Search

The extraction of blood vessels has recently experienced a widespread interest in medical image analysis. Automatic vessel segmentation is highly desirable to guide clinicians in computer-assisted diagnosis, therapy or surgical planning. Despite a good ability to extract large anatomical structures, the capacity of U-Net inspired architectures to automatically delineate vascular systems remains a major issue, especially given the scarcity of existing datasets. In this paper, we present a novel approach that integrates into deep segmentation shape priors from a Semi-Overcomplete Convolutional Auto-Encoder (S-OCAE) embedding. Compared to standard Convolutional Auto-Encoders (CAE), it exploits an over-complete branch that projects data onto higher dimensions to better characterize tiny structures. Experiments on retinal and liver vessel extraction, respectively performed on publicly-available DRIVE and 3D-IRCADb datasets, highlight the effectiveness of our method compared to U-Net trained without and with shape priors from a traditional CAE., Comment: 5 pages, 4 figures, conference

Diabetic retinopathy and diabetic macular edema are significant complications of diabetes that can lead to vision loss. Early detection through ultra-widefield fundus imaging enhances patient outcomes but presents challenges in image quality and analysis scale. This paper introduces deep learning solutions for automated UWF image analysis within the framework of the MICCAI 2024 UWF4DR challenge. We detail methods and results across three tasks: image quality assessment, detection of referable DR, and identification of DME. Employing advanced convolutional neural network architectures such as EfficientNet and ResNet, along with preprocessing and augmentation strategies, our models demonstrate robust performance in these tasks. Results indicate that deep learning can significantly aid in the automated analysis of UWF images, potentially improving the efficiency and accuracy of DR and DME detection in clinical settings.

The precise delineation of blood vessels in medical images is critical for many clinical applications, including pathology detection and surgical planning. However, fully-automated vascular segmentation is challenging because of the variability in shape, size, and topology. Manual segmentation remains the gold standard but is time-consuming, subjective, and impractical for large-scale studies. Hence, there is a need for automatic and reliable segmentation methods that can accurately detect blood vessels from medical images. The integration of shape and topological priors into vessel segmentation models has been shown to improve segmentation accuracy by offering contextual information about the shape of the blood vessels and their spatial relationships within the vascular tree. To further improve anatomical consistency, we propose a new joint prior encoding mechanism which incorporates both shape and topology in a single latent space. The effectiveness of our method is demonstrated on the publicly available 3D-IRCADb dataset. More globally, the proposed approach holds promise in overcoming the challenges associated with automatic vessel delineation and has the potential to advance the field of deep priors encoding., Comment: 5 pages, 3 figures, conference

Extracting hepatic vessels from abdominal images is of high interest for clinicians since it allows to divide the liver into functionally-independent Couinaud segments. In this respect, an automated liver blood vessel extraction is widely summoned. Despite the significant growth in performance of semantic segmentation methodologies, preserving the complex multi-scale geometry of main vessels and ramifications remains a major challenge. This paper provides a new deep supervised approach for vessel segmentation, with a strong focus on representations arising from the different scales inherent to the vascular tree geometry. In particular, we propose a new clustering technique to decompose the tree into various scale levels, from tiny to large vessels. Then, we extend standard 3D UNet to multi-task learning by incorporating scale-specific auxiliary tasks and contrastive learning to encourage the discrimination between scales in the shared representation. Promising results, depicted in several evaluation metrics, are revealed on the public 3D-IRCADb dataset., Comment: 5 pages, 5 figures, conference

Knowledge graphs (KGs) have recently been used for many tools and applications, making them rich resources in structured format. However, in the real world, KGs grow due to the additions of new knowledge in the form of entities and relations, making these KGs dynamic. This chapter formally defines several types of dynamic KGs and summarizes how these KGs can be represented. Additionally, many neurosymbolic methods have been proposed for learning representations over static KGs for several tasks such as KG completion and entity alignment. This chapter further focuses on neurosymbolic methods for dynamic KGs with or without temporal information. More specifically, it provides an insight into neurosymbolic methods for dynamic (temporal or non-temporal) KG completion and entity alignment tasks. It further discusses the challenges of current approaches and provides some future directions.

Instead of ensuring that fluxes across edges add up to zero, we split the edge in two halves and also associate different fluxes to each of its sides. This is possible due to non-standard Riemann solvers with free parameters. We then enforce conservation by making sure that the fluxes around a node sum up to zero, which fixes the value of the free parameter. We demonstrate that for linear acoustics one of the non-standard Riemann solvers leads to a vorticity preserving method on unstructured meshes.

