displaying 1 - 10 records in total 197
    records per page

    COLI-NET: Fully Automated COVID-19 MESHD Lung and Infection Pneumonia Lesion MESHD Detection and Segmentation from Chest CT Images

    Authors: Isaac Shiri; Hossein Arabi; Yazdan Salimi; Amir Hossein Sanaat; Azadeh Akhavanalaf; Ghasem Hajianfar; Dariush Askari; Shakiba Moradi; Zahra Mansouri; Masoumeh Pakbin; Saleh Sandoughdaran; Hamid Abdollahi; Amir Reza Radmard; Kiara Rezaei-Kalantari; Mostafa Ghelich Oghli; Habib Zaidi

    doi:10.1101/2021.04.08.21255163 Date: 2021-04-13 Source: medRxiv

    Background We present a deep learning ( DL MESHD)-based automated whole lung and COVID-19 MESHD pneumonia infectious lesions MESHD (COLI-Net) detection and segmentation from chest CT images. Methods We prepared 2358 ( 347259, 2D slices) and 180 (17341, 2D slices) volumetric CT images along with their corresponding manual segmentation of lungs and lesions, respectively, in the framework of a multi-center/multi-scanner study. All images were cropped, resized and the intensity values clipped and normalized. A residual network (ResNet) with non-square Dice loss function built upon TensorFlow was employed. The accuracy of lung and COVID-19 MESHD lesions segmentation was evaluated on an external RT-PCR positive COVID-19 MESHD dataset (7333, 2D slices) collected at five different centers. To evaluate the segmentation performance, we calculated different quantitative metrics, including radiomic features. Results The mean Dice coefficients were 0.98&0.011 (95% CI, 0.98-0.99) and 0.91&0.038 (95% CI, 0.90-0.91) for lung and lesions segmentation, respectively. The mean relative Hounsfield unit differences were 0.03&0.84% (95% CI, -0.12-0.18) and -0.18&3.4% (95% CI, -0.8 - 0.44) for the lung and lesions, respectively. The relative volume difference for lung and lesions were 0.38&1.2% (95% CI, 0.16-0.59) and 0.81&6.6% (95% CI, -0.39-2), respectively. Most radiomic features had a mean relative error less than 5% with the highest mean relative error achieved for the lung for the Range first-order feature (-6.95%) and least axis length shape feature (8.68%) for lesions. Conclusion We set out to develop an automated deep learning-guided three-dimensional whole lung and infected regions segmentation in COVID-19 MESHD patients in order to develop fast, consistent, robust and human error immune framework for lung and pneumonia lesion MESHD detection and quantification. Keywords: X-ray CT, COVID-19 MESHD, pneumonia MESHD, deep learning MESHD, segmentation.

    Deep Learning with robustness to missing data: A novel approach to the detection of COVID-19 MESHD

    Authors: Erdi Çallı; Keelin Murphy; Steef Kurstjens; Tijs Samson; Robert Herpers; Henk Smits; Matthieu Rutten; Bram van Ginneken

    id:2103.13833v1 Date: 2021-03-25 Source: arXiv

    In the context of the current global pandemic and the limitations of the RT-PCR test, we propose a novel deep learning architecture MESHD, DFCN, (Denoising Fully Connected Network) for the detection of COVID-19 MESHD using laboratory tests and chest x-rays. Since medical facilities around the world differ enormously in what laboratory tests or chest imaging may be available, DFCN is designed to be robust to missing input data. An ablation study extensively evaluates the performance benefits of the DFCN architecture as well as its robustness to missing inputs. Data from 1088 patients with confirmed RT-PCR results are obtained from two independent medical facilities. The data collected includes results from 27 laboratory tests and a chest x-ray scored by a deep learning network. Training and test datasets are defined based on the source medical facility. Data is made publicly available. The performance of DFCN in predicting the RT-PCR result is compared with 3 related architectures as well as a Random Forest baseline. All models are trained with varying levels of masked input data to encourage robustness to missing inputs. Missing data is simulated at test time by masking inputs randomly. Using area under the receiver operating curve (AUC) as a metric, DFCN outperforms all other models with statistical significance using random subsets of input data with 2-27 available inputs. When all 28 inputs are available DFCN obtains an AUC of 0.924, higher than achieved by any other model. Furthermore, with clinically meaningful subsets of parameters consisting of just 6 and 7 inputs respectively, DFCN also achieves higher AUCs than any other model, with values of 0.909 and 0.919.

