Search

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications., Comment: CVPR 2024 MedSAM on Laptop Competition Summary: https://www.codabench.org/competitions/1847/

The use of copyrighted materials in training generative language models raises critical legal and ethical questions. This paper presents a framework for and the results of empirically assessing the impact of copyrighted materials on the performance of large language models (LLMs) for Norwegian. We found that both books and newspapers contribute positively when the models are evaluated on a diverse set of Norwegian benchmarks, while fiction works possibly lead to decreased performance. Our experiments could inform the creation of a compensation scheme for authors whose works contribute to AI development., Comment: pre-print, under review

The inference cost of Large Language Models (LLMs) is a significant challenge due to their computational demands, specially on tasks requiring long outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed that LLMs can generate distilled language-concise outputs that retain essential meaning, when prompted appropriately. We propose TRIM, a pipeline for saving computational cost in which a shorter distilled output from the LLM is reconstructed into a full narrative by a smaller model with lower inference costs. Our experiments show promising results, particularly in general knowledge domains with 20.58% saved tokens on average with tiny decrease in evaluation metrics, hinting that this approach can effectively balance efficiency and accuracy in language processing tasks., Comment: 12 pages

Predicting stroke risk is a complex challenge that can be enhanced by integrating diverse clinically available data modalities. This study introduces a self-supervised multimodal framework that combines 3D brain imaging, clinical data, and image-derived features to improve stroke risk prediction prior to onset. By leveraging large unannotated clinical datasets, the framework captures complementary and synergistic information across image and tabular data modalities. Our approach is based on a contrastive learning framework that couples contrastive language-image pretraining with an image-tabular matching module, to better align multimodal data representations in a shared latent space. The model is trained on the UK Biobank, which includes structural brain MRI and clinical data. We benchmark its performance against state-of-the-art unimodal and multimodal methods using tabular, image, and image-tabular combinations under diverse frozen and trainable model settings. The proposed model outperformed self-supervised tabular (image) methods by 2.6% (2.6%) in ROC-AUC and by 3.3% (5.6%) in balanced accuracy. Additionally, it showed a 7.6% increase in balanced accuracy compared to the best multimodal supervised model. Through interpretable tools, our approach demonstrated better integration of tabular and image data, providing richer and more aligned embeddings. Gradient-weighted Class Activation Mapping heatmaps further revealed activated brain regions commonly associated in the literature with brain aging, stroke risk, and clinical outcomes. This robust self-supervised multimodal framework surpasses state-of-the-art methods for stroke risk prediction and offers a strong foundation for future studies integrating diverse data modalities to advance clinical predictive modelling., Comment: Accepted as oral paper at AIM-FM workshop, Neurips 2024

Stroke remains a leading cause of global morbidity and mortality, placing a heavy socioeconomic burden. Over the past decade, advances in endovascular reperfusion therapy and the use of CT and MRI imaging for treatment guidance have significantly improved patient outcomes and are now standard in clinical practice. To develop machine learning algorithms that can extract meaningful and reproducible models of brain function for both clinical and research purposes from stroke images - particularly for lesion identification, brain health quantification, and prognosis - large, diverse, and well-annotated public datasets are essential. While only a few datasets with (sub-)acute stroke data were previously available, several large, high-quality datasets have recently been made publicly accessible. However, these existing datasets include only MRI data. In contrast, our dataset is the first to offer comprehensive longitudinal stroke data, including acute CT imaging with angiography and perfusion, follow-up MRI at 2-9 days, as well as acute and longitudinal clinical data up to a three-month outcome. The dataset includes a training dataset of n = 150 and a test dataset of n = 100 scans. Training data is publicly available, while test data will be used exclusively for model validation. We are making this dataset available as part of the 2024 edition of the Ischemic Stroke Lesion Segmentation (ISLES) challenge (https://www.isles-challenge.org/), which continuously aims to establish benchmark methods for acute and sub-acute ischemic stroke lesion segmentation, aiding in creating open stroke imaging datasets and evaluating cutting-edge image processing algorithms.

