KHKlaus Hildebrandt

Klaus Hildebrandt

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Klaus Hildebrandt has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    GravoTet: A Fast Multigrid Hierarchy Construction for Tetrahedral Meshes

    by Marcel Padilla, Tim Huisman, Jackson Campolattaro, Ruben Wiersma, Klaus Hildebrandt, Olga Sorkine-Hornung

    Geometric multigrid (GMG) methods are a fundamental tool for efficiently solving large sparse linear systems. A requirement for GMG is a hierarchy of grids; however, many practical volumetric domains are available only as single, irregular tetrahedral meshes, making the construction of a multigrid hierarchy necessary. Existing approaches often trade off speed against hierarchy quality: remeshing- or coarsening-based methods can be expensive to construct, whereas graph-based techniques are fast but often yield weaker multigrid performance.We introduce GravoTet, which bridges this gap by combining geometric structure with graph‑based efficiency to construct fast and effective multigrid hierarchies. GravoTet builds a vertex hierarchy and then generates graph‑Voronoi diagrams whose dual cells define coarse tetrahedra, enabling rapid construction of multigrid levels. Boundary elements are explicitly prioritized during both sampling and tet generation to preserve boundary. In our evaluation, we solve Poisson and biharmonic problems on irregular tetrahedral meshes and compare GravoTet against state‑of‑the‑art geometric multigrid, algebraic multigrid and direct solvers, demonstrating superior performance, particularly on large meshes.

  • LoGCC: Local-to-Global Correlation Clustering for Scalar Field Ensembles

    by Nicolas F. Chaves-De-Plaza, Renata G. Raidou, Prerak Mody, Marius Staring, René van Egmond, Anna Vilanova, Klaus Hildebrandt

    Correlation clustering (CC) offers an effective approach to analyze scalar field ensembles by detecting correlated regions and consistent structures, enabling the extraction of meaningful patterns. However, existing CC methods are computationally expensive, making them impractical for both interactive analysis and large-scale scalar fields. We introduce the Local-to-Global Correlation Clustering (LoGCC) framework, which accelerates pivot-based CC by leveraging the spatial structure of scalar fields and the weak transitivity of correlation. LoGCC operates in two stages: a local step that uses the neighborhood graph of the scalar field's spatial domain to build highly correlated local clusters, and a global step that merges them into global clusters. We implement the LoGCC framework for two well-known pivot-based CC methods, Pivot and CN-Pivot, demonstrating its generality. Our evaluation using synthetic and real-world meteorological and medical image segmentation datasets shows that LoGCC achieves speedups-up to 15× for Pivot and 200× for CN-Pivot-and improved scalability to larger scalar fields, while maintaining cluster quality. These contributions broaden the applicability of correlation clustering in large-scale and interactive analysis settings.

  • Open Access

    A novel 3D image registration technique for augmented reality vision in minimally invasive thoracoscopic pulmonary segmentectomy

    by J. J. Peek, X. Zhang, K. Hildebrandt, S. A. Max, A. H. Sadeghi, A. J. J. C. Bogers, E. A. F. Mahtab

    Purpose: In this feasibility study, we aimed to create a dedicated pulmonary augmented reality (AR) workflow to enable a semi-automated intraoperative overlay of the pulmonary anatomy during video-assisted thoracoscopic surgery (VATS) or robot-assisted thoracoscopic surgery (RATS). Methods: Initially, the stereoscopic cameras were calibrated to obtain the intrinsic camera parameters. Intraoperatively, stereoscopic images were recorded and a 3D point cloud was generated from these images. By manually selecting the bifurcation key points, the 3D segmentation (from the diagnostic CT scan) was registered onto the intraoperative 3D point cloud. Results: Image reprojection errors were 0.34 and 0.22 pixels for the VATS and RATS cameras, respectively. We created disparity maps and point clouds for all eight patients. Time for creation of the 3D AR overlay was 5 min. Validation of the point clouds was performed, resulting in a median absolute error of 0.20 mm [IQR 0.10–0.54]. We were able to visualize the AR overlay and identify the arterial bifurcations adequately for five patients. In addition to creating AR overlays of the visible or invisible structures intraoperatively, we successfully visualized branch labels and altered the transparency of the overlays. Conclusion: An algorithm was developed transforming the operative field into a 3D point cloud surface. This allowed for an accurate registration and visualization of preoperative 3D models. Using this system, surgeons can navigate through the patient's anatomy intraoperatively, especially during crucial moments, by visualizing otherwise invisible structures. This proposed registration method lays the groundwork for automated intraoperative AR navigation during minimally invasive pulmonary resections.


