[Analysis of chest imaging features of novel coronavirus pneumonia, bacterial pneumonia and viral pneumonia].

OBJECTIVE: To investigate and summarize the chest CT imaging features of patients with novel coronavirus pneumonia (COVID-19), bacterial pneumonia and other viral pneumonia. METHODS: Chest CT data of 102 patients with pulmonary infection due to different etiologies were retrospectively analyzed, including 36 patients with COVID-19 admitted to Hainan Provincial People's Hospital and the Second Affiliated Hospital of Hainan Medical University from December 2019 to March 2020, 16 patients with other viral pneumonia admitted to Hainan Provincial People's Hospital from January 2018 to February 2020, and 50 patients with bacterial pneumonia admitted to Haikou Affiliated Hospital of Central South University Xiangya School of Medicine from April 2018 to May 2020. Two senior radiologists and two senior intensive care physicians were participated to evaluated the extent of lesions involvement and imaging features of the first chest CT after the onset of the disease. RESULTS: Bilateral pulmonary lesions were more common in patients with COVID-19 and other viral pneumonia, and the incidence was significantly higher than that of bacterial pneumonia (91.6%, 75.0% vs. 26.0%, P < 0.05). Compared with other viral pneumonia and COVID-19, bacterial pneumonia was mainly characterized by single-lung and multi-lobed lesion (62.0% vs. 18.8%, 5.6%, P < 0.05), accompanied by pleural effusion and lymph node enlargement. The proportion of ground-glass opacity in the lung tissues of patients with COVID-19 was 97.2%, that of patients with other viral pneumonia was 56.2%, and that of patients with bacterial pneumonia was only 2.0% (P < 0.05). The incidence rate of lung tissue consolidation (25.0%, 12.5%), air bronchial sign (13.9%, 6.2%) and pleural effusion (16.7%, 37.5%) in patients with COVID-19 and other viral pneumonia were significantly lower than those in patients with bacterial pneumonia (62.0%, 32.0%, 60.0%, all P < 0.05), paving stone sign (22.2%, 37.5%), fine mesh sign (38.9%, 31.2%), halo sign (11.1%, 25.0%), ground-glass opacity with interlobular septal thickening (30.6%, 37.5%), bilateral patchy pattern/rope shadow (80.6%, 50.0%) etc. were significantly higher than those of bacterial pneumonia (2.0%, 4.0%, 2.0%, 0%, 22.0%, all P < 0.05). The incidence of local patchy shadow in patients with COVID-19 was only 8.3%, significantly lower than that in patients with other viral pneumonia and bacterial pneumonia (8.3% vs. 68.8%, 50.0%, P < 0.05). There was no significant difference in the incidence of peripheral vascular shadow thickening in patients with COVID-19, other viral pneumonia and bacterial pneumonia (27.8%, 12.5%, 30.0%, P > 0.05). CONCLUSIONS: The probability of ground-glass opacity, paving stone and grid shadow in chest CT of patients with COVID-19 was significantly higher than those of bacterial pneumonia, and it was more common in the lower lungs and lateral dorsal segment. In other patients with viral pneumonia, ground-glass opacity was distributed in both upper and lower lungs. Bacterial pneumonia is usually characterized by single lung consolidation, distributed in lobules or large lobes and accompanied by pleural effusion.

Impact of lung ultrasound during the SARS-CoV-2 pandemic: Distinction between viral and bacterial pneumonia.

INTRODUCTION: Lung Ultrasound is an accessible, low-cost technique that has demonstrated its usefulness in the prognostic stratification of COVID-19 patients. In addition, according to previous studies, it can guide us towards the potential aetiology, especially in epidemic situations such as the current one. PATIENTS AND METHODS: 40 patients were prospectively recruited, 30 with confirmed SARS-CoV-2 pneumonia and 10 with community-acquired pneumonia (CAP). The patients included underwent both a chest X-ray and ultrasound. RESULTS: There were no differences in the 2 groups in terms of clinical and laboratory characteristics. The main ultrasound findings in the SARS-CoV-2 group were the presence of confluent B lines and subpleural consolidations and hepatinization in the CAP group. Pleural effusion was more frequent in the CAP group. There were no normal lung ultrasound exams. Analysis of the area under the curve (AUC) curves showed an area under the curve for Lung Ultrasound of 89.2% (95% CI: 75%.0-100%, p < .001) in the identification of SARS-CoV-2 pneumonia. The cut-off value for the lung score of 10 had a sensitivity of 93.3% and a specificity of 80.0% (p < .001). DISCUSSION: The combination of the findings of the Lung Ultrasound, with a Lung Score greater than 10, added to the rest of the additional tests, can be an excellent tool to predict the aetiology of the pneumonia.