Semiconductor nanowires are believed to play a crucial role for future applications in electronics, spintronics and quantum technologies. A potential candidate is HgTe but its sensitivity to nanofabrication processes restrain its development. A way to circumvent this obstacle is the selective area growth technique. Here, in-plane HgTe nanostructures are grown thanks to selective area molecular beam epitaxy on a semi-insulating CdTe substrate covered with a patterned SiO$_{\mathrm{2}}$ mask. The shape of these nanostructures is defined by the in-plane orientation of the mask aperture along the <$110$>, <$1\bar{\mathrm{1}}0$>, or <$100$> direction, the deposited thickness, and the growth temperature. Several micron long in-plane nanowires can be achieved as well as more complex nanostructures such as networks, diamond structures or rings. A good selectivity is achieved with very little parasitic growth on the mask even for a growth temperature as low as $140${\deg}C and growth rate up to $0.5$ ML/s. For <$110$> oriented nanowires, the center of the nanostructure exhibits a trapezoidal shape with {$111$}B facets and two grains on the sides, while <$1\bar{\mathrm{1}}0$> oriented nanowires show {$111$}A facets with adatoms accumulation on the sides of the top surface. Transmission electron microscopy observations reveal a continuous epitaxial relation between the CdTe substrate and the HgTe nanowire. Measurements of the resistance with fourpoint scanning tunneling microscopy indicates a good electrical homogeneity along the main NW axis and a thermally activated transport. This growth method paves the way toward the fabrication of complex HgTe-based nanostructures for electronic transport measurements., Comment: 18 pages and 8 figures. Submitted to Nanotechnology

In this work, we construct galactic halos in order to fit the rotation curves (RCs) of a sample of low surface brightness (LSB) galaxies. These halos are made of Fuzzy Dark Matter (FDM) with a multimode expansion of non-spherical modes that in average contribute to the appropriate density profile consisting of a core and an envelope needed to fit the rotation curves. The coefficients of the expansion are calculated using a genetic algorithm, that minimizes the difference between the spatial average density of the multimode order parameter describing the FDM and the target dark matter density that fits the RCs. The FDM halos are constructed assuming a solitonic core at the center and two types of envelopes, Navarro-Frenk-White and Pseudo-Isothermal density profiles. The resulting FDM configurations are then evolved in order to show how the average density changes in time due to the secular dynamical evolution, along with a condensation process that lead to the growth of the solitonic core., Comment: 12 pages, 5 figures. Accepted - Phys. Rev. D

A model of magnetic universe based on nonlinear electrodynamics has been introduced by Kruglov. This model describes an early inflation era followed by a radiation era. We show that this model is related to our model of universe based on a quadratic equation of state. We discuss two quantitatively different models of early universe. In Model I, the primordial density of the universe is identified with the Planck density. At $t=0$, the universe had the characteristics of a Planck black hole. During the inflation, which takes place on a Planck timescale, the size of the universe evolves from the Planck length to a size comparable to the Compton wavelength of the neutrino. If we interpret the radius of the universe at the end of the inflation (neutrino's Compton wavelength) as a minimum length related to quantum gravity and use Zeldovich's first formula of the vacuum energy, we obtain the correct value of the cosmological constant. In Model II, the primordial density of the universe is identified with the electron density as a consequence of nonlinear electrodynamics. At $t=0$, the universe had the characteristics of an electron. During the inflation, which takes place on a gravitoelectronic timescale, the size of the universe evolves from the electron's classical radius to a size comparable to the size of a dark energy star of the stellar mass. If we interpret the radius of the universe at the begining of the inflation (electron's classical radius) as a minimum length related to quantum gravity and use Zeldovich's second formula of the vacuum energy, we obtain the correct value of the cosmological constant. This provides an accurate form of Eddington relation between the cosmological constant and the mass of the electron. We also introduce a nonlinear electromagnetic Lagrangian that describes simultaneously the early inflation, the radiation era, and the dark energy era.

