Christoph Brune

University of Twente | UT · Department of Applied Mathematics

In an inhomogeneously illuminated photoacoustic image, important information like vascular geometry is not readily available when only the initial pressure is reconstructed. To obtain the desired information, algorithms for image segmentation are often applied as a post-processing step. In this work, we propose to jointly acquire the photoacoustic...

Our world is full of physics-driven data where effective mappings between data manifolds are desired. There is an increasing demand for understanding combined model-driven and data-driven learning methods. We propose a nonlinear, learned singular value decomposition (L-SVD), which combines autoencoders that simultaneously learn and connect latent c...

Circulating tumour cells (CTCs) found in the blood of cancer patients are a promising biomarker in precision medicine. However, their use is currently hindered by their low frequency, tedious manual scoring and extensive cell heterogeneities. Those challenges limit the effectiveness of classical machine-learning methods for automated CTC analysis....

Complex systems manifest a small number of instabilities and bifurcations that are canonical in nature, resulting in universal pattern forming characteristics as a function of some parametric dependence. Such parametric instabilities are mathematically characterized by their universal un-foldings, or normal form dynamics, whereby a parsimonious mod...

This work proposes a Stochastic Variational Deep Kernel Learning method for the data-driven discovery of low-dimensional dynamical models from high-dimensional noisy data. The framework is composed of an encoder that compresses high-dimensional measurements into low-dimensional state variables, and a latent dynamical model for the state variables t...

The application of deep learning models to large-scale data sets requires means for automatic quality assurance. We have previously developed a fully automatic algorithm for carotid artery wall segmentation in black-blood MRI that we aim to apply to large-scale data sets. This method identifies nested artery walls in 3D patches centered on the caro...

Though modern microscopes have an autofocusing system to ensure optimal focus, out-of-focus images can still occur when cells within the medium are not all in the same focal plane, affecting the image quality for medical diagnosis and analysis of diseases. We propose a method that can deblur images as well as synthesize defocus blur. We train autoe...

Epicardial adipose tissue (EAT) located inside the pericardium is a marker for increased risk of many cardiovascular diseases. Automatic segmentation methods for pericardium or EAT are necessary to support the otherwise extremely time-consuming manual delineation in CT scans. Powerful deep learning-based methods have been applied to such segmentati...

The application of deep learning models to large-scale data sets requires means for automatic quality assurance. We have previously developed a fully automatic algorithm for carotid artery wall segmentation in black-blood MRI that we aim to apply to large-scale data sets. This method identifies nested artery walls in 3D patches centered on the caro...

Neural networks are prone to learn easy solutions from superficial statistics in the data, namely shortcut learning, which impairs generalization and robustness of models. We propose a data augmentation strategy, named DFM-X, that leverages knowledge about frequency shortcuts, encoded in Dominant Frequencies Maps computed for image classification m...

Epicardial adipose tissue (EAT) is located between the visceral pericardium and myocardium, and EAT volume is correlated with cardiovascular risk. Nowadays, many deep learning-based automated EAT segmentation and quantification methods in the U-net family have been developed to reduce the workload for radiologists. The automatic assessment of EAT o...

Though modern microscopes have an autofocusing system to ensure optimal focus, out-of-focus images can still occur when cells within the medium are not all in the same focal plane, affecting the image quality for medical diagnosis and analysis of diseases. We propose a method that can deblur images as well as synthesize defocus blur. We train autoe...

Frequency analysis is useful for understanding the mechanisms of representation learning in neural networks (NNs). Most research in this area focuses on the learning dynamics of NNs for regression tasks, while little for classification. This study empirically investigates the latter and expands the understanding of frequency shortcuts. First, we pe...

We present a framework for safety-critical optimal control of physical systems based on denoising diffusion probabilistic models (DDPMs). The technology of control barrier functions (CBFs), encoding desired safety constraints, is used in combination with DDPMs to plan actions by iteratively denoising trajectories through a CBF-based guided sampling...

It is well known that conservative mechanical systems exhibit local oscillatory behaviors due to their elastic and gravitational potentials, which completely characterize these periodic motions together with the inertial properties of the system. The classification of these periodic behaviors and their geometric characterization are in an ongoing s...

Hemodynamic velocity fields in coronary arteries could be the basis of valuable biomarkers for diagnosis, prognosis and treatment planning in cardiovascular disease. Velocity fields are typically obtained from patient-specific 3D artery models via computational fluid dynamics (CFD). However, CFD simulation requires meticulous setup by experts and i...

