@article{XieGruberCrampenetal.2025, author = {Xie, Kunpeng and Gruber, Lennart Johannes and Crampen, Martin and Li, Yao and Ferreira, Andr{\´e} and Tappeiner, Elias and Gillot, Maxime and Schepers, Jan and Xu, Jiangchang and Pankert, Tobias and Beyer, Michel and Shahamiri, Negar and ten Brink, Reinier and Dot, Gauthier and Weschke, Charlotte and van Nistelrooij, Niels and Verhelst, Pieter-Jan and Guo, Yan and Xu, Zhibin and Bienzeisler, Jonas and Rashad, Ashkan and Fl{\"u}gge, Tabea and Cotton, Ross and Vinayahalingam, Shankeeth and Ilesan, Robert and Raith, Stefan and Madsen, Dennis and Seibold, Constantin and Xi, Tong and Berg{\´e}, Stefaan and Nebelung, Sven and Kodym, Oldřich and Sundqvist, Osku and Thieringer, Florian and Lamecker, Hans and Coppens, Antoine and Potrusil, Thomas and Kraeima, Joep and Witjes, Max and Wu, Guomin and Chen, Xiaojun and Lambrechts, Adriaan and Cevidanes, Lucia H Soares and Zachow, Stefan and Hermans, Alexander and Truhn, Daniel and Alves, Victor and Egger, Jan and R{\"o}hrig, Rainer and H{\"o}lzle, Frank and Puladi, Behrus}, title = {Beyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems}, volume = {299}, journal = {Expert Systems With Applications}, number = {Part D}, doi = {10.1016/j.eswa.2025.130031}, year = {2025}, abstract = {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.}, language = {en} } @article{LiPimentelSzengeletal.2021, author = {Li, Jianning and Pimentel, Pedro and Szengel, Angelika and Ehlke, Moritz and Lamecker, Hans and Zachow, Stefan and Estacio, Laura and Doenitz, Christian and Ramm, Heiko and Shi, Haochen and Chen, Xiaojun and Matzkin, Franco and Newcombe, Virginia and Ferrante, Enzo and Jin, Yuan and Ellis, David G. and Aizenberg, Michele R. and Kodym, Oldrich and Spanel, Michal and Herout, Adam and Mainprize, James G. and Fishman, Zachary and Hardisty, Michael R. and Bayat, Amirhossein and Shit, Suprosanna and Wang, Bomin and Liu, Zhi and Eder, Matthias and Pepe, Antonio and Gsaxner, Christina and Alves, Victor and Zefferer, Ulrike and von Campe, Cord and Pistracher, Karin and Sch{\"a}fer, Ute and Schmalstieg, Dieter and Menze, Bjoern H. and Glocker, Ben and Egger, Jan}, title = {AutoImplant 2020 - First MICCAI Challenge on Automatic Cranial Implant Design}, volume = {40}, journal = {IEEE Transactions on Medical Imaging}, number = {9}, issn = {0278-0062}, doi = {10.1109/TMI.2021.3077047}, pages = {2329 -- 2342}, year = {2021}, abstract = {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.}, language = {en} }