Refine
Year of publication
Document Type
- Article (90)
- In Proceedings (81)
- ZIB-Report (25)
- Book chapter (7)
- Poster (6)
- Other (5)
- Research data (4)
- In Collection (2)
- Doctoral Thesis (1)
- Master's Thesis (1)
Language
- English (222) (remove)
Is part of the Bibliography
- no (222)
Keywords
- statistical shape and intensity models (5)
- Statistical shape analysis (3)
- 3d-reconstruction from 2d X-rays (2)
- 3d-reconstruction from 2d Xrays (2)
- Articulated Models, Statistical Shape And Intensity Models, 2D/3D Anatomy Reconstruction, Pelvic Parameters Measurement, Total Hip Arthroplasty (2)
- Classification (2)
- Lie groups (2)
- Manifold valued statistics (2)
- Sparse Geometry Reconstruction (2)
- Statistical Shape Models (2)
Institute
- Visual and Data-centric Computing (210)
- Visual Data Analysis (202)
- Therapy Planning (176)
- Numerical Mathematics (18)
- Computational Medicine (15)
- Visual Data Analysis in Science and Engineering (11)
- Geometric Data Analysis and Processing (6)
- Mathematics for Life and Materials Science (4)
- Computational Systems Biology (1)
- ZIB Allgemein (1)
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.
For medical diagnosis, visualization, and model-based therapy planning three-dimensional geometric reconstructions of individual anatomical structures are often indispensable. Computer-assisted, model-based planning procedures typically cover specific modifications of “virtual anatomy” as well as numeric simulations of associated phenomena, like e.g. mechanical loads, fluid dynamics, or diffusion processes, in order to evaluate a potential therapeutic outcome. Since internal anatomical structures cannot be measured optically or mechanically in vivo, three-dimensional reconstruction of tomographic image data remains the method of choice. In this work the process chain of individual anatomy reconstruction is described which consists of segmentation of medical image data, geometrical reconstruction of all relevant tissue interfaces, up to the generation of geometric approximations (boundary surfaces and volumetric meshes) of three-dimensional anatomy being suited for finite element analysis. All results presented herein are generated with amira ® – a highly interactive software system for 3D data analysis, visualization and geometry reconstruction.
The Facial Profile
(2015)
Facial appearance in our societies is often associated with notions of attractiveness, juvenileness, beauty, success, and so forth. Hence, the role of facial plastic surgery is highly interrelated to a patient's desire to feature many of these positively connoted attributes, which of course, are subject of different cultural perceptions or social trends. To judge about somebody's facial appearance, appropriate quantitative measures as well as methods to obtain and compare individual facial features are required.
This special issue on facial profile is intended to provide an overview on how facial characteristics are surgically managed in an interdisciplinary way based on experience, instrumentation, and modern technology to obtain an aesthetic facial appearance with harmonious facial proportions.
The facial profile will be discussed within the context of facial aesthetics. Latest concepts for capturing facial morphology in high speed and impressive detail are presented for quantitative analysis of even subtle changes, aging effects, or facial expressions. In addition, the perception of facial profiles is evaluated based on eye tracking technology.
Maxillofacial surgery planning with 3D soft tissue prediction - modeling, planning, simulation
(2005)
3D Osteotomieplanung in der MKG-Chirurgie unter Berücksichtigung der räumlichen Weichgewebeanordnung
(2001)
This article reflects the research of the last two decades in computational planning for cranio-maxillofacial surgery. Model-guided and computer-assisted surgery planning has tremendously developed due to ever increasing computational capabilities. Simulators for education, planning, and training of surgery are often compared with flight simulators, where maneuvers are also trained to reduce a possible risk of failure. Meanwhile, digital patient models can be derived from medical image data with astonishing accuracy and thus can serve for model surgery to derive a surgical template model that represents the envisaged result. Computerized surgical planning approaches, however, are often still explorative, meaning that a surgeon tries to find a therapeutic concept based on his or her expertise using computational tools that are mimicking real procedures. Future perspectives of an improved computerized planning may be that surgical objectives will be generated algorithmically by employing mathematical modeling, simulation, and optimization techniques. Planning systems thus act as intelligent decision support systems. However, surgeons can still use the existing tools to vary the proposed approach, but they mainly focus on how to transfer objectives into reality. Such a development may result in a paradigm shift for future surgery planning.
