Search

Cardio-mechanical models can be used to support clinical decision-making. Unfortunately, the substantial computational effort involved in many cardiac models hinders their application in the clinic, despite the fact that they may provide valuable information. In this work, we present a probabilistic reduced-order modeling (ROM) framework to dramatically reduce the computational effort of such models while providing a credibility interval. In the online stage, a fast-to-evaluate generalized one-fiber model is considered. This generalized one-fiber model incorporates correction factors to emulate patient-specific attributes, such as local geometry variations. In the offline stage, Bayesian inference is used to calibrate these correction factors on training data generated using a full-order isogeometric cardiac model (FOM). A Gaussian process is used in the online stage to predict the correction factors for geometries that are not in the training data. The proposed framework is demonstrated using two examples. The first example considers idealized left-ventricle geometries, for which the behavior of the ROM framework can be studied in detail. In the second example, the ROM framework is applied to scan-based geometries, based on which the application of the ROM framework in the clinical setting is discussed. The results for the two examples convey that the ROM framework can provide accurate online predictions, provided that adequate FOM training data is available. The uncertainty bands provided by the ROM framework give insight into the trustworthiness of its results. Large uncertainty bands can be considered as an indicator for the further population of the training data set.

Uncertainty in the aging of batteries in battery electric vehicles impacts both the daily driving range as well as the expected economic lifetime. This paper presents a method to determine online the capacity and internal resistance of a battery cell based on real-world data. The method, based on a Joint Extended Kalman Filter combined with Recursive Least Squares, is computationally efficient and does not a priori require a fully characterized cell model. Offline simulation of the algorithm on data from differently aged cells shows convergence of the algorithm and indicates that capacity and resistance follow the expected trends. Furthermore, the algorithm is tested online on a Hardware-in-the-Loop setup to demonstrate real-time parameter updates in a realistic driving scenario., Comment: 6 pages, 9 figures, to be presented at VPPC 2024

Drug discovery is a complex and resource-intensive process, with significant time and cost investments required to bring new medicines to patients. Recent advancements in generative machine learning (ML) methods offer promising avenues to accelerate early-stage drug discovery by efficiently exploring chemical space. This paper addresses the gap between in silico generative approaches and practical in vitro methodologies, highlighting the need for their integration to optimize molecule discovery. We introduce SynthFormer, a novel ML model that utilizes a 3D equivariant encoder for pharmacophores to generate fully synthesizable molecules, constructed as synthetic trees. Unlike previous methods, SynthFormer incorporates 3D information and provides synthetic paths, enhancing its ability to produce molecules with good docking scores across various proteins. Our contributions include a new methodology for efficient chemical space exploration using 3D information, a novel architecture called Synthformer for translating 3D pharmacophore representations into molecules, and a meaningful embedding space that organizes reagents for drug discovery optimization. Synthformer generates molecules that dock well and enables effective late-stage optimization restricted by synthesis paths.

This study aims to investigate whether GPT-4 can effectively grade assignments for design university students and provide useful feedback. In design education, assignments do not have a single correct answer and often involve solving an open-ended design problem. This subjective nature of design projects often leads to grading problems,as grades can vary between different raters,for instance instructor from engineering background or architecture background. This study employs an iterative research approach in developing a Custom GPT with the aim of achieving more reliable results and testing whether it can provide design students with constructive feedback. The findings include: First,through several rounds of iterations the inter-reliability between GPT and human raters reached a level that is generally accepted by educators. This indicates that by providing accurate prompts to GPT,and continuously iterating to build a Custom GPT, it can be used to effectively grade students' design assignments, serving as a reliable complement to human raters. Second, the intra-reliability of GPT's scoring at different times is between 0.65 and 0.78. This indicates that, with adequate instructions, a Custom GPT gives consistent results which is a precondition for grading students. As consistency and comparability are the two main rules to ensure the reliability of educational assessment, this study has looked at whether a Custom GPT can be developed that adheres to these two rules. We finish the paper by testing whether Custom GPT can provide students with useful feedback and reflecting on how educators can develop and iterate a Custom GPT to serve as a complementary rater., Comment: 25 pages, 5 figures

