cord-006683-7rsmbk3j	2011	The primary lesions assessed at CXR and chest CT were [13] and recent publications [10, 11] describing the main radiological pulmonary manifestations of A/H1N1 infl uenza: interstitial reticulation (RI; linear opacities of the central and peripheral interstitium appearing as radio-opaque lines on CXR and hyperdensities on CT), nodules (N; well-or illdefi ned, rounded opacities/hyperdensities, with maximum diameter of 3 cm.), ground-glass opacities (GGO; heterogeneous increase in parenchymal opacity with preservation of bronchial and vascular margins), consolidation (CONS; homogenously increased parenchymal attenuation that obscures the margins of the bronchial and vessels walls). To date, few studies addressing chest imaging in patients affected by infl uenza A/H1N1 have been published [10] [11] [12] , and the presentation of H1N1 virus pneumonia on both CXR and chest CT seems to refl ect the general features of viral pneumonia [23] . One study [11] reported on the main CXR and chest CT fi ndings in seven patients affected by infl uenza A/H1N1: bilateral GGO, more frequently associated with focal or multifocal areas of consolidation.
cord-006708-nionk55w	2019	MATERIALS AND METHODS: A total of 165 patients who were diagnosed with CCHF and examined through chest X-ray (CXR) due to respiratory symptoms at their first examination and/or during their hospitalization were included in this study. CONCLUSION: According to the results of our study, it can be suggested that radiological examination in lungs should be performed primarily with CXR and pulmonary involvement (pleural effusion and consolidation) affects survival in CCHF negatively. As a result of CXR findings obtained based on the first examination and clinical follow-up within the first 5 days, consolidation in 74 patients (44.8%), pleural effusion in 64 patients (39.8%), ground glass opacity in 49 patients (29.7%), and atelectasis in 30 patients (18.2%) were detected (Fig. 2) . In a study performed on dengue hemorrhagic fever, a total of 468 CXR taken from 363 patients were examined and parenchymal infiltration and pleural effusion were observed in more than half of the patients on the third day of follow-up.
cord-013065-oj0wsstz	2020	title: Procalcitonin and lung ultrasound algorithm to diagnose severe pneumonia in critical paediatric patients (PROLUSP study). Besides this, the use of biomarkers such as procalcitonin (PCT) has become more widespread during the past 10 years, helping clinicians diagnose bacterial etiology, especially in patients who have only had a fever for a few hours or those admitted to intensive care units [16] [17] [18] [19] [20] . Therefore, we propose this clinical trial, based on combining LUS and PCT in an algorithm with the aim to improve quality of care in children with pneumonia in a PICU. The use procalcitonin and lung ultrasound algorithm will help us diagnose bacterial pneumonia accurately and prescribe the correct antibiotic treatment. This clinical trial is focused on improving the quality of care for paediatric patients with suspected bacterial pneumonia. This clinical trial is focused on improving the quality of care for paediatric patients with suspected bacterial pneumonia.
cord-015352-2d02eq3y	2017	Lapierre; Montreal/CA Summary: Objectives: To review the classification of visceroatrial situs To describe the associated cardiac and non-cardiac anomalies To illustrate typical findings in fetuses, neonates and children To discuss the surgical consideration and the long-term follow-up in these patients Abstract: By definition, the type of situs is determined by the relationship between the atria and the adjacent organs. As is often the case, radiology in JIA is all about: knowing your clinicians (i.e. the pretest likelihood for disease) being technically eloquent (e.g. using high-resolution US probes, not delaying post-contrast MRI acquisitions) knowing what is normal (e.g. normal undulations in the articular surface, focal bone marrow signal variation) not being dogmatic about individual observations or measurements interpreting your findings in a clinical context The lecture will demonstrate similarities and differences among joints and modalities in children with variable-severity JIA.
cord-018027-goxdiyv3	2014	Clinically, lungs are affected in 30 % of febrile neutropenic patients and allogeneic hematopoietic stem cell transplant (aSCT) recipients, paranasal sinuses in 3 % of neutropenic patients, and 30 % in the aSCT setting (concomitant to pneumonia), while the gastrointestinal tract, liver, spleen, central nervous system, and kidneys are less frequently involved [ 4 ] . While CXR provides relevant clinical information concerning central venous catheters (CVC), pleural effusion, and pulmonary congestion [ 17 ] , it fails to enable early detection or exclusion of pneumonia, which is a major task in immunocompromised hosts. For use in the context of clinical and epidemiological research in neutropenic patients, standards for the interpretation of radiological fi ndings in invasive fungal infections have been elaborated [ 10 , 51 ] ; newly emerged "typical" CT patterns (dense, well-circumscribed lesions with or without a halo sign, air-crescent sign) are classifi ed as a clinical criterion for fungal pneumonia Figs.