Accurate estimation of core (irreversibly damaged tissue) and penumbra (salvageable tissue) volumes is essential for ischemic stroke treatment decisions. Perfusion CT, the clinical standard, estimates these volumes but is affected by variations in deconvolution algorithms, implementations, and thresholds. Core tissue expands over time, with growth rates influenced by thrombus location, collateral circulation, and inherent patient-specific factors. Understanding this tissue growth is crucial for determining the need to transfer patients to comprehensive stroke centers, predicting the benefits of additional reperfusion attempts during mechanical thrombectomy, and forecasting final clinical outcomes. This work presents the ISLES'24 challenge, which addresses final post-treatment stroke infarct prediction from pre-interventional acute stroke imaging and clinical data. ISLES'24 establishes a unique 360-degree setting where all feasibly accessible clinical data are available for participants, including full CT acute stroke imaging, sub-acute follow-up MRI, and clinical tabular data. The contributions of this work are two-fold: first, we introduce a standardized benchmarking of final stroke infarct segmentation algorithms through the ISLES'24 challenge; second, we provide insights into infarct segmentation using multimodal imaging and clinical data strategies by identifying outperforming methods on a finely curated dataset. The outputs of this challenge are anticipated to enhance clinical decision-making and improve patient outcome predictions. All ISLES'24 materials, including data, performance evaluation scripts, and leading algorithmic strategies, are available to the research community following \url{https://isles-24.grand-challenge.org/}.

In this paper, we further consider the symmetry-based method for seeking nonlocally related systems for partial differential equations. In particular, we show that the symmetry-based method for partial differential equations is the natural extension of Lie's reduction of order algorithm for ordinary differential equations by looking at this algorithm from a different point of view. Many examples exhibit various situations that can arise.

Travel planning is a complex task that involves generating a sequence of actions related to visiting places subject to constraints and maximizing some user satisfaction criteria. Traditional approaches rely on problem formulation in a given formal language, extracting relevant travel information from web sources, and use an adequate problem solver to generate a valid solution. As an alternative, recent Large Language Model (LLM) based approaches directly output plans from user requests using language. Although LLMs possess extensive travel domain knowledge and provide high-level information like points of interest and potential routes, current state-of-the-art models often generate plans that lack coherence, fail to satisfy constraints fully, and do not guarantee the generation of high-quality solutions. We propose TRIP-PAL, a hybrid method that combines the strengths of LLMs and automated planners, where (i) LLMs get and translate travel information and user information into data structures that can be fed into planners; and (ii) automated planners generate travel plans that guarantee constraint satisfaction and optimize for users' utility. Our experiments across various travel scenarios show that TRIP-PAL outperforms an LLM when generating travel plans., Comment: 9 pages, 5 figures

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES'22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model achieved superior ischemic lesion detection and segmentation accuracy on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm's segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model's generalizability. The algorithm's outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm (https://github.com/Tabrisrei/ISLES22_Ensemble) that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)radiologists. Second, we show the potential for biomedical challenge outputs to extend beyond the challenge's initial objectives, demonstrating their real-world clinical applicability.

Let $\mathbb{D}$ denote the unit disc in $\mathbb{C}$. We define the generalized Ces\`aro operator as follows $$ C_{\omega}(f)(z)=\int_0^1 f(tz)\left(\frac{1}{z}\int_0^z B^{\omega}_t(u)\,du\right)\,\omega(t)dt,$$ where $\{B^{\omega}_\zeta\}_{\zeta\in\mathbb{D}}$ are the reproducing kernels of the Bergman space $A^2_\omega$ induced by a radial weight $\omega$ in the unit disc $\mathbb{D}$. We study the action of the operator $C_{\omega}$ on weighted Hardy spaces of analytic functions $\mathcal{H}_{\gamma}$, $\gamma >0$ and on general weighted Bergman spaces $A^2_{\mu}$.

In this paper, by applying the multiplier method we obtain a complete classification of low-order local conservation laws for a generalized seventh-order KdV equation depending on seven arbitrary nonzero parameters. We apply the Lie method in order to classify all point symmetries admitted by the equation in terms of the arbitrary parameters. We find that there are no special cases of the parameters for which the equation admits extra symmetries, other than those that can be found by inspection (scaling symmetry and space and time translation symmetries). We consider the reduced ordinary differential equations and we determined all integrating factors of the reduced equation from the combined $x$- and $t$- translation symmetries. Finally, we observe that all integrating factors arise by reduction of the low-order multipliers of the generalized seventh-order KdV equation., Comment: 12 pages

In this paper we consider a generalized Kuramoto-Sivashinsky equation. The equivalence group of the class under consideration has been constructed. This group allows us to perform a comprehensive study and a clear and concise formulation of the results. We have constructed the optimal system of subalgebras of the projections of the equivalence algebra on the space formed by the dependent variable and the arbitrary functions. By using this optimal system, all nonequivalent equations admitting an extension by one of the principal Lie algebra of the class under consideration can be determined. Taking into account the additional symmetries obtained we reduce some partial differential equations belonging to the class into ordinary differential equations. We derive some exact solutions of these equations., Comment: 18 pages