  • Open Access

    Implementation of delineation error detection systems in time-critical radiotherapy: Do AI-supported optimization and human preferences meet?

    by Nicolas F. Chaves-De-Plaza, Prerak Mody, Klaus Hildebrandt, Marius Staring, Eleftheria Astreinidou, Mischa de Ridder, Huib de Ridder, Anna Vilanova, René van Egmond

  • Open Access

    Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation

    by Prerak Mody, Nicolas F. Chaves-De-Plaza, Chinmay Rao, Eleftheria Astrenidou, Mischa de Ridder, Nienke Hoekstra, Klaus Hildebrandt, Marius Staring

    Increased usage of automated tools like deep learning in medical image segmentation has alleviated the bottleneck of manual contouring. This has shifted manual labour to quality assessment (QA) of automated contours which involves detecting errors and correcting them. A potential solution to semi-automated QA is to use deep Bayesian uncertainty to recommend potentially erroneous regions, thus reducing time spent on error detection. Previous work has investigated the correspondence between uncertainty and error, however, no work has been done on improving the “utility” of Bayesian uncertainty maps such that it is only present in inaccurate regions and not in the accurate ones. Our work trains the FlipOut model with the Accuracy-vs-Uncertainty (AvU) loss which promotes uncertainty to be present only in inaccurate regions. We apply this method on datasets of two radiotherapy body sites, c.f. head-and-neck CT and prostate MR scans. Uncertainty heatmaps (i.e. predictive entropy) are evaluated against voxel inaccuracies using Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves. Numerical results show that when compared to the Bayesian baseline the proposed method successfully suppresses uncertainty for accurate voxels, with similar presence of uncertainty for inaccurate voxels. Code to reproduce experiments is available at https://github.com/prerakmody/bayesuncertainty-error-correspondence


  • Open Access

    Depth for Multi‐Modal Contour Ensembles

    by N.F. Chaves‐De‐Plaza, M. Molenaar, P. Mody, M. Staring, R. van Egmond, E. Eisemann, A. Vilanova, K. Hildebrandt

    The contour depth methodology enables non‐parametric summarization of contour ensembles by extracting their representatives, confidence bands, and outliers for visualization (via contour boxplots) and robust downstream procedures. We address two shortcomings of these methods. Firstly, we significantly expedite the computation and recomputation of Inclusion Depth (ID), introducing a linear‐time algorithm for epsilon ID, a variant used for handling ensembles with contours with multiple intersections. We also present the inclusion matrix, which contains the pairwise inclusion relationships between contours, and leverage it to accelerate the recomputation of ID. Secondly, extending beyond the single distribution assumption, we present the Relative Depth (ReD), a generalization of contour depth for ensembles with multiple modes. Building upon the linear‐time eID, we introduce CDclust, a clustering algorithm that untangles ensemble modes of variation by optimizing ReD. Synthetic and real datasets from medical image segmentation and meteorological forecasting showcase the speed advantages, illustrate the use case of progressive depth computation and enable non‐parametric multimodal analysis. To promote research and adoption, we offer the contour‐depth Python package.