cord-028786-400vglzm	2020	We propose a Computer-Aided Detection model using Deep Convolutional Neural Networks to automatically detect TB from Montgomery County (MC) Tuberculosis radiographs. As a result, to profer solution to the issue of limited or lack of expert radiologist and misdiagnosis of CXR, we propose a Deep Convolutional Neural Networks (CNN) model that will automatically diagnose large numbers of CXR at a time for TB manifestation in developing regions where TB is most prevalent. A model based on Deep Convolutional Neural Network (CNN) structure has been proposed in this work for the detection and classification of Tuberculosis. Presented in this paper is a model that aids early detection of Tuberculosis using CNN structure to automatically extract distinctive features from chest radiographs and classify them into normal and abnormal categories. TX-CNN: detecting tuberculosis in chest X-ray images using convolutional neural network
cord-103840-2diao7zh	2020	The World Health Organization (WHO) recommends the use of chest X-ray (CXR) as a mass screening tool in TB prevalence surveys and active case finding activities to identify patients eligible for bacteriological investigation. We systematically searched MEDLINE, CINHAL, Global Health and Google scholar databases from 1940-2019 to identify studies that described the prevalence of non-TB CXR findings during TB prevalence surveys or mass screening activities. The main finding from this analysis of X-ray images from the 2016 Kenya TB prevalence survey was that the use of CXR for TB population-based studies identified a large number of patients with abnormalities, including noncommunicable diseases (NCDs) such as cardiovascular abnormalities and chronic respiratory diseases that require clinical attention. Clinically relevant cardiac and chronic pulmonary diseases accounted for 66% of the non-TB abnormalities in our setting.To our knowledge, this is the first study in sub-Saharan Africa to characterise and quantify non-TB CXR findings among participants who underwent mass screening as part of a population-based TB prevalence survey.
cord-127759-wpqdtdjs	2020	In this study, we design a novel multi-feature convolutional neural network (CNN) architecture for multi-class improved classification of COVID-19 from CXR images. In this work we show how local phase CXR features based image enhancement improves the accuracy of CNN architectures for COVID-19 diagnosis. Our proposed method is designed for processing CXR images and consists of two main stages as illustrated in Figure 1 : 1-We enhance the CXR images (CXR(x, y)) using local phase-based image processing method in order to obtain a multi-feature CXR image (M F (x, y)), and 2-we classify CXR(x, y) by designing a deep learning approach where multi feature CXR images (M F (x, y)), together with original CXR data (CXR(x, y)), is used for improving the classification performance. Our proposed multi-feature CNN architectures were trained on a large dataset in terms of the number of COVID-19 CXR scans and have achieved improved classification accuracy across all classes.
cord-157444-huvnyali	2020	In this work, we evaluated the DLS''s performance on 6 independent test sets consisting of different patient populations, spanning three countries, and with two unseen diseases (TB and COVID-19). However, as other acute diseases may share a similar clinical presentation, many cases negative for COVID-19 exhibited abnormal CXR findings that likely triggered the DLS ( Figure 5, Supplementary Figure 5 ). Finally, to facilitate the continued development of AI models for chest radiography, we are releasing our abnormal versus normal labels from 3 radiologists (2430 labels on 810 images) for the publicly-available CXR-14 test set. Two datasets were used to evaluate the DLS''s performance in distinguishing normal and abnormal findings in a general abnormality detection setting. To compare the DLS with radiologists in classifying CXRs as normal versus abnormal, additional radiologists reviewed all test images without referencing additional clinical or patient data.
