TY - JOUR A1 - Li, Jianning A1 - Pimentel, Pedro A1 - Szengel, Angelika A1 - Ehlke, Moritz A1 - Lamecker, Hans A1 - Zachow, Stefan A1 - Estacio, Laura A1 - Doenitz, Christian A1 - Ramm, Heiko A1 - Shi, Haochen A1 - Chen, Xiaojun A1 - Matzkin, Franco A1 - Newcombe, Virginia A1 - Ferrante, Enzo A1 - Jin, Yuan A1 - Ellis, David G. A1 - Aizenberg, Michele R. A1 - Kodym, Oldrich A1 - Spanel, Michal A1 - Herout, Adam A1 - Mainprize, James G. A1 - Fishman, Zachary A1 - Hardisty, Michael R. A1 - Bayat, Amirhossein A1 - Shit, Suprosanna A1 - Wang, Bomin A1 - Liu, Zhi A1 - Eder, Matthias A1 - Pepe, Antonio A1 - Gsaxner, Christina A1 - Alves, Victor A1 - Zefferer, Ulrike A1 - von Campe, Cord A1 - Pistracher, Karin A1 - Schäfer, Ute A1 - Schmalstieg, Dieter A1 - Menze, Bjoern H. A1 - Glocker, Ben A1 - Egger, Jan T1 - AutoImplant 2020 - First MICCAI Challenge on Automatic Cranial Implant Design JF - IEEE Transactions on Medical Imaging N2 - The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. Y1 - 2021 U6 - https://doi.org/10.1109/TMI.2021.3077047 SN - 0278-0062 VL - 40 IS - 9 SP - 2329 EP - 2342 ER - TY - JOUR A1 - Xie, Kunpeng A1 - Gruber, Lennart Johannes A1 - Crampen, Martin A1 - Li, Yao A1 - Ferreira, André A1 - Tappeiner, Elias A1 - Gillot, Maxime A1 - Schepers, Jan A1 - Xu, Jiangchang A1 - Pankert, Tobias A1 - Beyer, Michel A1 - Shahamiri, Negar A1 - ten Brink, Reinier A1 - Dot, Gauthier A1 - Weschke, Charlotte A1 - van Nistelrooij, Niels A1 - Verhelst, Pieter-Jan A1 - Guo, Yan A1 - Xu, Zhibin A1 - Bienzeisler, Jonas A1 - Rashad, Ashkan A1 - Flügge, Tabea A1 - Cotton, Ross A1 - Vinayahalingam, Shankeeth A1 - Ilesan, Robert A1 - Raith, Stefan A1 - Madsen, Dennis A1 - Seibold, Constantin A1 - Xi, Tong A1 - Bergé, Stefaan A1 - Nebelung, Sven A1 - Kodym, Oldřich A1 - Sundqvist, Osku A1 - Thieringer, Florian A1 - Lamecker, Hans A1 - Coppens, Antoine A1 - Potrusil, Thomas A1 - Kraeima, Joep A1 - Witjes, Max A1 - Wu, Guomin A1 - Chen, Xiaojun A1 - Lambrechts, Adriaan A1 - Cevidanes, Lucia H Soares A1 - Zachow, Stefan A1 - Hermans, Alexander A1 - Truhn, Daniel A1 - Alves, Victor A1 - Egger, Jan A1 - Röhrig, Rainer A1 - Hölzle, Frank A1 - Puladi, Behrus T1 - Beyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems JF - Expert Systems With Applications N2 - Despite the advances in automated medical image segmentation, AI models still underperform in various clinical settings, challenging real-world integration. In this multicenter evaluation, we analyzed 20 state-of-the-art mandibular segmentation models across 19,218 segmentations of 1,000 clinically resampled CT/CBCT scans. We show that segmentation accuracy varies by up to 25% depending on socio-technical factors such as voxel size, bone orientation, and patient conditions such as osteosynthesis or pathology. Higher sharpness, isotropic smaller voxels, and neutral orientation significantly improved results, while metallic osteosynthesis and anatomical complexity led to significant degradation. Our findings challenge the common view of AI models as “plug-and-play” tools and suggest evidence-based optimization recommendations for both clinicians and developers. This will in turn boost the integration of AI segmentation tools in routine healthcare. Y1 - 2025 UR - https://www.medrxiv.org/content/10.1101/2025.06.11.25329022v1 U6 - https://doi.org/10.1016/j.eswa.2025.130031 VL - 299 IS - Part D ER -