Validation of Three Dimensional Models of the Distal Femur Created from Surgical Navigation Data
(2015)
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.
Temperature-based estimation of time of death (ToD) can be per-
formed either with the help of simple phenomenological models of corpse
cooling or with detailed mechanistic (thermodynamic) heat transfer mod-
els. The latter are much more complex, but allow a higher accuracy of
ToD estimation as in principle all relevant cooling mechanisms can be
taken into account.
The potentially higher accuracy depends on the accuracy of tissue and
environmental parameters as well as on the geometric resolution. We in-
vestigate the impact of parameter variations and geometry representation
on the estimated ToD based on a highly detailed 3D corpse model, that
has been segmented and geometrically reconstructed from a computed to-
mography (CT) data set, differentiating various organs and tissue types.
From that we identify the most crucial parameters to measure or estimate,
and obtain a local uncertainty quantifcation for the ToD.
Temperature-based estimation of time of death (ToD) can be per-
formed either with the help of simple phenomenological models of corpse
cooling or with detailed mechanistic (thermodynamic) heat transfer mod-
els. The latter are much more complex, but allow a higher accuracy of
ToD estimation as in principle all relevant cooling mechanisms can be
taken into account.
The potentially higher accuracy depends on the accuracy of tissue and
environmental parameters as well as on the geometric resolution. We in-
vestigate the impact of parameter variations and geometry representation
on the estimated ToD based on a highly detailed 3D corpse model, that
has been segmented and geometrically reconstructed from a computed to-
mography (CT) data set, differentiating various organs and tissue types.
Purpose:
To investigate the influence of teeth and dental restorations on the facial skeleton's gray value distributions in cone-beam computed tomography (CBCT).
Methods:
Gray value selection for the upper and lower jaw segmentation was performed in 40 patients. In total, CBCT data of 20 maxillae and 20 mandibles, ten partial edentulous and ten fully edentulous in each jaw, respectively, were evaluated using two different gray value selection procedures: manual lower threshold selection and automated lower threshold selection. Two sample t tests, linear regression models, linear mixed models, and Pearson's correlation coefficients were computed to evaluate the influence of teeth, dental restorations, and threshold selection procedures on gray value distributions.
Results:
Manual threshold selection resulted in significantly different gray values in the fully and partially edentulous mandible. (p = 0.015, difference 123). In automated threshold selection, only tendencies to different gray values in fully edentulous compared to partially edentulous jaws were observed (difference: 58–75). Significantly different gray values were evaluated for threshold selection approaches, independent of the dental situation of the analyzed jaw. No significant correlation between the number of teeth and gray values was assessed, but a trend towards higher gray values in patients with more teeth was noted.
Conclusions:
Standard gray values derived from CT imaging do not apply for threshold-based bone segmentation in CBCT. Teeth influence gray values and segmentation results. Inaccurate bone segmentation may result in ill-fitting surgical guides produced on CBCT data and misinterpreting bone density, which is crucial for selecting surgical protocols.
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.
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-Euclidian structure. A key advantage of our framework is that statistics in a manifold shape space become 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 Euclidian approach in terms of shape-based classification of morphological disorders.
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.
Volumetry of the cartilage of the knee, as needed for the assessment of knee osteoarthritis (KOA), is typically performed in a tedious and subjective process. We present an automated segmentation-based method for the quantification of cartilage volume by employing 3D Convolutional Neural Networks
(CNNs). CNNs were trained in a supervised manner using magnetic resonance imaging data as well as cartilage volumetry readings given by clinical experts for 1378 subjects. It was shown that 3D CNNs can be employed for cartilage volumetry with an accuracy similar to expert volumetry readings. In future, accurate automated cartilage volumetry might support both, diagnosis of KOA as well as assessment of KOA progression via longitudinal analysis.
We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on a complete 3D MRI scan. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, meniscal body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data or how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences.
We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on a complete 3D MRI scan. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, meniscal body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually.
For optimal performance of our method, we investigate how to preprocess the MRI data or how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection.
We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci.
We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences.
For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM.