cord-167889-um3djluz	2020	The progress of CT image inspection based on AI usually includes the following steps: Region Of Interest (ROI) segmentation, lung tissue feature extraction, candidate infection region detection, and COVID-19 classification. Data sources Methods Country/region Huang [82] Yang [231] , WHO [216] CNN, LSTM, MLP, GRU China Hu [80, 81] The Paper [148] , WHO [216] MAE, clustering China Yang [233] Baidu [16] SEIR, LSTM China Fong [51, 52] NHC [139] SVM, PNN China Ai [3] WHO [54, 216] ANFIS, FPA China, USA Rizk [168] WHO [216] ISACL-MFNN USA, Italy, Spain Giuliani [62] Italy [144] EMTMGL Italy Ayyoubzadeh [14] Worldometer [218] , Google [201] LR, LSTM Iran Marini [129, 130] Swiss population Enerpol Switzerland Lai [110] IATA [126] , Worldpop [219] ML Global Punn [155] JHU CSSE [49] SVR, PR, DNN, LSTM, RNN Predicting commercially available antiviral drugs that may act on the novel coronavirus (sars-cov-2) through a drug-target interaction deep learning model
cord-238881-tupom7fb	2020	Although the recent international joint effort on making the availability of all sorts of open data, the public collection of CXR images is still relatively small for reliably training a deep neural network (DNN) to carry out COVID-19 prediction. Although the recent international joint effort on making the availability of all sorts of open data, the public collection of CXR images is still relatively small for reliably training a deep neural network (DNN) to carry out COVID-19 prediction. Our approach leverages a large CXR image dataset of non-COVID-19 pneumonia to generalize the original well-trained classification model via a cascaded learning scheme. Our approach leverages a large CXR image dataset of non-COVID-19 pneumonia to generalize the original well-trained classification model via a cascaded learning scheme. To extend the model, we collaborate with several medical research centers in Taiwan to collect chest x-ray images from COVID-19 patients at various stages, and re-train the pneumonia classification system using a three-stage cascaded learning strategy.
cord-266672-t85wd0xq	2020	title: Performance of Radiologists in the Evaluation of the Chest Radiography with the Use of a "new software score" in Coronavirus Disease 2019 Pneumonia Suspected Patients OBJECTIVES: The purpose of this study is to assess the performance of radiologists using a new software called "COVID-19 score" when performing chest radiography on patients potentially infected by coronavirus disease 2019 (COVID-19) pneumonia. MATERIAL AND METHODS: From February–April 2020, 14 radiologists retrospectively evaluated a pool of 312 chest X-ray exams to test a new software function for lung imaging analysis based on radiological features and graded on a three-point scale. To evaluate a new tool called "COVID-19 score" made available to radiologists for lung imaging analysis, we retrospectively included in the study patients who underwent at least two consecutive chest X-rays for a total of 312 exams. In this study, we tested a new software application called "COVID-19 score" that can be used in the reporting of chest X-ray imaging in patients suspected COVID-19, based on radiological semantic features.
cord-269014-ck27fm58	2020	title: Enhanced Private Sector Engagement for Tuberculosis Diagnosis and Reporting through an Intermediary Agency in Ho Chi Minh City, Viet Nam We tabulated descriptive statistics for private provider engagement and participation, the number and proportion of referred people progressing through the study''s TB care cascade by intervention district and the private TB treatment reported to our study. The study identified 1203 people with TB of whom 7.6% (91/1203) were referred and linked to care with the NTP (Figure 2 ), while 92.4% (1112/1203) consisted of private TB treatment reports and remained un-notified (Table 3) . Table 4 and Figure 3 summarize changes in the NTP''s TB case notifications in the study''s intervention area and present the modeled impact of including private TB treatment on official notification statistics. Our pilot study showed that the PPIA model was effective in engaging a large number of private providers in the Vietnamese urban setting to contribute to TB care and prevention efforts.
cord-275974-uqd30v7b	2020	In summary, following are the contributions of our work: (a) A meta learning framework called MetaCOVID based on Siamese neural network is presented for diagnosis of COVID-19 patients from chest X-ray images, (b) The proposed work focuses on the benefit of using contrastive loss and n-shot learning in framework design, (c) A fine-tuned pre-trained VGG encoder is used to capture unbiased feature representations to improve feature embeddings from the input images, (d) The COVID-19 diagnosis problem is formulated as a k-way, n-shot classification problem where k and n represent the number of class labels and data samples used for model training, (e) Performance evaluation is presented to demonstrate the efficacy of the proposed framework with a limited dataset. In contrast, we have proposed an end-to-end trainable nshot deep meta learning framework based on Siamese neural network to classify COVID-19 cases with limited training CXR images.
