Li Jianning, Zhou Zongwei, Yang Jiancheng, Pepe Antonio, Gsaxner Christina, Luijten Gijs, Qu Chongyu, Zhang Tiezheng, Chen Xiaoxi, Li Wenxuan, Wodzinski Marek, Friedrich Paul, Xie Kangxian, Jin Yuan, Ambigapathy Narmada, Nasca Enrico, Solak Naida, Melito Gian Marco, Vu Viet Duc, Memon Afaque R, Schlachta Christopher, De Ribaupierre Sandrine, Patel Rajnikant, Eagleson Roy, Chen Xiaojun, Mächler Heinrich, Kirschke Jan Stefan, de la Rosa Ezequiel, Christ Patrick Ferdinand, Li Hongwei Bran, Ellis David G, Aizenberg Michele R, Gatidis Sergios, Küstner Thomas, Shusharina Nadya, Heller Nicholas, Andrearczyk Vincent, Depeursinge Adrien, Hatt Mathieu, Sekuboyina Anjany, Löffler Maximilian T, Liebl Hans, Dorent Reuben, Vercauteren Tom, Shapey Jonathan, Kujawa Aaron, Cornelissen Stefan, Langenhuizen Patrick, Ben-Hamadou Achraf, Rekik Ahmed, Pujades Sergi, Boyer Edmond, Bolelli Federico, Grana Costantino, Lumetti Luca, Salehi Hamidreza, Ma Jun, Zhang Yao, Gharleghi Ramtin, Beier Susann, Sowmya Arcot, Garza-Villarreal Eduardo A, Balducci Thania, Angeles-Valdez Diego, Souza Roberto, Rittner Leticia, Frayne Richard, Ji Yuanfeng, Ferrari Vincenzo, Chatterjee Soumick, Dubost Florian, Schreiber Stefanie, Mattern Hendrik, Speck Oliver, Haehn Daniel, John Christoph, Nürnberger Andreas, Pedrosa João, Ferreira Carlos, Aresta Guilherme, Cunha António, Campilho Aurélio, Suter Yannick, Garcia Jose, Lalande Alain, Vandenbossche Vicky, Van Oevelen Aline, Duquesne Kate, Mekhzoum Hamza, Vandemeulebroucke Jef, Audenaert Emmanuel, Krebs Claudia, van Leeuwen Timo, Vereecke Evie, Heidemeyer Hauke, Röhrig Rainer, Hölzle Frank, Badeli Vahid, Krieger Kathrin, Gunzer Matthias, Chen Jianxu, van Meegdenburg Timo, Dada Amin, Balzer Miriam, Fragemann Jana, Jonske Frederic, Rempe Moritz, Malorodov Stanislav, Bahnsen Fin H, Seibold Constantin, Jaus Alexander, Marinov Zdravko, Jaeger Paul F, Stiefelhagen Rainer, Santos Ana Sofia, Lindo Mariana, Ferreira André, Alves Victor, Kamp Michael, Abourayya Amr, Nensa Felix, Hörst Fabian, Brehmer Alexander, Heine Lukas, Hanusrichter Yannik, Weßling Martin, Dudda Marcel, Podleska Lars E, Fink Matthias A, Keyl Julius, Tserpes Konstantinos, Kim Moon-Sung, Elhabian Shireen, Lamecker Hans, Zukić Dženan, Paniagua Beatriz, Wachinger Christian, Urschler Martin, Duong Luc, Wasserthal Jakob, Hoyer Peter F, Basu Oliver, Maal Thomas, Witjes Max J H, Schiele Gregor, Chang Ti-Chiun, Ahmadi Seyed-Ahmad, Luo Ping, Menze Bjoern, Reyes Mauricio, Deserno Thomas M, Davatzikos Christos, Puladi Behrus, Fua Pascal, Yuille Alan L, Kleesiek Jens, Egger Jan
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.
Biomed Tech (Berl). 2024 Dec 30;70(1):71-90. doi: 10.1515/bmt-2024-0396. Print 2025 Feb 25.
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.
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/.
形状通常用于描述物体。医学成像领域的先进算法主要与计算机视觉不同，在计算机视觉中使用体素网格、网格、点云及隐式曲面模型。从ShapeNet（51300个模型）和普林斯顿ModelNet（127915个模型）越来越受欢迎可以看出这一点。然而，缺少大量的解剖形状（如骨骼、器官、血管）和手术器械的三维模型。
我们提出MedShapeNet，将数据驱动的视觉算法转化为医学应用，并使先进的视觉算法适用于医学问题。作为一个独特的特点，我们直接在真实患者的成像数据上对大多数形状进行建模。我们展示了在脑肿瘤分类、颅骨重建、多类解剖结构完成、教育和3D打印方面的用例。
到目前为止，MedShapeNet包括23个数据集，有超过100000个与注释（真实情况）配对的形状。我们的数据可通过网络界面和Python应用程序编程接口免费获取，可用于判别、重建和变分基准测试，以及在虚拟、增强或混合现实和3D打印中的各种应用。
MedShapeNet包含来自解剖结构和手术器械的医学形状，并将继续收集用于基准测试和应用的数据。项目页面为：https://medshapenet.ikim.nrw/ 。
