TY - CHAP A1 - Kainmüller, Dagmar A1 - Lamecker, Hans A1 - Seim, Heiko A1 - Zinser, Max A1 - Zachow, Stefan ED - Yang, Guang-Zhong ED - J. Hawkes, David ED - Rueckert, Daniel ED - Noble, J. Alison ED - J. Taylor, Chris T1 - Automatic Extraction of Mandibular Nerve and Bone from Cone-Beam CT Data T2 - Proceedings of Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2009 SP - 76 EP - 83 CY - London, UK ER - TY - CHAP A1 - Seim, Heiko A1 - Kainmüller, Dagmar A1 - Heller, Markus O. A1 - Zachow, Stefan A1 - Hege, Hans-Christian T1 - Automatic Extraction of Anatomical Landmarks from Medical Image Data: An Evaluation of Different Methods T2 - Proc. of IEEE Int. Symposium on Biomedical Imaging (ISBI) Y1 - 2009 SP - 538 EP - 541 CY - Boston, MA, USA ER - TY - CHAP A1 - Nguyen, The Duy A1 - Lamecker, Hans A1 - Kainmüller, Dagmar A1 - Zachow, Stefan ED - Ayache, Nicholas ED - Delingette, Hervé ED - Golland, Polina ED - Mori, Kensaku T1 - Automatic Detection and Classification of Teeth in CT Data T2 - Proc. Medical Image Computing and Computer Assisted Intervention (MICCAI) Y1 - 2012 VL - 7510 SP - 609 EP - 616 ER - TY - JOUR A1 - Schenkl, Sebastian A1 - Muggenthaler, Holger A1 - Hubig, Michael A1 - Erdmann, Bodo A1 - Weiser, Martin A1 - Zachow, Stefan A1 - Heinrich, Andreas A1 - Güttler, Felix Victor A1 - Teichgräber, Ulf A1 - Mall, Gita T1 - Automatic CT-based finite element model generation for temperature-based death time estimation: feasibility study and sensitivity analysis JF - International Journal of Legal Medicine N2 - Temperature based death time estimation is based either on simple phenomenological models of corpse cooling or on detailed physical heat transfer models. The latter are much more complex, but allow a higher accuracy of death time estimation as in principle all relevant cooling mechanisms can be taken into account. Here, a complete work flow for finite element based cooling simulation models is presented. The following steps are demonstrated on CT-phantoms: • CT-scan • Segmentation of the CT images for thermodynamically relevant features of individual geometries • Conversion of the segmentation result into a Finite Element (FE) simulation model • Computation of the model cooling curve • Calculation of the cooling time For the first time in FE-based cooling time estimation the steps from the CT image over segmentation to FE model generation are semi-automatically performed. The cooling time calculation results are compared to cooling measurements performed on the phantoms under controlled conditions. In this context, the method is validated using different CTphantoms. Some of the CT phantoms thermodynamic material parameters had to be experimentally determined via independent experiments. Moreover the impact of geometry and material parameter uncertainties on the estimated cooling time is investigated by a sensitivity analysis. KW - temperature based death time estimation KW - finite element method KW - CT segmentation KW - sensitivity analysis Y1 - 2017 U6 - https://doi.org/doi:10.1007/s00414-016-1523-0 VL - 131 IS - 3 SP - 699 EP - 712 ER - TY - JOUR A1 - Nguyen, The Duy A1 - Kainmüller, Dagmar A1 - Lamecker, Hans A1 - Zachow, Stefan T1 - Automatic bone and tooth detection for CT-based dental implant planning JF - Int. J. Computer Assisted Radiology and Surgery Y1 - 2012 VL - 7, Supplement 1 IS - 1 SP - 293 EP - 294 PB - Springer ER - TY - JOUR A1 - Pimentel, Pedro A1 - Szengel, Angelika A1 - Ehlke, Moritz A1 - Lamecker, Hans A1 - Zachow, Stefan A1 - Estacio, Laura A1 - Doenitz, Christian A1 - Ramm, Heiko ED - Li, Jianning ED - Egger, Jan T1 - Automated Virtual Reconstruction of Large Skull Defects using Statistical Shape Models and Generative Adversarial Networks BT - First Challenge, AutoImplant 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 8, 2020, Proceedings JF - Towards the Automatization of Cranial Implant Design in Cranioplasty N2 - 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. Y1 - 2020 U6 - https://doi.org/10.1007/978-3-030-64327-0_3 N1 - Best Paper Award VL - 12439 SP - 16 EP - 27 PB - Springer International Publishing ET - 1 ER - TY - GEN A1 - Ambellan, Felix A1 - Tack, Alexander A1 - Ehlke, Moritz A1 - Zachow, Stefan T1 - Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative (Supplementary Material) T2 - Medical Image Analysis N2 - We present a method for the automated segmentation of knee bones and cartilage from magnetic resonance imaging that combines a priori knowledge of anatomical shape with Convolutional Neural Networks (CNNs). The proposed approach incorporates 3D Statistical Shape Models (SSMs) as well as 2D and 3D CNNs to achieve a robust and accurate segmentation of even highly pathological knee structures. The shape models and neural networks employed are