cord-282198-ugmv9om1	2020	Our primary objective was to determine whether lung ultrasound (LUS) B-lines, when excluding patients with alternative etiologies for B-lines, are more sensitive for the associated diagnosis of COVID-19 than CXR. METHODS: This was a retrospective cohort study of all patients who presented to a single, academic emergency department in the United States between March 20 and April 6, 2020, and received LUS, CXR, and viral testing for COVID-19 as part of their diagnostic evaluation. Lung ultrasound (LUS) has been shown to outperform chest radiograph (CXR) in its ability to detect abnormalities with non-coronavirus disease 2019 (COVID-19) pulmonary infections. This was a retrospective, observational, cohort study of patients undergoing COVID-19 testing (based on real-time reverse transcriptase-polymerase chain reaction [RT-PCR] of nasopharyngeal sampling performed on an assay developed by the Center for Regenerative Medicine at Boston University, operating under an Emergency Use Authorization], who also had both diagnostic LUS and CXR for the evaluation of COVID-19 in the emergency department (ED).
cord-292341-uo54ghf3	2020	Univariate logistic regression analysis of factors associated with level of care revealed that sex, age, smoking history, FiO2, pO2 in room air at admission, bacterial co-infections developed during hospitalization, CVDs, metabolic and oncologic diseases and chest X-ray global score had significant positive association with a higher level of care in the entire study population (Table 3) . Univariate logistic regression analysis of factors associated with level of care revealed that sex, age, smoking history, FiO2, pO2 in room air at admission, bacterial co-infections developed during hospitalization, CVDs, metabolic and oncologic diseases and chest X-ray global score had significant positive association with a higher level of care in the entire study population (Table 3) . This is a retrospective analysis of clinical features and radiographic severity scores in patients with COVID-19 and how these parameters on hospital admission correlate with different levels of medical care (i.e., HIMC vs.
cord-294557-4h0sybiy	2020	Objectives include to: i) outline pathophysiology and basic epidemiology useful for radiographers, ii) discuss the role of medical imaging in the diagnosis of Covid-19, iii) summarise national and international guidelines of imaging Covid-19, iv) present main clinical and imaging findings and v) summarise current safety recommendations for medical imaging practice. CXR imaging of suspected or confirmed Covid-19 cases should be performed with portable equipment within specifically designated isolated rooms for eliminating the risks of cross-infection within the Radiology department. After the outbreak of the Covid-19 pandemic, many professional bodies and learned societies have been quick to issue official guidelines on how medical imaging should optimally be performed for early diagnosis and related management of these patients, but also how staff should be protected from cross-infection. Chest radiographic and CT findings of the 2019 novel Coronavirus disease (COVID-19): analysis of nine patients treated in Korea Imaging and clinical features of patients with 2019 novel coronavirus SARS-CoV-2: a systematic review and meta-analysis
cord-296208-uy1r6lt2	2020	We focus on three specific use-cases for which AI systems can be built: early disease detection, management in a hospital setting, and building patient-specific predictive models that require the combination of imaging with additional clinical data. Many studies have emerged in the last several months from the medical imaging community with many research groups as well as companies introducing deep learning based solutions to tackle the various tasks: mostly in detection of the disease (vs normal), and more recently also for staging disease severity. In Section 2 of this paper we focus on three specific use-cases for which AI systems can be built: detection, patient management, and predictive models in which the imaging is combined with additional clinical features. Rapid ai development cycle for the coronavirus (covid-19) pandemic: Initial results for automated detection and patient monitoring using deep learning ct image analysis
cord-297198-dneycnyr	2020	In answering Question 2, the authors comment that "CXR may be abnormal in the majority of COVID-19 cases", incorrectly inferring that the study of Huang et al. in The Lancet does mistakenly state that they found "bilateral involvement of chest radiographs" in 40/41 patients in Table 2 of their results; however, from reading the main text, it is clear that the imaging method they are referring to is actually chest computed tomography (CT), not chest radiography (CXR): "On admission, abnormalities in chest CT images were detected among all patients. The study of Guan et al., also cited by Nair et al., reported CXR abnormalities in only 162/274 (59.1%) of COVID-19 patients. reported abnormal CXR in 44/64 (68.8%) of COVID-19 patients on presentation 4 ; however, it is important to note that both of these studies included hospitalised patients, representing individuals with more severe illness. reported CXR findings of 636 COVID-19 patients presenting to urgent-care centres and found that only 168 (26.4%) were reported originally as abnormal.
