A Large-Scale Dataset of 3D Medical Shapes

Initiators    Jianning Li   Gijs Luijten    Jacob Murray    Yuan Jin    Antonio Pepe    Christina Gsaxner   
Moon Kim   Felix Nensa    Jens Kleesiek    Jan Egger  

Project Overview

Prior to the deep learning era, the wide application of statistical shape model (SSM) in the medical domain is evidence that shapes are commom in medical imaging. Inspired by the well-known ShapeNet and Princeton ModelNet in the field of 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.

Medical Shapes

  Human Face   Mandibular   Healthy Human Skull   Cranial Defects
  Glioblastoma (GBM)   Human Brain   Aortic Vessel Tree   Liver

Human Face Models (Link 1, Link 2)

Human Face

Mandibular CT Dataset Collection (Link)


MUG500+ (Link)


Cranil Defects (Link)

Cranil Defects

Glioblastoma (GBM) (Link)

Human Face

Human Brain (Link)

Human Brain

Aortic Vessel Tree (Link)

Aortic Vessel Tree

Liver (Link)


Spine (Link1, Link2)


Shape Completion and super-resolution demo [Link to paper]

Contact Us:

Institute for Artificial Intelligence in Medicine, University Hospital Essen (AöR), Girardetstraße 2, 45131 Essen.
Please contact Prof. Jan Egger ( or Jianning Li ( for collaboration and/or inqueries.