trained using data of the Osteoarthritis Initiative (OAI) and the MICCAI grand challenge "Segmentation of Knee Images 2010" (SKI10), respectively. We evaluate our method on 40 validation and 50 submission datasets of the SKI10 challenge. For the first time, an accuracy equivalent to the inter-observer variability of human readers has been achieved in this challenge. Moreover, the quality of the proposed method is thoroughly assessed using various measures for data from the OAI, i.e. 507 manual segmentations of bone and cartilage, and 88 additional manual segmentations of cartilage. Our method yields sub-voxel accuracy for both OAI datasets. We made the 507 manual segmentations as well as our experimental setup publicly available to further aid research in the field of medical image segmentation. In conclusion, combining statistical anatomical knowledge via SSMs with the localized classification via CNNs results in a state-of-the-art segmentation method for knee bones and cartilage from MRI data. Y1 - 2019 U6 - https://doi.org/10.12752/4.ATEZ.1.0 N1 - OAI-ZIB dataset VL - 52 IS - 2 SP - 109 EP - 118 ER - TY - GEN A1 - Ambellan, Felix A1 - Tack, Alexander A1 - Ehlke, Moritz A1 - Zachow, Stefan T1 - Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative N2 - We present a method for the automated segmentation of knee bones and cartilage from magnetic resonance imaging (MRI) that combines a priori knowledge of anatomical shape with Convolutional Neural Networks (CNNs).The proposed approach incorporates 3D Statistical Shape Models (SSMs) as well as 2D and 3D CNNs to achieve a robust and accurate segmentation of even highly pathological knee structures.The shape models and neural networks employed are trained using data from the Osteoarthritis Initiative (OAI) and the MICCAI grand challenge "Segmentation of Knee Images 2010" (SKI10), respectively. We evaluate our method on 40 validation and 50 submission datasets from the SKI10 challenge.For the first time, an accuracy equivalent to the inter-observer variability of human readers is achieved in this challenge.Moreover, the quality of the proposed method is thoroughly assessed using various measures for data from the OAI, i.e. 507 manual segmentations of bone and cartilage, and 88 additional manual segmentations of cartilage. Our method yields sub-voxel accuracy for both OAI datasets. We make the 507 manual segmentations as well as our experimental setup publicly available to further aid research in the field of medical image segmentation.In conclusion, combining localized classification via CNNs with statistical anatomical knowledge via SSMs results in a state-of-the-art segmentation method for knee bones and cartilage from MRI data. T3 - ZIB-Report - 19-06 Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-72704 SN - 1438-0064 N1 - Innovation Excellence Award 2020 ER - TY - JOUR A1 - Ambellan, Felix A1 - Tack, Alexander A1 - Ehlke, Moritz A1 - Zachow, Stefan T1 - Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative JF - Medical Image Analysis N2 - We present a method for the automated segmentation of knee bones and cartilage from magnetic resonance imaging that combines a priori knowledge of anatomical shape with Convolutional Neural Networks (CNNs). The proposed approach incorporates 3D Statistical Shape Models (SSMs) as well as 2D and 3D CNNs to achieve a robust and accurate segmentation of even highly pathological knee structures. The shape models and neural networks employed are trained using data of the Osteoarthritis Initiative (OAI) and the MICCAI grand challenge "Segmentation of Knee Images 2010" (SKI10), respectively. We evaluate our method on 40 validation and 50 submission datasets of the SKI10 challenge. For the first time, an accuracy equivalent to the inter-observer variability of human readers has been achieved in this challenge. Moreover, the quality of the proposed method is thoroughly assessed using various measures for data from the OAI, i.e. 507 manual segmentations of bone and cartilage, and 88 additional manual segmentations of cartilage. Our method yields sub-voxel accuracy for both OAI datasets. We made the 507 manual segmentations as well as our experimental setup publicly available to further aid research in the field of medical image segmentation. In conclusion, combining statistical anatomical knowledge via SSMs with the localized classification via CNNs results in a state-of-the-art segmentation method for knee bones and cartilage from MRI data. Y1 - 2019 U6 - https://doi.org/10.1016/j.media.2018.11.009 VL - 52 IS - 2 SP - 109 EP - 118 ER - TY - CHAP A1 - Ambellan, Felix A1 - Tack, Alexander A1 - Ehlke, Moritz A1 - Zachow, Stefan T1 - Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative T2 - Medical Imaging with Deep Learning N2 - We