Explore the vast range of titles available.

In the last two decades, Computer Aided Detection (CAD) systems were developed to help radiologists analyse screening mammograms, however benefits of current CAD technologies appear to be contradictory, therefore they should be improved to be ultimately considered useful. Since 2012, deep convolutional neural networks (CNN) have been a tremendous success in image recognition, reaching human performance. These methods have greatly surpassed the traditional approaches, which are similar to currently used CAD solutions. Deep CNN-s have the potential to revolutionize medical image analysis. We propose a CAD system based on one of the most successful object detection frameworks, Faster R-CNN. The system detects and classifies malignant or benign lesions on a mammogram without any human intervention. The proposed method sets the state of the art classification performance on the public INbreast database, AUC = 0.95. The approach described here has achieved 2nd place in the Digital Mammography DREAM Challenge with AUC = 0.85. When used as a detector, the system reaches high sensitivity with very few false positive marks per image on the INbreast dataset. Source code, the trained model and an OsiriX plugin are published online at https://github.com/riblidezso/frcnn_cad .

Background The willingness to get COVID-19 or seasonal influenza vaccines has not yet been thoroughly investigated together, thus, this study aims to explore this notion within the general adult population. Methods The responses of 840 Hungarian participants were analysed who took part in a nationwide computer-assisted telephone interviewing. During the survey questions concerning various demographic characteristics, perceived financial status, and willingness to get the two types of vaccines were asked. Descriptive statistics, comparative statistics and word co-occurrence network analysis were conducted. Results 48.2% of participants were willing to get a COVID-19 vaccine, while this ratio for the seasonal influenza was only 25.7%. The difference was significant. Regardless of how the participants were grouped, based on demographic data or perceived financial status, the significant difference always persisted. Being older than 59 years significantly increased the willingness to get both vaccines when compared to the middle-aged groups, but not when compared to the younger ones. Having higher education significantly elevated the acceptance of COVID-19 vaccination in comparison to secondary education. The willingness of getting any type of COVID-19 vaccine correlated with the willingness to get both influenza and COVID-19. Finally, those who were willing to get either vaccine coupled similar words together to describe their thoughts about a COVID-19 vaccination. Conclusion The overall results show a clear preference for a COVID-19 vaccine and there are several similarities between the nature of willingness to get either type of vaccine.

Statistical learning algorithms strongly rely on an oversimplified assumption for optimal performance, that is, source (training) and target (testing) data are independent and identically distributed. Variation in human tissue, physician labeling and physical imaging parameters (PIPs) in the generative process, yield medical image datasets with statistics that render this central assumption false. When deploying models, new examples are often out of distribution with respect to training data, thus, training robust dependable and predictive models is still a challenge in medical imaging with significant accuracy drops common for deployed models. This statistical variation between training and testing data is referred to as domain shift (DS).To the best of our knowledge we provide the first empirical evidence that variation in PIPs between test and train medical image datasets is a significant driver of DS and model generalization error is correlated with this variance. We show significant covariate shift occurs due to a selection bias in sampling from a small area of PIP space for both inter and intra-hospital regimes. In order to show this, we control for population shift, prevalence shift, data selection biases and annotation biases to investigate the sole effect of the physical generation process on model generalization for a proxy task of age group estimation on a combined 44 k image mammogram dataset collected from five hospitals.We hypothesize that training data should be sampled evenly from PIP space to produce the most robust models and hope this study provides motivation to retain medical image generation metadata that is almost always discarded or redacted in open source datasets. This metadata measured with standard international units can provide a universal regularizing anchor between distributions generated across the world for all current and future imaging modalities.