cord-297396-r1p7xn3a	2020	OBJECTIVES: To develop:(1) two validated risk prediction models for COVID-19 positivity using readily available parameters in a general hospital setting; (2) nomograms and probabilities to allow clinical utilisation.  Developed two simple-to use nomograms for identifying COVID-19 positive patients  Probabilities are provided to allow healthcare leaders to decide suitable cut-offs  Variables are age, white cell count, chest x-ray appearances and contact history  Model variables are easily available in the general hospital setting. To develop: (1) two validated risk prediction models for COVID-19 positivity using readily available parameters in a general hospital setting; (2) nomograms and probabilities to allow clinical utilisation. Thus, a COVID-19 prediction model based on clinical, laboratory and radiological findings which presents the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) would allow public healthcare systems to decide a suitable strategy on prioritizing tests when such RT-PCR availability is constrained.
cord-303483-wendrxee	2020	Thoracic imaging with chest radiography (CXR) and computed tomography (CT) are key tools for pulmonary disease diagnosis and management, but their role in the management of COVID-19 has not been considered within the multivariable context of the severity of respiratory disease, pre-test probability, risk factors for disease progression, and critical resource constraints. Thoracic imaging with chest radiography (CXR) and computed tomography (CT) are key tools for pulmonary disease diagnosis and management, but their role in the management of COVID-19 has not been considered within the multivariable context of the severity of respiratory disease, pre-test probability, risk factors for disease progression, and critical resource constraints. The severity of respiratory disease and pre-test probability of COVID-19 infection are specified for each scenario, with additional key considerations including the presence of risk factors for disease progression, evidence of disease progression, and the presence of significant critical resource constraints ( Table 1) .
cord-310228-bqpvykce	2020	We utilized publicly available CXR images for patients with COVID-19 pneumonia, pneumonia from other etiologies, and normal CXRs as a dataset to train Microsoft CustomVision. We then validated the program using CXRs of patients from our institution with confirmed COVID-19 diagnoses along with non-COVID-19 pneumonia and normal CXRs. Our model performed with 100% sensitivity, 95% specificity, 97% accuracy, 91% positive predictive value, and 100% negative predictive value. We first trained the Microsoft CustomVision automated image classification and object detection system to differentiate cases of COVID-19 from pneumonia from other etiologies as well as normal lung CXRs. We then tested our model against known patients from our medical center. We have utilized a readily available, commercial platform to demonstrate the potential of AI to assist in the successful diagnosis of COVID-19 pneumonia on CXR images.
cord-312251-t6omrr07	2020	OBJECTIVE: To analyze the most frequent radiographic features of COVID-19 pneumonia and assess the effectiveness of chest X-ray (CXR) in detecting pulmonary alterations. Alteration''s type (reticular/ground-glass opacity (GGO)/consolidation) and distribution (bilateral/unilateral, upper/middle/lower fields, peripheral/central) were noted. CONCLUSIONS: The most frequent lesions in COVID-19 patients were GGO (intermediate/late phase) and reticular alteration (early phase) while consolidation gradually increased over time. Our study aimed to evaluate the percentage of abnormal chest radiographs at different time intervals from the onset of symptoms and to identify the type and distribution of radiographic alterations and their frequency at different times throughout the disease course of COVID-19 pneumonia. Chest CT showed high sensitivity in detecting GGO, which is considered a typical finding in COVID-19 pneumonia and, in some cases, may be the only alteration present in the early phases of the disease [3, 16] .
cord-327257-doygrgrc	2020	title: Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs This study employed deep-learning convolutional neural networks to stage lung disease severity of Coronavirus Disease 2019 (COVID-19) infection on portable chest x-ray (CXR) with radiologist score of disease severity as ground truth. Deep-learning convolutional neural network (CNN) was used to predict lung disease severity scores. In conclusion, deep-learning CNN accurately stages disease severity on portable chest x-ray of COVID-19 lung infection. This study tested the hypothesis that deep-learning convolutional neural networks accurately stage disease severity on portable chest x-rays using radiologists'' severity scores as ground truths associated with COVID-19 lung infection. Deep-learning AI, specifically a convolutional neural network, is well suited to extract information from CXR and stage disease severity by training using chest radiologist determination of disease severity scores. In conclusion, deep-learning convolutional neural networks accurately stage lung disease severity on portable chest x-rays associated with COVID-19 lung infection.
