Video capsule endoscopy has transformed gastrointestinal endoscopy (GIE) diagnostics by offering a non-invasive method for capturing detailed images of the gastrointestinal tract, enabling early disease detection. However, its potential is limited by the sheer volume of images generated during the imaging procedure, which can take anywhere from 6-8 hours and often produce up to 1 million images, necessitating automated analysis. Additionally, the variability of these images, combined with the need for expert annotations and the scarcity of large, high-quality labeled datasets, constrains the effectiveness of current medical image analysis models. To address this, we introduce a novel large GIE dataset, called EndoExtend24, created by merging ten existing public and private datasets, ensuring patient integrity across splits. EndoExtend24 includes over 226,000 labeled images, as well as dynamic class mappings, which allow unified training across datasets with differing labeling granularity, supporting up to 123 distinct pathological findings. Further, we propose to leverage domain adaptive pre-training of foundation models trained with self-supervision on generic image data, to adapt
Elucidating the statistical properties of extreme meteo-climatic events and capturing the physical processes responsible for their occurrence are key steps for improving our understanding of climate variability and climate change and for better evaluating the associated hazards. It has recently become apparent that large deviation theory is very useful for investigating persistent extreme events, and specifically, for flexibly estimating long return periods and for introducing a notion of dynamical typicality. Using a methodological framework based on large deviation theory and taking advantage of long simulations by a state-of-the-art Earth System Model, we investigate the 2021 North America Heatwave. Indeed, our analysis shows that the 2021 event can be seen as an unlikely but possible manifestation of climate variability, whilst its probability of occurrence is greatly amplified by the ongoing climate change. We also clarify the properties of spatial coherence of the 2021 heatwave and elucidate the role played by the Rocky Mountains in modulating hot, dry, and persistent extreme events in the Western Pacific region of North America.
Gastrointestinal diseases impose a growing global health burden, and endoscopy is a primary tool for early diagnosis. However, routine endoscopic image interpretation still suffers from missed lesions and limited efficiency. Although AI-assisted diagnosis has shown promise, existing models often lack generalizability, adaptability, robustness, and scalability because of limited medical data, domain shift, and heterogeneous annotations. To address these challenges, we develop RATNet, a foundation model for gastrointestinal endoscopy imaging based on analogical reasoning. RATNet acquires and transfers knowledge from heterogeneous expert annotations across five gastrointestinal endoscopy datasets through a cyclic pre-training strategy. Its architecture consists of an encoder, a relevance-knowledge acquisition and transfer (RAT) module, a projector, and a multi-task head, and supports fine-tuning, linear probing, and zero-shot transfer. Evaluations show that RATNet outperforms existing foundation models, including GastroNet and GastroVision, across six scenarios: diagnosis of common gastrointestinal diseases, few-shot learning for rare diseases, zero-shot transfer to new medical sites,
Automatic speech recognition (ASR) is a critical interface for human-AI interaction in gastrointestinal endoscopy, yet its reliability in real-world clinical settings is limited by domain-specific terminology and complex acoustic conditions. Here, we present EndoASR, a domain-adapted ASR system designed for real-time deployment in endoscopic workflows. We develop a two-stage adaptation strategy based on synthetic endoscopy reports, targeting domain-specific language modeling and noise robustness. In retrospective evaluation across six endoscopists, EndoASR substantially improves both transcription accuracy and clinical usability, reducing character error rate (CER) from 20.52% to 14.14% and increasing medical term accuracy (Med ACC) from 54.30% to 87.59%. In a prospective multi-center study spanning five independent endoscopy centers, EndoASR demonstrates consistent generalization under heterogeneous real-world conditions. Compared with the baseline Paraformer model, CER is reduced from 16.20% to 14.97%, while Med ACC is improved from 61.63% to 84.16%, confirming its robustness in practical deployment scenarios. Notably, EndoASR achieves a real-time factor (RTF) of 0.005, significa
Multimodal Large Language Models (MLLMs) show promise in gastroenterology, yet their performance against comprehensive clinical workflows and human benchmarks remains unverified. To systematically evaluate state-of-the-art MLLMs across a panoramic gastrointestinal endoscopy workflow and determine their clinical utility compared with human endoscopists. We constructed GI-Bench, a benchmark encompassing 20 fine-grained lesion categories. Twelve MLLMs were evaluated across a five-stage clinical workflow: anatomical localization, lesion identification, diagnosis, findings description, and management. Model performance was benchmarked against three junior endoscopists and three residency trainees using Macro-F1, mean Intersection-over-Union (mIoU), and multi-dimensional Likert scale. Gemini-3-Pro achieved state-of-the-art performance. In diagnostic reasoning, top-tier models (Macro-F1 0.641) outperformed trainees (0.492) and rivaled junior endoscopists (0.727; p>0.05). However, a critical "spatial grounding bottleneck" persisted; human lesion localization (mIoU >0.506) significantly outperformed the best model (0.345; p<0.05). Furthermore, qualitative analysis revealed a "fluen