We discuss the kinetic theory of stellar systems and two-dimensional vortices and stress their analogies. We recall the derivation of the Landau and Lenard-Balescu equations from the Klimontovich formalism. These equations take into account two-body correlations and are valid at the order $1/N$, where $N$ is the number of particles in the system. They have the structure of a Fokker-Planck equation involving a diffusion term and a drift term. The systematic drift of a vortex is the counterpart of the dynamical friction experienced by a star. At equilibrium, the diffusion and the drift terms balance each other establishing the Boltzmann distribution of statistical mechanics. We discuss the problem of kinetic blocking in certain cases and how it can be solved at the order $1/N^2$ by the consideration of three-body correlations. We also consider the behavior of the system close to the critical point following a recent suggestion by Hamilton and Heinemann (2023). We present a simple calculation, valid for spatially homogeneous systems with long-range interactions described by the Cauchy distribution, showing how the consideration of the Landau modes regularizes the divergence of the friction by polarization at the critical point., Comment: arXiv admin note: text overlap with arXiv:2211.14353, arXiv:2308.09016

We consider an isothermal self-gravitating system surrounding a central body. This model can represent a galaxy or a globular cluster harboring a central black hole. It can also represent a gaseous atmosphere surrounding a protoplanet. In three dimensions, the Boltzmann-Poisson equation must be solved numerically in order to obtain the density profile of the gas [Chavanis {\it et al.}, Phys. Rev. E {\bf 109}, 014118 (2024)]. In one and two dimensions, we show that the Boltzmann-Poisson equation can be solved analytically. We obtain explicit analytical expressions of the density profile around a central body which generalize the analytical solutions found by Camm (1950) and Ostriker (1964) in the absence of a central body. Our results also have applications for self-gravitating Brownian particles (Smoluchowski-Poisson system), for the chemotaxis of bacterial populations (Keller-Segel model), and for two-dimensional point vortices (Onsager's model). In the case of bacterial populations, the central body could represent a supply of ``food'' that attracts the bacteria (chemoattractant). In the case of two-dimensional vortices, the central body could be a central vortex

Multimodal medical imaging plays a pivotal role in clinical diagnosis and research, as it combines information from various imaging modalities to provide a more comprehensive understanding of the underlying pathology. Recently, deep learning-based multimodal fusion techniques have emerged as powerful tools for improving medical image classification. This review offers a thorough analysis of the developments in deep learning-based multimodal fusion for medical classification tasks. We explore the complementary relationships among prevalent clinical modalities and outline three main fusion schemes for multimodal classification networks: input fusion, intermediate fusion (encompassing single-level fusion, hierarchical fusion, and attention-based fusion), and output fusion. By evaluating the performance of these fusion techniques, we provide insight into the suitability of different network architectures for various multimodal fusion scenarios and application domains. Furthermore, we delve into challenges related to network architecture selection, handling incomplete multimodal data management, and the potential limitations of multimodal fusion. Finally, we spotlight the promising future of Transformer-based multimodal fusion techniques and give recommendations for future research in this rapidly evolving field.

This work proposes a novel framework for analyzing disease progression using time-aware neural ordinary differential equations (NODE). We introduce a "time-aware head" in a framework trained through self-supervised learning (SSL) to leverage temporal information in latent space for data augmentation. This approach effectively integrates NODEs with SSL, offering significant performance improvements compared to traditional methods that lack explicit temporal integration. We demonstrate the effectiveness of our strategy for diabetic retinopathy progression prediction using the OPHDIAT database. Compared to the baseline, all NODE architectures achieve statistically significant improvements in area under the ROC curve (AUC) and Kappa metrics, highlighting the efficacy of pre-training with SSL-inspired approaches. Additionally, our framework promotes stable training for NODEs, a commonly encountered challenge in time-aware modeling., Comment: Submitted to MICCAI 2024

Segmentation in medical imaging is an essential and often preliminary task in the image processing chain, driving numerous efforts towards the design of robust segmentation algorithms. Supervised learning methods achieve excellent performances when fed with a sufficient amount of labeled data. However, such labels are typically highly time-consuming, error-prone and expensive to produce. Alternatively, semi-supervised learning approaches leverage both labeled and unlabeled data, and are very useful when only a small fraction of the dataset is labeled. They are particularly useful for cerebrovascular segmentation, given that labeling a single volume requires several hours for an expert. In addition to the challenge posed by insufficient annotations, there are concerns regarding annotation consistency. The task of annotating the cerebrovascular tree is inherently ambiguous. Due to the discrete nature of images, the borders and extremities of vessels are often unclear. Consequently, annotations heavily rely on the expert subjectivity and on the underlying clinical objective. These discrepancies significantly increase the complexity of the segmentation task for the model and consequently impair the results. Consequently, it becomes imperative to provide clinicians with precise guidelines to improve the annotation process and construct more uniform datasets. In this article, we investigate the data dependency of deep learning methods within the context of imperfect data and semi-supervised learning, for cerebrovascular segmentation. Specifically, this study compares various state-of-the-art semi-supervised methods based on unsupervised regularization and evaluates their performance in diverse quantity and quality data scenarios. Based on these experiments, we provide guidelines for the annotation and training of cerebrovascular segmentation models.

Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of typical SSL is not straightforward in medical imaging. Additionally, those pretext tasks often lack context, which is critical for computer-aided clinical decision support. In this paper, we developed a longitudinal masked auto-encoder (MAE) based on the well-known Transformer-based MAE. In particular, we explored the importance of time-aware position embedding as well as disease progression-aware masking. Taking into account the time between examinations instead of just scheduling them offers the benefit of capturing temporal changes and trends. The masking strategy, for its part, evolves during follow-up to better capture pathological changes, ensuring a more accurate assessment of disease progression. Using OPHDIAT, a large follow-up screening dataset targeting diabetic retinopathy (DR), we evaluated the pre-trained weights on a longitudinal task, which is to predict the severity label of the next visit within 3 years based on the past time series examinations. Our results demonstrated the relevancy of both time-aware position embedding and masking strategies based on disease progression knowledge. Compared to popular baseline models and standard longitudinal Transformers, these simple yet effective extensions significantly enhance the predictive ability of deep classification models.

Diabetic Retinopathy (DR), an ocular complication of diabetes, is a leading cause of blindness worldwide. Traditionally, DR is monitored using Color Fundus Photography (CFP), a widespread 2-D imaging modality. However, DR classifications based on CFP have poor predictive power, resulting in suboptimal DR management. Optical Coherence Tomography Angiography (OCTA) is a recent 3-D imaging modality offering enhanced structural and functional information (blood flow) with a wider field of view. This paper investigates automatic DR severity assessment using 3-D OCTA. A straightforward solution to this task is a 3-D neural network classifier. However, 3-D architectures have numerous parameters and typically require many training samples. A lighter solution consists in using 2-D neural network classifiers processing 2-D en-face (or frontal) projections and/or 2-D cross-sectional slices. Such an approach mimics the way ophthalmologists analyze OCTA acquisitions: 1) en-face flow maps are often used to detect avascular zones and neovascularization, and 2) cross-sectional slices are commonly analyzed to detect macular edemas, for instance. However, arbitrary data reduction or selection might result in information loss. Two complementary strategies are thus proposed to optimally summarize OCTA volumes with 2-D images: 1) a parametric en-face projection optimized through deep learning and 2) a cross-sectional slice selection process controlled through gradient-based attribution. The full summarization and DR classification pipeline is trained from end to end. The automatic 2-D summary can be displayed in a viewer or printed in a report to support the decision. We show that the proposed 2-D summarization and classification pipeline outperforms direct 3-D classification with the advantage of improved interpretability.

This paper introduces a fully algebraic two-level additive Schwarz preconditioner for general sparse large-scale matrices. The preconditioner is analyzed for symmetric positive definite (SPD) matrices. For those matrices, the coarse space is constructed based on approximating two local subspaces in each subdomain. These subspaces are obtained by approximating a number of eigenvectors corresponding to dominant eigenvalues of two judiciously posed generalized eigenvalue problems. The number of eigenvectors can be chosen to control the condition number. For general sparse matrices, the coarse space is constructed by approximating the image of a local operator that can be defined from information in the coefficient matrix. The connection between the coarse spaces for SPD and general matrices is also discussed. Numerical experiments show the great effectiveness of the proposed preconditioners on matrices arising from a wide range of applications. The set of matrices includes SPD, symmetric indefinite, nonsymmetric, and saddle-point matrices. In addition, we compare the proposed preconditioners to the state-of-the-art domain decomposition preconditioners.

