@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} } @misc{ZilskeLameckerZachow2007, author = {Zilske, Michael and Lamecker, Hans and Zachow, Stefan}, title = {Adaptive Remeshing of Non-Manifold Surfaces}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-9445}, number = {07-01}, year = {2007}, abstract = {We present a unified approach for consistent remeshing of arbitrary non-manifold triangle meshes with additional user-defined feature lines, which together form a feature skeleton. Our method is based on local operations only and produces meshes of high regularity and triangle quality while preserving the geometry as well as topology of the feature skeleton and the input mesh.}, language = {en} } @misc{EhlkeRammLameckeretal.2013, author = {Ehlke, Moritz and Ramm, Heiko and Lamecker, Hans and Hege, Hans-Christian and Zachow, Stefan}, title = {Fast Generation of Virtual X-ray Images from Deformable Tetrahedral Meshes}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-41896}, year = {2013}, abstract = {We propose a novel GPU-based approach to render virtual X-ray projections of deformable tetrahedral meshes. These meshes represent the shape and the internal density distribution of a particular anatomical structure and are derived from statistical shape and intensity models (SSIMs). We apply our method to improve the geometric reconstruction of 3D anatomy (e.g.\ pelvic bone) from 2D X-ray images. For that purpose, shape and density of a tetrahedral mesh are varied and virtual X-ray projections are generated within an optimization process until the similarity between the computed virtual X-ray and the respective anatomy depicted in a given clinical X-ray is maximized. The OpenGL implementation presented in this work deforms and projects tetrahedral meshes of high resolution (200.000+ tetrahedra) at interactive rates. It generates virtual X-rays that accurately depict the density distribution of an anatomy of interest. Compared to existing methods that accumulate X-ray attenuation in deformable meshes, our novel approach significantly boosts the deformation/projection performance. The proposed projection algorithm scales better with respect to mesh resolution and complexity of the density distribution, and the combined deformation and projection on the GPU scales better with respect to the number of deformation parameters. The gain in performance allows for a larger number of cycles in the optimization process. Consequently, it reduces the risk of being stuck in a local optimum. We believe that our approach contributes in orthopedic surgery, where 3D anatomy information needs to be extracted from 2D X-rays to support surgeons in better planning joint replacements.}, language = {en} } @inproceedings{HegeSchirmacherWesterhoffetal.2002, author = {Hege, Hans-Christian and Schirmacher, Hartmut and Westerhoff, Malte and Lamecker, Hans and Prohaska, Steffen and Zachow, Stefan}, title = {From Image Data to Three-Dimensional Models - Case Studies on the Impact of 3D Patient Models}, booktitle = {Proceedings of the Japan Korea Computer Graphics Conference 2002}, publisher = {Kanazawa University}, address = {Kanazawa City, Ishikawa, Japan}, year = {2002}, language = {en} } @article{LameckerZachowWittmersetal.2006, author = {Lamecker, Hans and Zachow, Stefan and Wittmers, Antonia and Weber, Britta and Hege, Hans-Christian and Elsholtz, Barbara and Stiller, Michael}, title = {Automatic segmentation of mandibles in low-dose CT-data}, volume = {1(1)}, journal = {Int. J. Computer Assisted Radiology and Surgery}, pages = {393 -- 395}, year = {2006}, language = {en} } @article{LameckerZachowHegeetal.2006, author = {Lamecker, Hans and Zachow, Stefan and Hege, Hans-Christian and Z{\"o}ckler, Maja}, title = {Surgical treatment of craniosynostosis based on a statistical 3D-shape model}, volume = {1(1)}, journal = {Int. J. Computer Assisted Radiology and Surgery}, doi = {10.1007/s11548-006-0024-x}, pages = {253 -- 254}, year = {2006}, language = {en} } @article{ZachowLameckerElsholtzetal.2006, author = {Zachow, Stefan and Lamecker, Hans and Elsholtz, Barbara and Stiller, Michael}, title = {Is the course of the mandibular nerve deducible from the shape of the mandible?}, journal = {Int. J. of Computer Assisted Radiology and Surgery}, publisher = {Springer}, pages = {415 -- 417}, year = {2006}, language = {en} } @misc{EhlkeRammLameckeretal.2012, author = {Ehlke, Moritz and Ramm, Heiko and Lamecker, Hans and Zachow, Stefan}, title = {Efficient projection and deformation of volumetric intensity models for accurate simulation of X-ray images}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-16580}, year = {2012}, abstract = {We present an efficient GPU-based method to generate virtual X-ray images from tetrahedral meshes which are associated with attenuation values. In addition, a novel approach is proposed that performs the model deformation on the GPU. The tetrahedral grids are derived from volumetric statistical shape and intensity models (SSIMs) and describe anatomical structures. Our research targets at reconstructing 3D anatomical shapes by comparing virtual X-ray images generated using our novel approach with clinical data while varying the shape and density of the SSIM in an optimization process. We assume that a deformed SSIM adequately represents an anatomy of interest when the similarity between the virtual and the clinical X-ray image is maximized. The OpenGL implementation presented here generates accurate (virtual) X-ray images at interactive rates, thus qualifying it for its use in the reconstruction process.