@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} } @misc{AmbellanTackEhlkeetal.2019, author = {Ambellan, Felix and Tack, Alexander and Ehlke, Moritz and Zachow, Stefan}, title = {Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-72704}, year = {2019}, abstract = {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.}, 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} } @inproceedings{TackZachow2019, author = {Tack, Alexander and Zachow, Stefan}, title = {Accurate Automated Volumetry of Cartilage of the Knee using Convolutional Neural Networks: Data from the Osteoarthritis Initiative}, booktitle = {IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)}, doi = {10.1109/ISBI.2019.8759201}, pages = {40 -- 43}, year = {2019}, abstract = {Volumetry of cartilage of the knee is needed for knee osteoarthritis (KOA) assessment. It is typically performed manually in a tedious and subjective process. We developed a method for an automated, segmentation-based quantification of cartilage volume by employing 3D Convolutional Neural Networks (CNNs). CNNs were trained in a supervised manner using magnetic resonance imaging data and cartilage volumetry readings performed by clinical experts for 1378 subjects provided by the Osteoarthritis Initiative. It was shown that 3D CNNs are able to achieve volume measures comparable to the magnitude of variation between expert readings and the real in vivo situation. In the future, accurate automated cartilage volumetry might support both, diagnosis of KOA as well as longitudinal analysis of KOA progression.}, language = {en} } @misc{AmbellanTackEhlkeetal.2019, author = {Ambellan, Felix and Tack, Alexander and Ehlke, Moritz and Zachow, Stefan}, title = {Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative (Supplementary Material)}, volume = {52}, journal = {Medical Image Analysis}, number = {2}, doi = {10.12752/4.ATEZ.1.0}, pages = {109 -- 118}, year = {2019}, abstract = {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.}, language = {en} } @article{AmbellanTackEhlkeetal.2019, author = {Ambellan, Felix and Tack, Alexander and Ehlke, Moritz and Zachow, Stefan}, title = {Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative}, volume = {52}, journal = {Medical Image Analysis}, number = {2}, doi = {10.1016/j.media.2018.11.009}, pages = {109 -- 118}, year = {2019}, abstract = {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.}, 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} } @article{AkbariShandizBoulosSavarssonetal.2018, author = {Akbari Shandiz, Mohsen and Boulos, Paul and S{\ae}varsson, Stefan and Ramm, Heiko and Fu, Chun Kit and Miller, Stephen and Zachow, Stefan and Anglin, Carolyn}, title = {Changes in Knee Shape and Geometry Resulting from Total Knee Arthroplasty}, volume = {232}, journal = {Journal of Engineering in Medicine}, number = {1}, doi = {10.1177/0954411917743274}, pages = {67 -- 79}, year = {2018}, abstract = {Changes in knee shape and geometry resulting from total knee arthroplasty can affect patients in numerous important ways: pain, function, stability, range of motion, and kinematics. Quantitative data concerning these changes have not been previously available, to our knowledge, yet are essential to understand individual experiences of total knee arthroplasty and thereby improve outcomes for all patients. The limiting factor has been the challenge of accurately measuring these changes. Our study objective was to develop a conceptual framework and analysis method to investigate changes in knee shape and geometry, and prospectively apply it to a sample total knee arthroplasty population. Using clinically available computed tomography and radiography imaging systems, the three-dimensional knee shape and geometry of nine patients (eight varus and one valgus) were compared before and after total knee arthroplasty. All patients had largely good outcomes after their total knee arthroplasty. Knee shape changed both visually and numerically. On average, the distal condyles were slightly higher medially and lower laterally (range: +4.5 mm to -4.4 mm), the posterior condyles extended farther out medially but not laterally (range: +1.8 to -6.4 mm), patellofemoral distance increased throughout flexion by 1.8-3.5 mm, and patellar thickness alone increased by 2.9 mm (range: 0.7-5.2 mm). External femoral rotation differed preop and postop. Joint line distance, taking cartilage into account, changed by +0.7 to -1.5 mm on average throughout flexion. Important differences in shape and geometry were seen between pre-total knee arthroplasty and post-total knee arthroplasty knees. While this is qualitatively known, this is the first study to report it quantitatively, an important precursor to identifying the reasons for the poor outcome of some patients. Using the developed protocol and visualization techniques to compare patients with good versus poor clinical outcomes could lead to changes in implant design, implant selection, component positioning, and surgical technique. Recommendations based on this sample population are provided. Intraoperative and postoperative feedback could ultimately improve patient satisfaction.