arXiv subjects

Vincent Heuveline

Publications and source records attributed to Vincent Heuveline.

13 recordsLinked to original sources

arXiv2026

Clinical application of HEDI for biomechanical evaluation and visualisation in incisional hernia repair

Background: Abdominal wall defects, such as incisional hernias, are a common source of pain and discomfort and often require repeated surgical interventions. Traditional mesh repair techniques typically rely on fixed overlap based on defect size, without considering important biomechanical factors like muscle activity, internal pressure, and tissue elasticity. This study aims to introduce a biomechanical approach to incisional hernia repair that accounts for abdominal wall instability and to evaluate a visualisation tool designed to support surgical planning. Methods: We developed HEDI, a tool that uses computed tomography with Valsalva maneuver to automatically assess hernia size, volume, and abdominal wall instability. This tool was applied in the preoperative evaluation of 31 patients undergoing incisional hernia repair. Surgeries were performed concurrently with the development of the tool, and patient outcomes were monitored over a three-year period. Results: Here we show that all 31 patients remain free of pain and hernia recurrence three years after surgery. The tool provides valuable visual insights into abdominal wall dynamics, supporting surgical decision-making. However, it should be used as an adjunct rather than a standalone guide. Conclusions: This study presents a biomechanical strategy for hernia repair and introduces a visualisation tool that enhances preoperative assessment. While early results are promising, the tool's evolving nature and its role as a visual aid should be considered when interpreting outcomes. Further research is needed to validate its broader clinical utility.

cs.CV↗

arXiv2025

A Systematic Review of Conformal Inference Procedures for Treatment Effect Estimation: Methods and Challenges

Treatment effect estimation is essential for informed decision-making in many fields such as healthcare, economics, and public policy. While flexible machine learning models have been widely applied for estimating heterogeneous treatment effects, quantifying the inherent uncertainty of their point predictions remains an issue. Recent advancements in conformal prediction address this limitation by allowing for inexpensive computation, as well as distribution shifts, while still providing frequentist, finite-sample coverage guarantees under minimal assumptions for any point-predictor model. This advancement holds significant potential for improving decision-making in especially high-stakes environments. In this work, we perform a systematic review regarding conformal prediction methods for treatment effect estimation and provide for both the necessary theoretical background. Through a systematic filtering process, we select and analyze eleven key papers, identifying and describing current state-of-the-art methods in this area. Based on our findings, we propose directions for future research.

cs.LG↗

arXiv2023

Shot Noise Reduction in Radiographic and Tomographic Multi-Channel Imaging with Self-Supervised Deep Learning

Noise is an important issue for radiographic and tomographic imaging techniques. It becomes particularly critical in applications where additional constraints force a strong reduction of the Signal-to-Noise Ratio (SNR) per image. These constraints may result from limitations on the maximum available flux or permissible dose and the associated restriction on exposure time. Often, a high SNR per image is traded for the ability to distribute a given total exposure capacity per pixel over multiple channels, thus obtaining additional information about the object by the same total exposure time. These can be energy channels in the case of spectroscopic imaging or time channels in the case of time-resolved imaging. In this paper, we report on a method for improving the quality of noisy multi-channel (time or energy-resolved) imaging datasets. The method relies on the recent Noise2Noise (N2N) self-supervised denoising approach that learns to predict a noise-free signal without access to noise-free data. N2N in turn requires drawing pairs of samples from a data distribution sharing identical signals while being exposed to different samples of random noise. The method is applicable if adjacent channels share enough information to provide images with similar enough information but independent noise. We demonstrate several representative case studies, namely spectroscopic (k-edge) X-ray tomography, in vivo X-ray cine-radiography, and energy-dispersive (Bragg edge) neutron tomography. In all cases, the N2N method shows dramatic improvement and outperforms conventional denoising methods. For such imaging techniques, the method can therefore significantly improve image quality, or maintain image quality with further reduced exposure time per image.

cs.CV↗

arXiv2023

Optimizing the Procedure of CT Segmentation Labeling

In Computed Tomography, machine learning is often used for automated data processing. However, increasing model complexity is accompanied by increasingly large volume datasets, which in turn increases the cost of model training. Unlike most work that mitigates this by advancing model architectures and training algorithms, we consider the annotation procedure and its effect on the model performance. We assume three main virtues of a good dataset collected for a model training to be label quality, diversity, and completeness. We compare the effects of those virtues on the model performance using open medical CT datasets and conclude, that quality is more important than diversity early during labeling; the diversity, in turn, is more important than completeness. Based on this conclusion and additional experiments, we propose a labeling procedure for the segmentation of tomographic images to minimize efforts spent on labeling while maximizing the model performance.

cs.CV↗

arXiv2023

A Knowledge Distillation framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image

