Quantitative analysis of bioimaging data is often skewed by both shading in space and background variation in time. We introduce BaSiC, an image correction method based on low-rank and sparse decomposition which solves both issues. In comparison to existing shading correction tools, BaSiC achieves high-accuracy with significantly fewer input images, works for diverse imaging conditions and is robust against artefacts. Moreover, it can correct temporal drift in time-lapse microscopy data and thus improve continuous single-cell quantification. BaSiC requires no manual parameter setting and is available as a Fiji/ImageJ plugin.

Graph deep learning has recently emerged as a powerful ML concept allowing to generalize successful deep neural architectures to non-euclidean structured data. Such methods have shown promising results on a broad spectrum of applications ranging from social science, biomedicine, and particle physics to computer vision, graphics, and chemistry. One of the limitations of the majority of current graph neural network architectures is that they are often restricted to the transductive setting and rely on the assumption that the underlying graph is known and fixed . Often, this assumption is not true since the graph may be noisy, or partially and even completely unknown. In such cases, it would be helpful to infer the graph directly from the data, especially in inductive settings where some nodes were not present in the graph at training time. Furthermore, learning a graph may become an end in itself, as the inferred structure may provide complementary insights next to the downstream task. In this paper, we introduce Differentiable Graph Module (DGM), a learnable function that predicts edge probabilities in the graph which are optimal for the downstream task. DGM can be combined with convolutional graph neural network layers and trained in an end-to-end fashion. We provide an extensive evaluation of applications from the domains of healthcare (disease prediction), brain imaging (age prediction), computer graphics (3D point cloud segmentation), and computer vision (zero-shot learning). We show that our model provides a significant improvement over baselines both in transductive and inductive settings and achieves state-of-the-art results.

In this paper a low-drift monocular SLAM method is proposed targeting indoor scenarios, where monocular SLAM often fails due to the lack of textured surfaces. Our approach decouples rotation and translation estimation of the tracking process to reduce the long-term drift in indoor environments. In order to take full advantage of the available geometric information in the scene, surface normals are predicted by a convolutional neural network from each input RGB image in real-time. First, a drift-free rotation is estimated based on lines and surface normals using spherical mean-shift clustering, leveraging the weak Manhattan World assumption. Then translation is computed from point and line features. Finally, the estimated poses are refined with a map-to-frame optimization strategy. The proposed method outperforms the state of the art on common SLAM benchmarks such as ICL-NUIM and TUM RGB-D.

Mobile C-arm is an essential tool in everyday trauma and orthopedics surgery. Minimally invasive solutions, based on X-ray imaging and coregistered external navigation created a lot of interest within the surgical community and started to replace the traditional open surgery for many procedures. These solutions usually increase the accuracy and reduce the trauma. In general, they introduce new hardware into the OR and add the line of sight constraints imposed by optical tracking systems. They thus impose radical changes to the surgical setup and overall procedure. We augment a commonly used mobile C-arm with a standard video camera and a double mirror system allowing real-time fusion of optical and X-ray images. The video camera is mounted such that its optical center virtually coincides with the C-arm's X-ray source. After a one-time calibration routine, the acquired X-ray and optical images are coregistered. This paper describes the design of such a system, quantifies its technical accuracy, and provides a qualitative proof of its efficiency through cadaver studies conducted by trauma surgeons. In particular, it studies the relevance of this system for surgical navigation within pedicle screw placement, vertebroplasty, and intramedullary nail locking procedures. The image overlay provides an intuitive interface for surgical guidance with an accuracy of <;1 mm, ideally with the use of only one single X-ray image. The new system is smoothly integrated into the clinical application with no additional hardware especially for down-the-beam instrument guidance based on the anteroposterior oblique view, where the instrument axis is aligned with the X-ray source. Throughout all experiments, the camera augmented mobile C-arm system proved to be an intuitive and robust guidance solution for selected clinical routines.