Myopic macular degeneration is the most common complication of myopia and the primary cause of vision loss in individuals with pathological myopia. Early detection and prompt treatment are crucial in preventing vision impairment due to myopic maculopathy. This was the focus of the Myopic Maculopathy Analysis Challenge (MMAC), in which we participated. In task 1, classification of myopic maculopathy, we employed the contrastive learning framework, specifically SimCLR, to enhance classification accuracy by effectively capturing enriched features from unlabeled data. This approach not only improved the intrinsic understanding of the data but also elevated the performance of our classification model. For Task 2 (segmentation of myopic maculopathy plus lesions), we have developed independent segmentation models tailored for different lesion segmentation tasks and implemented a test-time augmentation strategy to further enhance the model's performance. As for Task 3 (prediction of spherical equivalent), we have designed a deep regression model based on the data distribution of the dataset and employed an integration strategy to enhance the model's prediction accuracy. The results we obtained are promising and have allowed us to position ourselves in the Top 6 of the classification task, the Top 2 of the segmentation task, and the Top 1 of the prediction task. The code is available at \url{https://github.com/liyihao76/MMAC_LaTIM_Solution}., Comment: 18 pages

We present a novel Finite Volume (FV) scheme on unstructured polygonal meshes that is provably compliant with the Second Law of Thermodynamics and the Geometric Conservation Law (GCL) at the same time. The governing equations are provided by a subset of the class of symmetric and hyperbolic thermodynamically compatible (SHTC) models. Our numerical method discretizes the equations for the conservation of momentum, total energy, distortion tensor and thermal impulse vector, hence accounting in one single unified mathematical formalism for a wide range of physical phenomena in continuum mechanics. By means of two conservative corrections directly embedded in the definition of the numerical fluxes, the new schemes are proven to satisfy two extra conservation laws, namely an entropy balance law and a geometric equation that links the distortion tensor to the density evolution. As such, the classical mass conservation equation can be discarded. Firstly, the GCL is derived at the continuous level, and subsequently it is satisfied by introducing the new concepts of general potential and generalized Gibbs relation. Once compatibility of the GCL is ensured, thermodynamic compatibility is tackled in the same manner, thus achieving the satisfaction of a local cell entropy inequality. The two corrections are orthogonal, meaning that they can coexist simultaneously without interfering with each other. The compatibility of the new FV schemes holds true at the semi-discrete level, and time integration of the governing PDE is carried out relying on Runge-Kutta schemes. A large suite of test cases demonstrates the structure preserving properties of the schemes at the discrete level as well.

In this paper we design, analyse and test domain decomposition methods for linear systems of equations arising from conforming finite element discretisations of positive Maxwell-type equations, namely for $\mathbf{H}(\mathbf{curl})$ problems. It is well known that convergence of domain decomposition methods rely heavily on the efficiency of the coarse space used in the second level. We design adaptive coarse spaces that complement a near-kernel space made from the gradient of scalar functions. The new class of preconditioner is inspired by the idea of subspace decomposition, but based on spectral coarse spaces, and is specially designed for curl-conforming discretisations of Maxwell's equations in heterogeneous media on general domains which may have holes. We also address the practical robustness of various solvers in the case of non-trivial topologies and/or high aspect ratio of the domain.

We introduce MAFALDA, a benchmark for fallacy classification that merges and unites previous fallacy datasets. It comes with a taxonomy that aligns, refines, and unifies existing classifications of fallacies. We further provide a manual annotation of a part of the dataset together with manual explanations for each annotation. We propose a new annotation scheme tailored for subjective NLP tasks, and a new evaluation method designed to handle subjectivity. We then evaluate several language models under a zero-shot learning setting and human performances on MAFALDA to assess their capability to detect and classify fallacies.

A portable imaging system for the on-site detection of shoulder injury is necessary to identify its extent and avoid its development to severe condition. Here, firstly a microwave tomography system is introduced using state-of-the-art numerical modeling and parallel computing for imaging different tissues in the shoulder. The results show that the proposed method is capable of accurately detecting and localizing rotator cuff tears of different size. In the next step, an efficient design in terms of computing time and complexity is proposed to detect the variations in the injured model with respect to the healthy model. The method is based on finite element discretization and uses parallel preconditioners from the domain decomposition method to accelerate computations. It is implemented using the open source FreeFEM software.