Abdominal aortic aneurysms (AAAs) are progressive dilatations of the abdominal aorta that, if left untreated, can rupture with lethal consequences. Imaging-based patient monitoring is required to select patients eligible for surgical repair. In this work, we present a model based on implicit neural representations (INRs) to model AAA progression. W...

The approximation properties of infinitely wide shallow neural networks heavily depend on the choice of the activation function. To understand this influence, we study embeddings between Barron spaces with different activation functions. These embeddings are proven by providing push-forward maps on the measures $\mu$ used to represent functions $f$...

Shape encoding and shape analysis are valuable tools for comparing shapes and for dimensionality reduction. A specific framework for shape analysis is the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework, which is capable of shape matching and dimensionality reduction. Researchers have recently introduced neural networks into this f...

Abdominal aortic aneurysms (AAAs) are progressive dilatations of the abdominal aorta that, if left untreated, can rupture with lethal consequences. Imaging-based patient monitoring is required to select patients eligible for surgical repair. In this work, we present a model based on implicit neural representations (INRs) to model AAA progression. W...

Personalised 3D vascular models are valuable for diagnosis, prognosis and treatment planning in patients with cardiovascular disease. Traditionally, such models have been constructed with explicit representations such as meshes and voxel masks, or implicit representations such as radial basis functions or atomic (cylindrical) shapes. Here, we propo...

It is well known that conservative mechanical systems exhibit local oscillatory behaviours due to their elastic and gravitational potentials, which completely characterise these periodic motions together with the inertial properties of the system. The classification of these periodic behaviours and their geometric characterisation are in an on-goin...

This work proposes a stochastic variational deep kernel learning method for the data-driven discovery of low-dimensional dynamical models from high-dimensional noisy data. The framework is composed of an encoder that compresses high-dimensional measurements into low-dimensional state variables, and a latent dynamical model for the state variables t...

Computational fluid dynamics (CFD) is a valuable asset for patient-specific cardiovascular-disease diagnosis and prognosis, but its high computational demands hamper its adoption in practice. Machine-learning methods that estimate blood flow in individual patients could accelerate or replace CFD simulation to overcome these limitations. In this wor...

Reproducing Kernel Hilbert spaces (RKHS) have been a very successful tool in various areas of machine learning. Recently, Barron spaces have been used to proof bounds on the generalisation error for neural networks. Unfortunately, Barron spaces cannot be understood in terms of RKHS due to the strong nonlinear coupling of the weights. We show that t...

This review addresses the problem of learning abstract representations of the measurement data in the context of Deep Reinforcement Learning (DRL). While the data are often ambiguous, high-dimensional, and complex to interpret, many dynamical systems can be effectively described by a low-dimensional set of state variables. Discovering these state v...

Personalised 3D vascular models are valuable for diagnosis, prognosis and treatment planning in patients with cardiovascular disease. Traditionally, such models have been constructed with explicit representations such as meshes and voxel masks, or implicit representations such as radial basis functions or atomic (tubular) shapes. Here, we propose t...

Recently, super-resolution ultrasound imaging with ultrasound localization microscopy (ULM) has received much attention. However, ULM relies on low concentrations of microbubbles in the blood vessels, ultimately resulting in long acquisition times. Here, we present an alternative super-resolution approach, based on direct deconvolution of single-ch...

Recently, super-resolution ultrasound imaging with ultrasound localization microscopy (ULM) has received much attention. However, ULM relies on low concentrations of microbubbles in the blood vessels, ultimately resulting in long acquisition times. Here, we present an alternative super-resolution approach, based on direct deconvolution of single-ch...

Background: Epicardial adipose tissue (EAT) locates between the visceral pericardium and myocardium and the EAT volume is correlated with cardiovascular risk. Nowadays, many deep learning-based automated EAT segmentation and quantification methods in the U-net family were developed to reduce the workload for radiologists. However, most of the works...

Inspection and maintenance are two crucial aspects of industrial pipeline plants. While robotics has made tremendous progress in the mechanic design of in-pipe inspection robots, the autonomous control of such robots is still a big open challenge due to the high number of actuators and the complex manoeuvres required. To address this problem, we in...

The European Union (EU) Commission’s whitepaper on Artificial Intelligence (AI) proposes shaping the emerging AI market so that it better reflects common European values. It is a master plan that builds upon the EU AI High-Level Expert Group guidelines. This article reviews the masterplan, from a culture cycle perspective, to reflect on its potenti...