The major limitations of gastrointestinal (GI) endoscopy AI systems arise from a shortage of annotated data, strict privacy policies, and significant bottlenecks in conventional model fine-tuning. Such limitations impede the successful application of sophisticated AI models in clinical practice, particularly affecting the reliability and scalability of diagnosis. In this paper, we present a dual-pipeline PEFT model that addresses two fundamental problems: medical Visual Question Answering (VQA) and the generation of privacy-preserving synthetic data. For clinical VQA, we adopt the Florence-2 vision-language model. Leveraging PEFT enhances model interpretability while substantially reducing the computational cost of training. Simultaneously, we employ Low-Rank Adaptation (LoRA) with Stable Diffusion 2.1 to generate high-quality GI images that enhance training databases without violating patient privacy. This research utilized the Kvasir-VQA dataset. Our Florence-2 VQA model achieved ROUGE-1 of 0.92, ROUGE-L of 0.91, and BLEU score improvements from 0.08 to 0.24. Fine-tuning on private datasets consistently showed better results than fine-tuning on public datasets. The rank-4 LoRA sy
The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy da
We present observations of near-infrared 2.12 micro-meter molecular hydrogen outflows emerging from 1.1 mm dust continuum clumps in the North America and Pelican Nebula (NAP) complex selected from the Bolocam Galactic Plane Survey (BGPS). Hundreds of individual shocks powered by over 50 outflows from young stars are identified, indicating that the dusty molecular clumps surrounding the NGC 7000 / IC 5070 / W80 HII region are among the most active sites of on-going star formation in the Solar vicinity. A spectacular X-shaped outflow, MHO 3400, emerges from a young star system embedded in a dense clump more than a parsec from the ionization front associated with the Pelican Nebula (IC 5070). Suspected to be a binary, the source drives a pair of outflows with orientations differing by 80 degrees. Each flow exhibits S-shaped symmetry and multiple shocks indicating a pulsed and precessing jet. The `Gulf of Mexico' located south of the North America Nebula (NGC 7000), contains a dense cluster of molecular hydrogen objects (MHOs), Herbig-Haro (HH) objects, and over 300 YSOs, indicating a recent burst of star formation. The largest outflow detected thus far in the North America and Pelican
We propose a Bayesian, noisy-input, spatial-temporal generalised additive model to examine regional relative sea-level (RSL) changes over time. The model provides probabilistic estimates of component drivers of regional RSL change via the combination of a univariate spline capturing a common regional signal over time, random slopes and intercepts capturing site-specific (local), long-term linear trends and a spatial-temporal spline capturing residual, non-linear, local variations. Proxy and instrumental records of RSL and corresponding measurement errors inform the model and a noisy-input method accounts for proxy temporal uncertainties. Results focus on the decomposition of RSL over the past 3000 years along the Atlantic coast of North America.
We present and discuss broad band CCD $UBV(I)_C$ photometry and low resolution spectroscopy for stars in the region of the open cluster NGC 6996, located in the North America Nebula. The new data allow us to tightly constrain the basic properties of this object. We revise the cluster size, which in the past has been significantly underestimated. The width of the Main Sequence is mainly interpreted in terms of differential reddening, and indeed the stars' color excess $E_{B-V}$ ranges from 0.43 to 0.65, implying the presence of a significant and evenly distributed dust component. We cross-correlate our optical photometry with near infrared from 2MASS, and by means of spectral classification we are able to build up extinction curves for an handful of bright members. We find that the reddening slope and the total to selective absorption ratio $R_V$ toward NGC 6996 are anomalous. Moreover the reddening corrected colors and magnitudes allow us to derive estimates for the cluster distance and age, which turn out to be $760 \pm 70 pc$ ($V_{0}-M_{V} = 9.4 \pm 0.2$) and $\sim 350$ Myr, respectively. Basing on our results, we suggest that NGC 6996 is located in front of the North America Neb
In the area covering the complex of the North America and Pelican nebulae we identified 13 faint stars with J-H and H-Ks color indices which simulate heavily reddened O-type stars. One of these stars is CP05-4 classified as O5 V by Comeron and Pasquali (2005). Combining magnitudes of these stars in the passbands I, J, H, Ks and [8.3] we were able to suspect that two of them are carbon stars and five are late M-type AGB stars. Interstellar extinction in the direction of these stars was estimated from the background red clump giants in the J-H vs. H-Ks diagram and from star counts in the Ks passband. Four or five stars are found to have a considerable probability of being O-type stars, contributing to the ionization of North America and Pelican. If they really are O-type stars, their interstellar extinction A(V) should be from 16 to 35 mag. Two of them seem to be responsible for bright E and J radio rims discovered by Matthews and Goss (1980).