Morphological atlases are an important tool in organismal studies, and modern high-throughput Computed Tomography (CT) facilities can produce hundreds of full-body high-resolution volumetric images of organisms. However, creating an atlas from these volumes requires accurate organ segmentation. In the last decade, machine learning approaches have achieved incredible results in image segmentation tasks, but they require large amounts of annotated data for training. In this paper, we propose a self-training framework for multi-organ segmentation in tomographic images of Medaka fish. We utilize the pseudo-labeled data from a pretrained Teacher model and adopt a Quality Classifier to refine the pseudo-labeled data. Then, we introduce a pixel-wise knowledge distillation method to prevent overfitting to the pseudo-labeled data and improve the segmentation performance. The experimental results demonstrate that our method improves mean Intersection over Union (IoU) by 5.9% on the full dataset and enables keeping the quality while using three times less markup.

cs.CV↗

arXiv2023

Self-Supervised Learning for Biological Sample Localization in 3D Tomographic Images

In synchrotron-based Computed Tomography (CT) there is a trade-off between spatial resolution, field of view and speed of positioning and alignment of samples. The problem is even more prominent for high-throughput tomography--an automated setup, capable of scanning large batches of samples without human interaction. As a result, in many applications, only 20-30% of the reconstructed volume contains the actual sample. Such data redundancy clutters the storage and increases processing time. Hence, an automated sample localization becomes an important practical problem. In this work, we describe two self-supervised losses designed for biological CT. We further demonstrate how to employ the uncertainty estimation for sample localization. This approach shows the ability to localize a sample with less than 1.5\% relative error and reduce the used storage by a factor of four. We also show that one of the proposed losses works reasonably well as a pre-training task for the semantic segmentation.

cs.CV↗

arXiv2022

Using the Order of Tomographic Slices as a Prior for Neural Networks Pre-Training

The technical advances in Computed Tomography (CT) allow to obtain immense amounts of 3D data. For such datasets it is very costly and time-consuming to obtain the accurate 3D segmentation markup to train neural networks. The annotation is typically done for a limited number of 2D slices, followed by an interpolation. In this work, we propose a pre-training method SortingLoss. It performs pre-training on slices instead of volumes, so that a model could be fine-tuned on a sparse set of slices, without the interpolation step. Unlike general methods (e.g. SimCLR or Barlow Twins), the task specific methods (e.g. Transferable Visual Words) trade broad applicability for quality benefits by imposing stronger assumptions on the input data. We propose a relatively mild assumption -- if we take several slices along some axis of a volume, structure of the sample presented on those slices, should give a strong clue to reconstruct the correct order of those slices along the axis. Many biomedical datasets fulfill this requirement due to the specific anatomy of a sample and pre-defined alignment of the imaging setup. We examine the proposed method on two datasets: medical CT of lungs affected by COVID-19 disease, and high-resolution synchrotron-based full-body CT of model organisms (Medaka fish). We show that the proposed method performs on par with SimCLR, while working 2x faster and requiring 1.5x less memory. In addition, we present the benefits in terms of practical scenarios, especially the applicability to the pre-training of large models and the ability to localize samples within volumes in an unsupervised setup.

eess.IV↗

arXiv2021

Hierarchical surrogate-based Approximate Bayesian Computation for an electric motor test bench

Inferring parameter distributions of complex industrial systems from noisy time series data requires methods to deal with the uncertainty of the underlying data and the used simulation model. Bayesian inference is well suited for these uncertain inverse problems. Standard methods used to identify uncertain parameters are Markov Chain Monte Carlo (MCMC) methods with explicit evaluation of a likelihood function. However, if the likelihood is very complex, such that its evaluation is computationally expensive, or even unknown in its explicit form, Approximate Bayesian Computation (ABC) methods provide a promising alternative. In this work both methods are first applied to artificially generated data and second on a real world problem, by using data of an electric motor test bench. We show that both methods are able to infer the distribution of varying parameters with a Bayesian hierarchical approach. But the proposed ABC method is computationally much more efficient in order to achieve results with similar accuracy. We suggest to use summary statistics in order to reduce the dimension of the data which significantly increases the efficiency of the algorithm. Further the simulation model is replaced by a Polynomial Chaos Expansion (PCE) surrogate to speed up model evaluations. We proof consistency for the proposed surrogate-based ABC method with summary statistics under mild conditions on the (approximated) forward model.

stat.AP↗

arXiv2020

A Simple Model for Portable and Fast Prediction of Execution Time and Power Consumption of GPU Kernels

Characterizing compute kernel execution behavior on GPUs for efficient task scheduling is a non-trivial task. We address this with a simple model enabling portable and fast predictions among different GPUs using only hardware-independent features. This model is built based on random forests using 189 individual compute kernels from benchmarks such as Parboil, Rodinia, Polybench-GPU and SHOC. Evaluation of the model performance using cross-validation yields a median Mean Average Percentage Error (MAPE) of 8.86-52.00% and 1.84-2.94%, for time respectively power prediction across five different GPUs, while latency for a single prediction varies between 15 and 108 milliseconds.

