(searched for: Covid 19 Chest Imaging)
Journal of Clinical Medicine, Volume 9; doi:10.3390/jcm9093014
The sensitivity of reverse transcriptase polymerase chain reaction (RT-PCR) has been questioned due to negative results in some patients who were strongly suspected of having coronavirus disease 2019 (COVID-19). The aim of our study was to analyze the prognosis of infected patients with initial negative RT-PCR in the emergency department (ED) during the COVID-19 outbreak. This study included two cohorts of adult inpatients admitted into the ED. All patients who were suspected to be infected with SARS-CoV-2 and who underwent a typical chest CT imaging were included. Thus, we studied two distinct cohorts: patients with positive RT-PCR (PCR+) and those with negative initial RT-PCR (PCR–). The data were analyzed using Bayesian methods. We included 66 patients in the PCR– group and 198 in the PCR+ group. The baseline characteristics did not differ except in terms of a proportion of lower chronic respiratory disease in the PCR– group. We noted a less severe clinical presentation in the PCR– group (lower respiratory rate, lower oxygen need and mechanical ventilation requirement). Hospital mortality (9.1% vs. 9.6%) did not differ between the two groups. Despite an initially less serious clinical presentation, the mortality of patients infected by SARS-CoV-2 with a negative RT-PCR did not differ from those with positive RT-PCR.
Symmetry, Volume 12; doi:10.3390/sym12091526
The limitations and high false-negative rates (30%) of COVID-19 test kits have been a prominent challenge during the 2020 coronavirus pandemic. Manufacturing those kits and performing the tests require extensive resources and time. Recent studies show that radiological images like chest X-rays can offer a more efficient solution and faster initial screening of COVID-19 patients. In this study, we develop a COVID-19 diagnosis model using Multilayer Perceptron and Convolutional Neural Network (MLP-CNN) for mixed-data (numerical/categorical and image data). The model predicts and differentiates between COVID-19 and non-COVID-19 patients, such that early diagnosis of the virus can be initiated, leading to timely isolation and treatments to stop further spread of the disease. We also explore the benefits of using numerical/categorical data in association with chest X-ray images for screening COVID-19 patients considering both balanced and imbalanced datasets. Three different optimization algorithms are used and tested:adaptive learning rate optimization algorithm (Adam), stochastic gradient descent (Sgd), and root mean square propagation (Rmsprop). Preliminary computational results show that, on a balanced dataset, a model trained with Adam can distinguish between COVID-19 and non-COVID-19 patients with a higher accuracy of 96.3%. On the imbalanced dataset, the model trained with Rmsprop outperformed all other models by achieving an accuracy of 95.38%. Additionally, our proposed model outperformed selected existing deep learning models (considering only chest X-ray or CT scan images) by producing an overall average accuracy of 94.6% ± 3.42%.
Journal of Clinical Medicine, Volume 9; doi:10.3390/jcm9092990
Coronavirus disease 2019 (COVID-19) has rapidly become a global pandemic with lung disease representing the main cause of morbidity and mortality. Conventional chest-X ray (CXR) and ultrasound (US) are valuable instruments to assess the extent of lung involvement. We investigated the relationship between CXR scores on admission and the level of medical care required in patients with COVID-19. Further, we assessed the CXR-US correlation to explore the role of ultrasound in monitoring the course of COVID-19 pneumonia. Clinical features and CXR scores were obtained at admission and correlated with the level of intensity of care required [high- (HIMC) versus low-intensity medical care (LIMC)]. In a subgroup of patients, US findings were correlated with clinical and radiographic parameters. On hospital admission, CXR global score was higher in HIMCs compared to LIMC. Smoking history, pO2 on admission, cardiovascular and oncologic diseases were independent predictors of HIMC. The US score was positively correlated with FiO2 while the correlation with CXR global score only trended towards significance. Our study identifies clinical and radiographic features that strongly correlate with higher levels of medical care. The role of lung ultrasound in this setting remains undetermined and needs to be explored in larger prospective studies.
