Medshapenet–a large-scale dataset of 3d medical shapes for computer vision
Published in Biomedical Engineering/Biomedizinische Technik, 2025
The shape is commonly used to describe the objects. State-of-the-art algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from the growing popularity of ShapeNet (51,300 models) and Princeton ModelNet (127,915 models). However, a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D models of surgical instruments is missing.
We present MedShapeNet to translate data-driven vision algorithms to medical applications and to adapt state-of-the-art vision algorithms to medical problems. As a unique feature, we directly model the majority of shapes on the imaging data of real patients. We present use cases in classifying brain tumors, skull reconstructions, multi-class anatomy completion, education, and 3D printing.
By now, MedShapeNet includes 23 datasets with more than 100,000 shapes that are paired with annotations (ground truth). Our data is freely accessible via a web interface and a Python application programming interface and can be used for discriminative, reconstructive, and variational benchmarks as well as various applications in virtual, augmented, or mixed reality, and 3D printing.
Examples of 3D anatomical shapes included in MedShapeNet, such as skull, brain, pulmonary artery, lung, rib, heart, vessel tree, autochthon, vertebrae, liver, coronary artery, hips+femurs+sacrum, stomach, trachea, colon, collarbone+scapula, spleen, esophagus, clavicle, kidney, bladder, and small bowel.
Recommended citation: Li, Jianning; Zhou, Zongwei; Yang, Jiancheng; Pepe, Antonio; Gsaxner, Christina; Luijten, Gijs; Qu, Chongyu; Zhang, Tiezheng; Chen, Xiaoxi; Li, Wenxuan; . (2025). "Medshapenet–a large-scale dataset of 3d medical shapes for computer vision." Biomedical Engineering/Biomedizinische Technik. 70(1): 71-90.
Download Paper