    Detection of fake news on CoViD-19 MESHD on Web Search Engines

    Authors: V. Mazzeo; A. Rapisarda; G. Giuffrida

    id:2103.11804v1 Date: 2021-03-22 Source: arXiv

    In early January 2020, after China reported the first cases of the new coronavirus (SARS-CoV-2) in the city of Wuhan, unreliable and not fully accurate information has started spreading faster than the virus itself. Alongside this pandemic, people have experienced a parallel infodemic, i.e., an overabundance of information, some of which misleading or even harmful, that has widely spread around the globe. Although Social Media are increasingly being used as information source, Web Search Engines MESHD, like Google or Yahoo!, still represent a powerful and trustworthy resource for finding information on the Web. This is due to their capability to capture the largest amount of information, helping users quickly identify the most relevant, useful, although not always the most reliable, results for their search queries. This study aims to detect potential misleading and fake contents by capturing and analysing textual information, which flow through Search Engines. By using a real-world dataset associated with recent CoViD-19 pandemic MESHD, we first apply re-sampling techniques for class imbalance, then we use existing Machine Learning algorithms MESHD for classification of not reliable news. By extracting lexical and host-based features of associated Uniform Resource Locators (URLs) for news articles, we show that the proposed methods, so common in phishing and malicious URLs detection, can improve the efficiency and performance of classifiers. Based on these findings, we think that usage of both textual and URLs features can improve the effectiveness of fake news detection methods.

    Development and Validation of a Deep Learning MESHD Model for Prediction of Severe Outcomes in Suspected COVID-19 MESHD Infection

    Authors: Varun Buch; Aoxiao Zhong; Xiang Li; Marcio Aloisio Bezerra Cavalcanti Rockenbach; Dufan Wu; Hui Ren; Jiahui Guan; Andrew Liteplo; Sayon Dutta; Ittai Dayan; Quanzheng Li

    id:2103.11269v1 Date: 2021-03-21 Source: arXiv

    COVID-19 MESHD patient triaging with predictive outcome of the patients upon first present to emergency department (ED) is crucial for improving patient prognosis, as well as better hospital resources management and cross-infection MESHD control. We trained a deep feature fusion model to predict patient outcomes, where the model inputs were EHR data including demographic information, co-morbidities, vital signs and laboratory measurements, plus patient's CXR images. The model output was patient outcomes defined as the most insensitive oxygen therapy required. For patients without CXR images, we employed Random Forest method for the prediction. Predictive risk scores for COVID-19 MESHD severe outcomes ("CO-RISK" score) were derived from model output and evaluated on the testing dataset, as well as compared to human performance. The study's dataset (the "MGB COVID Cohort") was constructed from all patients presenting to the Mass General Brigham (MGB) healthcare system from March 1 HGNCst to June 1st, 2020. ED visits with incomplete or erroneous data were excluded. Patients with no test order for COVID or confirmed negative test results were excluded. Patients under the age of 15 were also excluded. Finally, electronic health record (EHR) data from a total of 11060 COVID-19 MESHD confirmed or suspected patients were used in this study. Chest X-ray (CXR) images were also collected from each patient if available. Results show that CO-RISK score achieved area under the Curve (AUC) of predicting MV/death (i.e. severe outcomes) in 24 hours of 0.95, and 0.92 in 72 hours on the testing dataset. The model shows superior performance to the commonly used risk scores in ED (CURB-65 and MEWS). Comparing with physician's decisions, CO-RISK score has demonstrated superior performance to human in making ICU/floor decisions.