}, language = {en} } @article{TackMukhopadhyayZachow2018, author = {Tack, Alexander and Mukhopadhyay, Anirban and Zachow, Stefan}, title = {Knee Menisci Segmentation using Convolutional Neural Networks: Data from the Osteoarthritis Initiative}, volume = {26}, journal = {Osteoarthritis and Cartilage}, number = {5}, doi = {10.1016/j.joca.2018.02.907}, pages = {680 -- 688}, year = {2018}, abstract = {Abstract: Objective: To present a novel method for automated segmentation of knee menisci from MRIs. To evaluate quantitative meniscal biomarkers for osteoarthritis (OA) estimated thereof. Method: A segmentation method employing convolutional neural networks in combination with statistical shape models was developed. Accuracy was evaluated on 88 manual segmentations. Meniscal volume, tibial coverage, and meniscal extrusion were computed and tested for differences between groups of OA, joint space narrowing (JSN), and WOMAC pain. Correlation between computed meniscal extrusion and MOAKS experts' readings was evaluated for 600 subjects. Suitability of biomarkers for predicting incident radiographic OA from baseline to 24 months was tested on a group of 552 patients (184 incident OA, 386 controls) by performing conditional logistic regression. Results: Segmentation accuracy measured as Dice Similarity Coefficient was 83.8\% for medial menisci (MM) and 88.9\% for lateral menisci (LM) at baseline, and 83.1\% and 88.3\% at 12-month follow-up. Medial tibial coverage was significantly lower for arthritic cases compared to non-arthritic ones. Medial meniscal extrusion was significantly higher for arthritic knees. A moderate correlation between automatically computed medial meniscal extrusion and experts' readings was found (ρ=0.44). Mean medial meniscal extrusion was significantly greater for incident OA cases compared to controls (1.16±0.93 mm vs. 0.83±0.92 mm; p<0.05). Conclusion: Especially for medial menisci an excellent segmentation accuracy was achieved. Our meniscal biomarkers were validated by comparison to experts' readings as well as analysis of differences w.r.t groups of OA, JSN, and WOMAC pain. It was confirmed that medial meniscal extrusion is a predictor for incident OA.}, language = {en} } @inproceedings{AmbellanTackEhlkeetal.2018, author = {Ambellan, Felix and Tack, Alexander and Ehlke, Moritz and Zachow, Stefan}, title = {Automated Segmentation of Knee Bone and Cartilage combining Statistical Shape Knowledge and Convolutional Neural Networks: Data from the Osteoarthritis Initiative}, booktitle = {Medical Imaging with Deep Learning}, year = {2018}, abstract = {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.}, 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} } @article{OeltzeJaffraMeuschkeNeugebaueretal.2019, author = {Oeltze-Jaffra, Steffen and Meuschke, Monique and Neugebauer, Mathias and Saalfeld, Sylvia and Lawonn, Kai and Janiga, Gabor and Hege, Hans-Christian and Zachow, Stefan and Preim, Bernhard}, title = {Generation and Visual Exploration of Medical Flow Data: Survey, Research Trends, and Future Challenges}, volume = {38}, journal = {Computer Graphics Forum}, number = {1}, publisher = {Wiley}, doi = {10.1111/cgf.13394}, pages = {87 -- 125}, year = {2019}, abstract = {Simulations and measurements of blood and air flow inside the human circulatory and respiratory system play an increasingly important role in personalized medicine for prevention, diagnosis, and treatment of diseases. This survey focuses on three main application areas. (1) Computational Fluid Dynamics (CFD) simulations of blood flow in cerebral aneurysms assist in predicting the outcome of this pathologic process and of therapeutic interventions. (2) CFD simulations of nasal airflow allow for investigating the effects of obstructions and deformities and provide therapy decision support. (3) 4D Phase-Contrast (4D PC) Magnetic Resonance Imaging (MRI) of aortic hemodynamics supports the diagnosis of various vascular and valve pathologies as well as their treatment. An investigation of the complex and often dynamic simulation and measurement data requires the coupling of sophisticated visualization, interaction, and data analysis techniques. In this paper, we survey the large body of work that has been conducted within this realm. We extend previous surveys by incorporating nasal airflow, addressing the joint investigation of blood flow and vessel wall properties, and providing a more fine-granular taxonomy of the existing techniques. From the survey, we extract major research trends and identify open problems and future challenges. The survey is intended for researchers interested in medical flow but also more general, in the combined visualization of physiology and anatomy, the extraction of features from flow field data and feature-based visualization, the visual comparison of different simulation results, and the interactive visual analysis of the flow field and derived characteristics.