Longitudinal analysis in medical imaging is crucial to investigate the progressive changes in anatomical structures or disease progression over time. In recent years, a novel class of algorithms has emerged with the goal of learning disease progression in a self-supervised manner, using either pairs of consecutive images or time series of images. By capturing temporal patterns without external labels or supervision, longitudinal self-supervised learning (LSSL) has become a promising avenue. To better understand this core method, we explore in this paper the LSSL algorithm under different scenarios. The original LSSL is embedded in an auto-encoder (AE) structure. However, conventional self-supervised strategies are usually implemented in a Siamese-like manner. Therefore, (as a first novelty) in this study, we explore the use of Siamese-like LSSL. Another new core framework named neural ordinary differential equation (NODE). NODE is a neural network architecture that learns the dynamics of ordinary differential equations (ODE) through the use of neural networks. Many temporal systems can be described by ODE, including modeling disease progression. We believe that there is an interesting connection to make between LSSL and NODE. This paper aims at providing a better understanding of those core algorithms for learning the disease progression with the mentioned change. In our different experiments, we employ a longitudinal dataset, named OPHDIAT, targeting diabetic retinopathy (DR) follow-up. Our results demonstrate the application of LSSL without including a reconstruction term, as well as the potential of incorporating NODE in conjunction with LSSL.

Longitudinal imaging is able to capture both static anatomical structures and dynamic changes in disease progression toward earlier and better patient-specific pathology management. However, conventional approaches rarely take advantage of longitudinal information for detection and prediction purposes, especially for Diabetic Retinopathy (DR). In the past years, Mix-up training and pretext tasks with longitudinal context have effectively enhanced DR classification results and captured disease progression. In the meantime, a novel type of neural network named Neural Ordinary Differential Equation (NODE) has been proposed for solving ordinary differential equations, with a neural network treated as a black box. By definition, NODE is well suited for solving time-related problems. In this paper, we propose to combine these three aspects to detect and predict DR progression. Our framework, Longitudinal Mixing Training (LMT), can be considered both as a regularizer and as a pretext task that encodes the disease progression in the latent space. Additionally, we evaluate the trained model weights on a downstream task with a longitudinal context using standard and longitudinal pretext tasks. We introduce a new way to train time-aware models using $t_{mix}$, a weighted average time between two consecutive examinations. We compare our approach to standard mixing training on DR classification using OPHDIAT a longitudinal retinal Color Fundus Photographs (CFP) dataset. We were able to predict whether an eye would develop a severe DR in the following visit using a single image, with an AUC of 0.798 compared to baseline results of 0.641. Our results indicate that our longitudinal pretext task can learn the progression of DR disease and that introducing $t_{mix}$ augmentation is beneficial for time-aware models.

Diabetic Retinopathy (DR), a prevalent and severe complication of diabetes, affects millions of individuals globally, underscoring the need for accurate and timely diagnosis. Recent advancements in imaging technologies, such as Ultra-WideField Color Fundus Photography (UWF-CFP) imaging and Optical Coherence Tomography Angiography (OCTA), provide opportunities for the early detection of DR but also pose significant challenges given the disparate nature of the data they produce. This study introduces a novel multimodal approach that leverages these imaging modalities to notably enhance DR classification. Our approach integrates 2D UWF-CFP images and 3D high-resolution 6x6 mm$^3$ OCTA (both structure and flow) images using a fusion of ResNet50 and 3D-ResNet50 models, with Squeeze-and-Excitation (SE) blocks to amplify relevant features. Additionally, to increase the model's generalization capabilities, a multimodal extension of Manifold Mixup, applied to concatenated multimodal features, is implemented. Experimental results demonstrate a remarkable enhancement in DR classification performance with the proposed multimodal approach compared to methods relying on a single modality only. The methodology laid out in this work holds substantial promise for facilitating more accurate, early detection of DR, potentially improving clinical outcomes for patients., Comment: Accepted preprint for presentation at MICCAI-OMIA 20023, Vancouver, Canada

Knowledge Bases (KBs) find applications in many knowledge-intensive tasks and, most notably, in information retrieval. Wikidata is one of the largest public general-purpose KBs. Yet, its collaborative nature has led to a convoluted schema and taxonomy. The YAGO 4 KB cleaned up the taxonomy by incorporating the ontology of Schema.org, resulting in a cleaner structure amenable to automated reasoning. However, it also cut away large parts of the Wikidata taxonomy, which is essential for information retrieval. In this paper, we extend YAGO 4 with a large part of the Wikidata taxonomy - while respecting logical constraints and the distinction between classes and instances. This yields YAGO 4.5, a new, logically consistent version of YAGO that adds a rich layer of informative classes. An intrinsic and an extrinsic evaluation show the value of the new resource., Comment: Published at SIGIR 2024, cite that paper in scientific articles