cord-331891-a6b1xanm	2020	MATERIALS AND METHODS: This is a retrospective study involving patients with clinical-epidemiological suspect of COVID-19 infection, who performed CXRs at the emergency department (ED) of our University Hospital from March 1 to March 31, 2020. Radiological evaluation of patients with clinical-epidemiological suspect of COVID-19 is mandatory, especially in the emergency department (ED) while waiting for RT-PCR results, in order to have a rapid evaluation of thoracic involvement. Therefore, the purpose of our study is to better understand the main radiographic features of COVID-19 pneumonia, by describing the main CXR findings in a selected cohort of patients, also correlating the radiological appearance with RT-PCR examination and patients outcome (intended as discharged or hospitalized into a medicine department or intensive care unit). An independent and retrospective review of each CXR was performed by two thoracic radiologists in order to define the number of radiological suspects of COVID-19 infection; after this, they defined the predominant pattern of COVID-19 pneumonia presentation in patients with a positive RT-PCR.
cord-334495-7y1la856	2020	From a clinical point of view, cardiac involvement during COVID-19 may present a wide spectrum of severity ranging from subclinical myocardial injury to well-defined clinical entities (myocarditis, myocardial infarction, pulmonary embolism and heart failure), whose incidence and prognostic implications are currently largely unknown due to a significant lack of imaging data. The use of integrated heart and lung multimodality imaging plays a central role in different clinical settings and is essential in diagnosis, risk stratification and management of COVID-19 patients. In this context, the use of multiple diagnostic imaging techniques may apply to both heart and lung to provide an integrated assessment of cardiac and pulmonary function and to refine diagnosis, risk stratification and management of COVID-19 patients. patients not requiring ICU, when clinical presentation and biomarker alterations suggest acute-onset myocardial inflammation, if the diagnosis is likely to impact on management, CMR may be considered to confirm acute myocarditis, after exclusion of alternative relevant clinical conditions, including ACS and HF, by means of other rapidly available imaging modalities (i.e. cardiac CT scan or TTE).
cord-336843-c0sr3six	2017	title: Improving early diagnosis of pulmonary infections in patients with febrile neutropenia using low-dose chest computed tomography We performed a prospective study in patients with chemotherapy induced febrile neutropenia to investigate the diagnostic value of low-dose computed tomography compared to standard chest radiography. Two studies comparing LDCT to CXR in patients with persistent febrile neutropenia demonstrated an increased detection of pulmonary abnormalities. The diagnosis of possible IFD in the patient with a negative LDCT scan was based on abnormalities on HRCT made on day 4 of fever. We conducted a prospective study to evaluate whether pulmonary focus detection would improve using a LDCT scan instead of CXR on the first day of febrile neutropenia. [3] In a retrospective study 1083 adult SCT patients were evaluated, but in none of the 242 CXRs performed in asymptomatic patients with febrile neutropenia pulmonary abnormalities indicative of infection were detected.
cord-337507-cqbbrnku	2020	METHODS: In this retrospective observational study we enrolled all patients presenting to the emergency department of a Milan-based university hospital from February 24th to April 8th 2020 who underwent nasopharyngeal swab for reverse transcriptase-polymerase chain reaction (RT-PCR) and anteroposterior bedside CXR within 12 h. The two largest by far are a retrospective review by a single radiologist of 518 CXRs acquired during the first phase of the pandemic peak (from March 1 st to March 15 th )with a resulting overall sensitivity of 57% [22] and a study coming from our group and performed on 535 patients [23] . Real-world data from this study, albeit conducted in a highprevalence region and during a SARS-CoV-2 pandemic peak, seem to provide a better scenario, in which radiologists with less than 10 years of experience matched the 89.0% sensitivity attained by radiologists with more than 10 years of experience, with similar disease prevalence in the CXR subsets read by each group (73% versus 77%, respectively).