}, language = {en} } @misc{RammMorilloVictoriaTodtetal.2013, author = {Ramm, Heiko and Morillo Victoria, Oscar Salvador and Todt, Ingo and Schirmacher, Hartmut and Ernst, Arneborg and Zachow, Stefan and Lamecker, Hans}, title = {Visual Support for Positioning Hearing Implants}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42495}, year = {2013}, abstract = {We present a software planning tool that provides intuitive visual feedback for finding suitable positions of hearing implants in the human temporal bone. After an automatic reconstruction of the temporal bone anatomy the tool pre-positions the implant and allows the user to adjust its position interactively with simple 2D dragging and rotation operations on the bone's surface. During this procedure, visual elements like warning labels on the implant or color encoded bone density information on the bone geometry provide guidance for the determination of a suitable fit.}, language = {en} } @misc{AmbellanLameckervonTycowiczetal.2019, author = {Ambellan, Felix and Lamecker, Hans and von Tycowicz, Christoph and Zachow, Stefan}, title = {Statistical Shape Models - Understanding and Mastering Variation in Anatomy}, issn = {1438-0064}, doi = {10.1007/978-3-030-19385-0_5}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-72699}, year = {2019}, abstract = {In our chapter we are describing how to reconstruct three-dimensional anatomy from medical image data and how to build Statistical 3D Shape Models out of many such reconstructions yielding a new kind of anatomy that not only allows quantitative analysis of anatomical variation but also a visual exploration and educational visualization. Future digital anatomy atlases will not only show a static (average) anatomy but also its normal or pathological variation in three or even four dimensions, hence, illustrating growth and/or disease progression. Statistical Shape Models (SSMs) are geometric models that describe a collection of semantically similar objects in a very compact way. SSMs represent an average shape of many three-dimensional objects as well as their variation in shape. The creation of SSMs requires a correspondence mapping, which can be achieved e.g. by parameterization with a respective sampling. If a corresponding parameterization over all shapes can be established, variation between individual shape characteristics can be mathematically investigated. We will explain what Statistical Shape Models are and how they are constructed. Extensions of Statistical Shape Models will be motivated for articulated coupled structures. In addition to shape also the appearance of objects will be integrated into the concept. Appearance is a visual feature independent of shape that depends on observers or imaging techniques. Typical appearances are for instance the color and intensity of a visual surface of an object under particular lighting conditions, or measurements of material properties with computed tomography (CT) or magnetic resonance imaging (MRI). A combination of (articulated) statistical shape models with statistical models of appearance lead to articulated Statistical Shape and Appearance Models (a-SSAMs).After giving various examples of SSMs for human organs, skeletal structures, faces, and bodies, we will shortly describe clinical applications where such models have been successfully employed. Statistical Shape Models are the foundation for the analysis of anatomical cohort data, where characteristic shapes are correlated to demographic or epidemiologic data. SSMs consisting of several thousands of objects offer, in combination with statistical methods ormachine learning techniques, the possibility to identify characteristic clusters, thus being the foundation for advanced diagnostic disease scoring.}, language = {en} } @incollection{AmbellanLameckervonTycowiczetal.2019, author = {Ambellan, Felix and Lamecker, Hans and von Tycowicz, Christoph and Zachow, Stefan}, title = {Statistical Shape Models - Understanding and Mastering Variation in Anatomy}, volume = {3}, booktitle = {Biomedical Visualisation}, number = {1156}, editor = {Rea, Paul M.}, edition = {1}, publisher = {Springer Nature Switzerland AG}, isbn = {978-3-030-19384-3}, doi = {10.1007/978-3-030-19385-0_5}, pages = {67 -- 84}, year = {2019}, abstract = {In our chapter we are describing how to reconstruct three-dimensional anatomy from medical image data and how to build Statistical 3D Shape Models out of many such reconstructions yielding a new kind of anatomy that not only allows quantitative analysis of anatomical variation but also a visual exploration and educational visualization. Future digital anatomy atlases will not only show a static (average) anatomy but also its normal or pathological variation in three or even four dimensions, hence, illustrating growth and/or disease progression. Statistical Shape Models (SSMs) are geometric models that describe a collection of semantically similar objects in a very compact way. SSMs