Radiographic Imaging of Community-Acquired Pneumonia: A Case-Based Review.

The chest radiograph is the most common imaging examination performed in most radiology departments, and one of the more common indications for these studies is suspected infection. Radiologists must therefore be aware of less common radiographic patterns of pulmonary infection if they are to add value in the interpretation of chest radiographs for this indication. This review uses a case-based format to illustrate a range of imaging findings that can be associated with acute pulmonary infection and highlight findings that should prompt investigation for diseases other than community-acquired pneumonia to prevent misdiagnosis and delays in appropriate management.

CT features of community-acquired pneumonia at the emergency department.

BACKGROUND: Chest computed tomography (CT) was reported to improve the diagnosis of community-acquired pneumonia (CAP) as compared to chest X-ray (CXR). The aim of this study is to describe the CT-patterns of CAP in a large population visiting the emergency department and to see if some of them are more frequently missed on CXR. MATERIALS AND METHODS: This is an ancillary analysis of the prospective multicenter ESCAPED study including 319 patients. We selected the 163 definite or probable CAP based on adjudication committee classification; 147 available chest CT scans were reinterpreted by 3 chest radiologists to identify CAP patterns. These CT-patterns were correlated to epidemiological, biological and microbiological data, and compared between false negative and true positive CXR CAP. RESULTS: Six patterns were identified: lobar pneumonia (51/147, 35%), including 35 with plurifocal involvement; lobular pneumonia (43/147, 29%); unilobar infra-segmental consolidation (24/147, 16%); bronchiolitis (16/147, 11%), including 4 unilobar bronchiolitis; atelectasis and bronchial abnormalities (8/147, 5.5%); interstitial pneumonia (5/147, 3.5%). Bacteria were isolated in 41% of patients with lobar pneumonia-pattern (mostly Streptococcus pneumoniae and Mycoplasma pneumonia) versus 19% in other patients (p = 0.01). Respiratory viruses were equally distributed within all patterns. CXR was falsely negative in 46/147 (31%) patients. Lobar pneumonia was significantly less missed on CXR than other patterns (p = 0.003), especially lobular pneumonia and unilobar infra-segmental consolidation, missed in 35% and 58% of cases, respectively. CONCLUSION: Lobar and lobular pneumonias are the most frequent CT-patterns. Lobar pneumonia is appropriately detected on CXR and mainly due to Streptococcus pneumoniae or Mycoplasma pneumoniae. Chest CT is very useful to identify CAP in other CT-patterns. Prior the COVID pandemic, CAP was rarely responsible for interstitial opacities on CT.

Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia.

BACKGROUND: Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality. METHODS: Deep-learning model using convolutional neural network (CNN) was trained with a retrospective cohort of 2235 CXRs from 1966 unique adult patients admitted for CAP from 1 January 2019 to 31 December 2019. A single-centre prospective cohort between 11 May 2020 and 15 June 2020 was analysed for model performance. CAPE mortality risk score based on CNN analysis of the first CXR performed for CAP was used to determine the area under the receiver operating characteristic curve (AUC) for 30-day mortality. RESULTS: 315 inpatient episodes for CAP occurred, with 30-day mortality of 19.4% (n=61/315). Non-survivors were older than survivors (mean (SD)age, 80.4 (10.3) vs 69.2 (18.7)); more likely to have dementia (n=27/61 vs n=58/254) and malignancies (n=16/61 vs n=18/254); demonstrate higher serum C reactive protein (mean (SD), 109 mg/L (98.6) vs 59.3 mg/L (69.7)) and serum procalcitonin (mean (SD), 11.3 (27.8) µg/L vs 1.4 (5.9) µg/L). The AUC for CAPE mortality risk score for 30-day mortality was 0.79 (95% CI 0.73 to 0.85, p<0.001); Pneumonia Severity Index (PSI) 0.80 (95% CI 0.74 to 0.86, p<0.001); Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 (CURB-65) score 0.76 (95% CI 0.70 to 0.81, p<0.001), respectively. CAPE combined with CURB-65 model has an AUC of 0.83 (95% CI 0.77 to 0.88, p<0.001). The best performing model was CAPE incorporated with PSI, with an AUC of 0.84 (95% CI 0.79 to 0.89, p<0.001). CONCLUSION: CXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined.

Prediction of COVID-19 with Computed Tomography Images using Hybrid Learning Techniques.