The development of a kilometer-scale E3SM Land Model (km-scale ELM) is an integral part of the E3SM project, which seeks to advance energy-related Earth system science research with state-of-the-art modeling and simulation capabilities on exascale computing systems. Through the utilization of high-fidelity data products, such as atmospheric forcing and soil properties, the km-scale ELM plays a critical role in accurately modeling geographical characteristics and extreme weather occurrences. The model is vital for enhancing our comprehension and prediction of climate patterns, as well as their effects on ecosystems and human activities. This study showcases the first set of full-capability, km-scale ELM simulations over various computational domains, including simulations encompassing 21.6 million land gridcells, reflecting approximately 21.5 million square kilometers of North America at a 1 km x 1 km resolution. We present the largest km-scale ELM simulation using up to 100,800 CPU cores across 2,400 nodes. This continental-scale simulation is 300 times larger than any previous studies, and the computational resources used are about 400 times larger than those used in prior efforts
Wireless capsule endoscopy (WCE) is a non-invasive diagnostic procedure that enables visualization of the gastrointestinal (GI) tract. Deep learning-based methods have shown effectiveness in disease screening using WCE data, alleviating the burden on healthcare professionals. However, existing capsule endoscopy classification methods mostly rely on pre-defined categories, making it challenging to identify and classify out-of-distribution (OOD) data, such as undefined categories or anatomical landmarks. To address this issue, we propose the Endoscopy Out-of-Distribution (EndoOOD) framework, which aims to effectively handle the OOD detection challenge in WCE diagnosis. The proposed framework focuses on improving the robustness and reliability of WCE diagnostic capabilities by incorporating uncertainty-aware mixup training and long-tailed in-distribution (ID) data calibration techniques. Additionally, virtual-logit matching is employed to accurately distinguish between OOD and ID data while minimizing information loss. To assess the performance of our proposed solution, we conduct evaluations and comparisons with 12 state-of-the-art (SOTA) methods using two publicly available datasets
We evaluate the performance of various configurations of the Canadian Regional Climate Model (CRCM6-GEM5) in simulating 10-meter wind speeds using data from 27 AmeriFlux stations across North America. The assessment employs a hierarchy of error metrics, ranging from simple mean bias to advanced metrics that account for the dependence of wind speeds on variables such as friction velocity and stability. The results reveal that (i) the value of roughness length (z0) has a large effect on the simulation of wind speeds, (ii) using a lower limit for the Obhukov length instead of a lower limit for the lowest level wind speed seems to deteriorate the simulation of wind speeds under very stable conditions, (iii) the choice of stability function has a small but noticeable impact on the wind speeds, (iv) the turbulent orographic form drag scheme shows improvement over effective roughness length approach.