We provide a complete classification of point symmetries and low-order local conservation laws of the generalized quasilinear KdV equation in terms of the arbitrary function. The corresponding interpretation of symmetry transformation groups are given. In addition, a physical description of the conserved quantities is included. Finally, few travelling wave solutions have been obtained., Comment: 14 pages

In this paper, a family of variable-coefficient fifth-order KdV equations has been considered. By using an infinitesimal method based on the determination of the equivalence group, differential invariants and invariant equations are obtained. Invariants provide an alternative way to find equations from the family which may be equivalent to a specific subclass of the same family and the invertible transformation which maps both equivalent equations. Here, differential invariants are applied to obtain exact solutions., Comment: 14 pages

In this work we study a generalized variable-coefficient Gardner equation from the point of view of Lie symmetries in partial differential equations. We find conservation laws by using the multipliers method of Anco and Bluman which does not require the use of a variational principle. We also construct conservation laws using Ibragimov theorem which is based on the concept of adjoint equation for nonlinear differential equations., Comment: 19 pages. arXiv admin note: text overlap with arXiv:2402.02601

A fifth-order KdV equation with time dependent coefficients and linear damping has been studied. Symmetry groups have several different applications in the context of nonlinear differential equations. For instance, they can be used to determine conservation laws. We obtain the symmetries of the model applying Lie's classical method. The choice of some arbitrary functions of the equation by the equivalence transformation enhances the study of Lie symmetries of the equation. We have determined the subclasses of the equation which are nonlinearly self-adjoint. This allow us to obtain conservation laws by using a theorem proved by Ibragimov which is based on the concept of adjoint equation for nonlinear differential equations., Comment: 13 pages

In this paper we study the generalized variable-coefficient Gardner equations of the form $u_t + A(t)u^n\,u_x+ C(t)\,u^{2n}u_x + B(t)\,u_{xxx} + Q(t)\,u =0$. This class broadens out many other equations previously considered: Johnpillai and Khalique (2010), Molati and Ramollo (2012) and Vaneeva, Kuriksha and Sophocleous (2015). Equivalence group of the class under consideration has been constructed which permit an exhaustive study and a simple and clear formulation of the results. Some conservation laws are derived for the nonlinearly self-adjoint equations, based on differential substitutions, and by using the direct method of the multipliers., Comment: 16 pages

This article introduces NB-Whisper, an adaptation of OpenAI's Whisper, specifically fine-tuned for Norwegian language Automatic Speech Recognition (ASR). We highlight its key contributions and summarise the results achieved in converting spoken Norwegian into written forms and translating other languages into Norwegian. We show that we are able to improve the Norwegian Bokm{\aa}l transcription by OpenAI Whisper Large-v3 from a WER of 10.4 to 6.6 on the Fleurs Dataset and from 6.8 to 2.2 on the NST dataset.

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically., Comment: 24 pages, 11 figures, 9 tables. Summary Paper for the MICCAI TopCoW 2023 Challenge

Photo-trapping cameras are widely employed for wildlife monitoring. Those cameras take photographs when motion is detected to capture images where animals appear. A significant portion of these images are empty - no wildlife appears in the image. Filtering out those images is not a trivial task since it requires hours of manual work from biologists. Therefore, there is a notable interest in automating this task. Automatic discarding of empty photo-trapping images is still an open field in the area of Machine Learning. Existing solutions often rely on state-of-the-art supervised convolutional neural networks that require the annotation of the images in the training phase. PARDINUS (Weakly suPervised discARDINg of photo-trapping empty images based on aUtoencoderS) is constructed on the foundation of weakly supervised learning and proves that this approach equals or even surpasses other fully supervised methods that require further labeling work.

This paper introduces panoptica, a versatile and performance-optimized package designed for computing instance-wise segmentation quality metrics from 2D and 3D segmentation maps. panoptica addresses the limitations of existing metrics and provides a modular framework that complements the original intersection over union-based panoptic quality with other metrics, such as the distance metric Average Symmetric Surface Distance. The package is open-source, implemented in Python, and accompanied by comprehensive documentation and tutorials. panoptica employs a three-step metrics computation process to cover diverse use cases. The efficacy of panoptica is demonstrated on various real-world biomedical datasets, where an instance-wise evaluation is instrumental for an accurate representation of the underlying clinical task. Overall, we envision panoptica as a valuable tool facilitating in-depth evaluation of segmentation methods., Comment: 15 pages, 6 figures, 3 tables