Reverse Transcription Polymerase Chain Reaction (RT-PCR) used for diagnosing COVID-19 has been found to give low detection rate during early stages of infection. Radiological analysis of CT images has given higher prediction rate when compared to RT-PCR technique. In this paper, hybrid learning models are used to classify COVID-19 CT images, Community-Acquired Pneumonia (CAP) CT images, and normal CT images with high specificity and sensitivity. The proposed system in this paper has been compared with various machine learning classifiers and other deep learning classifiers for better data analysis. The outcome of this study is also compared with other studies which were carried out recently on COVID-19 classification for further analysis. The proposed model has been found to outperform with an accuracy of 96.69%, sensitivity of 96%, and specificity of 98%.

An Insight of the First Community Infected COVID-19 Patient in Beijing by Imported Case: Role of Deep Learning-Assisted CT Diagnosis.

In the era of coronavirus disease 2019 (COVID-19) pandemic, imported COVID-19 cases pose great challenges to many countries. Chest CT examination is considered to be complementary to nucleic acid test for COVID-19 detection and diagnosis. We report the first community infected COVID-19 patient by an imported case in Beijing, which manifested as nodular lesions on chest CT imaging at the early stage. Deep Learning (DL)-based diagnostic systems quantitatively monitored the progress of pulmonary lesions in 6 days and timely made alert for suspected pneumonia, so that prompt medical isolation was taken. The patient was confirmed as COVID-19 case after nucleic acid test, for which the community transmission was prevented timely. The roles of DL-assisted diagnosis in helping radiologists screening suspected COVID cases were discussed.

Risk of acute pulmonary embolism in COVID-19 pneumonia compared to community-acquired pneumonia: a retrospective case-control study.

AIM: To compare the incidence of pulmonary embolism (PE) in COVID-19 pneumonia and non-COVID-19-related community-acquired pneumonia (CAP) in hospitalised patients. MATERIALS AND METHODS: A retrospective case-control study was conducted. This included patients hospitalised with pneumonia and investigated for suspected PE with computed tomography pulmonary angiogram (CTPA). Cases were defined as patients with COVID-19 pneumonia from 1 March 2020 to 17 May 2020; controls were patients with CAP from 5 July 2019 to 31 January 2020. The primary outcome was to determine the risk of developing PE in both groups. Multivariable logistic regression was used to calculate the adjusted odds ratio for PE. RESULTS: One hundred and forty-four patients were included; 72 cases (47% male; mean age 59 (±15) years), and 72 controls (56% male; mean age 58 (±20) years). PE was diagnosed in 23.6% of the cases versus 6.9% of the controls. The adjusted odds ratio for PE in hospitalised patients with COVID-19 pneumonia compared with those with CAP was 3.23 (95% confidence interval [CI] 1.04-10.04, p=0.04). CONCLUSION: The odds of developing PE in hospitalised patients with COVID-19 pneumonia are three-times higher than in those with CAP. The results provide a quantitative assessment of the risk of PE in COVID-19 pneumonia, a condition new to healthcare, compared to other forms of pneumonia with a well-established scientific basis.

Computing infection distributions and longitudinal evolution patterns in lung CT images.

BACKGROUND: Spatial and temporal lung infection distributions of coronavirus disease 2019 (COVID-19) and their changes could reveal important patterns to better understand the disease and its time course. This paper presents a pipeline to analyze statistically these patterns by automatically segmenting the infection regions and registering them onto a common template. METHODS: A VB-Net is designed to automatically segment infection regions in CT images. After training and validating the model, we segmented all the CT images in the study. The segmentation results are then warped onto a pre-defined template CT image using deformable registration based on lung fields. Then, the spatial distributions of infection regions and those during the course of the disease are calculated at the voxel level. Visualization and quantitative comparison can be performed between different groups. We compared the distribution maps between COVID-19 and community acquired pneumonia (CAP), between severe and critical COVID-19, and across the time course of the disease. RESULTS: For the performance of infection segmentation, comparing the segmentation results with manually annotated ground-truth, the average Dice is 91.6% ± 10.0%, which is close to the inter-rater difference between two radiologists (the Dice is 96.1% ± 3.5%). The distribution map of infection regions shows that high probability regions are in the peripheral subpleural (up to 35.1% in probability). COVID-19 GGO lesions are more widely spread than consolidations, and the latter are located more peripherally. Onset images of severe COVID-19 (inpatients) show similar lesion distributions but with smaller areas of significant difference in the right lower lobe compared to critical COVID-19 (intensive care unit patients). About the disease course, critical COVID-19 patients showed four subsequent patterns (progression, absorption, enlargement, and further absorption) in our collected dataset, with remarkable concurrent HU patterns for GGO and consolidations. CONCLUSIONS: By segmenting the infection regions with a VB-Net and registering all the CT images and the segmentation results onto a template, spatial distribution patterns of infections can be computed automatically. The algorithm provides an effective tool to visualize and quantify the spatial patterns of lung infection diseases and their changes during the disease course. Our results demonstrate different patterns between COVID-19 and CAP, between severe and critical COVID-19, as well as four subsequent disease course patterns of the severe COVID-19 patients studied, with remarkable concurrent HU patterns for GGO and consolidations.