represent an average shape of many three-dimensional objects as well as their variation in shape. The creation of SSMs requires a correspondence mapping, which can be achieved e.g. by parameterization with a respective sampling. If a corresponding parameterization over all shapes can be established, variation between individual shape characteristics can be mathematically investigated. We will explain what Statistical Shape Models are and how they are constructed. Extensions of Statistical Shape Models will be motivated for articulated coupled structures. In addition to shape also the appearance of objects will be integrated into the concept. Appearance is a visual feature independent of shape that depends on observers or imaging techniques. Typical appearances are for instance the color and intensity of a visual surface of an object under particular lighting conditions, or measurements of material properties with computed tomography (CT) or magnetic resonance imaging (MRI). A combination of (articulated) statistical shape models with statistical models of appearance lead to articulated Statistical Shape and Appearance Models (a-SSAMs).After giving various examples of SSMs for human organs, skeletal structures, faces, and bodies, we will shortly describe clinical applications where such models have been successfully employed. Statistical Shape Models are the foundation for the analysis of anatomical cohort data, where characteristic shapes are correlated to demographic or epidemiologic data. SSMs consisting of several thousands of objects offer, in combination with statistical methods ormachine learning techniques, the possibility to identify characteristic clusters, thus being the foundation for advanced diagnostic disease scoring.}, language = {en} } @article{HildebrandtBrueningSchmidtetal.2019, author = {Hildebrandt, Thomas and Bruening, Jan Joris and Schmidt, Nora Laura and Lamecker, Hans and Heppt, Werner and Zachow, Stefan and Goubergrits, Leonid}, title = {The Healthy Nasal Cavity - Characteristics of Morphology and Related Airflow Based on a Statistical Shape Model Viewed from a Surgeon's Perspective}, volume = {35}, journal = {Facial Plastic Surgery}, number = {1}, doi = {10.1055/s-0039-1677721}, pages = {9 -- 13}, year = {2019}, abstract = {Functional surgery on the nasal framework requires referential criteria to objectively assess nasal breathing for indication and follow-up. Thismotivated us to generate amean geometry of the nasal cavity based on a statistical shape model. In this study, the authors could demonstrate that the introduced nasal cavity's mean geometry features characteristics of the inner shape and airflow, which are commonly observed in symptom-free subjects. Therefore, the mean geometry might serve as a reference-like model when one considers qualitative aspects. However, to facilitate quantitative considerations and statistical inference, further research is necessary. Additionally, the authorswere able to obtain details about the importance of the isthmus nasi and the inferior turbinate for the intranasal airstream.}, language = {en} } @article{HildebrandtBrueningLameckeretal.2019, author = {Hildebrandt, Thomas and Bruening, Jan Joris and Lamecker, Hans and Zachow, Stefan and Heppt, Werner and Schmidt, Nora and Goubergrits, Leonid}, title = {Digital Analysis of Nasal Airflow Facilitating Decision Support in Rhinosurgery}, volume = {35}, journal = {Facial Plastic Surgery}, number = {1}, doi = {10.1055/s-0039-1677720}, pages = {1 -- 8}, year = {2019}, abstract = {Successful functional surgery on the nasal framework requires reliable and comprehensive diagnosis. In this regard, the authors introduce a new methodology: Digital Analysis of Nasal Airflow (diANA). It is based on computational fluid dynamics, a statistical shape model of the healthy nasal cavity and rhinologic expertise. diANA necessitates an anonymized tomographic dataset of the paranasal sinuses including the complete nasal cavity and, when available, clinical information. The principle of diANA is to compare the morphology and the respective airflow of an individual nose with those of a reference. This enablesmorphometric aberrations and consecutive flow field anomalies to localize and quantify within a patient's nasal cavity. Finally, an elaborated expert opinion with instructive visualizations is provided. Using diANA might support surgeons in decision-making, avoiding unnecessary surgery, gaining more precision, and target-orientation for indicated operations.