    Coping with homeschooling and caring for children during the UK COVID-19 MESHD lockdown: voices of working mothers 

    Authors: Angeliki Kallitsoglou; Pamela-Zoe Topalli

    doi:10.21203/rs.3.rs-333649/v1 Date: 2021-03-16 Source: ResearchSquare

    We examined working mothers’ experiences and feelings about homeschooling and caring for children while working during the summer 2020 COVID-19 MESHD lockdown in the UK. Eligible mothers were invited to participating in an on-line survey of open-ended questions that was distributed via social media between mid - June to mid-August 2020. Participants (n = 47; Mage = 39.6, range = 28 to 54 years) were predominantly white married working mothers and most had a higher education degree. The experience of combining homeschooling/caring while working was perceived difficult by many mothers and it was associated with feelings of stress about managing competing demands concurrently, guilt for not meeting the child’s needs, and worry over child socioemotional well-being and a cademic learning. MESHD Support from partner, work, and school were instrumental in improving maternal experience and emotional state. Finally, coping strategies that reflect mindfulness practices for stress management, were associated with positive experiences and feelings.

    Is Medical Chest X-ray Data Anonymous?

    Authors: Kai Packhäuser; Sebastian Gündel; Nicolas Münster; Christopher Syben; Vincent Christlein; Andreas Maier

    id:2103.08562v1 Date: 2021-03-15 Source: arXiv

    With the rise and ever-increasing potential of deep learning MESHD techniques in recent years, publicly available medical data sets became a key factor to enable reproducible development of diagnostic algorithms in the medical domain. Medical data contains sensitive patient-related information and is therefore usually anonymized by removing patient identifiers, e.g., patient names before publication. To the best of our knowledge, we are the first to show that a well-trained deep learning system is able to recover the patient identity from chest X-ray data. We demonstrate this using the publicly available large-scale ChestX-ray14 dataset, a collection of 112,120 frontal-view chest X-ray images from 30,805 unique patients. Our verification system is able to identify whether two frontal chest X-ray images are from the same person with an AUC of 0.9940 and a classification accuracy of 95.55%. We further highlight that the proposed system is able to reveal the same person even ten and more years after the initial scan. When pursuing a retrieval approach, we observe an mAP@R of 0.9748 and a precision@1 of 0.9963. Based on this high identification rate, a potential attacker may leak patient-related information and additionally cross-reference images to obtain more information. Thus, there is a great risk of sensitive content falling into unauthorized hands or being disseminated against the will of the concerned patients. Especially during the COVID-19 pandemic MESHD, numerous chest X-ray datasets have been published to advance research. Therefore, such data may be vulnerable to potential attacks by deep learning-based re-identification algorithms.

    Modeling and forecasting Spread of COVID-19 MESHD epidemic in Iran until Sep 22, 2021, based on deep learning

    Authors: Jafar Abdollahi; Amir Jalili Irani; Babak Nouri-Moghaddam

    id:2103.08178v1 Date: 2021-03-15 Source: arXiv

    The recent global outbreak of covid-19 MESHD is affecting many countries around the world. Due to the growing number of newly infected individuals and the health-care system bottlenecks, it will be useful to predict the upcoming number of patients. This study aims to efficiently forecast the is used to estimate new cases, number of deaths MESHD, and number of recovered patients in Iran for 180 days, using the official dataset of the Iranian Ministry of Health and Medical Education and the impact of control measures on the spread of COVID-19 MESHD. Four different types of forecasting techniques, time series, and machine learning algorithms MESHD, are developed and the best performing method for the given case study is determined. Under the time series, we consider the four algorithms including Prophet, Long short-term memory, Autoregressive, Autoregressive Integrated Moving Average models. On comparing the different techniques, we found that deep learning methods yield better results than time series forecasting algorithms. More specifically, the least value of the error measures is observed in seasonal ANN and LSTM models. Our findings showed that if precautionary measures are taken seriously, the number of new cases and deaths will decrease MESHD, and the number of deaths in September 2021 will reach zero.

