We develop a system for 3D object retrieval based on sketched feature lines as input. For objective evaluation, we collect a large number of query sketches from human users that are related to an ...existing data base of objects. The sketches turn out to be generally quite abstract with large local and global deviations from the original shape. Based on this observation, we decide to use a bag-of-features approach over computer generated line drawings of the objects. We develop a targeted feature transform based on Gabor filters for this system. We can show objectively that this transform is better suited than other approaches from the literature developed for similar tasks. Moreover, we demonstrate how to optimize the parameters of our, as well as other approaches, based on the gathered sketches. In the resulting comparison, our approach is significantly better than any other system described so far.
Brain vessel status is a promising biomarker for better prevention and treatment in cerebrovascular disease. However, classic rule-based vessel segmentation algorithms need to be hand-crafted and are ...insufficiently validated. A specialized deep learning method-the U-net-is a promising alternative. Using labeled data from 66 patients with cerebrovascular disease, the U-net framework was optimized and evaluated with three metrics: Dice coefficient, 95% Hausdorff distance (95HD) and average Hausdorff distance (AVD). The model performance was compared with the traditional segmentation method of graph-cuts. Training and reconstruction was performed using 2D patches. A full and a reduced architecture with less parameters were trained. We performed both quantitative and qualitative analyses. The U-net models yielded high performance for both the full and the reduced architecture: A Dice value of ~0.88, a 95HD of ~47 voxels and an AVD of ~0.4 voxels. The visual analysis revealed excellent performance in large vessels and sufficient performance in small vessels. Pathologies like cortical laminar necrosis and a rete mirabile led to limited segmentation performance in few patients. The U-net outperfomed the traditional graph-cuts method (Dice ~0.76, 95HD ~59, AVD ~1.97). Our work highly encourages the development of clinically applicable segmentation tools based on deep learning. Future works should focus on improved segmentation of small vessels and methodologies to deal with specific pathologies.
Virtual and augmented reality (VR/AR) exergames are promising tools for increasing training motivation. However, the use of exergames with mixed reality (MR) headsets remains under-researched. Older ...adults with hypertension could also benefit from the increased training adherence associated with MR. Endurance and strength endurance exercises are recommended for this group to lower blood pressure. The aim of the preliminary study (n = 22) was to compare the usability and acceptance of two exergames, which represent two different training types—strength endurance training (SET) and endurance training (ET). The developed exergame prototypes were applied in “simulated MR” using a VR head-mounted display. We examined the following outcomes: usability (TUI), intention to use (TUI), subjective task load (NASA-TLX), frustration (NASA-TLX), and presence (PQ). The results showed that frustration was significantly greater in the ET than in the SET (p = 0.038). Presence was significantly higher in the SET (p = 0.002). No significant differences in usability and acceptance were found in the exergames. The results indicate that usability and acceptance are not related to the type of training when utilizing MR exergames. Whether the results are transferable with a real MR headset must be determined in further research.
Stroke is a major cause of death or disability. As imaging-based patient stratification improves acute stroke therapy, dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) is of major ...interest in image brain perfusion. However, expert-level perfusion maps require a manual or semi-manual post-processing by a medical expert making the procedure time-consuming and less-standardized. Modern machine learning methods such as generative adversarial networks (GANs) have the potential to automate the perfusion map generation on an expert level without manual validation. We propose a modified pix2pix GAN with a temporal component (temp-pix2pix-GAN) that generates perfusion maps in an end-to-end fashion. We train our model on perfusion maps infused with expert knowledge to encode it into the GANs. The performance was trained and evaluated using the structural similarity index measure (SSIM) on two datasets including patients with acute stroke and the steno-occlusive disease. Our temp-pix2pix architecture showed high performance on the acute stroke dataset for all perfusion maps (mean SSIM 0.92-0.99) and good performance on data including patients with the steno-occlusive disease (mean SSIM 0.84-0.99). While clinical validation is still necessary for future studies, our results mark an important step toward automated expert-level perfusion maps and thus fast patient stratification.