The emergence of large Vision-Language Models (VLMs) has recently established new baselines in image classification across multiple domains. However, the performance of VLMs in the specific task of artwork classification, particularly art style classification of paintings - a domain traditionally mastered by art historians - has not been explored yet. Artworks pose a unique challenge compared to natural images due to their inherently complex and diverse structures, characterized by variable compositions and styles. Art historians have long studied the unique aspects of artworks, with style prediction being a crucial component of their discipline. This paper investigates whether large VLMs, which integrate visual and textual data, can effectively predict the art historical attributes of paintings. We conduct an in-depth analysis of four VLMs, namely CLIP, LLaVA, OpenFlamingo, and GPT-4o, focusing on zero-shot classification of art style, author and time period using two public benchmarks of artworks. Additionally, we present ArTest, a well-curated test set of artworks, including pivotal paintings studied by art historians.

In this paper, we present high-performance computing for the BGK model of the Boltzmann equations with a meshfree method. We use the Arbitrary-Lagrangian-Eulerian (ALE) method, where the approximation of spatial derivatives and the reconstruction of a function is based on the weighted least squares method. We have used the Graphics Processing Unit (GPU) to accelerate the code and compared with the CPU code. Two and three dimensional driven cavity problems are solved, where we have obtained the speed up up to 307 times and 127 times in two and three dimensional cases, respectively., Comment: arXiv admin note: text overlap with arXiv:2109.05822

We propose a straightforward yet highly effective few-shot fine-tuning strategy for adapting the Segment Anything (SAM) to anatomical segmentation tasks in medical images. Our novel approach revolves around reformulating the mask decoder within SAM, leveraging few-shot embeddings derived from a limited set of labeled images (few-shot collection) as prompts for querying anatomical objects captured in image embeddings. This innovative reformulation greatly reduces the need for time-consuming online user interactions for labeling volumetric images, such as exhaustively marking points and bounding boxes to provide prompts slice by slice. With our method, users can manually segment a few 2D slices offline, and the embeddings of these annotated image regions serve as effective prompts for online segmentation tasks. Our method prioritizes the efficiency of the fine-tuning process by exclusively training the mask decoder through caching mechanisms while keeping the image encoder frozen. Importantly, this approach is not limited to volumetric medical images, but can generically be applied to any 2D/3D segmentation task. To thoroughly evaluate our method, we conducted extensive validation on four datasets, covering six anatomical segmentation tasks across two modalities. Furthermore, we conducted a comparative analysis of different prompting options within SAM and the fully-supervised nnU-Net. The results demonstrate the superior performance of our method compared to SAM employing only point prompts (approximately 50% improvement in IoU) and performs on-par with fully supervised methods whilst reducing the requirement of labeled data by at least an order of magnitude., Comment: 9 pages, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2024

Deep convolutional neural networks are widely used in medical image segmentation but require many labeled images for training. Annotating three-dimensional medical images is a time-consuming and costly process. To overcome this limitation, we propose a novel semi-supervised segmentation method that leverages mostly unlabeled images and a small set of labeled images in training. Our approach involves assessing prediction uncertainty to identify reliable predictions on unlabeled voxels from the teacher model. These voxels serve as pseudo-labels for training the student model. In voxels where the teacher model produces unreliable predictions, pseudo-labeling is carried out based on voxel-wise embedding correspondence using reference voxels from labeled images. We applied this method to automate hip bone segmentation in CT images, achieving notable results with just 4 CT scans. The proposed approach yielded a Hausdorff distance with 95th percentile (HD95) of 3.30 and IoU of 0.929, surpassing existing methods achieving HD95 (4.07) and IoU (0.927) at their best., Comment: 13 pages, MIDL2024 oral