Automated detection of COVID-19 through convolutional neural network using chest x-ray images.

The COVID-19 epidemic has a catastrophic impact on global well-being and public health. More than 27 million confirmed cases have been reported worldwide until now. Due to the growing number of confirmed cases, and challenges to the variations of the COVID-19, timely and accurate classification of healthy and infected patients is essential to control and treat COVID-19. We aim to develop a deep learning-based system for the persuasive classification and reliable detection of COVID-19 using chest radiography. Firstly, we evaluate the performance of various state-of-the-art convolutional neural networks (CNNs) proposed over recent years for medical image classification. Secondly, we develop and train CNN from scratch. In both cases, we use a public X-Ray dataset for training and validation purposes. For transfer learning, we obtain 100% accuracy for binary classification (i.e., Normal/COVID-19) and 87.50% accuracy for tertiary classification (Normal/COVID-19/Pneumonia). With the CNN trained from scratch, we achieve 93.75% accuracy for tertiary classification. In the case of transfer learning, the classification accuracy drops with the increased number of classes. The results are demonstrated by comprehensive receiver operating characteristics (ROC) and confusion metric analysis with 10-fold cross-validation.

Deep Learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) With CT Images.

A novel coronavirus (COVID-19) recently emerged as an acute respiratory syndrome, and has caused a pneumonia outbreak world-widely. As the COVID-19 continues to spread rapidly across the world, computed tomography (CT) has become essentially important for fast diagnoses. Thus, it is urgent to develop an accurate computer-aided method to assist clinicians to identify COVID-19-infected patients by CT images. Here, we have collected chest CT scans of 88 patients diagnosed with COVID-19 from hospitals of two provinces in China, 100 patients infected with bacteria pneumonia, and 86 healthy persons for comparison and modeling. Based on the data, a deep learning-based CT diagnosis system was developed to identify patients with COVID-19. The experimental results showed that our model could accurately discriminate the COVID-19 patients from the bacteria pneumonia patients with an AUC of 0.95, recall (sensitivity) of 0.96, and precision of 0.79. When integrating three types of CT images, our model achieved a recall of 0.93 with precision of 0.86 for discriminating COVID-19 patients from others. Moreover, our model could extract main lesion features, especially the ground-glass opacity (GGO), which are visually helpful for assisted diagnoses by doctors. An online server is available for online diagnoses with CT images by our server (http://biomed.nscc-gz.cn/model.php). Source codes and datasets are available at our GitHub (https://github.com/SY575/COVID19-CT).

An AI-based auxiliary empirical antibiotic therapy model for children with bacterial pneumonia using low-dose chest CT images.

PURPOSE: To construct an auxiliary empirical antibiotic therapy (EAT) multi-class classification model for children with bacterial pneumonia using radiomics features based on artificial intelligence and low-dose chest CT images. MATERIALS AND METHODS: Data were retrospectively collected from children with pathogen-confirmed bacterial pneumonia including Gram-positive bacterial pneumonia (122/389, 31%), Gram-negative bacterial pneumonia (159/389, 41%) and atypical bacterial pneumonia (108/389, 28%) from January 1 to June 30, 2019. Nine machine-learning models were separately evaluated based on radiomics features extracted from CT images; three optimal submodels were constructed and integrated to form a multi-class classification model. RESULTS: We selected five features to develop three radiomics submodels: a Gram-positive model, a Gram-negative model and an atypical model. The comprehensive radiomics model using support vector machine method yielded an average area under the curve (AUC) of 0.75 [95% confidence interval (CI), 0.65-0.83] and accuracy (ACC) of 0.58 [sensitivity (SEN), 0.57; specificity (SPE), 0.78] in the training set, and an average AUC of 0.73 (95% CI 0.61-0.79) and ACC of 0.54 (SEN, 0.52; SPE, 0.75) in the test set. CONCLUSION: This auxiliary EAT radiomics multi-class classification model was deserved to be researched in differential diagnosing bacterial pneumonias in children.