We complete the kinetic theory of inhomogeneous systems with long-range interactions initiated in previous works. We use a simpler and more physical formalism. We consider a system of particles submitted to a small external stochastic perturbation and determine the response of the system to the perturbation. We derive the diffusion tensor and the friction by polarization of a test particle. We introduce a general Fokker-Planck equation involving a diffusion term and a friction term. When the friction by polarization can be neglected, we obtain a secular dressed diffusion (SDD) equation sourced by the external noise. When the external perturbation is created by a discrete collection of $N$ field particles, we obtain the inhomogeneous Lenard-Balescu kinetic equation reducing to the inhomogeneous Landau kinetic equation when collective effects are neglected. We consider a multi-species system of particles. When the field particles are at statistical equilibrium (thermal bath), we establish the proper expression of the fluctuation-dissipation theorem for systems with long-range interactions relating the power spectrum of the fluctuations to the response function of the system. In that case, the friction and diffusion coefficients satisfy the Einstein relation and the Fokker-Planck equation reduces to the inhomogeneous Kramers equation. We also consider a gas of Brownian particles with long-range interactions described by $N$ coupled stochastic Langevin equations and determine its mean and mesoscopic evolution. We discuss the notion of stochastic kinetic equations and the role of fluctuations possibly triggering random transitions from one equilibrium state to the other. Our presentation parallels the one given for two-dimensional point vortices in a previous paper [P.H. Chavanis, Eur. Phys. J. Plus 138, 136 (2023)]., Comment: arXiv admin note: substantial text overlap with arXiv:2211.14353

Over the last decade, convolutional neural networks have emerged and advanced the state-of-the-art in various image analysis and computer vision applications. The performance of 2D image classification networks is constantly improving and being trained on databases made of millions of natural images. However, progress in medical image analysis has been hindered by limited annotated data and acquisition constraints. These limitations are even more pronounced given the volumetry of medical imaging data. In this paper, we introduce an efficient way to transfer the efficiency of a 2D classification network trained on natural images to 2D, 3D uni- and multi-modal medical image segmentation applications. In this direction, we designed novel architectures based on two key principles: weight transfer by embedding a 2D pre-trained encoder into a higher dimensional U-Net, and dimensional transfer by expanding a 2D segmentation network into a higher dimension one. The proposed networks were tested on benchmarks comprising different modalities: MR, CT, and ultrasound images. Our 2D network ranked first on the CAMUS challenge dedicated to echo-cardiographic data segmentation and surpassed the state-of-the-art. Regarding 2D/3D MR and CT abdominal images from the CHAOS challenge, our approach largely outperformed the other 2D-based methods described in the challenge paper on Dice, RAVD, ASSD, and MSSD scores and ranked third on the online evaluation platform. Our 3D network applied to the BraTS 2022 competition also achieved promising results, reaching an average Dice score of 91.69% (91.22%) for the whole tumor, 83.23% (84.77%) for the tumor core, and 81.75% (83.88%) for enhanced tumor using the approach based on weight (dimensional) transfer. Experimental and qualitative results illustrate the effectiveness of our methods for multi-dimensional medical image segmentation., Comment: 30 pages, 12 figures, 6 tables, Accepted for publication in the Journal of Medical Image Analysis

The equations of Lagrangian gas dynamics fall into the larger class of overdetermined hyperbolic and thermodynamically compatible (HTC) systems of partial differential equations. They satisfy an entropy inequality (second principle of thermodynamics) and conserve total energy (first principle of thermodynamics). The aim of this work is to construct a novel thermodynamically compatible cell-centered Lagrangian finite volume scheme on unstructured meshes. Unlike in existing schemes, we choose to directly discretize the entropy inequality, hence obtaining total energy conservation as a consequence of the new thermodynamically compatible discretization of the other equations. First, the governing equations are written in fluctuation form. Next, the non-compatible centered numerical fluxes are corrected according to the approach recently introduced by Abgrall et al., using a scalar correction factor that is defined at the nodes of the grid. This perfectly fits into the formalism of nodal solvers which is typically adopted in cell-centered Lagrangian finite volume methods. Semi-discrete entropy conservative and entropy stable Lagrangian schemes are devised, and they are adequately blended together via a convex combination based on either a priori or a posteriori detectors of discontinuous solutions. The nonlinear stability in the energy norm is rigorously demonstrated and the new schemes are provably positivity preserving for density and pressure. Furthermore, they exhibit zero numerical diffusion for isentropic flows while being still nonlinearly stable. The new schemes are tested against classical benchmarks for Lagrangian hydrodynamics, assessing their convergence and robustness and comparing their numerical dissipation with classical Lagrangian finite volume methods.