cord-345528-rk16pt0i	2020	This tool delivers a rapid screening test by analyzing the X-ray Chest Radiograph scans via Artificial Intelligence (AI) and it also evaluates the mortality rate of patients with the synthesis of the patient history with the machine learning methods. A rapid analysis for the Chest X-ray (CXR) scans, CT, Infection Rate or Mortality Rate with the machine learning methods are some of the helpful tools and researchers are trying to build such tools for pre-screening COVID-19. This study defines a deployed environment 1 for rapid evaluation of the mortality rate and CXR scans via machine learning tools. The evaluation platform has two outputs after screening the group of patients as the prediction about the risk in COVID-19 via CXR and the mortality rate. . https://doi.org/10.1101/2020.05.04.20090779 doi: medRxiv preprint mantisCOVID cannot catch COVID-19 patient via AI elimination from CXR, the physician can change approaching style to the patient via evaluating the mortality rate.
cord-346942-88l03lf0	2020	The purpose of this study was to assess the diagnostic and prognostic value of chest radiographs (CXR) for coronavirus disease 2019 (COVID-19) at presentation. 13 Data on the strengths and weaknesses of chest radiography for the diagnosis of COVID-19 are important, as CXRs are the most commonly used triage imaging tool in any patient presenting with respiratory symptoms. We identified our study population by extracting severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) RT-PCR test results (positive or negative) of nasopharyngeal swabs from all consecutive patients older than 18 years analyzed at our hospital''s laboratory from the ED from March 6-31, 2020, who had a CXR at presentation (within 24 hours of the first RT-PCR). When the RALE score was evaluated as a prognostic indicator within the COVID-19 patient group, both readers had statistically significant discriminatory accuracy for severe disease and poor outcomes (Table 3) .
cord-347691-ia2i8svg	2020	The purpose of this comprehensive review is to understand the diagnostic capabilities and limitations of chest X-ray (CXR) and high-resolution computed tomography (HRCT) in defining the common imaging features of COVID-19 pneumonia and correlating them with the underlying pathogenic mechanisms. As suggested in the recently published WHO (World Health Organization) advice guide for the diagnosis and management of COVID-19, chest imaging should be used for diagnostic purpose in symptomatic patients if RT-PCR is not available or its results are delayed, or in case of negative result in the presence of a high clinical suspicion of COVID-19 [11] . Apart from recognizing COVID-19 pneumonia features, imaging -especially CT -may reveal possible alternative diagnoses (e.g. pulmonary oedema, alveolar haemorrhage, other type of lung infections) that justify patient''s respiratory symptoms [25, 26] .
cord-350636-ufwfitue	2020	We aimed to investigate patterns of ChUS in COVID-19 patients and compare the findings with results from chest X-ray (CRX). We aimed to investigate patterns of ChUS in COVID-19 patients and compare the findings with results from chest X-ray (CRX). Besides pathological B-lines and subpleural consolidations, pleural line abnormality (89 %; n = 16/18) was the third most common feature in patients with respiratory manifestations of COVID-19 detected by ChUS. Besides pathological B-lines and subpleural consolidations, pleural line abnormality (89 %; n = 16/18) was the third most common feature in patients with respiratory manifestations of COVID-19 detected by ChUS. A Clinical Study of Noninvasive Assessment of Lung Lesions in Patients with Coronavirus Disease-19 (COVID-19) by Bedside Ultrasound
cord-355218-eici4eit	2020	Recently, with the release of publicly available datasets of corona positive patients comprising of computed tomography (CT) and chest X-ray (CXR) imaging; scientists, researchers and healthcare experts are contributing for faster and automated diagnosis of COVID-19 by identifying pulmonary infections using deep learning approaches to achieve better cure and treatment. Following from this context, this article presents the random oversampling and weighted class loss function approach for unbiased fine-tuned learning (transfer learning) in various state-of-the-art deep learning approaches such as baseline ResNet, Inception-v3, Inception ResNet-v2, DenseNet169, and NASNetLarge to perform binary classification (as normal and COVID-19 cases) and also multi-class classification (as COVID-19, pneumonia, and normal case) of posteroanterior CXR images. [31] proposed a deep convolutional neural network based automatic prediction model of COVID-19 with the help of pre-trained transfer models using CXR images. Detection of coronavirus (covid-19) associated pneumonia based on generative adversarial networks and a fine-tuned deep transfer learning model using chest x-ray dataset