Analysis of SARS-CoV-2 PCR and Chest CT Findings at a Single Facility in Tokyo (Machida Municipal Hospital).

INTRODUCTION: The SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR) test is useful for diagnosing COVID-19, and the RT-PCR positive rate is an important indicator for estimating the incidence rate and number of infections. COVID-19 pneumonia is also associated with characteristic findings on chest CT, which can aid in diagnosis. METHODS: We retrospectively evaluated patient background characteristics, the number of cases, the positivity rate, and chest CT findings for positive and negative cases in 672 patients who underwent RT-PCR for suspected COVID-19 at our hospital between April 3 and August 28, 2020. In addition, we compared trends in the positive rates at approximately weekly intervals with trends in the number of new infections in Machida City, Tokyo. RESULTS: The study included 323 men and 349 women, with a median age of 46 years (range: 1 month-100 years). RT-PCR findings were positive in 37 cases, and the positive rate was 5.51%. Trends in the positive rate at our hospital and the number of new COVID-19 cases in the city were similar during the study period. Among patients with positive results, 15 (40.5%) had chest CT findings, and 14 had bilateral homogeneous GGOs. Among patients with negative results, 190 had chest CT findings at the time of examination, and 150 were diagnosed with bacterial pneumonia or bronchitis, with main findings consisting of consolidations and centrilobular opacities. Only 11 of these patients exhibited bilateral homogeneous GGOs. CONCLUSION: Bilateral homogeneous GGOs are characteristic of COVID-19 pneumonia and may aid in the diagnosis of COVID-19.

Convolutional Sparse Support Estimator-Based COVID-19 Recognition From X-Ray Images.

Coronavirus disease (COVID-19) has been the main agenda of the whole world ever since it came into sight. X-ray imaging is a common and easily accessible tool that has great potential for COVID-19 diagnosis and prognosis. Deep learning techniques can generally provide state-of-the-art performance in many classification tasks when trained properly over large data sets. However, data scarcity can be a crucial obstacle when using them for COVID-19 detection. Alternative approaches such as representation-based classification [collaborative or sparse representation (SR)] might provide satisfactory performance with limited size data sets, but they generally fall short in performance or speed compared to the neural network (NN)-based methods. To address this deficiency, convolution support estimation network (CSEN) has recently been proposed as a bridge between representation-based and NN approaches by providing a noniterative real-time mapping from query sample to ideally SR coefficient support, which is critical information for class decision in representation-based techniques. The main premises of this study can be summarized as follows: 1) A benchmark X-ray data set, namely QaTa-Cov19, containing over 6200 X-ray images is created. The data set covering 462 X-ray images from COVID-19 patients along with three other classes; bacterial pneumonia, viral pneumonia, and normal. 2) The proposed CSEN-based classification scheme equipped with feature extraction from state-of-the-art deep NN solution for X-ray images, CheXNet, achieves over 98% sensitivity and over 95% specificity for COVID-19 recognition directly from raw X-ray images when the average performance of 5-fold cross validation over QaTa-Cov19 data set is calculated. 3) Having such an elegant COVID-19 assistive diagnosis performance, this study further provides evidence that COVID-19 induces a unique pattern in X-rays that can be discriminated with high accuracy.

Accurately Discriminating COVID-19 from Viral and Bacterial Pneumonia According to CT Images Via Deep Learning.

Computed tomography (CT) is one of the most efficient diagnostic methods for rapid diagnosis of the widespread COVID-19. However, reading CT films brings a lot of concentration and time for doctors. Therefore, it is necessary to develop an automatic CT image diagnosis system to assist doctors in diagnosis. Previous studies devoted to COVID-19 in the past months focused mostly on discriminating COVID-19 infected patients from healthy persons and/or bacterial pneumonia patients, and have ignored typical viral pneumonia since it is hard to collect samples for viral pneumonia that is less frequent in adults. In addition, it is much more challenging to discriminate COVID-19 from typical viral pneumonia as COVID-19 is also a kind of virus. In this study, we have collected CT images of 262, 100, 219, and 78 persons for COVID-19, bacterial pneumonia, typical viral pneumonia, and healthy controls, respectively. To the best of our knowledge, this was the first study of quaternary classification to include also typical viral pneumonia. To effectively capture the subtle differences in CT images, we have constructed a new model by combining the ResNet50 backbone with SE blocks that was recently developed for fine image analysis. Our model was shown to outperform commonly used baseline models, achieving an overall accuracy of 0.94 with AUC of 0.96, recall of 0.94, precision of 0.95, and F1-score of 0.94. The model is available in https://github.com/Zhengfudan/COVID-19-Diagnosis-and-Pneumonia-Classification .