The integro-differential formulation of the RTE and its solution by iterations on the source has been extended here to handle anisotropic scattering. The iterative part of the method is O(N ln N ), thanks to an efficient use of H-matrices. The precision is good enough to evaluate the effect of sensitive parameters for the study of contrails. Most of the time the stratified 1D approximation should suffice, but in complex cases with high relief the 3D formulation is needed.

In a recent article the authors showed that the radiative Transfer equations with multiple frequencies and scattering can be formulated as a nonlinear integral system. In the present article, the formulation is extended to handle reflective boundary conditions. The fixed point method to solve the system is shown to be monotone. The discretization is done with a $P^1$ Finite Element Method. The convolution integrals are precomputed at every vertices of the mesh and stored in compressed hierarchical matrices, using Partially Pivoted Adaptive Cross-Approximation. Then the fixed point iterations involve only matrix vector products. The method is $O(N\sqrt[3]{N}\ln N)$, with respect to the number of vertices, when everything is smooth. A numerical implementation is proposed and tested on two examples. As there are some analogies with ray tracing the programming is complex.

Public Procurement refers to governments' purchasing activities of goods, services, and construction of public works. In the European Union (EU), it is an essential sector, corresponding to 15% of the GDP. EU public procurement generates large amounts of data, because award notices related to contracts exceeding a predefined threshold must be published on the TED (EU's official journal). Under the framework of the DeCoMaP project, which aims at leveraging such data in order to predict fraud in public procurement, we constitute the FOPPA (French Open Public Procurement Award notices) database. It contains the description of 1,380,965 lots obtained from the TED, covering the 2010--2020 period for France. We detect a number of substantial issues in these data, and propose a set of automated and semi-automated methods to solve them and produce a usable database. It can be leveraged to study public procurement in an academic setting, but also to facilitate the monitoring of public policies, and to improve the quality of the data offered to buyers and suppliers.

\textit{Objectives}: Data scarcity and domain shifts lead to biased training sets that do not accurately represent deployment conditions. A related practical problem is cross-modal image segmentation, where the objective is to segment unlabelled images using previously labelled datasets from other imaging modalities. \textit{Methods}: We propose a cross-modal segmentation method based on conventional image synthesis boosted by a new data augmentation technique called Generative Blending Augmentation (GBA). GBA leverages a SinGAN model to learn representative generative features from a single training image to diversify realistically tumor appearances. This way, we compensate for image synthesis errors, subsequently improving the generalization power of a downstream segmentation model. The proposed augmentation is further combined to an iterative self-training procedure leveraging pseudo labels at each pass. \textit{Results}: The proposed solution ranked first for vestibular schwannoma (VS) segmentation during the validation and test phases of the MICCAI CrossMoDA 2022 challenge, with best mean Dice similarity and average symmetric surface distance measures. \textit{Conclusion and significance}: Local contrast alteration of tumor appearances and iterative self-training with pseudo labels are likely to lead to performance improvements in a variety of segmentation contexts.

Diabetes is a chronic disease characterized by excess sugar in the blood and affects 422 million people worldwide, including 3.3 million in France. One of the frequent complications of diabetes is diabetic retinopathy (DR): it is the leading cause of blindness in the working population of developed countries. As a result, ophthalmology is on the verge of a revolution in screening, diagnosing, and managing of pathologies. This upheaval is led by the arrival of technologies based on artificial intelligence. The "Evaluation intelligente de la r\'etinopathie diab\'etique" (EviRed) project uses artificial intelligence to answer a medical need: replacing the current classification of diabetic retinopathy which is mainly based on outdated fundus photography and providing an insufficient prediction precision. EviRed exploits modern fundus imaging devices and artificial intelligence to properly integrate the vast amount of data they provide with other available medical data of the patient. The goal is to improve diagnosis and prediction and help ophthalmologists to make better decisions during diabetic retinopathy follow-up. In this study, we investigate the fusion of different modalities acquired simultaneously with a PLEXElite 9000 (Carl Zeiss Meditec Inc. Dublin, California, USA), namely 3-D structural optical coherence tomography (OCT), 3-D OCT angiography (OCTA) and 2-D Line Scanning Ophthalmoscope (LSO), for the automatic detection of proliferative DR., Comment: Abstract