Sharing labeled data is crucial to acquire large datasets for various Deep Learning applications. In medical imaging, this is often not feasible due to privacy regulations. Whereas anonymization ...would be a solution, standard techniques have been shown to be partially reversible. Here, synthetic data using a Generative Adversarial Network (GAN) with differential privacy guarantees could be a solution to ensure the patient's privacy while maintaining the predictive properties of the data. In this study, we implemented a Wasserstein GAN (WGAN) with and without differential privacy guarantees to generate privacy-preserving labeled Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) image patches for brain vessel segmentation. The synthesized image-label pairs were used to train a U-net which was evaluated in terms of the segmentation performance on real patient images from two different datasets. Additionally, the Fréchet Inception Distance (FID) was calculated between the generated images and the real images to assess their similarity. During the evaluation using the U-Net and the FID, we explored the effect of different levels of privacy which was represented by the parameter ϵ. With stricter privacy guarantees, the segmentation performance and the similarity to the real patient images in terms of FID decreased. Our best segmentation model, trained on synthetic and private data, achieved a Dice Similarity Coefficient (DSC) of 0.75 for ϵ = 7.4 compared to 0.84 for ϵ = ∞ in a brain vessel segmentation paradigm (DSC of 0.69 and 0.88 on the second test set, respectively). We identified a threshold of ϵ <5 for which the performance (DSC <0.61) became unstable and not usable. Our synthesized labeled TOF-MRA images with strict privacy guarantees retained predictive properties necessary for segmenting the brain vessels. Although further research is warranted regarding generalizability to other imaging modalities and performance improvement, our results mark an encouraging first step for privacy-preserving data sharing in medical imaging.
Slicing is the procedure necessary to prepare a shape for layered manufacturing. There are degrees of freedom in this process, such as the starting point of the slicing sequence and the thickness of ...each slice. The choice of these parameters influences the manufacturing process and its result: The number of slices significantly affects the time needed for manufacturing, while their thickness affects the error. Assuming a discrete setting, we measure the error as the number of voxels that are incorrectly assigned due to slicing. We provide an algorithm that generates, for a given set of available slice heights and a shape, a slicing that is provably optimal. By optimal, we mean that the algorithm generates sequences with minimal error for any possible number of slices. The algorithm is fast and flexible, that is, it can accommodate a user driven importance modulation of the error function and allows the interactive exploration of the desired quality/time tradeoff. We demonstrate the practical importance of our optimization on several three-dimensional-printed results.
We introduce a benchmark for evaluating the performance of large-scale sketch-based image retrieval systems. The necessary data are acquired in a controlled user study where subjects rate how well ...given sketch/image pairs match. We suggest how to use the data for evaluating the performance of sketch-based image retrieval systems. The benchmark data as well as the large image database are made publicly available for further studies of this type. Furthermore, we develop new descriptors based on the bag-of-features approach and use the benchmark to demonstrate that they significantly outperform other descriptors in the literature.
We introduce an algorithm and representation for fabricating 3D shape ions using mutually intersecting planar cut‐outs. The planes have prefabricated slits at their intersections and are assembled by ...sliding them together. Often such ions are used as a sculptural art form or in architecture and are colloquially called ‘cardboard sculptures’. Based on an analysis of construction rules, we propose an extended binary space partitioning tree as an efficient representation of such cardboard models which allows us to quickly evaluate the feasibility of newly added planar elements. The complexity of insertion order quickly increases with the number of planar elements and manual analysis becomes intractable. We provide tools for generating cardboard sculptures with guaranteed constructibility. In combination with a simple optimization and sampling strategy for new elements, planar shape ion models can be designed by iteratively adding elements. As an output, we obtain a fabrication plan that can be printed or sent to a laser cutter. We demonstrate the complete process by designing and fabricating cardboard models of various well‐known 3D shapes.
Slicing is the procedure necessary to prepare a shape for layered manufacturing. There are degrees of freedom in this process, such as the starting point of the slicing sequence and the thickness of ...each slice. The choice of these parameters influences the manufacturing process and its result: The number of slices significantly affects the time needed for manufacturing, while their thickness affects the error. Assuming a discrete setting, we measure the error as the number of voxels that are incorrectly assigned due to slicing. We provide an algorithm that generates, for a given set of available slice heights and a shape, a slicing that is provably optimal. By optimal, we mean that the algorithm generates sequences with minimal error for any possible number of slices. The algorithm is fast and flexible, that is, it can accommodate a user driven importance modulation of the error function and allows the interactive exploration of the desired quality/time tradeoff. We demonstrate the practical importance of our optimization on several three-dimensional-printed results.