Quantitative Assessment of Chest CT Patterns in COVID-19 and Bacterial Pneumonia Patients: a Deep Learning Perspective.

BACKGROUND: It is difficult to distinguish subtle differences shown in computed tomography (CT) images of coronavirus disease 2019 (COVID-19) and bacterial pneumonia patients, which often leads to an inaccurate diagnosis. It is desirable to design and evaluate interpretable feature extraction techniques to describe the patient's condition. METHODS: This is a retrospective cohort study of 170 confirmed patients with COVID-19 or bacterial pneumonia acquired at Yeungnam University Hospital in Daegu, Korea. The Lung and lesion regions were segmented to crop the lesion into 2D patches to train a classifier model that could differentiate between COVID-19 and bacterial pneumonia. The K-means algorithm was used to cluster deep features extracted by the trained model into 20 groups. Each lesion patch cluster was described by a characteristic imaging term for comparison. For each CT image containing multiple lesions, a histogram of lesion types was constructed using the cluster information. Finally, a Support Vector Machine classifier was trained with the histogram and radiomics features to distinguish diseases and severity. RESULTS: The 20 clusters constructed from 170 patients were reviewed based on common radiographic appearance types. Two clusters showed typical findings of COVID-19, with two other clusters showing typical findings related to bacterial pneumonia. Notably, there is one cluster that showed bilateral diffuse ground-glass opacities (GGOs) in the central and peripheral lungs and was considered to be a key factor for severity classification. The proposed method achieved an accuracy of 91.2% for classifying COVID-19 and bacterial pneumonia patients with 95% reported for severity classification. The CT quantitative parameters represented by the values of cluster 8 were correlated with existing laboratory data and clinical parameters. CONCLUSION: Deep chest CT analysis with constructed lesion clusters revealed well-known COVID-19 CT manifestations comparable to manual CT analysis. The constructed histogram features improved accuracy for both diseases and severity classification, and showed correlations with laboratory data and clinical parameters. The constructed histogram features can provide guidance for improved analysis and treatment of COVID-19.

Point-of-care lung ultrasound for the assessment of pneumonia: a narrative review in the COVID-19 era.

In the coronavirus disease-2019 (COVID-19) era, point-of-care lung ultrasound (LUS) has attracted increased attention. Prospective studies on LUS for the assessment of pneumonia in adult patients were extensively carried out for more than 10 years before this era. None of these prospective studies attempted to differentiate bacterial and viral pneumonia in adult patients using LUS. The majority of studies considered the LUS examination to be positive if sonographic consolidations or multiple B-lines were observed. Significant differences existed in the accuracy of these studies. Some studies revealed that LUS showed superior sensitivity to chest X-ray. These results indicate that point-of-care LUS has the potential to be an initial imaging modality for the diagnosis of pneumonia. The LUS diagnosis of ventilator-associated pneumonia in intensive care units is more challenging in comparison with the diagnosis of community-acquired pneumonia in emergency departments due to the limited access to the mechanically ventilated patients and the high prevalence of atelectasis. However, several studies have demonstrated that the combination of LUS findings with other clinical markers improved the diagnostic accuracy. In the COVID-19 era, many case reports and small observational studies on COVID-19 pneumonia have been published in a short period. Multiple B-lines were the most common and consistent finding in COVID-19 pneumonia. Serial LUS showed the deterioration of the disease. The knowledge and ideas on the application of LUS in the management of pneumonia that are expected to accumulate in the COVID-19 era may provide us with clues regarding more appropriate management.

Pneumonia in children admitted to the national referral hospital in Bhutan: A prospective cohort study.

