MedShapeNet - A Large-scale Dataset of 3D Medical Shapes for Computer Vision

Prior to the deep learning era, the wide application of statistical shape model (SSM) in the medical domain is evidence that shapes are common in medical imaging. Inspired by the well-known ShapeNet and Princeton ModelNet in computer graphics (CG) and vision (CV), the goal of MedShapeNet is to promote the translation of methods developed in the context of CG/CV to clinical applications. MedShapeNet contains over 100,000 medical shapes, including bones, organs, vessels, muscles, etc., as well as surgical instruments.

note: the streamlit site is currently hosted on a free streamlit server, which often crashes due to high traffic. Kindly notify Jianning Li (Jianning.Li@uk-essen.de) to reboot the server if this happens. You can also go to the Download page and use the default search function (CTRL+F) to locate the direct download link of the shapes. Save MedShapeNetDataset.txt and use wget --content-disposition --trust-server-names -i MedShapeNetDataset.txt to download the entire database.

Share our website:

If you want to work with us on MedShapeNet, contact Jianning Li (Jianning.Li@uk-essen.de) with your CV (including a list of publications, if any).

Project contacts

Avatar

Jianning Li

Institute for AI in Medicine, University Hospital Essen, Germany

Avatar

Gijs Luijten

Institute for AI in Medicine, University Hospital Essen, Germany

Avatar

Jens Kleesiek

Institute for AI in Medicine, University Hospital Essen, Germany

Avatar

Jan Egger

Institute for AI in Medicine, University Hospital Essen, Germany

Contact

We provide a text file containing the urls of the shapes.
Obtain the MedShapeNetDataset.txt and use the following command to download the shapes.

wget -i MedShapeNetDataset.txt

ad