PSSPNN: PatchShuffle Stochastic Pooling Neural Network for an Explainable Diagnosis of COVID-19 with Multiple-Way Data Augmentation.

AIM: COVID-19 has caused large death tolls all over the world. Accurate diagnosis is of significant importance for early treatment. METHODS: In this study, we proposed a novel PSSPNN model for classification between COVID-19, secondary pulmonary tuberculosis, community-captured pneumonia, and healthy subjects. PSSPNN entails five improvements: we first proposed the n-conv stochastic pooling module. Second, a novel stochastic pooling neural network was proposed. Third, PatchShuffle was introduced as a regularization term. Fourth, an improved multiple-way data augmentation was used. Fifth, Grad-CAM was utilized to interpret our AI model. RESULTS: The 10 runs with random seed on the test set showed our algorithm achieved a microaveraged F1 score of 95.79%. Moreover, our method is better than nine state-of-the-art approaches. CONCLUSION: This proposed PSSPNN will help assist radiologists to make diagnosis more quickly and accurately on COVID-19 cases.

Lung volume reduction and infection localization revealed in Big data CT imaging of COVID-19.

The ongoing worldwide COVID-19 pandemic has become a huge threat to global public health. Using CT image, 3389 COVID-19 patients, 1593 community-acquired pneumonia (CAP) patients, and 1707 nonpneumonia subjects were included to explore the different patterns of lung and lung infection. We found that COVID-19 patients have a significant reduced lung volume with increased density and mass, and the infections tend to present as bilateral lower lobes. The findings provide imaging evidence to improve our understanding of COVID-19.

Early clinical and CT features of COVID-19 and community-acquired pneumonia from a fever observation ward in Ningbo, China.

INTRODUCTION: We aimed to compare the early clinical manifestations, laboratory results and chest computed tomography (CT) images of COVID-19 patients with those of other community-acquired pneumonia (CAP) patients to differentiate CAP from COVID-19 before reverse transcription-polymerase chain reaction results are obtained. METHODS: The clinical and laboratory data and chest CT images of 51 patients were assessed in a fever observation ward for evidence of COVID-19 between January and February 2020. RESULTS: 24 patients had laboratory-confirmed COVID-19, whereas 27 individuals had negative results. No statistical difference in clinical features was found between COVID-19 and CAP patients, except for diarrhoea. There was a significant difference in lymphocyte and eosinophil counts between COVID-19 and CAP patients. In total, 22 (91.67%) COVID-19 patients had bilateral involvement and multiple lesions according to their lung CT images; the left lower lobe (87.50%) and right lower lobe (95.83%) were affected most often, and all lesions were located in the peripheral zones of the lung. The most common CT feature of COVID-19 was ground-glass opacity, found in 95.83% of patients, compared to 66.67% of CAP patients. CONCLUSION: Diarrhoea, lymphocyte counts, eosinophil counts and CT findings (e.g. ground-glass opacity) could help to distinguish COVID-19 from CAP at an early stage of infection, based on findings from our fever observation ward.

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.

COVID-19 mimics on chest CT: a pictorial review and radiologic guide.