OBJECTIVES: The study aim was to describe the etiological profile and clinical characteristics of pneumonia among children hospitalized in Thimphu, Bhutan. METHODS: This prospective study enrolled children aged 2-59 months admitted to the Jigme Dorji Wangchuck National Referral Hospital with World Health Organization (WHO)-defined clinical pneumonia. Demographic and clinico-radiological data were collected through questionnaires, physical examination, and chest radiography. Blood samples and nasopharyngeal washing were collected for microbiological analysis including culture and molecular methods. RESULTS: From July 2017 to June 2018, 189 children were enrolled, of which 53.4% were infants. Pneumonia-related admissions were less frequent over the winter. Chest radiographies were obtained in 149 children; endpoints included pneumonia in 39 cases (26.2%), other infiltrates in 31 (20.8%), and were normal in 79 children (53.0%). Non-contaminated bacterial growth was detected in 8/152 (5.3%) blood cultures, with only two cases of Streptococcus pneumoniae. Viral detection in upper respiratory secretions was common, with at least one virus detected in 103/115 (89.6%). The three most-commonly isolated viruses were respiratory syncytial virus (52/115; 45.2%), rhinovirus (42/115; 36.5%), and human parainfluenza virus (19/115; 16.5%). A third of patients with viral infections showed mixed infections. Case fatality rate was 3.2% (6/189). CONCLUSION: Respiratory viral infections predominated among this cohort of WHO-defined clinical pneumonia cases, whereas bacterial aetiologies were uncommon, highlighting the epidemiologic transition that Bhutan seems to have reached.

A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis.

Coronavirus disease 2019 (COVID-19) has spread globally, and medical resources become insufficient in many regions. Fast diagnosis of COVID-19 and finding high-risk patients with worse prognosis for early prevention and medical resource optimisation is important. Here, we proposed a fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis by routinely used computed tomography.We retrospectively collected 5372 patients with computed tomography images from seven cities or provinces. Firstly, 4106 patients with computed tomography images were used to pre-train the deep learning system, making it learn lung features. Following this, 1266 patients (924 with COVID-19 (471 had follow-up for >5 days) and 342 with other pneumonia) from six cities or provinces were enrolled to train and externally validate the performance of the deep learning system.In the four external validation sets, the deep learning system achieved good performance in identifying COVID-19 from other pneumonia (AUC 0.87 and 0.88, respectively) and viral pneumonia (AUC 0.86). Moreover, the deep learning system succeeded to stratify patients into high- and low-risk groups whose hospital-stay time had significant difference (p=0.013 and p=0.014, respectively). Without human assistance, the deep learning system automatically focused on abnormal areas that showed consistent characteristics with reported radiological findings.Deep learning provides a convenient tool for fast screening of COVID-19 and identifying potential high-risk patients, which may be helpful for medical resource optimisation and early prevention before patients show severe symptoms.

Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks.

In this study, a dataset of X-ray images from patients with common bacterial pneumonia, confirmed Covid-19 disease, and normal incidents, was utilized for the automatic detection of the Coronavirus disease. The aim of the study is to evaluate the performance of state-of-the-art convolutional neural network architectures proposed over the recent years for medical image classification. Specifically, the procedure called Transfer Learning was adopted. With transfer learning, the detection of various abnormalities in small medical image datasets is an achievable target, often yielding remarkable results. The datasets utilized in this experiment are two. Firstly, a collection of 1427 X-ray images including 224 images with confirmed Covid-19 disease, 700 images with confirmed common bacterial pneumonia, and 504 images of normal conditions. Secondly, a dataset including 224 images with confirmed Covid-19 disease, 714 images with confirmed bacterial and viral pneumonia, and 504 images of normal conditions. The data was collected from the available X-ray images on public medical repositories. The results suggest that Deep Learning with X-ray imaging may extract significant biomarkers related to the Covid-19 disease, while the best accuracy, sensitivity, and specificity obtained is 96.78%, 98.66%, and 96.46% respectively. Since by now, all diagnostic tests show failure rates such as to raise concerns, the probability of incorporating X-rays into the diagnosis of the disease could be assessed by the medical community, based on the findings, while more research to evaluate the X-ray approach from different aspects may be conducted.