Computational fluid dynamics (CFD) is a valuable tool for personalised, non-invasive evaluation of hemodynamics in arteries, but its complexity and time-consuming nature prohibit large-scale use in practice. Recently, the use of deep learning for rapid estimation of CFD parameters like wall shear stress (WSS) on surface meshes has been investigated...

Training effective models for segmentation or classification of microscopy images is a hard task, complicated by the scarcity of adequately labeled data sets. In this context, self-supervised learning strategies can be deployed to learn suitable image representations from the available large quantity of unlabeled data, e.g. the 500k electron micros...

Deformable medical image registration has in past years been revolutionized by the use of convolutional neural networks. These methods surpass conventional image registration techniques in speed but not in accuracy. Here, we present an alternative approach to leveraging neural networks for image registration. Instead of using a convolutional neural...

Carotid artery vessel wall thickness measurement is an essential step in the monitoring of patients with atherosclerosis. This requires accurate segmentation of the vessel wall, i.e., the region between an artery's lumen and outer wall, in black-blood magnetic resonance (MR) images. Commonly used convolutional neural networks (CNNs) for semantic se...

The development of physics-informed deep learning is radically changing computational science and engineering, allowing for an effective integration of physics-based and data-driven modeling. Deep learning provides a powerful tool for the discovery of governing dynamics underneath data and enables nonlinear model reduction. A Bayesian viewpoint of...

Computational fluid dynamics (CFD) is a valuable tool for personalised, non-invasive evaluation of hemodynamics in arteries, but its complexity and time-consuming nature prohibit large-scale use in practice. Recently, the use of deep learning for rapid estimation of CFD parameters like wall shear stress (WSS) on surface meshes has been investigated...

Inspection and maintenance are two crucial aspects of industrial pipeline plants. While robotics has made tremendous progress in the mechanic design of in-pipe inspection robots, the autonomous control of such robots is still a big open challenge due to the high number of actuators and the complex manoeuvres required. To address this problem, we in...

Deep Reinforcement Learning has shown its ability in solving complicated problems directly from high-dimensional observations. However, in end-to-end settings, Reinforcement Learning algorithms are not sample-efficient and requires long training times and quantities of data. In this work, we proposed a framework for sample-efficient Reinforcement L...

Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain. Reinforcement learning algorithms have proven to be capable of solving complicated robotics tasks in an end-to-end fash...

Autonomously exploring and mapping is one of the open challenges of robotics and artificial intelligence. Especially when the environments are unknown, choosing the optimal navigation directive is not straightforward. In this paper, we propose a reinforcement learning framework for navigating, exploring, and mapping unknown environments. The reinfo...

Deep learning has become widely used for medical image segmentation in recent years. However, despite these advances, there are still problems for which deep learning-based segmentation fails. Recently, some deep learning approaches had a breakthrough by using anatomical information which is the crucial cue for manual segmentation. In this paper, w...

Drugs targeting the VEGF (vascular endothelial growth factor) signaling pathway are approved for several malignancies. Unfortunately, VEGF inhibitors lead to hypertension in 30% to 80% patients. Reduced nitric oxide synthase activity, microvascular rarefaction, and increased vascular resistance have been proposed as potential mechanisms. We aimed t...

In this research, we investigate the use of Reinforcement Learning (RL) for an effective and robust solution for exploring unknown and indoor environments and reconstructing their maps. We benefit from a Simultaneous Localization and Mapping (SLAM) algorithm for real-time robot localization and mapping. Three different reward functions are compared...

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations, often requires processing and storage of a huge amount of data. In the context of robotics, the cost of data fro...

In an inhomogeneously illuminated photoacoustic image, important information like vascular geometry is not readily available when only the initial pressure is reconstructed. To obtain the desired information, algorithms for image segmentation are often applied as a post-processing step. In this work, we propose to jointly acquire the photoacoustic...

Introduction: Drugs targeting Vascular Endothelial Growth Factor (VEGF) signaling pathway are approved therapies for cancer. Unfortunately, VEGF inhibitors lead to hypertension in 30-80% patients. Reduced nitric oxide synthase activity and increased vascular resistance have been proposed as potential mechanisms. We aimed to assess these mechanisms...

We replace part of a model‐based iterative algorithm with a convolutional neural network in order to improve the quality of tomography reconstructions. We analyse its robustness against uncertainties in the image and uncertainties in system settings. Results are presented for the application of photoacoustic tomography in a limited angle setup.