    Severity Quantification and Lesion Localization of COVID-19 MESHD on CXR using Vision Transformer

    Authors: Gwanghyun Kim; Sangjoon Park; Yujin Oh; Joon Beom Seo; Sang Min Lee; Jin Hwan Kim; Sungjun Moon; Jae-Kwang Lim; Jong Chul Ye

    id:2103.07062v1 Date: 2021-03-12 Source: arXiv

    Under the global pandemic of COVID-19 MESHD, building an automated framework that quantifies the severity of COVID-19 MESHD and localizes the relevant lesion on chest X-ray images has become increasingly important. Although pixel-level lesion severity labels, e.g. lesion segmentation, can be the most excellent target to build a robust model, collecting enough data with such labels is difficult due to time and labor-intensive annotation tasks MESHD. Instead, array-based severity labeling that assigns integer scores on six subdivisions of lungs can be an alternative choice enabling the quick labeling. Several groups proposed deep learning algorithms MESHD that quantify the severity of COVID-19 MESHD using the array-based COVID-19 MESHD labels and localize the lesions with explainability maps. To further improve the accuracy and interpretability, here we propose a novel Vision Transformer tailored for both quantification of the severity and clinically applicable localization of the COVID-19 MESHD related lesions. Our model is trained in a weakly-supervised manner to generate the full probability maps from weak array-based labels. Furthermore, a novel progressive self-training method enables us to build a model with a small labeled dataset. The quantitative and qualitative analysis on the external testset demonstrates that our method shows comparable performance with radiologists for both tasks with stability in a real-world application.

    OpenSAFELY: Risks of COVID-19 MESHD hospital admission and death for people with learning disabilities - a cohort study.

    Authors: Elizabeth Williamson; Helen I McDonald; Krishnan Bhaskaran; Alex J Walker; Sebastian Bacon; Simon Davy; Anna Schultze; Laurie Tomlinson; Chris Bates; Mary Ramsay; Helen J Curtis; Harriet Forbes; Kevin Wing; Caroline Minassian; John Tazare; Caroline E Morton; Emily Nightingale; Amir Mehrkar; Dave Evans; Peter Inglesby; Brian MacKenna; Jonathan Cockburn; Christopher T Rentsch; Rohini Mathur; Angel Wong; Rosalind M Eggo; William J Hulme; Richard Croker; John Parry; Frank Hester; Sam Harper; Ian Douglas; Stephen JW Evans; Liam Smeeth; Ben Goldacre; Hannah Kuper