}, 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} } @inproceedings{MukhopadhyayMorilloZachowetal.2016, author = {Mukhopadhyay, Anirban and Morillo, Oscar and Zachow, Stefan and Lamecker, Hans}, title = {Robust and Accurate Appearance Models Based on Joint Dictionary Learning Data from the Osteoarthritis Initiative}, volume = {9993}, booktitle = {Lecture Notes in Computer Science, Patch-Based Techniques in Medical Imaging. Patch-MI 2016}, doi = {10.1007/978-3-319-47118-1_4}, pages = {25 -- 33}, year = {2016}, abstract = {Deformable model-based approaches to 3D image segmentation have been shown to be highly successful. Such methodology requires an appearance model that drives the deformation of a geometric model to the image data. Appearance models are usually either created heuristically or through supervised learning. Heuristic methods have been shown to work effectively in many applications but are hard to transfer from one application (imaging modality/anatomical structure) to another. On the contrary, supervised learning approaches can learn patterns from a collection of annotated training data. In this work, we show that the supervised joint dictionary learning technique is capable of overcoming the traditional drawbacks of the heuristic approaches. Our evaluation based on two different applications (liver/CT and knee/MR) reveals that our approach generates appearance models, which can be used effectively and efficiently in a deformable model-based segmentation framework.}, language = {en} } @article{SahuMukhopadhyaySzengeletal.2017, author = {Sahu, Manish and Mukhopadhyay, Anirban and Szengel, Angelika and Zachow, Stefan}, title = {Addressing multi-label imbalance problem of Surgical Tool Detection using CNN}, volume = {12}, journal = {International Journal of Computer Assisted Radiology and Surgery}, number = {6}, publisher = {Springer}, doi = {10.1007/s11548-017-1565-x}, pages = {1013 -- 1020}, year = {2017}, abstract = {Purpose: A fully automated surgical tool detection framework is proposed for endoscopic video streams. State-of-the-art surgical tool detection methods rely on supervised one-vs-all or multi-class classification techniques, completely ignoring the co-occurrence relationship of the tools and the associated class imbalance. Methods: In this paper, we formulate tool detection as a multi-label classification task where tool co-occurrences are treated as separate classes. In addition, imbalance on tool co-occurrences is analyzed and stratification techniques are employed to address the imbalance during Convolutional Neural Network (CNN) training. Moreover, temporal smoothing is introduced as an online post-processing step to enhance run time prediction. Results: Quantitative analysis is performed on the M2CAI16 tool detection dataset to highlight the importance of stratification, temporal smoothing and the overall framework for tool detection. Conclusion: The analysis on tool imbalance, backed by the empirical results indicates the need and superiority of the proposed framework over state-of-the-art techniques.}, language = {en} } @article{WilsonAnglinAmbellanetal.2017, author = {Wilson, David and Anglin, Carolyn and Ambellan, Felix and Grewe, Carl Martin and Tack, Alexander and Lamecker, Hans and Dunbar, Michael and Zachow, Stefan}, title = {Validation of three-dimensional models of the distal femur created from surgical navigation point cloud data for intraoperative and postoperative analysis of total knee arthroplasty}, volume = {12}, journal = {International Journal of Computer Assisted Radiology and Surgery}, number = {12}, publisher = {Springer}, doi = {10.1007/s11548-017-1630-5}, pages = {2097 -- 2105}, year = {2017}, abstract = {Purpose: Despite the success of total knee arthroplasty there continues to be a significant proportion of patients who are dissatisfied. One explanation may be a shape mismatch between pre and post-operative distal femurs. The purpose of this study was to investigate a method to match a statistical shape model (SSM) to intra-operatively acquired point cloud data from a surgical navigation system, and to validate it against the pre-operative magnetic resonance imaging (MRI) data from the same patients. Methods: A total of 10 patients who underwent navigated total knee arthroplasty also had an MRI scan less than 2 months