present a method for the automated segmentation of knee bones and cartilage from magnetic resonance imaging, that combines a priori knowledge of anatomical shape with Convolutional Neural Networks (CNNs). The proposed approach incorporates 3D Statistical Shape Models (SSMs) as well as 2D and 3D CNNs to achieve a robust and accurate segmentation of even highly pathological knee structures. The method is evaluated on data of the MICCAI grand challenge "Segmentation of Knee Images 2010". For the first time an accuracy equivalent to the inter-observer variability of human readers has been achieved in this challenge. Moreover, the quality of the proposed method is thoroughly assessed using various measures for 507 manual segmentations of bone and cartilage, and 88 additional manual segmentations of cartilage. Our method yields sub-voxel accuracy. In conclusion, combining of anatomical knowledge using SSMs with localized classification via CNNs results in a state-of-the-art segmentation method. Y1 - 2018 ER - 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 - CHAP A1 - Ehlke, Moritz A1 - Heyland, Mark A1 - Märdian, Sven A1 - Duda, Georg A1 - Zachow, Stefan T1 - Assessing the relative positioning of an osteosynthesis plate to the patient-specific femoral shape from plain 2D radiographs T2 - Proceedings of the 15th Annual Meeting of CAOS-International (CAOS) N2 - We present a novel method to derive the surface distance of an osteosynthesis plate w.r.t. the patient­specific surface of the distal femur based on 2D X­ray images. Our goal is to study from clinical data, how the plate­to­bone distance affects bone healing. The patient­specific 3D shape of the femur is, however, seldom recorded for cases of femoral osteosynthesis since this typically requires Computed Tomography (CT), which comes at high cost and radiation dose. Our method instead utilizes two postoperative X­ray images to derive the femoral shape and thus can be applied on radiographs that are taken in clinical routine for follow­up. First, the implant geometry is used as a calibration object to relate the implant and the individual X­ray images spatially in a virtual X­ray setup. In a second step, the patient­specific femoral shape and pose are reconstructed in the virtual setup by fitting a deformable statistical shape and intensity model (SSIM) to the images. The relative positioning between femur and implant is then assessed in terms of displacement between the reconstructed 3D shape of the femur and the plate. A preliminary evaluation based on 4 cadaver datasets shows that the method derives the plate­to­bone distance with a mean absolute error of less than 1mm and a maximum error of 4.7 mm compared to ground truth from CT. We believe that the approach presented in this paper constitutes a meaningful tool to elucidate the effect of implant positioning on fracture healing. KW - 3d-­reconstruction from 2d X­rays KW - statistical shape and intensity models KW - fracture fixation of the distal femur KW - pose estimation Y1 - 2015 ER - TY - GEN A1 - Ehlke, Moritz A1 - Heyland, Mark A1 - Märdian, Sven A1 - Duda, Georg A1 - Zachow, Stefan T1 - Assessing the Relative Positioning of an Osteosynthesis Plate to the Patient-Specific Femoral Shape from Plain 2D Radiographs N2 - We present a novel method to derive the surface distance of an osteosynthesis plate w.r.t. the patient­specific surface of the distal femur based on 2D X­ray images. Our goal is to study from clinical data, how the plate­to­bone distance affects bone healing. The patient­specific 3D shape of the femur is, however, seldom recorded for cases of femoral osteosynthesis since this typically requires Computed Tomography (CT), which comes at high cost and radiation dose. Our method instead utilizes two postoperative X­ray images to derive the femoral shape and thus can be applied on radiographs that are taken in clinical routine for follow­up. First, the implant geometry is used as a calibration object to relate the implant and the individual X­ray images spatially in a virtual X­ray setup. In a second step, the patient­specific femoral shape and pose are reconstructed in the virtual setup by fitting a deformable statistical shape and intensity model (SSIM) to the images. The relative positioning between femur and implant is then assessed in terms of displacement between the reconstructed 3D shape of the femur and the plate. A preliminary evaluation based on 4 cadaver datasets shows that the method derives the plate­to­bone distance with a mean absolute error of less than 1mm and a maximum error of 4.7 mm compared to ground truth from CT. We believe that the approach presented in this paper constitutes a meaningful tool to elucidate the effect of implant positioning on fracture healing. T3 - ZIB-Report - 15-21 KW - 3d-­reconstruction from 2d X­rays KW - statistical shape and intensity models KW - fracture fixation of the distal femur KW - pose estimation Y1 - 2015 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-54268 SN - 1438-0064 ER - TY - JOUR A1 - Siqueira Rodrigues, Lucas A1 - Schmidt, Timo Torsten A1 - Nyakatura, John A1 - Zachow, Stefan A1 - Israel, Johann Habakuk A1 - Kosch, Thomas T1 - Assessing the Effects of Sensory Modality Conditions on Object Retention across Virtual Reality and Projected Surface Display Environments JF - Proceedings of the ACM on Human-Computer Interaction N2 - Haptic feedback reportedly enhances human interaction with 3D data, particularly improving the retention of mental representations of digital objects in immersive settings. However, the effectiveness of visuohaptic integration in promoting object retention across different display environments remains underexplored. Our study extends previous research on the retention effects of haptics from virtual reality to a projected surface display to assess whether earlier findings generalize to 2D environments. Participants performed a delayed match-to-sample task incorporating visual, haptic, and visuohaptic sensory feedback within a projected surface display environment. We compared error rates and response times across these sensory modalities and display environments. Our results reveal that visuohaptic integration significantly enhances object retention on projected surfaces, benefiting task performance across display environments. Our findings suggest that haptics can improve object retention without requiring fully immersive setups, offering insights for the design of interactive systems that assist professionals who rely on precise mental representations of digital objects. Y1 - 2024 U6 - https://doi.org/10.1145/3698137 VL - 8 IS - ISS SP - 255 EP - 282 ER - TY - GEN A1 - Kober, Cornelia A1 - Sader, Robert A1 - Zeilhofer, Hans-Florian A1 - Prohaska, Steffen A1 - Zachow, Stefan A1 - Deuflhard, Peter T1 - Anisotrope Materialmodellierung für den menschlichen Unterkiefer N2 - Im Rahmen der biomechanischen Simulation knöcherner Organe ist die Frage nach einer befriedigenden Materialbeschreibung nach wie vor ungelöst. Computertomographische Datensätze liefern eine räumliche Verteilung der (Röntgen-)Dichte und ermöglichen damit eine gute Darstellung der individuellen Geometrie. Weiter können die verschiedenen Materialbestandteile des Knochens, Spongiosa und Kortikalis, voneinander getrennt werden. Aber die richtungsabängige Information der Materialanisotropie ist verloren. In dieser Arbeit wird ein Ansatz für eine anisotrope Materialbeschreibung vorgestellt, die es ermöglicht, den Einfluss der individuellen knöchernen Struktur auf das makroskopische Materialverhalten abzuschätzen. T3 - ZIB-Report - 01-31 KW - menschlicher Unterkiefer KW - Simulation mit der Methode der finiten Elemente KW - innerer Aufbau des Knochens KW - anisotrope Elastizität Y1 - 2001 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-6574 ER - TY - JOUR A1 - Gladilin, Evgeny A1 - Zachow, Stefan A1 - Deuflhard, Peter A1 - Hege, Hans-Christian T1 - Anatomy- and physics-based facial animation for craniofacial surgery simulations JF - Med Biol Eng Comput. Y1 - 2004 U6 - https://doi.org/10.1007/BF02344627 VL - 42(2) SP - 167 EP - 170 ER - TY - GEN A1 - Sahu, Manish A1 - Szengel, Angelika A1 - Mukhopadhyay, Anirban A1 - Zachow, Stefan T1 - Analyzing laparoscopic cholecystectomy with deep learning: automatic detection of surgical tools and phases T2 - 28th International Congress of the European Association for Endoscopic Surgery (EAES) N2 - Motivation: The ever-rising volume of patients, high maintenance cost of operating rooms and time consuming analysis of surgical skills are fundamental problems that hamper the practical training of the next generation of surgeons. The hospitals prefer to keep the surgeons busy in real operations over training young surgeons for obvious economic reasons. One fundamental need in surgical training is the reduction of the time needed by the senior surgeon to review the endoscopic procedures performed by the young surgeon while minimizing the subjective bias in evaluation. The unprecedented performance of deep learning ushers the new age of data-driven automatic analysis of surgical skills. Method: Deep learning is capable of efficiently analyzing thousands of hours of laparoscopic video footage to provide an objective assessment of surgical skills. However, the traditional end-to-end setting of deep learning (video in, skill assessment out) is not explainable. Our strategy is to utilize the surgical process modeling framework to divide the surgical process into understandable components. This provides the opportunity to employ deep learning for superior yet automatic detection and evaluation of several aspects of laparoscopic cholecystectomy such as surgical tool and phase detection. We employ ZIBNet for the detection of surgical tool presence. ZIBNet employs pre-processing based on tool usage imbalance, a transfer learned 50-layer residual network (ResNet-50) and temporal smoothing. To encode the temporal evolution of tool usage (over the entire video sequence) that relates to the surgical phases, Long Short Term Memory (LSTM) units are employed with long-term dependency. Dataset: We used CHOLEC 80 dataset that consists of 80 videos of laparoscopic cholecystectomy performed by 13 surgeons, divided equally for training and testing. In these videos, up to three different tools (among 7 types of tools) can be present in a frame. Results: The mean average precision of the detection of all tools is 93.5 ranging between 86.8 and 99.3, a significant improvement (p <0.01) over the previous state-of-the-art. We observed that less frequent tools like Scissors, Irrigator, Specimen Bag etc. are more related to phase transitions. The overall precision (recall) of the detection of all surgical phases is 79.6 (81.3). Conclusion: While this is not the end goal for surgical skill analysis, the development of such a technological platform is essential toward a data-driven objective understanding of surgical skills. In future, we plan to investigate surgeon-in-the-loop analysis and feedback for surgical skill analysis. Y1 - 2020 UR - https://academy.eaes.eu/eaes/2020/28th/298882/manish.sahu.analyzing.laparoscopic.cholecystectomy.with.deep.learning.html?f=listing%3D0%2Abrowseby%3D8%2Asortby%3D2 ER - TY - GEN A1 - Bindernagel, Matthias A1 - Kainmüller, Dagmar A1 - Ramm, Heiko A1 - Lamecker, Hans A1 - Zachow, Stefan T1 - Analysis of inter-individual anatomical shape variations of joint structures T2 - Proc. Int. Society of Computer Assisted Orthopaedic Surgery (CAOS) Y1 - 2012 IS - 210 ER - TY - CHAP A1 - Siqueira Rodrigues, Lucas A1 - Nyakatura, John A1 - Zachow, Stefan A1 - Israel, Johann Habakuk T1 - An Immersive Virtual Paleontology Application T2 - 13th International Conference on Human Haptic Sensing and Touch Enabled Computer Applications, EuroHaptics 2022 N2 - Virtual paleontology studies digital fossils through data analysis and visualization systems. The discipline is growing in relevance for the evident advantages of non-destructive imaging techniques over traditional paleontological methods, and it has made significant advancements during the last few decades. However, virtual paleontology still faces a number of technological challenges, amongst which are interaction shortcomings of image segmentation applications. Whereas automated segmentation methods are seldom applicable to fossil datasets, manual exploration of these specimens is extremely time-consuming as it impractically delves into three-dimensional data through two-dimensional visualization and interaction means. This paper presents an application that employs virtual reality and haptics to virtual paleontology in order to evolve its interaction paradigms and address some of its limitations. We provide a brief overview of the challenges faced by virtual paleontology practitioners, a description of our immersive virtual paleontology prototype, and the results of a heuristic evaluation of our design. Y1 - 2022 U6 - https://doi.org/10.1007/978-3-031-06249-0 SP - 478 EP - 481 ER - TY - JOUR A1 - von Tycowicz, Christoph A1 - Ambellan, Felix A1 - Mukhopadhyay, Anirban A1 - Zachow, Stefan T1 - An Efficient Riemannian Statistical Shape Model using Differential Coordinates JF - Medical Image Analysis N2 - We propose a novel Riemannian framework for statistical analysis of shapes that is able to account for the nonlinearity in shape variation. By adopting a physical perspective, we introduce a differential representation that puts the local geometric variability into focus. We model these differential coordinates as elements of a Lie group thereby endowing our shape space with a non-Euclidean structure. A key advantage of our framework is that statistics in a manifold shape space becomes numerically tractable improving performance by several orders of magnitude over state-of-the-art. We show that our Riemannian model is well suited for the identification of intra-population variability as well as inter-population differences. In particular, we demonstrate the superiority of the proposed model in experiments on specificity and generalization ability. We further derive a statistical shape descriptor that outperforms the standard Euclidean approach in terms of shape-based classification of morphological disorders. Y1 - 2018 U6 - https://doi.org/10.1016/j.media.2017.09.004 VL - 43 IS - 1 SP - 1 EP - 9 ER -