  • Accelerating Hyperbolic t-SNE

    by Martin Skrodzki, Hunter van Geffen, Nicolas F. Chaves-De-Plaza, Thomas Höllt, Elmar Eisemann, Klaus Hildebrandt

    The need to understand the structure of hierarchical or high-dimensional data is present in a variety of fields. Hyperbolic spaces have proven to be an important tool for embedding computations and analysis tasks as their non-linear nature lends itself well to tree or graph data. Subsequently, they have also been used in the visualization of high-dimensional data, where they exhibit increased embedding performance. However, none of the existing dimensionality reduction methods for embedding into hyperbolic spaces scale well with the size of the input data. That is because the embeddings are computed via iterative optimization schemes and the computation cost of every iteration is quadratic in the size of the input. Furthermore, due to the non-linear nature of hyperbolic spaces, euclidean acceleration structures cannot directly be translated to the hyperbolic setting. This article introduces the first acceleration structure for hyperbolic embeddings, building upon a polar quadtree. We compare our approach with existing methods and demonstrate that it computes embeddings of similar quality in significantly less time. Implementation and scripts for the experiments can be found at https://graphics.tudelft.nl/accelerating-hyperbolic-tsne .


  • Open Access

    Accelerating hyperbolic t-SNE

    by Martin Skrodzki, Hunter van Geffen, Nicolas F. Chaves-De-Plaza, Thomas Höllt, Elmar Eisemann, Klaus Hildebrandt

    The need to understand the structure of hierarchical or high-dimensional data is present in a variety of fields. Hyperbolic spaces have proven to be an important tool for embedding computations and analysis tasks as their non-linear nature lends itself well to tree or graph data. Subsequently, they have also been used in the visualization of high-dimensional data, where they exhibit increased embedding performance. However, none of the existing dimensionality reduction methods for embedding into hyperbolic spaces scale well with the size of the input data. That is because the embeddings are computed via iterative optimization schemes and the computation cost of every iteration is quadratic in the size of the input. Furthermore, due to the non-linear nature of hyperbolic spaces, Euclidean acceleration structures cannot directly be translated to the hyperbolic setting. This paper introduces the first acceleration structure for hyperbolic embeddings, building upon a polar quadtree. We compare our approach with existing methods and demonstrate that it computes embeddings of similar quality in significantly less time. Implementation and scripts for the experiments can be found at https://graphics.tudelft.nl/accelerating-hyperbolic-tsne.

  • Open Access

    A Fast Geometric Multigrid Method for Curved Surfaces

    by Ruben Wiersma, Ahmad Nasikun, Elmar Eisemann, Klaus Hildebrandt


  • Open Access

    Report on AI-Infused Contouring Workflows for Adaptive Proton Therapy in the Head and Neck

    by Nicolas F. Chaves-De-Plaza, Prerak Mody, Klaus Hildebrandt, Marius Staring, Eleftheria Astreinidou, Mischa de Ridder, Huib de Ridder, Rene van Egmond

    Delineation of tumors and organs-at-risk permits detecting and correcting changes in the patients' anatomy throughout the treatment, making it a core step of adaptive proton therapy (APT). Although AI-based auto-contouring technologies have sped up this process, the time needed to perform the quality assessment (QA) of the generated contours remains a bottleneck, taking clinicians between several minutes up to an hour to complete. This paper introduces a fast contouring workflow suitable for time-critical APT, enabling detection of anatomical changes in shorter time frames and with a lower demand of clinical resources. The proposed AI-infused workflow follows two principles uncovered after reviewing the APT literature and conducting several interviews and an observational study in two radiotherapy centers in the Netherlands. First, enable targeted inspection of the generated contours by leveraging AI uncertainty and clinically-relevant features such as the proximity of the organs-at-risk to the tumor. Second, minimize the number of interactions needed to edit faulty delineations with redundancy-aware editing tools that provide the user a sense of predictability and control. We use a proof of concept that we validated with clinicians to demonstrate how current and upcoming AI capabilities support the workflow and how it would fit into clinical practice.