pre-operatively. The standard surgical protocol was followed which included partial digitization of the distal femur. Two different methods were employed to fit the SSM to the digitized point cloud data, based on (1) Iterative Closest Points (ICP) and (2) Gaussian Mixture Models (GMM). The available MRI data were manually segmented and the reconstructed three-dimensional surfaces used as ground truth against which the statistical shape model fit was compared. Results: For both approaches, the difference between the statistical shape model-generated femur and the surface generated from MRI segmentation averaged less than 1.7 mm, with maximum errors occurring in less clinically important areas. Conclusion: The results demonstrated good correspondence with the distal femoral morphology even in cases of sparse data sets. Application of this technique will allow for measurement of mismatch between pre and post-operative femurs retrospectively on any case done using the surgical navigation system and could be integrated into the surgical navigation unit to provide real-time feedback.}, language = {en} } @article{vonTycowiczAmbellanMukhopadhyayetal.2018, author = {von Tycowicz, Christoph and Ambellan, Felix and Mukhopadhyay, Anirban and Zachow, Stefan}, title = {An Efficient Riemannian Statistical Shape Model using Differential Coordinates}, volume = {43}, journal = {Medical Image Analysis}, number = {1}, doi = {10.1016/j.media.2017.09.004}, pages = {1 -- 9}, year = {2018}, abstract = {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.}, language = {en} } @incollection{LameckerZachow2016, author = {Lamecker, Hans and Zachow, Stefan}, title = {Statistical Shape Modeling of Musculoskeletal Structures and Its Applications}, volume = {23}, booktitle = {Computational Radiology for Orthopaedic Interventions}, publisher = {Springer}, isbn = {978-3-319-23481-6}, doi = {10.1007/978-3-319-23482-3}, pages = {1 -- 23}, year = {2016}, abstract = {Statistical shape models (SSM) describe the shape variability contained in a given population. They are able to describe large populations of complex shapes with few degrees of freedom. This makes them a useful tool for a variety of tasks that arise in computer-aided madicine. In this chapter we are going to explain the basic methodology of SSMs and present a variety of examples, where SSMs have been successfully applied.}, language = {en} } @inproceedings{MukhopadhyayOksuzBevilacquaetal.2015, author = {Mukhopadhyay, Anirban and Oksuz, Ilkay and Bevilacqua, Marco and Dharmakumar, Rohan and Tsaftaris, Sotirios}, title = {Data-Driven Feature Learning for Myocardial Segmentation of CP-BOLD MRI}, volume = {9126}, booktitle = {Functional Imaging and Modeling of the Heart}, publisher = {Springer}, doi = {10.1007/978-3-319-20309-6_22}, pages = {189 -- 197}, year = {2015}, abstract = {Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP- BOLD) MR is capable of diagnosing an ongoing ischemia by detecting changes in myocardial intensity patterns at rest without any contrast and stress agents. Visualizing and detecting these changes require significant post-processing, including myocardial segmentation for isolating the myocardium. But, changes in myocardial intensity pattern and myocardial shape due to the heart's motion challenge automated standard CINE MR myocardial segmentation techniques resulting in a significant drop of segmentation accuracy. We hypothesize that the main reason behind this phenomenon is the lack of discernible features. In this paper, a multi scale discriminative dictionary learning approach is proposed for supervised learning and sparse representation of the myocardium, to improve the myocardial feature selection. The technique is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canine subjects. The proposed method significantly outperforms standard cardiac segmentation techniques, including segmentation via registration, level sets and supervised methods for myocardial segmentation.}, language = {en} } @inproceedings{MukhopadhyayOksuzBevilacquaetal.2015, author = {Mukhopadhyay, Anirban and Oksuz, Ilkay and Bevilacqua, Marco and Dharmakumar, Rohan and Tsaftaris, Sotirios}, title = {Unsupervised myocardial segmentation for cardiac MRI}, volume = {LNCS 9351}, booktitle = {Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015}, doi = {10.1007/978-3-319-24574-4_2}, pages = {12 -- 20}, year = {2015}, abstract = {Though unsupervised segmentation was a de-facto standard for cardiac MRI segmentation early on, recently cardiac MRI segmentation literature has favored fully supervised techniques such as Dictionary Learning and Atlas-based techniques. But, the benefits of unsupervised techniques e.g., no need for large amount of training data and better potential of handling variability in anatomy and image contrast, is