Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Dec 30;70(1):71-90.
doi: 10.1515/bmt-2024-0396. Print 2025 Feb 25.

MedShapeNet - a large-scale dataset of 3D medical shapes for computer vision

Jianning Li  1   2   3 Zongwei Zhou  4 Jiancheng Yang  5 Antonio Pepe  2   3 Christina Gsaxner  2   3   6 Gijs Luijten  1   2   3   7 Chongyu Qu  4 Tiezheng Zhang  4 Xiaoxi Chen  8 Wenxuan Li  4 Marek Wodzinski  9   10 Paul Friedrich  11 Kangxian Xie  12 Yuan Jin  2   3   13 Narmada Ambigapathy  1 Enrico Nasca  1 Naida Solak  2   3 Gian Marco Melito  14 Viet Duc Vu  15 Afaque R Memon  16   17 Christopher Schlachta  18 Sandrine De Ribaupierre  18 Rajnikant Patel  18 Roy Eagleson  18 Xiaojun Chen  19   17 Heinrich Mächler  20 Jan Stefan Kirschke  21 Ezequiel de la Rosa  22   23 Patrick Ferdinand Christ  24 Hongwei Bran Li  24 David G Ellis  25 Michele R Aizenberg  25 Sergios Gatidis  26 Thomas Küstner  26 Nadya Shusharina  27 Nicholas Heller  28 Vincent Andrearczyk  29 Adrien Depeursinge  29   30 Mathieu Hatt  31 Anjany Sekuboyina  23 Maximilian T Löffler  32 Hans Liebl  32 Reuben Dorent  33   34 Tom Vercauteren  33 Jonathan Shapey  33 Aaron Kujawa  33 Stefan Cornelissen  35   36 Patrick Langenhuizen  35   36 Achraf Ben-Hamadou  37   38 Ahmed Rekik  37   38 Sergi Pujades  39 Edmond Boyer  39 Federico Bolelli  40 Costantino Grana  40 Luca Lumetti  40 Hamidreza Salehi  41 Jun Ma  42   43   44 Yao Zhang  45 Ramtin Gharleghi  46 Susann Beier  46 Arcot Sowmya  47 Eduardo A Garza-Villarreal  48 Thania Balducci  48 Diego Angeles-Valdez  48   49 Roberto Souza  50 Leticia Rittner  51 Richard Frayne  52   53 Yuanfeng Ji  54 Vincenzo Ferrari  55   56 Soumick Chatterjee  57   58 Florian Dubost  59 Stefanie Schreiber  60   61   62 Hendrik Mattern  60   61   63 Oliver Speck  60   61   63 Daniel Haehn  64 Christoph John  65 Andreas Nürnberger  61   57 João Pedrosa  66   67 Carlos Ferreira  66   67 Guilherme Aresta  68 António Cunha  66   69 Aurélio Campilho  66   67 Yannick Suter  70 Jose Garcia  71 Alain Lalande  72   73 Vicky Vandenbossche  74 Aline Van Oevelen  74 Kate Duquesne  74 Hamza Mekhzoum  75 Jef Vandemeulebroucke  75 Emmanuel Audenaert  74 Claudia Krebs  76 Timo van Leeuwen  77 Evie Vereecke  77 Hauke Heidemeyer  78 Rainer Röhrig  78 Frank Hölzle  6 Vahid Badeli  79 Kathrin Krieger  80 Matthias Gunzer  80   81 Jianxu Chen  80 Timo van Meegdenburg  1   82 Amin Dada  1 Miriam Balzer  1 Jana Fragemann  1 Frederic Jonske  1 Moritz Rempe  1 Stanislav Malorodov  1 Fin H Bahnsen  1 Constantin Seibold  1 Alexander Jaus  83 Zdravko Marinov  83 Paul F Jaeger  84   85 Rainer Stiefelhagen  83 Ana Sofia Santos  1   86 Mariana Lindo  1   86 André Ferreira  1   86 Victor Alves  86 Michael Kamp  1   87   88   89 Amr Abourayya  1   88 Felix Nensa  1   90 Fabian Hörst  1   87 Alexander Brehmer  1 Lukas Heine  1   87 Yannik Hanusrichter  91   92 Martin Weßling  91   92 Marcel Dudda  93   94 Lars E Podleska  95 Matthias A Fink  96 Julius Keyl  1 Konstantinos Tserpes  97 Moon-Sung Kim  1   90   87 Shireen Elhabian  98 Hans Lamecker  99 Dženan Zukić  100 Beatriz Paniagua  100 Christian Wachinger  101 Martin Urschler  102 Luc Duong  103 Jakob Wasserthal  104 Peter F Hoyer  105 Oliver Basu  106   7 Thomas Maal  107 Max J H Witjes  108 Gregor Schiele  109 Ti-Chiun Chang  110 Seyed-Ahmad Ahmadi  111 Ping Luo  54 Bjoern Menze  24 Mauricio Reyes  70   112 Thomas M Deserno  113 Christos Davatzikos  114 Behrus Puladi  6   78 Pascal Fua  5 Alan L Yuille  4 Jens Kleesiek  1   115   116   87 Jan Egger  1   2   3   87   7
Affiliations
Free article

MedShapeNet - a large-scale dataset of 3D medical shapes for computer vision

Jianning Li et al. Biomed Tech (Berl). .
Free article

Abstract

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/.

Keywords: 3D medical shapes; anatomy education; augmented reality; benchmark; shapeomics; virtual reality.

PubMed Disclaimer

References

    1. Esteva, A, Chou, K, Yeung, S, Naik, N, Madani, A, Mottaghi, A, et al.. Deep learning-enabled medical computer vision. npk Digital Med 2021;4:1–9. https://doi.org/10.1038/s41746-020-00376-2 . - DOI
    1. Young, T, Hazarika, D, Poria, S, Cambria, E. Recent trends in deep learning based natural language processing. IEEE Comput Intell Mag 2018;13:55–75. https://doi.org/10.1109/mci.2018.2840738 . - DOI
    1. Latif, S, Rana, R, Khalifa, S, Jurdak, R, Qadir, J, Schuller, BW. Deep representation learning in speech processing: challenges, recent advances, and future trends. arXiv preprint arXiv:2001.00378. 2020.
    1. Sun, C, Shrivastava, A, Singh, S, Gupta, A. Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE international conference on computer vision ; 2017:843–52 pp.
    1. Egger, J, Gsaxner, C, Pepe, A, Pomykala, KL, Jonske, F, Kurz, M, et al.. Medical deep learning—a systematic meta-review. Comput Methods Progr Biomed 2022;221:106874. https://doi.org/10.1016/j.cmpb.2022.106874 . - DOI

MeSH terms

LinkOut - more resources