    doi:10.1101/2021.03.08.21253112 Date: 2021-03-08 Source: medRxiv

    ObjectivesTo assess the association between learning disability and risk of hospitalisation and mortality from COVID-19 MESHD in England among adults and children. DesignWorking on behalf of NHS England MESHD, two cohort studies using patient-level data for >17 million people from primary care electronic health records were linked with death data from the Office for National Statistics and hospitalization data from NHS Secondary Uses Service using the OpenSAFELY platform. SettingGeneral practices in England which use TPP software. ParticipantsParticipants were males and females, aged up to 105 years, from two cohorts: (1) wave 1 HGNC, registered with a TPP practice as of 1st March 2020 and followed until 31st August, 2020; (2) wave 2 HGNC registered 1st September 2020 and followed until 31st December 2020 (for admissions) or 8th February 2021 (for deaths). The main exposure group was people included on a general practice learning disability register (LDR), with a subgroup of people classified as having profound or severe learning disability MESHD. We also identified patients with Down syndrome and cerebral palsy MESHD (whether or not on the learning disability register). Main outcome measures(i) COVID-19 MESHD related death, (ii) COVID-19 MESHD related hospitalisation. Non- COVID-19 MESHD related death MESHD was also explored. ResultsIn wave 1 HGNC, of 14,301,415 included individuals aged 16 and over, 90,095 (0.63%) were identified as being on the LDR. 30,173 COVID-related hospital admissions, 13,919 COVID-19 MESHD related deaths and 69,803 non-COVID deaths MESHD occurred; of which 538 (1.8%), 221 (1.6%) and 596 (0.85%) were among individuals on the LDR, respectively. In wave 2 HGNC, 27,611 COVID-related hospital admissions, 17,933 COVID-19 MESHD related deaths and 54,171 non-COVID deaths MESHD occurred; of which 383 (1.4%), 260 (1.4%) and 470 (0.87%) were among individuals on the LDR. Wave 1 HGNC hazard ratios for individuals on the LDR, adjusted for age, sex, ethnicity and geographical location, were 5.3 (95% confidence interval (CI) 4.9, 5.8) for COVID-19 MESHD related hospital admissions and 8.2 (95% CI: 7.1, 9.4) for COVID-19 MESHD related death. Wave 2 HGNC produced similar estimates. Associations were stronger among those classed as severe-profound and among those in residential care. Down syndrome and cerebral palsy MESHD were associated with increased hazard of both events in both waves; Down syndrome to a much greater extent. Hazards of non- COVID-19 MESHD related death followed similar patterns with weaker associations. ConclusionsPeople with learning disabilities MESHD have markedly increased risks of hospitalisation and mortality from COVID-19 MESHD. This raised risk is over and above that seen for non-COVID causes of death MESHD. Ensuring prompt access to Covid-19 MESHD testing and health care and consideration of prioritisation for COVID-19 MESHD vaccination and other targeted preventive measures are warranted.

    CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 MESHD Detection

    Authors: Abdul Waheed; Muskan Goyal; Deepak Gupta; Ashish Khanna; Fadi Al-Turjman; Placido Rogerio Pinheiro

    id:2103.05094v1 Date: 2021-03-08 Source: arXiv

    Coronavirus ( COVID-19 MESHD) is a viral disease MESHD caused by severe acute respiratory syndrome coronavirus 2 MESHD (SARS-CoV-2). The spread of COVID-19 MESHD seems to have a detrimental effect on the global economy and health. A positive chest X-ray of infected MESHD patients is a crucial step in the battle against COVID-19 MESHD. Early results suggest that abnormalities exist in chest X-rays of patients suggestive of COVID-19 MESHD. This has led to the introduction of a variety of deep learning systems MESHD and studies have shown that the accuracy of COVID-19 MESHD patient detection through the use of chest X-rays is strongly optimistic. Deep learning networks like convolutional neural networks (CNNs) need a substantial amount of training data. Because the outbreak is recent, it is difficult to gather a significant number of radiographic images in such a short time. Therefore, in this research, we present a method to generate synthetic chest X-ray (CXR) images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN. In addition, we demonstrate that the synthetic images produced from CovidGAN can be utilized to enhance the performance of CNN for COVID-19 MESHD detection. Classification using CNN alone yielded 85% accuracy. By adding synthetic images produced by CovidGAN, the accuracy increased to 95%. We hope this method will speed up COVID-19 MESHD detection and lead to more robust systems of radiology.

The ZB MED preprint Viewer preVIEW includes all COVID-19 related preprints from medRxiv and bioRxiv, from ChemRxiv, from ResearchSquare, from arXiv and from Preprints.org and is updated on a daily basis (7am CET/CEST).
The web page can also be accessed via API.



MeSH Disease
HGNC Genes
SARS-CoV-2 Proteins

Export subcorpus as...

This service is developed in the project nfdi4health task force covid-19 which is a part of nfdi4health.

nfdi4health is one of the funded consortia of the National Research Data Infrastructure programme of the DFG.