In this paper we propose a new joint model for the reconstruction of tomography data under limited angle sampling regimes. In many applications of tomography, e.g. electron microscopy and mammography, physical limitations on acquisition lead to regions of data which cannot be sampled. Depending on the severity of the restriction, reconstructions ca...

The presence of Circulating tumor cells (CTCs) is associated with relatively poor survival of cancer patients with a strong relation with increasing CTC numbers. Assignment of objects as CTC or not can therefore have large clinical implications. Yet, nearly all CTC isolation techniques lack a fully automated image analysis, thereby making CTC count...

This paper discusses the properties of certain risk estimators that recently regained popularity for choosing regularization parameters in ill-posed problems, in particular for sparsity regularization. They apply Stein's unbiased risk estimator (SURE) to estimate the risk in either the space of the unknown variables or in the data space. We will ca...

For using counts of circulating tumor cells (CTCs) in the clinic to aid a physician’s decision, its reported values will need to be accurate and comparable between institutions. Many technologies have become available to enumerate and characterize CTCs, thereby showing a large range of reported values. Here we introduce an Open Source CTC scoring t...

Introduction In patients with drug-resistant focal epilepsy, surgery can be considered. The goal is to remove the epileptogenic tissue, while sparing the eloquent cortex. Prior to surgery, a prolonged electroencephalography (ECoG) recording can assist in the delineation of epileptogenic tissue and functionality of the surrounding cortex. During the...

In this paper we propose a new joint model for the reconstruction of tomography data under limited angle sampling regimes. In many applications of Tomography, e.g. Electron Microscopy and Mammography, physical limitations on acquisition lead to regions of data which cannot be sampled. Depending on the severity of the restriction, reconstructions ca...

- ACCEPT (Automated CTC Classification Enumeration and PhenoTyping): Quantification and visualization of various cell populations by gating for several parameters using CellSearch images. Download for free at www.github.com/LeonieZ/ACCEPT. - Improving Cell Classification: CellSearch populations are improved by adding CD16-PerCP to the immunostainin...

By using advanced image analysis of fluorescent images obtained from EpCAM enriched blood samples, the complete cellular composition of the sample can be obtained. Operator variability in classification of objects is eliminated as well as the time spend by the operators to review the images. Download ACCEPT for free at www.github.com/LeonieZ/ACCEPT...

ABSTRACT Purpose: The presence of Circulating Tumor Cells (CTCs) in Castration-Resistant Prostate Cancer (CRPC) patients is associated with poor prognosis. In this study, we evaluated the association of clinical outcome in 129 CRPC patients with CTCs, tumor-derived Extracellular Vesicles (tdEVs) and plasma levels of total (CK18) and caspase-cleave...

Photoacoustic tomography is a hybrid imaging technique that combines high optical tissue contrast with high ultrasound resolution. Direct reconstruction methods such as filtered backprojection, time reversal and least squares suffer from curved line artefacts and blurring, especially in case of limited angles or strong noise. In recent years, there...

Circulating tumor cells (CTCs) isolated from blood can be probed for the expression of treatment targets. Immunofluorescence is often used for both the enumeration of CTC and the determination of protein expression levels related to treatment targets. Accurate and reproducible assessment of such treatment target expression levels is essential for t...

Linear calibration of the number of HER-2 antigens and the measured HER-2 signal intensity. Values plotted for each of the investigated cell lines together with the corresponding line equation and regression value. (TIF)

Comparisons of HER-2 assessment using ACCEPT versus CellTracks Analyzer II® (Menarini Silicon Biosystems Inc) visualization in relation to measured mean intensities. Expression of Cytokeratin and HER-2 on the 150 randomly chosen images of CTCs that were sent to six different investigators for scoring HER-2 positivity. Marker colors indicate if all,...

Significance We show how small-scale (less than millimeters ² ) neuronal dynamics relates to network activity observed across wide areas (greater than centimeters ² ) during certain network states, such as seizures. Simulations show how macroscopic network properties can affect frequency and amplitude of ictal oscillations. Additionally, the seizur...

Photoacoustic tomography is a hybrid imaging technique that combines high optical tissue contrast with high ultrasound resolution. Direct reconstruction methods such as filtered backprojection, time reversal and least squares suffer from curved line artefacts and blurring, especially in case of limited angles or strong noise. Recently, there has be...

In the field of Circulating Tumor Cell (CTC) research many new technologies are emerging to isolate CTCs. Some of them provide accompanying automated image analysis tools that present possible CTCs to the user. Others need fully manual image analysis. For all CTC isolation technologies the definition of a CTC based on the immuno-morphologic criteri...