European Radiology pp 1-10; doi:10.1007/s00330-020-07268-9
To determine CT’s role in the early detection of COVID-19 infection and serial CT changes in the disease course in patients with COVID-19 pneumonia. From January 21 to February 18, 2020, all of the patients who were suspected of novel coronavirus infection and verified by RT-PCR tests were retrospectively enrolled in our study. All of the patients underwent serial RT-PCR tests and serial CT imaging. The temporal relationship between the serial RT-PCR results (negative conversion to positive, positive to negative) and serial CT imaging was investigated, and serial CT changes were evaluated. A total of 155 patients with confirmed COVID-19 pneumonia were evaluated. Chest CT detection time of COVID-19 pneumonia was 2.61 days earlier than RT-PCR test (p = 0.000). The lung CT improvement time was significantly shorter than that of RT-PCR conversion to negative (p = 0.000). Three stages were identified from the onset of the initial symptoms: stage 1 (0–3 days), stage 2 (4–7 days), and stage 3 (8–14 days and later). Ground glass opacity (GGO) was predominant in stage 1, then consolidation and crazy paving signs were dramatically increased in stage 2. In stage 3, fibrotic lesions were rapidly increased. There were significant differences in the main CT features (p = 0.000), number of lobes involved (p = 0.001), and lesion distribution (p = 0.000) among the different stages. Chest CT detected COVID-19 pneumonia earlier than the RT-PCR results and can be used to monitor disease course. Combining imaging features with epidemiology history and clinical information could facilitate the early diagnosis of COVID-19 pneumonia. • The chest CT detection time of COVID-19 pneumonia was 2.61 days earlier than that of an initial RT-PCR positive result (t = − 7.31, p = 0.000). • The lung CT improvement time was significantly shorter than that of RT-PCR conversion to negative (t = − 4.72, p = 0.000). • At the early stage (0–3 days), the CT features of COVID-19 were predominantly GGO and small-vessel thickening; at stage 2 (4–7 days), GGO evolved to consolidation and crazy paving signs. At stage 3 (8–14 days and later), fibrotic lesions significantly increased, accompanied by consolidation, GGO, and crazy paving signs.
Published: 15 September 2020
Frontiers in Cellular and Infection Microbiology, Volume 10; doi:10.3389/fcimb.2020.548582
Objective: The present study aimed at investigating the clinical risk factors for COVID-19 patients developing from moderate condition to severe condition, and providing reference for early intervention and prognosis. Methods: We collected the clinical data of 24 patients with moderate-to-severe COVID-19 who were admitted to the isolation ward of the First Affiliated Hospital of Bengbu Medical College from January, 2020 to February 20, 2020, and evaluated the data of clinical characteristics, blood test results, inflammatory index, chest CT imaging characteristics, and antiviral treatment, comparing this with the clinical data of 41 patients with moderate condition in the same period. From this comparison we thus summarized the current knowledge of potential risk factors for COVID-19 patients developing from moderate to severe condition. Results: (1) Clinical characteristics: The moderate-to-severe group and the moderate group in terms of combined common underlying diseases and respiratory frequency showed significant difference statistically (t-value were 13.32, 6.17, respectively, P < 0.05), while no significant difference between the two groups in gender, age, or clinical symptoms was statistically observed(P > 0.05). (2) Analysis of blood test results: The lymphocyte count and plasma albumin of the moderate-to-severe group were significantly lower than those of the moderate group (t-values were 4.16, 4.11, respectively, P < 0.05), and the blood glucose and urea of the moderate-to-severe group were significantly higher than those of the moderate group (t-value were 3.27, 4.19, respectively, P < 0.05). However, there was no significant difference in terms of white blood cell count (WBC), platelet count (PLT), and glutamic-pyruvic transaminase (GPT) (P > 0.05). (3) Comparison of inflammatory indicators: The level of IL-6 and CRP of the moderate-to-severe group were significantly higher than those of the moderate group (t-values were 2.84, 4.88, respectively, P < 0.05). (4) Imaging comparison: As for patients with moderate COVID-19, the imaging manifestations were the concurrence of ground-glass opacity, patchy shadow, and consolidation shadow in both lungs, diffuse ground-glass opacity in both lungs accompanied by air bronchogram, and large area consolidation of both lungs with pulmonary interstitial changes. The possibility for these patients to develop into severe condition increased, and the differences were statistically significant (t = 10.92, P < 0.05). (5) Clinical antiviral treatment: There was no statistically significant difference in the combination of two or three antiviral drugs between the two groups (χ2 = 0.05, P > 0.05). Conclusion: Current evidence suggested that the combination of common underlying diseases, respiratory frequency, lymphocyte count, blood glucose, albumin, urea level, inflammatory factors (CRP, IL-6), and imaging manifestations collectively contributed to the potential risk factors for the development of COVID-19 from moderate condition to severe condition. Particular attention should be paid to early detection and intervention during clinical work, which will be of vital significance to the ascent of the recovery rate as well as the reduction of mortality.
