MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision
Biomedical Engineering / Biomedizinische Technik · 25.02.2025 · 70 (1) · 71-90
DOI: 10.1515/bmt-2024-0396 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Engineering / Biomedizinische Technik, online erschienen am 30.12.2024. Verfasst von Jianning Li und 59 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen (AöR), Essen, Germany. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 133 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIBIB NIH HHS, NHLBI NIH HHS.
Abstract (Originalsprache)
Objectives
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.
Methods
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.
Results
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.
Conclusions
MedShapeNet contains medical shapes from anatomy and surgical instruments and will continue to collect data for benchmarks and applications. The project page is: https://medshapenet.ikim.nrw/ .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen (AöR), Essen, Germany.
- Institute of Computer Graphics and Vision (ICG), Graz University of Technology, Graz, Austria.
- Computer Algorithms for Medicine Laboratory (Cafe), Graz, Austria.
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.
- Computer Vision Laboratory, Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne, Switzerland.
- Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen, Aachen, Germany.
Förderung
- NIBIB NIH HHS
- NHLBI NIH HHS
Zitieren
APA
Li, J., Zhou, Z., Yang, J., Pepe, A., Gsaxner, C., Luijten, G., Qu, C., Zhang, T., Chen, X., Li, W., Wodzinski, M., Friedrich, P., Xie, K., Jin, Y., Ambigapathy, N., Nasca, E., Solak, N., Melito, G. M., Vu, V. D., …, & Beier, S. (2025). MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision. Biomedical Engineering / Biomedizinische Technik, 70(1), 71-90. https://doi.org/10.1515/bmt-2024-0396
Vancouver
Li J, Zhou Z, Yang J, Pepe A, Gsaxner C, Luijten G, et al. MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision. Biomedical Engineering / Biomedizinische Technik. 2025;70(1):71-90. doi:10.1515/bmt-2024-0396
BibTeX
@article{Li2025,
author = {Li, Jianning and Zhou, Zongwei and Yang, Jiancheng and Pepe, Antonio and Gsaxner, Christina and Luijten, Gijs and Qu, Chongyu and Zhang, Tiezheng and Chen, Xiaoxi and Li, Wenxuan and Wodzinski, Marek and Friedrich, Paul and Xie, Kangxian and Jin, Yuan and Ambigapathy, Narmada and Nasca, Enrico and Solak, Naida and Melito, Gian Marco and Vu, Viet Duc and Memon, Afaque R and Schlachta, Christopher and De Ribaupierre, Sandrine and Patel, Rajnikant and Eagleson, Roy and Chen, Xiaojun and Mächler, Heinrich and Kirschke, Jan Stefan and de la Rosa, Ezequiel and Christ, Patrick Ferdinand and Li, Hongwei Bran and Ellis, David G and Aizenberg, Michele R and Gatidis, Sergios and Küstner, Thomas and Shusharina, Nadya and Heller, Nicholas and Andrearczyk, Vincent and Depeursinge, Adrien and Hatt, Mathieu and Sekuboyina, Anjany and Löffler, Maximilian T and Liebl, Hans and Dorent, Reuben and Vercauteren, Tom and Shapey, Jonathan and Kujawa, Aaron and Cornelissen, Stefan and Langenhuizen, Patrick and Ben-Hamadou, Achraf and Rekik, Ahmed and Pujades, Sergi and Boyer, Edmond and Bolelli, Federico and Grana, Costantino and Lumetti, Luca and Salehi, Hamidreza and Ma, Jun and Zhang, Yao and Gharleghi, Ramtin and Beier, Susann},
title = {MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision},
journal = {Biomedical Engineering / Biomedizinische Technik},
year = {2025},
volume = {70},
number = {1},
pages = {71--90},
doi = {10.1515/bmt-2024-0396}
}
EUVIMED