}, language = {en} } @article{BernardSalamancaThunbergetal.2016, author = {Bernard, Florian and Salamanca, Luis and Thunberg, Johan and Tack, Alexander and Jentsch, Dennis and Lamecker, Hans and Zachow, Stefan and Hertel, Frank and Goncalves, Jorge and Gemmar, Peter}, title = {Shape-aware Surface Reconstruction from Sparse Data}, journal = {arXiv}, arxiv = {http://arxiv.org/abs/arXiv:1602.08425v1}, pages = {1602.08425v1}, year = {2016}, abstract = {The reconstruction of an object's shape or surface from a set of 3D points is a common topic in materials and life sciences, computationally handled in computer graphics. Such points usually stem from optical or tactile 3D coordinate measuring equipment. Surface reconstruction also appears in medical image analysis, e.g. in anatomy reconstruction from tomographic measurements or the alignment of intra-operative navigation and preoperative planning data. In contrast to mere 3D point clouds, medical imaging yields contextual information on the 3D point data that can be used to adopt prior information on the shape that is to be reconstructed from the measurements. In this work we propose to use a statistical shape model (SSM) as a prior for surface reconstruction. The prior knowledge is represented by a point distribution model (PDM) that is associated with a surface mesh. Using the shape distribution that is modelled by the PDM, we reformulate the problem of surface reconstruction from a probabilistic perspective based on a Gaussian Mixture Model (GMM). In order to do so, the given measurements are interpreted as samples of the GMM. By using mixture components with anisotropic covariances that are oriented according to the surface normals at the PDM points, a surface-based tting is accomplished. By estimating the parameters of the GMM in a maximum a posteriori manner, the reconstruction of the surface from the given measurements is achieved. Extensive experiments suggest that our proposed approach leads to superior surface reconstructions compared to Iterative Closest Point (ICP) methods.}, language = {en} } @article{BernardSalamancaThunbergetal.2017, author = {Bernard, Florian and Salamanca, Luis and Thunberg, Johan and Tack, Alexander and Jentsch, Dennis and Lamecker, Hans and Zachow, Stefan and Hertel, Frank and Goncalves, Jorge and Gemmar, Peter}, title = {Shape-aware Surface Reconstruction from Sparse 3D Point-Clouds}, volume = {38}, journal = {Medical Image Analysis}, doi = {10.1016/j.media.2017.02.005}, pages = {77 -- 89}, year = {2017}, abstract = {The reconstruction of an object's shape or surface from a set of 3D points plays an important role in medical image analysis, e.g. in anatomy reconstruction from tomographic measurements or in the process of aligning intra-operative navigation and preoperative planning data. In such scenarios, one usually has to deal with sparse data, which significantly aggravates the problem of reconstruction. However, medical applications often provide contextual information about the 3D point data that allow to incorporate prior knowledge about the shape that is to be reconstructed. To this end, we propose the use of a statistical shape model (SSM) as a prior for surface reconstruction. The SSM is represented by a point distribution model (PDM), which is associated with a surface mesh. Using the shape distribution that is modelled by the PDM, we formulate the problem of surface reconstruction from a probabilistic perspective based on a Gaussian Mixture Model (GMM). In order to do so, the given points are interpreted as samples of the GMM. By using mixture components with anisotropic covariances that are "oriented" according to the surface normals at the PDM points, a surface-based fitting is accomplished. Estimating the parameters of the GMM in a maximum a posteriori manner yields the reconstruction of the surface from the given data points. We compare our method to the extensively used Iterative Closest Points method on several different anatomical datasets/SSMs (brain, femur, tibia, hip, liver) and demonstrate superior accuracy and robustness on sparse data.}, language = {en} } @inproceedings{RammVictoriaMorilloTodtetal.2013, author = {Ramm, Heiko and Victoria Morillo, Oscar Salvador and Todt, Ingo and Schirmacher, Hartmut and Ernst, Arneborg and Zachow, Stefan and Lamecker, Hans}, title = {Visual Support for Positioning Hearing Implants}, booktitle = {Proceedings of the 12th annual meeting of the CURAC society}, editor = {Freysinger, Wolfgang}, pages = {116 -- 120}, year = {2013}, language = {en} } @article{KainmuellerLameckerHelleretal.2013, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Heller, Markus O. and Weber, Britta and Hege, Hans-Christian and Zachow, Stefan}, title = {Omnidirectional Displacements for Deformable Surfaces}, volume = {17}, journal = {Medical Image Analysis}, number = {4}, publisher = {Elsevier}, doi = {10.1016/j.media.2012.11.006}, pages = {429 -- 441}, year = {2013}, language = {en} } @inproceedings{AmbellanTackWilsonetal.2017, author = {Ambellan, Felix and Tack, Alexander and Wilson, Dave and Anglin, Carolyn and Lamecker, Hans and Zachow, Stefan}, title = {Evaluating two methods for Geometry Reconstruction from Sparse Surgical Navigation Data}, volume = {16}, booktitle = {Proceedings of the Jahrestagung der Deutschen Gesellschaft f{\"u}r Computer- und Roboterassistierte Chirurgie (CURAC)}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-65339}, pages = {24 -- 30}, year = {2017}, abstract = {In this study we investigate methods for fitting a Statistical Shape Model (SSM) to intraoperatively acquired point cloud data from a surgical navigation system. We validate the fitted models against the pre-operatively acquired Magnetic Resonance Imaging (MRI) data from the same patients. We consider a cohort of 10 patients who underwent navigated total knee arthroplasty. As part of the surgical protocol the patients' distal femurs were partially digitized. All patients had an MRI scan two months pre-operatively. The MRI data were manually segmented and the reconstructed bone surfaces used as ground truth against which the fit was compared. Two methods were used to fit the SSM to the data, based on (1) Iterative Closest Points (ICP) and (2) Gaussian Mixture Models (GMM). For both approaches, the difference between model fit and ground truth surface averaged less than 1.7 mm and excellent correspondence with the distal femoral morphology can be demonstrated.