In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences.
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.
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.
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.
Convolutional neural networks (CNNs) are the state-of-the-art for automated assessment of knee osteoarthritis (KOA) from medical image data. However, these methods lack interpretability, mainly focus on image texture, and cannot completely grasp the analyzed anatomies’ shapes. In this study we assess the informative value of quantitative features derived from segmentations in order to assess their potential as an alternative or extension to CNN-based approaches regarding multiple aspects of KOA
A fully automated method is employed to segment six anatomical structures around the knee (femoral and tibial bones, femoral and tibial cartilages, and both menisci) in 46,996 MRI scans. Based on these segmentations, quantitative features are computed, i.e., measurements such as cartilage volume, meniscal extrusion and tibial coverage, as well as geometric features based on a statistical shape encoding of the anatomies. The feature quality is assessed by investigating their association to the Kellgren-Lawrence grade (KLG), joint space narrowing (JSN), incident KOA, and total knee replacement (TKR). Using gold standard labels from the Osteoarthritis Initiative database the balanced accuracy (BA), the area under the Receiver Operating Characteristic curve (AUC), and weighted kappa statistics are evaluated.
Features based on shape encodings of femur, tibia, and menisci plus the performed measurements showed most potential as KOA biomarkers. Differentiation between healthy and severely arthritic knees yielded BAs of up to 99%, 84% were achieved for diagnosis of early KOA. Substantial agreement with weighted kappa values of 0.73, 0.73, and 0.79 were achieved for classification of the grade of medial JSN, lateral JSN, and KLG, respectively. The AUC was 0.60 and 0.75 for prediction of incident KOA and TKR within 5 years, respectively.
Quantitative features from automated segmentations yield excellent results for KLG and JSN classification and show potential for incident KOA and TKR prediction. The validity of these features as KOA biomarkers should be further evaluated, especially as extensions of CNN-based approaches. To foster such developments we make all segmentations publicly available together with this publication.
Convolutional neural networks (CNNs) are the state-of-the-art for automated assessment of knee osteoarthritis (KOA) from medical image data. However, these methods lack interpretability, mainly focus on image texture, and cannot completely grasp the analyzed anatomies’ shapes. In this study we assess the informative value of quantitative features derived from segmentations in order to assess their potential as an alternative or extension to CNN-based approaches regarding multiple aspects of KOA.
Six anatomical structures around the knee (femoral and tibial bones, femoral and tibial cartilages, and both menisci) are segmented in 46,996 MRI scans. Based on these segmentations, quantitative features are computed, i.e., measurements such as cartilage volume, meniscal extrusion and tibial coverage, as well as geometric features based on a statistical shape encoding of the anatomies. The feature quality is assessed by investigating their association to the Kellgren-Lawrence grade (KLG), joint space narrowing (JSN), incident KOA, and total knee replacement (TKR). Using gold standard labels from the Osteoarthritis Initiative database the balanced accuracy (BA), the area under the Receiver Operating Characteristic curve (AUC), and weighted kappa statistics are evaluated.
Features based on shape encodings of femur, tibia, and menisci plus the performed measurements showed most potential as KOA biomarkers. Differentiation between non-arthritic and severely arthritic knees yielded BAs of up to 99%, 84% were achieved for diagnosis of early KOA. Weighted kappa values of 0.73, 0.72, and 0.78 were achieved for classification of the grade of medial JSN, lateral JSN, and KLG, respectively. The AUC was 0.61 and 0.76 for prediction of incident KOA and TKR within one year, respectively.
Quantitative features from automated segmentations provide novel biomarkers for KLG and JSN classification and show potential for incident KOA and TKR prediction. The validity of these features should be further evaluated, especially as extensions of CNN- based approaches. To foster such developments we make all segmentations publicly available together with this publication.
Manual processing of tomographic data volumes, such as interactive image segmentation in medicine or paleontology, is considered a time-consuming and cumbersome endeavor. Immersive volume sculpting stands as a potential solution to improve its efficiency and intuitiveness. However, current open-source software solutions do not yield the required performance and functionalities. We address this issue by contributing a novel open-source game engine voxel library that supports real-time immersive volume sculpting. Our design leverages GPU instancing, parallel computing, and a chunk-based data structure to optimize collision detection and rendering. We have implemented features that enable fast voxel interaction and improve precision. Our benchmark evaluation indicates that our implementation offers a significant improvement over the state-of-the-art and can render and modify millions of visible voxels while maintaining stable performance for real-time interaction in virtual reality.