Published: 14 September 2020
BackgroundSudden exacerbations and respiratory failure are major causes of death in patients with severe coronavirus disease 2019(COVID-19) pneumonia, but indicators for the prediction and treatment of severe patients are still lacking.MethodsA retrospective analysis of 67 collected cases was conducted and included approximately 67 patients with COVID-19 pneumonia who were admitted to the Suzhou Fifth People’s Hospital from January 1, 2020 to February 8, 2020. The epidemiological, clinical and imaging characteristics as well as laboratory data of the 67 patients were analyzed.ResultsThe study found that fibrinogen(FIB) was increased in 45 (65.2%) patients, and when FIB reached a critical value of 4.805 g/L, the sensitivity and specificity、DA, helping to distinguish general and severe cases, were 100% and 14%、92.9%, respectively, which were significantly better than those for lymphocyte count and myoglobin. Chest CT images indicated that the cumulative number of lung lobes with lesions in severe patients was significantly higher than that in general patients (P
Informatics in Medicine Unlocked; doi:10.1016/j.imu.2020.100427
Early detection and diagnosis are critical factors to control the COVID-19 spreading. A number of deep learning-based methodologies have been recently proposed for COVID-19 screening in CT scans as a tool to automate and help with the diagnosis. These approaches, however, suffer from at least one of the following problems: (i) they treat each CT scan slice independently and (ii) the methods are trained and tested with sets of images from the same dataset. Treating the slices independently means that the same patient may appear in the training and test sets at the same time which may produce misleading results. It also raises the question of whether the scans from the same patient should be evaluated as a group or not. Moreover, using a single dataset raises concerns about the generalization of the methods. Different datasets tend to present images of varying quality which may come from different types of CT machines reflecting the conditions of the countries and cities from where they come from. In order to address these two problems, in this work, we propose an Efficient Deep Learning Technique for the screening of COVID-19 with a voting-based approach. In this approach, the images from a given patient are classified as group in a voting system. The approach is tested in the two biggest datasets of COVID-19 CT analysis with a patient-based split. A cross dataset study is also presented to assess the robustness of the models in a more realistic scenario in which data comes from different distributions. The cross-dataset analysis has shown that the generalization power of deep learning models is far from acceptable for the task since accuracy drops from 87.68% to 56.16% on the best evaluation scenario. These results highlighted that the methods that aim at COVID-19 detection in CT-images have to improve significantly to be considered as a clinical option and larger and more diverse datasets are needed to evaluate the methods in a realistic scenario.