}, language = {en} } @misc{AmbellanTackWilsonetal.2017, author = {Ambellan, Felix and Tack, Alexander and Wilson, Dave and Anglin, Carolyn and Lamecker, Hans and Zachow, Stefan}, title = {Evaluating two methods for Geometry Reconstruction from Sparse Surgical Navigation Data}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-66052}, year = {2017}, abstract = {In this study we investigate methods for fitting a Statistical Shape Model (SSM) to intraoperatively acquired point cloud data from a surgical navigation system. We validate the fitted models against the pre-operatively acquired Magnetic Resonance Imaging (MRI) data from the same patients. We consider a cohort of 10 patients who underwent navigated total knee arthroplasty. As part of the surgical protocol the patients' distal femurs were partially digitized. All patients had an MRI scan two months pre-operatively. The MRI data were manually segmented and the reconstructed bone surfaces used as ground truth against which the fit was compared. Two methods were used to fit the SSM to the data, based on (1) Iterative Closest Points (ICP) and (2) Gaussian Mixture Models (GMM). For both approaches, the difference between model fit and ground truth surface averaged less than 1.7 mm and excellent correspondence with the distal femoral morphology can be demonstrated.}, language = {en} } @article{BrueningHildebrandtHepptetal.2020, author = {Br{\"u}ning, Jan and Hildebrandt, Thomas and Heppt, Werner and Schmidt, Nora and Lamecker, Hans and Szengel, Angelika and Amiridze, Natalja and Ramm, Heiko and Bindernagel, Matthias and Zachow, Stefan and Goubergrits, Leonid}, title = {Characterization of the Airflow within an Average Geometry of the Healthy Human Nasal Cavity}, volume = {3755}, journal = {Scientific Reports}, number = {10}, doi = {10.1038/s41598-020-60755-3}, year = {2020}, abstract = {This study's objective was the generation of a standardized geometry of the healthy nasal cavity. An average geometry of the healthy nasal cavity was generated using a statistical shape model based on 25 symptom-free subjects. Airflow within the average geometry and these geometries was calculated using fluid simulations. Integral measures of the nasal resistance, wall shear stresses (WSS) and velocities were calculated as well as cross-sectional areas (CSA). Furthermore, individual WSS and static pressure distributions were mapped onto the average geometry. The average geometry featured an overall more regular shape that resulted in less resistance, reduced wall shear stresses and velocities compared to the median of the 25 geometries. Spatial distributions of WSS and pressure of average geometry agreed well compared to the average distributions of all individual geometries. The minimal CSA of the average geometry was larger than the median of all individual geometries (83.4 vs. 74.7 mm²). The airflow observed within the average geometry of the healthy nasal cavity did not equal the average airflow of the individual geometries. While differences observed for integral measures were notable, the calculated values for the average geometry lay within the distributions of the individual parameters. Spatially resolved parameters differed less prominently.}, language = {en} } @article{PimentelSzengelEhlkeetal.2020, author = {Pimentel, Pedro and Szengel, Angelika and Ehlke, Moritz and Lamecker, Hans and Zachow, Stefan and Estacio, Laura and Doenitz, Christian and Ramm, Heiko}, title = {Automated Virtual Reconstruction of Large Skull Defects using Statistical Shape Models and Generative Adversarial Networks}, volume = {12439}, journal = {Towards the Automatization of Cranial Implant Design in Cranioplasty}, editor = {Li, Jianning and Egger, Jan}, edition = {1}, publisher = {Springer International Publishing}, doi = {10.1007/978-3-030-64327-0_3}, pages = {16 -- 27}, year = {2020}, abstract = {We present an automated method for extrapolating missing regions in label data of the skull in an anatomically plausible manner. The ultimate goal is to design patient-speci� c cranial implants for correcting large, arbitrarily shaped defects of the skull that can, for example, result from trauma of the head. Our approach utilizes a 3D statistical shape model (SSM) of the skull and a 2D generative adversarial network (GAN) that is trained in an unsupervised fashion from samples of healthy patients alone. By � tting the SSM to given input labels containing the skull defect, a First approximation of the healthy state of the patient is obtained. The GAN is then applied to further correct and smooth the output of the SSM in an anatomically plausible manner. Finally, the defect region is extracted using morphological operations and subtraction between the extrapolated healthy state of the patient and the defective input labels. The method is trained and evaluated based on data from the MICCAI 2020 AutoImplant challenge. It produces state-of-the art results on regularly shaped cut-outs that were present in the training and testing data of the challenge. Furthermore, due to unsupervised nature of the approach, the method generalizes well to previously unseen defects of varying shapes that were only present in the hidden test dataset.