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.
Fossil preparation is the activity of processing paleontological specimens for research and exhibition purposes. In addition to traditional mechanical extraction of fossils, preparation presently comprises non-destructive digital methods that are part of a relatively new field, namely virtual paleontology. Despite significant technological advances, both traditional and digital preparation remain cumbersome and time-consuming endeavors. However, this field has received scarce attention from a human-computer interaction perspective. The present study aims to elucidate the state-of-the-art for paleontological fossil preparation in order to determine its main challenges and start a conversation regarding opportunities for creating novel designs that tackle the field's current issues. We conducted a qualitative study involving both technical preparators and virtual paleontologists. The study was divided into two parts: First, we assembled technical preparators and paleontology researchers in a focus group session to discuss their workflows, obtain a preliminary understanding of their issues, and ideate solutions based on their counterparts' workflows. Next, we conducted a series of contextual inquiries involving direct observation and semi-structured in-depth interviews. We transcribed our recordings and examined the data through theoretical and inductive thematic analysis, clustering emerging themes and applying concepts from human-computer interaction and related fields. Our findings report on challenges faced by traditional and digital fossil preparators and potential opportunities to improve their tools and workflows. We contribute with a novel analysis of fossil preparation from an HCI perspective.
Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.
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.
Automatic recognition of surgical phases is an important component for developing an intra-operative context-aware system. Prior work in this area focuses on recognizing short-term tool usage patterns within surgical phases. However, the difference between intra- and inter-phase tool usage patterns has not been investigated for automatic phase recognition. We developed a Recurrent Neural Network (RNN), in particular a state-preserving Long Short Term Memory (LSTM) architecture to utilize the long-term evolution of tool usage within complete surgical procedures. For fully automatic tool presence detection from surgical video frames, a Convolutional Neural Network (CNN) based architecture namely ZIBNet is employed. Our proposed approach outperformed EndoNet by 8.1% on overall precision for phase detection tasks and 12.5% on meanAP for tool recognition tasks.
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.
Surgical tool segmentation in endoscopic videos is an important component of computer assisted interventions systems. Recent success of image-based solutions using fully-supervised deep learning approaches can be attributed to the collection of big labeled datasets. However, the annotation of a big dataset of real videos can be prohibitively expensive and time consuming. Computer simulations could alleviate the manual labeling problem, however, models trained on simulated data do not generalize to real data. This work proposes a consistency-based framework for joint learning of simulated and real (unlabeled) endoscopic data to bridge this performance generalization issue. Empirical results on two data sets (15 videos of the Cholec80 and EndoVis'15 dataset) highlight the effectiveness of the proposed Endo-Sim2Real method for instrument segmentation. We compare the segmentation of the proposed approach with state-of-the-art solutions and show that our method improves segmentation both in terms of quality and quantity.
Purpose
Segmentation of surgical instruments in endoscopic video streams is essential for automated surgical scene understanding and process modeling. However, relying on fully supervised deep learning for this task is challenging because manual annotation occupies valuable time of the clinical experts.
Methods
We introduce a teacher–student learning approach that learns jointly from annotated simulation data and unlabeled real data to tackle the challenges in simulation-to-real unsupervised domain adaptation for endoscopic image segmentation.
Results
Empirical results on three datasets highlight the effectiveness of the proposed framework over current approaches for the endoscopic instrument segmentation task. Additionally, we provide analysis of major factors affecting the performance on all datasets to highlight the strengths and failure modes of our approach.
Conclusions
We show that our proposed approach can successfully exploit the unlabeled real endoscopic video frames and improve generalization performance over pure simulation-based training and the previous state-of-the-art. This takes us one step closer to effective segmentation of surgical instrument in the annotation scarce setting.
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.
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.
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-specic 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.
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.