In the past few years COVID-19 posed a huge threat to healthcare systems around the world. One of the first waves of the pandemic hit Northern Italy severely resulting in high casualties and in the near breakdown of primary care. Due to these facts, the Covid CXR Hackathon—Artificial Intelligence for Covid-19 prognosis: aiming at accuracy and explainability challenge had been launched at the beginning of February 2022, releasing a new imaging dataset with additional clinical metadata for each accompanying chest X-ray (CXR). In this article we summarize our techniques at correctly diagnosing chest X-ray images collected upon admission for severity of COVID-19 outcome. In addition to X-ray imagery, clinical metadata was provided and the challenge also aimed at creating an explainable model. We created a best-performing, as well as, an explainable model that makes an effort to map clinical metadata to image features whilst predicting the prognosis. We also did many ablation studies in order to identify crucial parts of the models and the predictive power of each feature in the datasets. We conclude that CXRs at admission do not help the predicting power of the metadata significantly by itself and contain mostly information that is also mutually present in the blood samples and other clinical factors collected at admission.

Hierarchical organisation is a prevalent feature of many complex networks appearing in nature and society. A relating interesting, yet less studied question is how does a hierarchical network evolve over time? Here we take a data driven approach and examine the time evolution of the network between the Medical Subject Headings (MeSH) provided by the National Center for Biotechnology Information (NCBI, part of the U. S. National Library of Medicine). The network between the MeSH terms is organised into 16 different, yearly updated hierarchies such as \"Anatomy\", \"Diseases\", \"Chemicals and Drugs\", etc. The natural representation of these hierarchies is given by directed acyclic graphs, composed of links pointing from nodes higher in the hierarchy towards nodes in lower levels. Due to the yearly updates, the structure of these networks is subject to constant evolution: new MeSH terms can appear, terms becoming obsolete can be deleted or be merged with other terms, and also already existing parts of the network may be rewired. We examine various statistical properties of the time evolution, with a special focus on the attachment and detachment mechanisms of the links, and find a few general features that are characteristic for all MeSH hierarchies. According to the results, the hierarchies investigated display an interesting interplay between non-uniform preference with respect to multiple different topological and hierarchical properties.

DNA methylation provides one of the most widely studied biomarkers of ageing. Since the methylation of CpG dinucleotides function as switches in cellular mechanisms, it is plausible to assume that by proper adjustment of these switches age may be tuned. Though, adjusting hundreds of CpG methylation levels coherently may never be feasible and changing just a few positions may lead to biologically unstable state. A prominent example of methylation-based age estimators is provided by Horvath’s clock, based on 353 CpG dinucleotides, showing a high correlation (not necessarily causation) with chronological age across multiple tissue types. On this small subset of CpG dinucleotides we demonstrate how the adjustment of one methylation level leads to a cascade of changes at other sites. Among the studied subset, we locate the most important CpGs (and related genes) that may have a large influence on the rest of the sub-system. According to our analysis, the structure of this network is way more hierarchical compared to what one would expect based on ensembles of uncorrelated connections. Therefore, only a handful of CpGs is enough to modify the system towards a desired state. When propagation of the change over the network is taken into account, the resulting modification in the predicted age can be significantly larger compared to the effect of isolated CpG perturbations. By adjusting the most influential single CpG site and following the propagation of methylation level changes we can reach up to 5.74 years in virtual age reduction, significantly larger than without taking into account of the network control. Extending our approach to the whole methylation network may identify key nodes that have controller role in the ageing process.

Generative large language models (LLMs) have revolutionized the development of knowledge-based systems, enabling new possibilities in applications like ChatGPT, Bing, and Gemini. Two key strategies for domain adaptation in these systems are Domain-Specific Fine-Tuning (DFT) and Retrieval-Augmented Generation (RAG). In this study, we evaluate the performance of RAG and DFT on several LLM architectures, including GPT-J-6B, OPT-6.7B, LLaMA, and LLaMA-2. We use the ROUGE, BLEU, and METEOR scores to evaluate the performance of the models. We also measure the performance of the models with our own designed cosine similarity-based Coverage Score (CS). Our results, based on experiments across multiple datasets, show that RAG-based systems consistently outperform those fine-tuned with DFT. Specifically, RAG models outperform DFT by an average of 17% in ROUGE, 13% in BLEU, and 36% in CS. At the same time, DFT achieves only a modest advantage in METEOR, suggesting slightly better creative capabilities. We also highlight the challenges of integrating RAG with DFT, as such integration can lead to performance degradation. Furthermore, we propose a simplified RAG-based architecture that maximizes efficiency and reduces hallucination, underscoring the advantages of RAG in building reliable, domain-adapted knowledge systems.

The hidden variable formalism (based on the assumption of some intrinsic node parameters) turned out to be a remarkably efficient and powerful approach in describing and analyzing the topology of complex networks. Owing to one of its most advantageous property - namely proven to be able to reproduce a wide range of different degree distribution forms - it has become a standard tool for generating networks having the scale-free property. One of the most intensively studied version of this model is based on a thresholding mechanism of the exponentially distributed hidden variables associated to the nodes (intrinsic vertex weights), which give rise to the emergence of a scale-free network where the degree distribution p ( k ) ~ k − γ is decaying with an exponent of γ  = 2. Here we propose a generalization and modification of this model by extending the set of connection probabilities and hidden variable distributions that lead to the aforementioned degree distribution, and analyze the conditions leading to the above behavior analytically. In addition, we propose a relaxation of the hard threshold in the connection probabilities, which opens up the possibility for obtaining sparse scale free networks with arbitrary scaling exponent.

Astrocytes, a type of glial cell, significantly influence neuronal function, with variations in morphology and density linked to neurological disorders. Traditional methods for their accurate detection and density measurement are laborious and unsuited for large-scale operations. We introduce a dataset from human brain tissues stained with aldehyde dehydrogenase 1 family member L1 (ALDH1L1) and glial fibrillary acidic protein (GFAP). The digital whole slide images of these tissues were partitioned into 8730 patches of 500 × 500 pixels, comprising 2323 ALDH1L1 and 4714 GFAP patches at a pixel size of 0.5019/pixel, furthermore 1382 ADHD1L1 and 311 GFAP patches at 0.3557/pixel. Sourced from 16 slides and 8 patients our dataset promotes the development of tools for glial cell detection and quantification, offering insights into their density distribution in various brain areas, thereby broadening neuropathological study horizons. These samples hold value for automating detection methods, including deep learning. Derived from human samples, our dataset provides a platform for exploring astrocyte functionality, potentially guiding new diagnostic and treatment strategies for neurological disorders.

Histopathology is the gold standard method for staging and grading human tumors and provides critical information for the oncoteam’s decision making. Highly-trained pathologists are needed for careful microscopic analysis of the slides produced from tissue taken from biopsy. This is a time-consuming process. A reliable decision support system would assist healthcare systems that often suffer from a shortage of pathologists. Recent advances in digital pathology allow for high-resolution digitalization of pathological slides. Digital slide scanners combined with modern computer vision models, such as convolutional neural networks, can help pathologists in their everyday work, resulting in shortened diagnosis times. In this study, 200 digital whole-slide images are published which were collected via hematoxylin-eosin stained colorectal biopsy. Alongside the whole-slide images, detailed region level annotations are also provided for ten relevant pathological classes. The 200 digital slides, after pre-processing, resulted in 101,389 patches. A single patch is a 512 × 512 pixel image, covering 248 × 248 μm2 tissue area. Versions at higher resolution are available as well. Hopefully, HunCRC, this widely accessible dataset will aid future colorectal cancer computer-aided diagnosis and research.Measurement(s)H&E slide staining • ex vivo light microscopy with immunohistochemistry and digital image analysis • Image Annotation Statement • Screening ColonoscopyTechnology Type(s)Hematoxylin and Eosin Staining Method • bright-field microscopy • Observation • Biopsy of ColonFactor Type(s)screening status of colon cancer or normal tissueSample Characteristic - OrganismHomo sapiensSample Characteristic - LocationCentral Hungary