MedSeg

Segment like a pro with MedSeg.
Free online segmentation with AI-support.

Free, simple volume segmentation of radiological images with MedSeg. Use our AI models or segment manually.

Web-based

Experience seamless, lightning-fast performance with our cloud-free solution! Simply open in Google Chrome on a GPU-powered computer for optimal results.

User-friendly

Experience the future of image segmentation with our user-friendly tool designed by radiologists, for radiologists. Experience effortless workflows and improved accuracy with our radiology and gaming-inspired controls.

Fast

Our vanilla JavaScript implementation ensures maximum speed and efficiency, while GPU hardware acceleration through Canvas and WebGL provides an extra boost.

Launch MedSeg

Segmentation service

We provide segmentation services for CT or MRI datasets. Our radiologist-validated results use modern AI models to produce precise annotations in the form of masks, volumes, or 3D models/meshes in any file format. This service is available for a fee.

Research

We are open to collaborating on research and are dedicated to advancing the field. To support this effort, we are creating open-access segmentations whenever possible.

Learn More

Training AI-models

You can contribute by allowing us to train models on your data, which we'll share with the MedSeg community. You can also do segmentations to help us grow our open-access database. If interested, please get in touch.

Where to find data

Finding good quality data of sufficient abundance is a well known problem in AI. Here you'll find our top choices with detailed instructions and download walkthroughs

Read More
COVID-19 CT segmentation dataset

Still available at our old site, find it here.
COVID-19 image
Visit our forum for FAQ, feedback and other useful information
Forum image
Segmentation in radiology is crucial for many applications, such as volumetry, visualization, 3D printing, radiotherapy, and more. However, it is often seen as tedious and uninteresting. Recent advances in AI have made it possible to use automated and interactive segmentation, which we believe is ready for widespread clinical use. MedSeg is not intended for direct clinical use, but we hope that our open-access segmentation database will accelerate the development of clinically validated models. We believe that segmentation should be simple, fun, and accessible to everyone. If you share our vision, please consider helping us annotate more data or by collaboration.

MedSeg is based on the following openly available tools and resources:
DICOM reader: https://github.com/rii-mango/Daikon
Nifti reader: https://github.com/rii-mango/NIFTI-Reader-JS
Deep learning (DL) in browser: https://www.tensorflow.org/js
Development of DL models: https://keras.io/ + https://www.tensorflow.org/
DeepGrow module: https://arxiv.org/abs/1903.08205
Ideas and experience from a Python-based segmentation tool with AI-capabilities. RILContour: https://link.springer.com/article/10.1007/s10278-019-00232-0
Another great advanced application with many post-processing tools, 3D Slicer: https://www.slicer.org/
Overview of web-based DICOM viewers: https://medevel.com/14-best-browser-web-based-dicom-viewers-projects/

Get in touch with us