Klaus Tönnies

Oleksii Bashkanov, Anneke Meyer, Daniel Schindele et al.

Recent studies demonstrated the eligibility of convolutional neural networks (CNNs) for solving the image registration problem. CNNs enable faster transformation estimation and greater generalization capability needed for better support during medical interventions. Conventional fully-supervised training requires a lot of high-quality ground truth data such as voxel-to-voxel transformations, which typically are attained in a too tedious and error-prone manner. In our work, we use weakly-supervised learning, which optimizes the model indirectly only via segmentation masks that are a more accessible ground truth than the deformation fields. Concerning the weak supervision, we investigate two segmentation similarity measures: multiscale Dice similarity coefficient (mDSC) and the similarity between segmentation-derived signed distance maps (SDMs). We show that the combination of mDSC and SDM similarity measures results in a more accurate and natural transformation pattern together with a stronger gradient coverage. Furthermore, we introduce an auxiliary input to the neural network for the prior information about the prostate location in the MR sequence, which mostly is available preoperatively. This approach significantly outperforms the standard two-input models. With weakly labelled MR-TRUS prostate data, we showed registration quality comparable to the state-of-the-art deep learning-based method.

Georg Hille, Johannes Steffen, Max Dünnwald et al.

This study's objective was to segment spinal metastases in diagnostic MR images using a deep learning-based approach. Segmentation of such lesions can present a pivotal step towards enhanced therapy planning and validation, as well as intervention support during minimally invasive and image-guided surgeries like radiofrequency ablations. For this purpose, we used a U-Net like architecture trained with 40 clinical cases including both, lytic and sclerotic lesion types and various MR sequences. Our proposed method was evaluated with regards to various factors influencing the segmentation quality, e.g. the used MR sequences and the input dimension. We quantitatively assessed our experiments using Dice coefficients, sensitivity and specificity rates. Compared to expertly annotated lesion segmentations, the experiments yielded promising results with average Dice scores up to 77.6% and mean sensitivity rates up to 78.9%. To our best knowledge, our proposed study is one of the first to tackle this particular issue, which limits direct comparability with related works. In respect to similar deep learning-based lesion segmentations, e.g. in liver MR images or spinal CT images, our experiments showed similar or in some respects superior segmentation quality. Overall, our automatic approach can provide almost expert-like segmentation accuracy in this challenging and ambitious task.

Dennis Sprute, Klaus Tönnies, Matthias König

Virtual borders are employed to allow humans the interactive and flexible restriction of their mobile robots' workspaces in human-centered environments, e.g. to exclude privacy zones from the workspace or to indicate certain areas for working. They have been successfully specified in interaction processes using methods from human-robot interaction. However, these methods often lack an expressive feedback system, are restricted to robot's on-board interaction capabilities and require a direct line of sight between human and robot. This negatively affects the user experience and interaction time. Therefore, we investigate the effect of a smart environment on the teaching of virtual borders with the objective to enhance the perceptual and interaction capabilities of a robot. For this purpose, we propose a novel interaction method based on a laser pointer, that leverages a smart home environment in the interaction process. This interaction method comprises an architecture for a smart home environment designed to support the interaction process, the cooperation of human, robot and smart environment in the interaction process, a cooperative perception including stationary and mobile cameras to perceive laser spots and an algorithm to extract virtual borders from multiple camera observations. The results of an experimental evaluation support our hypotheses that our novel interaction method features a significantly shorter interaction time and a better user experience compared to an approach without support of a smart environment. Moreover, the interaction method does not negatively affect other user requirements concerning completeness and accuracy.

Dennis Sprute, Klaus Tönnies, Matthias König

We address the problem of interactively controlling the workspace of a mobile robot to ensure a human-aware navigation. This is especially of relevance for non-expert users living in human-robot shared spaces, e.g. home environments, since they want to keep the control of their mobile robots, such as vacuum cleaning or companion robots. Therefore, we introduce virtual borders that are respected by a robot while performing its tasks. For this purpose, we employ a RGB-D Google Tango tablet as human-robot interface in combination with an augmented reality application to flexibly define virtual borders. We evaluated our system with 15 non-expert users concerning accuracy, teaching time and correctness and compared the results with other baseline methods based on visual markers and a laser pointer. The experimental results show that our method features an equally high accuracy while reducing the teaching time significantly compared to the baseline methods. This holds for different border lengths, shapes and variations in the teaching process. Finally, we demonstrated the correctness of the approach, i.e. the mobile robot changes its navigational behavior according to the user-defined virtual borders.

Dennis Sprute, Klaus Tönnies, Matthias König

We address the problem of controlling the workspace of a 3-DoF mobile robot. In a human-robot shared space, robots should navigate in a human-acceptable way according to the users' demands. For this purpose, we employ virtual borders, that are non-physical borders, to allow a user the restriction of the robot's workspace. To this end, we propose an interaction method based on a laser pointer to intuitively define virtual borders. This interaction method uses a previously developed framework based on robot guidance to change the robot's navigational behavior. Furthermore, we extend this framework to increase the flexibility by considering different types of virtual borders, i.e. polygons and curves separating an area. We evaluated our method with 15 non-expert users concerning correctness, accuracy and teaching time. The experimental results revealed a high accuracy and linear teaching time with respect to the border length while correctly incorporating the borders into the robot's navigational map. Finally, our user study showed that non-expert users can employ our interaction method.

Dennis Sprute, Robin Rasch, Klaus Tönnies et al.

The increasing number of robots in home environments leads to an emerging coexistence between humans and robots. Robots undertake common tasks and support the residents in their everyday life. People appreciate the presence of robots in their environment as long as they keep the control over them. One important aspect is the control of a robot's workspace. Therefore, we introduce virtual borders to precisely and flexibly define the workspace of mobile robots. First, we propose a novel framework that allows a person to interactively restrict a mobile robot's workspace. To show the validity of this framework, a concrete implementation based on visual markers is implemented. Afterwards, the mobile robot is capable of performing its tasks while respecting the new virtual borders. The approach is accurate, flexible and less time consuming than explicit robot programming. Hence, even non-experts are able to teach virtual borders to their robots which is especially interesting in domains like vacuuming or service robots in home environments.