cs.DC↗

arXiv2020

Dielectrophoretic force-driven convection in annular geometry under Earth's gravity

Context: A radial temperature gradient together with an inhomogeneous radial electric field gradient is applied to a dielectric fluid confined in a vertical cylindrical annulus inducing thermal electro-hydrodynamic convection. Aims: Identification of the stability of the flow and hence of the line of marginal stability separating stable laminar free (natural) convection from thermal electro-hydrodynamic convection, its flow structures, pattern formation and critical parameters. Methods: Combination of different measurement techniques, namely the shadowgraph method and particle image velocimetry, as well as numerical simulation are used to qualify/quantify the flow. Results: We identify the transition from stable laminar free convection to thermal electro-hydrodynamic convective flow in a wide range of Rayleigh number and electric potential. The line of marginal stability found confirms results from linear stability analysis. The flow after first transition forms a structure of vertically aligned stationary columnar modes. We experimentally confirm critical parameters resulting from linear stability analysis and we show numerically an enhancement of heat transfer.

physics.flu-dyn↗

arXiv2017

Multilevel preconditioner of Polynomial Chaos Method for quantifying uncertainties in a blood pump

More than 23 million people are suffered by Heart failure worldwide. Despite the modern transplant operation is well established, the lack of heart donations becomes a big restriction on transplantation frequency. With respect to this matter, ventricular assist devices (VADs) can play an important role in supporting patients during waiting period and after the surgery. Moreover, it has been shown that VADs by means of blood pump have advantages for working under different conditions. While a lot of work has been done on modeling the functionality of the blood pump, but quantifying uncertainties in a numerical model is a challenging task. We consider the Polynomial Chaos (PC) method, which is introduced by Wiener for modeling stochastic process with Gaussian distribution. The Galerkin projection, the intrusive version of the generalized Polynomial Chaos (gPC), has been densely studied and applied for various problems. The intrusive Galerkin approach could represent stochastic process directly at once with Polynomial Chaos series expansions, it would therefore optimize the total computing effort comparing with classical non-intrusive methods. We compared different preconditioning techniques for a steady state simulation of a blood pump configuration in our previous work, the comparison shows that an inexact multilevel preconditioner has a promising performance. In this work, we show an instationary blood flow through a FDA blood pump configuration with Galerkin Projection method, which is implemented in our open source Finite Element library Hiflow3. Three uncertainty sources are considered: inflow boundary condition, rotor angular speed and dynamic viscosity, the numerical results are demonstrated with more than 30 Million degrees of freedom by using supercomputer.

physics.flu-dyn↗

arXiv2014

Benchmarking in a rotating annulus: a comparative experimental and numerical study of baroclinic wave dynamics

The differentially heated rotating annulus is a widely studied tabletop-size laboratory model of the general mid-latitude atmospheric circulation. The two most relevant factors of cyclogenesis, namely rotation and meridional temperature gradient are quite well captured in this simple arrangement. The radial temperature difference in the cylindrical tank and its rotation rate can be set so that the isothermal surfaces in the bulk tilt, leading to the formation of baroclinic waves. The signatures of these waves at the free water surface have been analyzed via infrared thermography in a wide range of rotation rates (keeping the radial temperature difference constant) and under different initial conditions. In parallel to the laboratory experiments, five groups of the MetStröm collaboration have conducted numerical simulations in the same parameter regime using different approaches and solvers, and applying different initial conditions and perturbations. The experimentally and numerically obtained baroclinic wave patterns have been evaluated and compared in terms of their dominant wave modes, spatio-temporal variance properties and drift rates. Thus certain ``benchmarks'' have been created that can later be used as test cases for atmospheric numerical model validation.

physics.flu-dyn↗

arXiv2008

Adaptive boundary conditions for exterior stationary flows in three dimensions

Recently there has been an increasing interest for a better understanding of ultra low Reynolds number flows. In this context we present a new setup which allows to efficiently solve the stationary incompressible Navier-Stokes equations in an exterior domain in three dimensions numerically. The main point is that the necessity to truncate for numerical purposes the exterior domain to a finite sub-domain leads to the problem of finding so called "artificial boundary conditions" to replace the conditions at infinity. To solve this problem we provide a vector filed that describes the leading asymptotic behavior of the solution at large distances. This vector field depends explicitly on drag and lift which are determined in a self-consistent way as part of the solution process. When compared with other numerical schemes the size of the computational domain that is needed to obtain the hydrodynamic forces with a given precision is drastically reduced, which in turn leads to an overall gain in computational efficiency of typically several orders of magnitude.

physics.flu-dyn↗