Let the abstract fractional space--time operator $(\partial_t + A)^s$ be given, where $s \in (0,\infty)$ and $-A \colon \mathsf{D}(A) \subseteq X \to X$ is a linear operator generating a uniformly bounded strongly measurable semigroup $(S(t))_{t\ge0}$ on a complex Banach space $X$. We consider the corresponding Dirichlet problem of finding a function $u \colon \mathbb{R} \to X$ such that $(\partial_t + A)^s u(t) = 0$ on $(t_0, \infty)$ and $u(t) = g(t)$ on $(-\infty, t_0]$, for given $t_0 \in \mathbb{R}$ and $g \colon (-\infty,t_0] \to X$. We derive a solution formula which expresses $u$ in terms of $g$ and $(S(t))_{t\ge0}$ and generalizes the well-known variation of constants formula for the mild solution to the abstract Cauchy problem $u' + Au = 0$ on $(t_0, \infty)$ with $u(t_0) = x \in \overline{\mathsf{D}(A)}$. Moreover, we include a comparison to analogous solution concepts arising from Riemann-Liouville and Caputo type initial value problems., Comment: 19 pages

In this paper, we consider the problem of estimating the causal effect of an endogenous variable $Z$ on a survival time $T$ that can be subject to different types of dependent censoring. Firstly, we extend the current literature by simultaneously allowing for both independent ($A$) and dependent ($C$) censoring. Moreover, we have different parametric transformations for $T$ and $C$ that result in a more additive structure with approximately normal and homoscedastic error terms. The model is shown to be identified and a two-step estimation method is specified. It is shown that this estimator results in consistent and asymptotically normal estimates. Secondly, a goodness-of-fit test is developed to check the model's validity. To estimate the distribution of the statistic, a parametric bootstrap approach is used. Lastly, we show how the model naturally extends to a competing risks setting. Simulations are used to evaluate the finite-sample performance of the proposed methods and approaches. Moreover, we investigate two data applications regarding the effect of job training programs on unemployment duration and the effect of periodic screenings on breast cancer mortality rates.

Cylinder pressure-based control is a key enabler for advanced pre-mixed combustion concepts. Besides guaranteeing robust and safe operation, it allows for cylinder pressure and heat release shaping. This requires fast control-oriented combustion models. Over the years, mean-value models have been proposed that can predict combustion measures (e.g., Gross Indicated Mean Effective Pressure, or the crank angle where 50% of the total heat is released) or models that predict the full in-cylinder pressure. However, these models are not able to capture cyclic variations. This is important in the control design for combustion concepts, like Reactivity Controlled Compression Ignition, that can suffer from large cyclic variations. In this study, the in-cylinder pressure and cyclic variation are modelled using a data-based approach. The model combines Principle Component Decomposition and Gaussian Process Regression. A detailed study is performed on the effects of the different hyperparameters and kernel choices. The approach is applicable to any combustion concept, but most valuable for advance combustion concepts with large cyclic variation. The potential of the proposed approach is demonstrated for an Reactivity Controlled Compression Ignition engine running on Diesel and E85. The prediction quality of the evaluated combustion measures has an overall accuracy of 13.5% and 65.5% in mean behaviour and standard deviation, respectively. The peak-pressure rise-rate is traditionally hard to predict, in the proposed model it has an accuracy of 22.7% and 96.4% in mean behaviour and standard deviation, respectively. This Principle Component Decomposition-based approach is an important step towards in-cylinder pressure shaping. The use of Gaussian Process Regression provides important information on cyclic variation and provides next-cycle controls information on safety and performance criteria., Comment: 16 pages, 7 figures, 7 tables; Submitted to MDPI Energies' special issue on 'Advanced Research in Combustion Energy: Optimization, Applications, and Analysis'

Monitoring the cardiac function often relies on non-invasive vital measurements, electrocardiograms, and low-resolution echocardiograms. The monitoring data can be augmented with numerical modeling results to support treatment-risk assessment. Often, medical images are not suitable for high-fidelity modeling due to their spatial sparsity and low resolution. In this work, we present a workflow that converts a limited number of two-dimensional (2D) echocardiogram images into analysis-suitable left-ventricle geometries using isogeometric analysis (IGA). The image data is fitted by reshaping a multi-patch NURBS template. This fitting procedure results in a smooth interpolation with a limited number of degrees of freedom. In addition, a coupled 3D-0D cardiac model is extended with a pre-stressing method to perform ventricular-cardiac-mechanic analyses based on in vivo images. The workflow is benchmarked using population-averaged imaging data, which demonstrates that both the shape of the left ventricle and its mechanical response are well predicted in sparse-data scenarios. The case of a clinical patient is considered to demonstrate the suitability of the workflow in a real-data setting.