more evident with emerging cardiac MR modalities. For example, CP-BOLD is a new MRI technique that has been shown to detect ischemia without any contrast at stress but also at rest conditions. Although CP-BOLD looks similar to standard CINE, changes in myocardial intensity patterns and shape across cardiac phases, due to the heart's motion, BOLD effect and artifacts affect the underlying mechanisms of fully supervised segmentation techniques resulting in a significant drop in segmentation accuracy. In this paper, we present a fully unsupervised technique for segmenting myocardium from the background in both standard CINE MR and CP-BOLD MR. We combine appearance with motion information (obtained via Optical Flow) in a dictionary learning framework to sparsely represent important features in a low dimensional space and separate myocardium from background accordingly. Our fully automated method learns background-only models and one class classifier provides myocardial segmentation. The advantages of the proposed technique are demonstrated on a dataset containing CP-BOLD MR and standard CINE MR image sequences acquired in baseline and ischemic condition across 10 canine subjects, where our method outperforms state-of-the-art supervised segmentation techniques in CP-BOLD MR and performs at-par for standard CINE MR.}, language = {en} } @inproceedings{OksuzMukhopadhyayBevilacquaetal.2015, author = {Oksuz, Ilkay and Mukhopadhyay, Anirban and Bevilacqua, Marco and Dharmakumar, Rohan and Tsaftaris, Sotirios}, title = {Dictionary Learning Based Image Descriptor for Myocardial Registration of CP-BOLD MR}, volume = {9350}, booktitle = {Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015}, publisher = {Springer}, doi = {10.1007/978-3-319-24571-3_25}, pages = {205 -- 213}, year = {2015}, abstract = {Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP- BOLD) MRI is a new contrast agent- and stress-free imaging technique for the assessment of myocardial ischemia at rest. The precise registration among the cardiac phases in this cine type acquisition is essential for automating the analysis of images of this technique, since it can potentially lead to better specificity of ischemia detection. However, inconsistency in myocardial intensity patterns and the changes in myocardial shape due to the heart's motion lead to low registration performance for state- of-the-art methods. This low accuracy can be explained by the lack of distinguishable features in CP-BOLD and inappropriate metric defini- tions in current intensity-based registration frameworks. In this paper, the sparse representations, which are defined by a discriminative dictionary learning approach for source and target images, are used to improve myocardial registration. This method combines appearance with Gabor and HOG features in a dictionary learning framework to sparsely represent features in a low dimensional space. The sum of squared differences of these distinctive sparse representations are used to define a similarity term in the registration framework. The proposed descriptor is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canines.}, language = {en} } @misc{MukhopadhyayKumarBhandarkar2016, author = {Mukhopadhyay, Anirban and Kumar, Arun and Bhandarkar, Suchendra}, title = {Joint Geometric Graph Embedding for Partial Shape Matching in Images}, journal = {IEEE Winter Conference on Applications of Computer Vision}, edition = {IEEE Winter Conference on Applications of Computer Vision (WACV)}, publisher = {IEEE}, pages = {1 -- 9}, year = {2016}, abstract = {A novel multi-criteria optimization framework for matching of partially visible shapes in multiple images using joint geometric graph embedding is proposed. The proposed framework achieves matching of partial shapes in images that exhibit extreme variations in scale, orientation, viewpoint and illumination and also instances of occlusion; conditions which render impractical the use of global contour-based descriptors or local pixel-level features for shape matching. The proposed technique is based on optimization of the embedding distances of geometric features obtained from the eigenspectrum of the joint image graph, coupled with regularization over values of the mean pixel intensity or histogram of oriented gradients. It is shown to obtain successfully the correspondences denoting partial shape similarities as well as correspondences between feature points in the images. A new benchmark dataset is proposed which contains disparate image pairs with extremely challenging variations in viewing conditions when compared to an existing dataset [18]. The proposed technique is shown to significantly outperform several state-of-the-art partial shape matching techniques on both datasets.}, 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} }