}, language = {en} } @inproceedings{EstacioEhlkeTacketal.2021, author = {Estacio, Laura and Ehlke, Moritz and Tack, Alexander and Castro-Gutierrez, Eveling and Lamecker, Hans and Mora, Rensso and Zachow, Stefan}, title = {Unsupervised Detection of Disturbances in 2D Radiographs}, booktitle = {2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)}, doi = {10.1109/ISBI48211.2021.9434091}, pages = {367 -- 370}, year = {2021}, abstract = {We present a method based on a generative model for detection of disturbances such as prosthesis, screws, zippers, and metals in 2D radiographs. The generative model is trained in an unsupervised fashion using clinical radiographs as well as simulated data, none of which contain disturbances. Our approach employs a latent space consistency loss which has the benefit of identifying similarities, and is enforced to reconstruct X-rays without disturbances. In order to detect images with disturbances, an anomaly score is computed also employing the Frechet distance between the input X-ray and the reconstructed one using our generative model. Validation was performed using clinical pelvis radiographs. We achieved an AUC of 0.77 and 0.83 with clinical and synthetic data, respectively. The results demonstrated a good accuracy of our method for detecting outliers as well as the advantage of utilizing synthetic data.}, language = {en} } @article{SekuboyinaBayatHusseinietal.2020, author = {Sekuboyina, Anjany and Bayat, Amirhossein and Husseini, Malek E. and L{\"o}ffler, Maximilian and Li, Hongwei and Tetteh, Giles and Kukačka, Jan and Payer, Christian and Štern, Darko and Urschler, Martin and Chen, Maodong and Cheng, Dalong and Lessmann, Nikolas and Hu, Yujin and Wang, Tianfu and Yang, Dong and Xu, Daguang and Ambellan, Felix and Amiranashvili, Tamaz and Ehlke, Moritz and Lamecker, Hans and Lehnert, Sebastian and Lirio, Marilia and de Olaguer, Nicol{\´a}s P{\´e}rez and Ramm, Heiko and Sahu, Manish and Tack, Alexander and Zachow, Stefan and Jiang, Tao and Ma, Xinjun and Angerman, Christoph and Wang, Xin and Wei, Qingyue and Brown, Kevin and Wolf, Matthias and Kirszenberg, Alexandre and Puybareau, {\´E}lodie and Valentinitsch, Alexander and Rempfler, Markus and Menze, Bj{\"o}rn H. and Kirschke, Jan S.}, title = {VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images}, journal = {arXiv}, arxiv = {http://arxiv.org/abs/2001.09193}, year = {2020}, language = {en} } @misc{GreweLameckerZachow2013, author = {Grewe, Carl Martin and Lamecker, Hans and Zachow, Stefan}, title = {Landmark-based Statistical Shape Analysis}, journal = {Auxology - Studying Human Growth and Development url}, editor = {Hermanussen, Michael}, publisher = {Schweizerbart Verlag, Stuttgart}, pages = {199 -- 201}, year = {2013}, language = {en} } @article{EhlkeRammLameckeretal.2013, author = {Ehlke, Moritz and Ramm, Heiko and Lamecker, Hans and Hege, Hans-Christian and Zachow, Stefan}, title = {Fast Generation of Virtual X-ray Images for Reconstruction of 3D Anatomy}, volume = {19}, journal = {IEEE Transactions on Visualization and Computer Graphics}, number = {12}, doi = {10.1109/TVCG.2013.159}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-35928}, pages = {2673 -- 2682}, year = {2013}, language = {en} } @misc{GreweLameckerZachow2011, author = {Grewe, Carl Martin and Lamecker, Hans and Zachow, Stefan}, title = {Digital morphometry: The Potential of Statistical Shape Models}, journal = {Anthropologischer Anzeiger. Journal of Biological and Clinical Anthropology}, pages = {506 -- 506}, year = {2011}, language = {en} } @inproceedings{LameckerKainmuellerSeimetal.2010, author = {Lamecker, Hans and Kainm{\"u}ller, Dagmar and Seim, Heiko and Zachow, Stefan}, title = {Automatische 3D Rekonstruktion des Unterkiefers und der Mandibul{\"a}rnerven auf Basis dentaler Bildgebung}, volume = {55 (Suppl. 1)}, booktitle = {Proc. BMT, Biomed Tech}, publisher = {Walter de Gruyter-Verlag}, pages = {35 -- 36}, year = {2010}, language = {en} } @article{DworzakLameckervonBergetal.2009, author = {Dworzak, Jalda and Lamecker, Hans and von Berg, Jens and Klinder, Tobias and Lorenz, Cristian and Kainm{\"u}ller, Dagmar and Seim, Heiko and Hege, Hans-Christian and Zachow, Stefan}, title = {3D Reconstruction of the Human Rib Cage from 2D Projection Images using a Statistical Shape Model}, volume = {5}, journal = {Int. J. Comput. Assist. Radiol. Surg.}, number = {2}, publisher = {Springer}, issn = {1861-6410}, doi = {10.1007/s11548-009-0390-2}, pages = {111 -- 124}, year = {2009}, language = {en} } @article{RybakKussLameckeretal.2010, author = {Rybak, J{\"u}rgen and Kuß, Anja and Lamecker, Hans and Zachow, Stefan and Hege, Hans-Christian and Lienhard, Matthias and Singer, Jochen and Neubert, Kerstin and Menzel, Randolf}, title = {The Digital Bee Brain: Integrating and Managing Neurons in a Common 3D Reference System}, volume = {4}, journal = {Front. Syst. Neurosci.