The escalating global mortality and morbidity rates associated with gastrointestinal (GI) bleeding, compounded by the complexities and limitations of traditional endoscopic methods, underscore the urgent need for a critical review of current methodologies used for addressing this condition. With an estimated 300,000 annual deaths worldwide, the demand for innovative diagnostic and therapeutic strategies is paramount. The introduction of Video Capsule Endoscopy (VCE) has marked a significant advancement, offering a comprehensive, non-invasive visualization of the digestive tract that is pivotal for detecting bleeding sources unattainable by traditional methods. Despite its benefits, the efficacy of VCE is hindered by diagnostic challenges, including time-consuming analysis and susceptibility to human error. This backdrop sets the stage for exploring Machine Learning (ML) applications in automating GI bleeding detection within capsule endoscopy, aiming to enhance diagnostic accuracy, reduce manual labor, and improve patient outcomes. Through an exhaustive analysis of 113 papers published between 2008 and 2023, this review assesses the current state of ML methodologies in bleeding det
White light endoscopy is the clinical gold standard for detecting diseases in the gastrointestinal tract. Most applications involve identifying visual abnormalities in tissue color, texture, and shape. Unfortunately, the contrast of these features is often subtle, causing many clinically relevant cases to go undetected. To overcome this challenge, we introduce Multi-contrast Laser Endoscopy (MLE): a platform for widefield clinical imaging with rapidly tunable spectral, coherent, and directional illumination. We demonstrate three capabilities of MLE: enhancing tissue chromophore contrast with multispectral diffuse reflectance, quantifying blood flow using laser speckle contrast imaging, and characterizing mucosal topography using photometric stereo. We validate MLE with benchtop models, then demonstrate MLE in vivo during clinical colonoscopies. MLE images from 31 polyps demonstrate an approximate three-fold improvement in contrast and a five-fold improvement in color difference compared to white light and narrow band imaging. With the ability to reveal multiple complementary types of tissue contrast while seamlessly integrating into the clinical environment, MLE shows promise as an
Magnitudes and color indices in the Vilnius seven-color system are measured for 690 stars down to ~13.2 mag in the area of the North America and Pelican nebulae. Spectral types, absolute magnitudes, color excesses, interstellar extinctions and distances of the stars are determined. The plots of interstellar extinction Av versus distance for the North America Nebula and for the dark cloud L935 show that both areas are covered by the same absorbing cloud, situated at a distance of 600 pc. The maximal extinction in the area of the nebula is ~3 mag, while in the dark cloud L935 it is much greater.
Solutions to vision tasks in gastrointestinal endoscopy (GIE) conventionally use image encoders pretrained in a supervised manner with ImageNet-1k as backbones. However, the use of modern self-supervised pretraining algorithms and a recent dataset of 100k unlabelled GIE images (Hyperkvasir-unlabelled) may allow for improvements. In this work, we study the fine-tuned performance of models with ResNet50 and ViT-B backbones pretrained in self-supervised and supervised manners with ImageNet-1k and Hyperkvasir-unlabelled (self-supervised only) in a range of GIE vision tasks. In addition to identifying the most suitable pretraining pipeline and backbone architecture for each task, out of those considered, our results suggest three general principles. Firstly, that self-supervised pretraining generally produces more suitable backbones for GIE vision tasks than supervised pretraining. Secondly, that self-supervised pretraining with ImageNet-1k is typically more suitable than pretraining with Hyperkvasir-unlabelled, with the notable exception of monocular depth estimation in colonoscopy. Thirdly, that ViT-Bs are more suitable in polyp segmentation and monocular depth estimation in colonosco
Endoscopy provides a major contribution to the diagnosis of the Gastrointestinal Tract (GIT) diseases. With Colon Endoscopy having its certain limitations, Wireless Capsule Endoscopy is gradually taking over it in the terms of ease and efficiency. WCE is performed with a miniature optical endoscope which is swallowed by the patient and transmits colour images wirelessly during its journey through the GIT, inside the body of the patient. These images are used to implement an effective and computationally efficient approach which aims to detect the abnormal and normal tissues in the GIT automatically, and thus helps in reducing the manual work of the reviewers. The algorithm further aims to classify the diseased tissues into various GIT diseases that are commonly known to be affecting the tract. In this manuscript, the descriptor used for the detection of the interest points is Speeded Up Robust Features (SURF), which uses the colour information contained in the images which is converted to CIELAB space colours for better identification. The features extracted at the interest points are then used to train and test a Support Vector Machine (SVM), so that it automatically classifies th
Scientists collaborate through intricate networks, which impact the quality and scope of their research. At the same time, funding and institutional arrangements, as well as scientific and political cultures, affect the structure of collaboration networks. Since such arrangements and cultures differ across regions in the world in systematic ways, we surmise that collaboration networks and impact should also differ systematically across regions. To test this, we compare the structure of collaboration networks among prominent researchers in North America and Europe. We find that prominent researchers in Europe establish denser collaboration networks, whereas those in North-America establish more decentralized networks. We also find that the impact of the publications of prominent researchers in North America is significantly higher than for those in Europe, both when they collaborate with other prominent researchers and when they do not. Although Europeans collaborate with other prominent researchers more often, which increases their impact, we also find that repeated collaboration among prominent researchers decreases the synergistic effect of collaborating.