Published: 13 September 2020
Introduction: Increasing corona virus disease 2019 (COVID-19) pre-test probability can minimize testing patients who are less likely to have COVID-19 and therefore reducing personal protective equipment and COVID-19 testing kit use. The aim of this study was to identify patients who were likely to test positive for COVID-19 among symptomatic patients suspected of having COVID-19 during hospitalization by comparing COVID-19 positive and negative patients. Method: We conducted a retrospective chart review of patients who were ≥18 years old and underwent COVID-19 Polymerase chain reaction test because they presented with symptoms thought to be due to COVID-19. The Poisson regression analysis was conducted after clinical presentation, demographic, medical co-morbidities, laboratory and chest image data was retrieved from the medical records. Results: Charts of 277 and 35 COVID-19 negative and positive patients respectively were analyzed. Dyspnea (61%) was the most common symptom among COVID-19 negative patients, while 83% and 77% COVID-19 positive patients had cough and fever respectively. COVID-19 positive patients were more likely to present initially with cough [1.082 (1.022 - 1.145)] and fever [1.066 (1.013 - 1.122)], besides being males [1.066 (1.013 - 1.123)] and 50 to 69 years old [1.090 (1.019 - 1.166)]. Dyspnea, weakness, lymphopenia and bilateral chest image abnormality were not associated with COVID-19 positivity. COVID-19 positive patients were less likely to have non-COVID-19 respiratory viral illness [0.934 (0.893 - 0.976)], human immunodeficiency virus [0.847 (0.763 - 0.942)] and heart failure history [0.945 (0.908 - 0.984)]. Other chronic medical problems (hypertension, diabetes mellitus, chronic obstructive pulmonary disease and coronary artery disease) were not associated with testing positive for COVID-19. Conclusion: Cough and fever are better predictors of symptomatic COVID-19 positivity during hospitalization. Despite published studies reporting a high prevalence of lymphopenia among COVID-19 positive patients, lymphopenia is not associated with the risk of testing positive for COVID-19. Key Words: COVID-19, Predictors, Symptomatic, Hospitalized
Applied Intelligence pp 1-12; doi:10.1007/s10489-020-01867-1
Chest X-rays are playing an important role in the testing and diagnosis of COVID-19 disease in the recent pandemic. However, due to the limited amount of labelled medical images, automated classification of these images for positive and negative cases remains the biggest challenge in their reliable use in diagnosis and disease progression. We implemented a transfer learning pipeline for classifying COVID-19 chest X-ray images from two publicly available chest X-ray datasets1,2. The classifier effectively distinguishes inflammation in lungs due to COVID-19 and Pneumonia from the ones with no infection (normal). We have used multiple pre-trained convolutional backbones as the feature extractor and achieved an overall detection accuracy of 90%, 94.3%, and 96.8% for the VGG16, ResNet50, and EfficientNetB0 backbones respectively. Additionally, we trained a generative adversarial framework (a CycleGAN) to generate and augment the minority COVID-19 class in our approach. For visual explanations and interpretation purposes, we implemented a gradient class activation mapping technique to highlight the regions of the input image that are important for predictions. Additionally, these visualizations can be used to monitor the affected lung regions during disease progression and severity stages.
Medicine, Volume 99; doi:10.1097/md.0000000000022229
Background: Since the outbreak of COVID-19, the number of COVID-19 patients has been on the rise. With the improvement of diagnosis and treatment level in various countries, more and more patients have recovered. Baduanjin exercise is a traditional Chinese health care method with a long history, easy-to-learn, and remarkable effect. It is not subject to the constraints of the field and can be practiced at any time. It can be used as an alternative therapy for COVID-19 rehabilitation patients. At present, there are no relevant articles for systematic review. Methods: We will retrieve a randomized controlled trial of Baduanjin exercise for COVID-19 from the beginning to July 2020. The following databases are areas of concern: Published randomized Cochrane Central Register of Controlled Trials (Central), PubMed, EMBASE, Web of Science, China National Knowledge Infrastructure, Chinese Biomedical Literature Database, and Wan-fang Database-controlled trials in Chinese and English related to Baduanjin exercise and COVID-19 were included. The main result was the effect of Baduanjin exercise on the quality of life in patients recovering from COVID-19. Secondary results to accompany symptoms (such as muscle pain, cough, sputum, runny nose, sore throat, chest tightness, shortness of breath, difficulty breathing, fatigue, headache, nausea, vomiting, anorexia, diarrhea), disappearance rate, 2 consecutive (not on the same day) COVID-19 negative rate of nucleic acid test results, the quality of life improved, improve CT images, the average hospitalization time, severe form of common clinical cure rate and mortality. Results: The results of this study will provide researchers in the field of COVID-19 with a current synthesis of high-quality evidence. Conclusion: The conclusion of this study will provide evidence for judging whether Baduanjin exercise is an effective intervention for the quality of life of rehabilitative patients. PROSPERO registration number: CRD42020199443