}, number = {30}, doi = {10.3389/fnsys.2010.00030}, year = {2010}, language = {en} } @inproceedings{vonBergDworzakKlinderetal.2011, author = {von Berg, Jens and Dworzak, Jalda and Klinder, Tobias and Manke, Dirk and Lamecker, Hans and Zachow, Stefan and Lorenz, Cristian}, title = {Temporal Subtraction of Chest Radiographs Compensating Pose Differences}, booktitle = {SPIE Medical Imaging}, year = {2011}, language = {en} } @inproceedings{BindernagelKainmuellerSeimetal.2011, author = {Bindernagel, Matthias and Kainm{\"u}ller, Dagmar and Seim, Heiko and Lamecker, Hans and Zachow, Stefan and Hege, Hans-Christian}, title = {An Articulated Statistical Shape Model of the Human Knee}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2011}, publisher = {Springer}, doi = {10.1007/978-3-642-19335-4_14}, pages = {59 -- 63}, year = {2011}, language = {en} } @inproceedings{KahntGallowaySeimetal.2011, author = {Kahnt, Max and Galloway, Francis and Seim, Heiko and Lamecker, Hans and Taylor, Mark and Zachow, Stefan}, title = {Robust and Intuitive Meshing of Bone-Implant Compounds}, booktitle = {CURAC}, address = {Magdeburg}, pages = {71 -- 74}, year = {2011}, language = {en} } @inproceedings{SeimKainmuellerLameckeretal.2010, author = {Seim, Heiko and Kainm{\"u}ller, Dagmar and Lamecker, Hans and Bindernagel, Matthias and Malinowski, Jana and Zachow, Stefan}, title = {Model-based Auto-Segmentation of Knee Bones and Cartilage in MRI Data}, booktitle = {Proc. MICCAI Workshop Medical Image Analysis for the Clinic}, editor = {v. Ginneken, B.}, pages = {215 -- 223}, year = {2010}, language = {en} } @inproceedings{KainmuellerLameckerSeimetal.2010, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Seim, Heiko and Zachow, Stefan and Hege, Hans-Christian}, title = {Improving Deformable Surface Meshes through Omni-directional Displacements and MRFs}, volume = {6361}, booktitle = {Proc. Medical Image Computing and Computer Assisted Intervention (MICCAI)}, editor = {Navab, Tianzi and P. W. Pluim, Josien and Viergever, Max}, publisher = {Springer}, doi = {10.1007/978-3-642-15705-9_28}, pages = {227 -- 234}, year = {2010}, language = {en} } @inproceedings{ZachowKubiackMalinowskietal.2010, author = {Zachow, Stefan and Kubiack, Kim and Malinowski, Jana and Lamecker, Hans and Essig, Harald and Gellrich, Nils-Claudius}, title = {Modellgest{\"u}tzte chirurgische Rekonstruktion komplexer Mittelgesichtsfrakturen}, volume = {55 (Suppl 1)}, booktitle = {Proc. BMT, Biomed Tech 2010}, publisher = {Walter de Gruyter-Verlag}, pages = {107 -- 108}, year = {2010}, language = {de} } @misc{BindernagelKainmuellerRammetal.2012, author = {Bindernagel, Matthias and Kainm{\"u}ller, Dagmar and Ramm, Heiko and Lamecker, Hans and Zachow, Stefan}, title = {Analysis of inter-individual anatomical shape variations of joint structures}, journal = {Proc. Int. Society of Computer Assisted Orthopaedic Surgery (CAOS)}, number = {210}, year = {2012}, language = {en} } @inproceedings{NguyenLameckerKainmuelleretal.2012, author = {Nguyen, The Duy and Lamecker, Hans and Kainm{\"u}ller, Dagmar and Zachow, Stefan}, title = {Automatic Detection and Classification of Teeth in CT Data}, volume = {7510}, booktitle = {Proc. Medical Image Computing and Computer Assisted Intervention (MICCAI)}, editor = {Ayache, Nicholas and Delingette, Herv{\´e} and Golland, Polina and Mori, Kensaku}, pages = {609 -- 616}, year = {2012}, language = {en} } @article{NguyenKainmuellerLameckeretal.2012, author = {Nguyen, The Duy and Kainm{\"u}ller, Dagmar and Lamecker, Hans and Zachow, Stefan}, title = {Automatic bone and tooth detection for CT-based dental implant planning}, volume = {7, Supplement 1}, journal = {Int. J. Computer Assisted Radiology and Surgery}, number = {1}, publisher = {Springer}, pages = {293 -- 294}, year = {2012}, language = {en} } @misc{EhlkeRammLameckeretal.2012, author = {Ehlke, Moritz and Ramm, Heiko and Lamecker, Hans and Zachow, Stefan}, title = {Efficient projection and deformation of volumetric shape and intensity models for accurate simulation of X-ray images}, journal = {Eurographics Workshop on Visual Computing for Biomedicine (NVIDIA best poster award)}, year = {2012}, language = {en} } @inproceedings{KahntRammLameckeretal.2012, author = {Kahnt, Max and Ramm, Heiko and Lamecker, Hans and Zachow, Stefan}, title = {Feature-Preserving, Multi-Material Mesh Generation using Hierarchical Oracles}, volume = {7599}, booktitle = {Proc. MICCAI Workshop on Mesh Processing in Medical Image Analysis (MeshMed)}, editor = {Levine, Joshua A. and Paulsen, Rasmus R. and Zhang, Yongjie}, pages = {101 -- 111}, year = {2012}, language = {en} } @inproceedings{KainmuellerLameckerSeimetal.2009, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Seim, Heiko and Zinser, Max and Zachow, Stefan}, title = {Automatic Extraction of Mandibular Nerve and Bone from Cone-Beam CT Data}, booktitle = {Proceedings of Medical Image Computing and Computer Assisted Intervention (MICCAI)}, editor = {Yang, Guang-Zhong and J. Hawkes, David and Rueckert, Daniel and Noble, J. Alison and J. Taylor, Chris}, address = {London, UK}, pages = {76 -- 83}, year = {2009}, language = {en} } @inproceedings{KainmuellerLameckerZachowetal.2009, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Zachow, Stefan and Hege, Hans-Christian}, title = {An Articulated Statistical Shape Model for Accurate Hip Joint Segmentation}, booktitle = {EBMC 2009. Int. Conf. of the IEEE Eng. in Med. and Biol. Society (EMBC)}, address = {Minneapolis, USA}, pages = {6345 -- 6351}, year = {2009}, language = {en} } @article{ZachowLameckerZoeckleretal.2009, author = {Zachow, Stefan and Lamecker, Hans and Z{\"o}ckler, Maja and Haberl, Ernst}, title = {Computergest{\"u}tzte Planung zur chirurgischen Korrektur von fr{\"u}hkindlichen Sch{\"a}delfehlbildungen (Craniosynostosen)}, journal = {Face 02/09, Int. Mag. of Orofacial Esthetics, Oemus Journale Leipzig}, pages = {48 -- 53}, year = {2009}, language = {en} } @article{KainmuellerLameckerZachow2009, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Zachow, Stefan}, title = {Multi-object Segmentation with Coupled Deformable Models}, volume = {5}, journal = {Annals of the British Machine Vision Association (BMVA)}, pages = {1 -- 10}, year = {2009}, language = {en} } @inproceedings{KainmuellerLameckerZachowetal.2008, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Zachow, Stefan and Hege, Hans-Christian}, title = {Coupling Deformable Models for Multi-object Segmentation}, booktitle = {Proc. Int. Symp. on Computational Models for Biomedical Simulation (ISBMS)}, doi = {10.1007/978-3-540-70521-5_8}, pages = {69 -- 78}, year = {2008}, language = {en} } @inproceedings{KainmuellerLameckerZachowetal.2008, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Zachow, Stefan and Heller, Markus O. and Hege, Hans-Christian}, title = {Multi-Object Segmentation with Coupled Deformable Models}, booktitle = {Proc. Medical Image Understanding and Analysis}, pages = {34 -- 38}, year = {2008}, language = {en} } @inproceedings{SeimKainmuellerKussetal.2008, author = {Seim, Heiko and Kainm{\"u}ller, Dagmar and Kuss, Anja and Lamecker, Hans and Zachow, Stefan and Menzel, Randolf and Rybak, Juergen}, title = {Model-based autosegmentation of the central brain of the honeybee, Apis mellifera, using active statistical shape models}, booktitle = {Proc. 1st INCF Congress of Neuroinformatics: Databasing and Modeling the Brain}, doi = {10.3389/conf.neuro.11.2008.01.064}, year = {2008}, language = {en} } @inproceedings{DworzakLameckervonBergetal.2008, author = {Dworzak, Jalda and Lamecker, Hans and von Berg, Jens and Klinder, Tobias and Lorenz, Cristian and Kainm{\"u}ller, Dagmar and Seim, Heiko and Hege, Hans-Christian and Zachow, Stefan}, title = {Towards model-based 3-D reconstruction of the human rib cage from radiographs}, booktitle = {Proc. 7. Jahrestagung der Deutschen Gesellschaft f{\"u}r Computer-Roboterassistierte Chirurgie (CURAC)}, pages = {193 -- 196}, year = {2008}, language = {en} } @inproceedings{SeimKainmuellerHelleretal.2008, author = {Seim, Heiko and Kainm{\"u}ller, Dagmar and Heller, Markus O. and Lamecker, Hans and Zachow, Stefan and Hege, Hans-Christian}, title = {Automatic Segmentation of the Pelvic Bones from CT Data Based on a Statistical Shape Model}, booktitle = {Eurographics Workshop on Visual Computing for Biomedicine (VCBM)}, address = {Delft, Netherlands}, pages = {93 -- 100}, year = {2008}, language = {en} } @inproceedings{ZilskeLameckerZachow2008, author = {Zilske, Michael and Lamecker, Hans and Zachow, Stefan}, title = {Adaptive Remeshing of Non-Manifold Surfaces}, booktitle = {Eurographics 2008 Annex to the Conf. Proc.}, pages = {207 -- 211}, year = {2008}, language = {en} } @inproceedings{SeimLameckerZachow2008, author = {Seim, Heiko and Lamecker, Hans and Zachow, Stefan}, title = {Segmentation of Bony Structures with Ligament Attachment Sites}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2008}, publisher = {Springer}, doi = {10.1007/978-3-540-78640-5_42}, pages = {207 -- 211}, year = {2008}, language = {en} } @article{LameckerKamerWittmersetal.2007, author = {Lamecker, Hans and Kamer, Lukas and Wittmers, Antonia and Zachow, Stefan and Kaup, Thomas and Schramm, Alexander and Noser, Hansrudi and Hammer, Beat}, title = {A method for the three-dimensional statistical shape analysis of the bony orbit}, journal = {Proc. Computer Aided Surgery around the Head}, pages = {94 -- 97}, year = {2007}, language = {en} } @article{KainmuellerLameckerSeimetal.2009, author = {Kainm{\"u}ller, Dagmar and Lamecker, Hans and Seim, Heiko and Zachow, Stefan}, title = {Multi-object segmentation of head bones}, journal = {MIDAS Journal}, year = {2009}, language = {en} } @inproceedings{SeimKainmuellerLameckeretal.2009, author = {Seim, Heiko and Kainm{\"u}ller, Dagmar and Lamecker, Hans and Zachow, Stefan}, title = {A System for Unsupervised Extraction of Orthopaedic Parameters from CT Data}, booktitle = {GI Workshop Softwareassistenten - Computerunterst{\"u}tzung f{\"u}r die medizinische Diagnose und Therapieplanung}, address = {L{\"u}beck, Germany}, pages = {1328 -- 1337}, year = {2009}, language = {en} } @misc{KamerNoserLameckeretal.2006, author = {Kamer, Lukas and Noser, Hansrudi and Lamecker, Hans and Zachow, Stefan and Wittmers, Antonia and Kaup, Thomas and Schramm, Alexander and Hammer, Beat}, title = {Three-dimensional statistical shape analysis - A useful tool for developing a new type of orbital implant?}, publisher = {AO Development Institute, New Products Brochure 2/06}, pages = {20 -- 21}, year = {2006}, language = {en} }