS), XNAT, Image Data Commons (IDC) or any other DICOM system. This feature will enable web developers to unlock the power of healthcare images using industry-standard toolsets.

Open Health Imaging Foundation (OHIF) Viewer

The OHIF Viewer is an open-source and web-based viewer. It is based on Cornerstone.js and works out-of-the-box with Image Archives that support DICOMweb. MONAI Label has OHIF embedded and it works with the DICOMweb server support.