In dentistry, software-based medical image analysis and visualization provide efficient and accurate diagnostic and therapy planning capabilities. We present an approach for the automatic recognition of tooth types and positions in digital volume tomography (DVT). By using deep learning techniques in combination with dimensionality reduction through non-planar reformatting of the jaw anatomy, DVT data can be efficiently processed and
teeth reliably recognized and classified, even in the presence of imaging artefacts, missing or dislocated teeth.
We evaluated our approach, which is based on 2D Convolutional Neural Networks (CNNs), on 118 manually
annotated cases of clinical DVT datasets. Our proposed method correctly classifies teeth with an accuracy of
94% within a limit of 2mm distance to ground truth labels.
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.
In an aging society where the number of joint replacements rises, it is important to also increase the longevity of implants.
In particular hip implants have a lifetime of at most 15 years. This derives primarily from
pain due to implant migration, wear, inflammation, and dislocation, which is affected by
the positioning of the implant during the surgery. Current joint replacement practice uses
2D software tools and relies on the experience of surgeons. Especially the 2D tools fail to
take the patients’ natural range of motion as well as stress distribution in the 3D joint
induced by different daily motions into account.
Optimizing the hip joint implant position for all possible parametrized motions under the
constraint of a contact problem is prohibitively expensive as there are too many motions
and every position change demands a recalculation of the contact problem. For the
reduction of the computational effort, we use adaptive refinement on the parameter
domain coupled with the interpolation method of Kriging. A coarse initial grid is to be
locally refined using goal-oriented error estimation, reducing locally high variances. This
approach will be combined with multi-grid optimization such that numerical errors are
reduced.
Statistical shape modeling aims at capturing shape variations of an anatomical structure that occur within a given population. Shape models are employed in many tasks, such as shape reconstruction and image segmentation, but also shape generation and classification. Existing shape priors either require dense correspondence between training examples or lack robustness and topological guarantees. We present FlowSSM, a novel shape modeling approach that learns shape variability without requiring dense correspondence between training instances. It relies on a hierarchy of continuous deformation flows, which are parametrized by a neural network. Our model outperforms state-of-the-art methods in providing an expressive and robust shape prior for distal femur and liver. We show that the emerging latent representation is discriminative by separating healthy from pathological shapes. Ultimately, we demonstrate its effectiveness on two shape reconstruction tasks from partial data. Our source code is publicly available (https://github.com/davecasp/flowssm).
Purpose: Morphological data pertaining to the pelvis and lower extremity muscles are increasingly being used in biomechanical modeling to compare healthy and pathological conditions. Very few data sets exist that encompass all of the muscles of the lower limb, allowing for comparisons between regions. The aims of this study were to (a) provide physiological cross-sectional area (PCSA) data for the pelvic, thigh, and leg muscles in young, healthy participants, using magnetic resonance imaging (MRI), and (b) to compare these data with summarized PCSAs obtained from the literature.
Materials and Methods: Six young and healthy volunteers participated and were scanned using 3 T MRI. PCSAs were calculated from volumetric segmentations obtained bilaterally of 28 muscles/muscle groups of the pelvis, thigh, and leg. These data were compared to published, summarized PCSA data derived from cadaveric, computed tomography, MRI and ultrasound studies.
Results: The PCSA of the pelvis, thigh, and leg muscles tended to be 20–130% larger in males than in females, except for the gemelli which were 34% smaller in males, and semitendinosus and triceps surae which did not differ (<20% different). The dominant and the non-dominant sides showed similar and minutely different PCSA with less than 18% difference between sides. Comparison to other studies revealed wide ranges within, and large differences between, the cadaveric and imaging PCSA data. Comparison of the PCSA of this study and published literature revealed major differences in the iliopsoas, gluteus minimus, tensor fasciae latae, gemelli, obturator internus, biceps femoris, quadriceps femoris, and the deep leg flexor muscles.
Conclusions: These volume-derived PCSAs of the pelvic and lower limb muscles alongside the data synthesised from the literature may serve as a basis for comparative and biomechanical studies of the living and healthy young, and enable calculation of muscle forces. Comparison of the literature revealed large variations in PCSA from each of the different investigative modalities, hampering omparability between studies. Sample size, age, post-mortem changes of muscle tone, chemical fixation of cadaveric tissues, and the underlying physics of the imaging techniques may potentially influence PCSA calculations.