Chest imaging is often used as a complementary tool in the evaluation of coronavirus disease 2019 (COVID-19) patients, helping physicians to augment their clinical suspicion. Despite not being diagnostic for COVID-19, chest CT may help clinicians to isolate high suspicion patients with suggestive imaging findings. However, COVID-19 findings on CT are also common to other pulmonary infections and non-infectious diseases, and radiologists and point-of-care physicians should be aware of possible mimickers. This state-of-the-art review goal is to summarize and illustrate possible etiologies that may have a similar pattern on chest CT as COVID-19. The review encompasses both infectious etiologies, such as non-COVID viral pneumonia, Mycoplasma pneumoniae, Pneumocystis jiroveci, and pulmonary granulomatous infectious, and non-infectious disorders, such as pulmonary embolism, fat embolism, cryptogenic organizing pneumonia, non-specific interstitial pneumonia, desquamative interstitial pneumonia, and acute and chronic eosinophilic pneumonia.

Hypergraph learning for identification of COVID-19 with CT imaging.

The coronavirus disease, named COVID-19, has become the largest global public health crisis since it started in early 2020. CT imaging has been used as a complementary tool to assist early screening, especially for the rapid identification of COVID-19 cases from community acquired pneumonia (CAP) cases. The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features. To tackle this challenge, we propose an Uncertainty Vertex-weighted Hypergraph Learning (UVHL) method to identify COVID-19 from CAP using CT images. In particular, multiple types of features (including regional features and radiomics features) are first extracted from CT image for each case. Then, the relationship among different cases is formulated by a hypergraph structure, with each case represented as a vertex in the hypergraph. The uncertainty of each vertex is further computed with an uncertainty score measurement and used as a weight in the hypergraph. Finally, a learning process of the vertex-weighted hypergraph is used to predict whether a new testing case belongs to COVID-19 or not. Experiments on a large multi-center pneumonia dataset, consisting of 2148 COVID-19 cases and 1182 CAP cases from five hospitals, are conducted to evaluate the prediction accuracy of the proposed method. Results demonstrate the effectiveness and robustness of our proposed method on the identification of COVID-19 in comparison to state-of-the-art methods.

Differential diagnosis of coronavirus disease 2019 from community-acquired-pneumonia by computed tomography scan and follow-up.

OBJECTIVE: Coronavirus disease 2019 (COVID-19) is currently the most serious infectious disease in the world. An accurate diagnosis of this disease in the clinic is very important. This study aims to improve the differential ability of computed tomography (CT) to diagnose COVID-19 and other community-acquired pneumonias (CAPs) and evaluate the short-term prognosis of these patients. METHODS: The clinical and imaging data of 165 COVID-19 and 118 CAP patients diagnosed in seven hospitals in Anhui Province, China from January 21 to February 28, 2020 were retrospectively analysed. The CT manifestations of the two groups were recorded and compared. A correlation analysis was used to examine the relationship between COVID-19 and age, size of lung lesions, number of involved lobes, and CT findings of patients. The factors that were helpful in diagnosing the two groups of patients were identified based on specificity and sensitivity. RESULTS: The typical CT findings of COVID-19 are simple ground-glass opacities (GGO), GGO with consolidation or grid-like changes. The sensitivity and specificity of the combination of age, white blood cell count, and ground-glass opacity in the diagnosis of COVID-19 were 92.7 and 66.1%, respectively. Pulmonary consolidation, fibrous cords, and bronchial wall thickening were used as indicators to exclude COVID-19. The sensitivity and specificity of the combination of these findings were 78.0 and 63.6%, respectively. The follow-up results showed that 67.8% (112/165) of COVID-19 patients had abnormal changes in their lung parameters, and the severity of the pulmonary sequelae of patients over 60 years of age worsened with age. CONCLUSIONS: Age, white blood cell count and ground-glass opacity have high accuracy in the early diagnosis of COVID-19 and the differential diagnosis from CAP. Patients aged over 60 years with COVID-19 have a poor prognosis. This result provides certain significant guidance for the diagnosis and treatment of new coronavirus pneumonia.

Dual-Sampling Attention Network for Diagnosis of COVID-19 From Community Acquired Pneumonia.

The coronavirus disease (COVID-19) is rapidly spreading all over the world, and has infected more than 1,436,000 people in more than 200 countries and territories as of April 9, 2020. Detecting COVID-19 at early stage is essential to deliver proper healthcare to the patients and also to protect the uninfected population. To this end, we develop a dual-sampling attention network to automatically diagnose COVID-19 from the community acquired pneumonia (CAP) in chest computed tomography (CT). In particular, we propose a novel online attention module with a 3D convolutional network (CNN) to focus on the infection regions in lungs when making decisions of diagnoses. Note that there exists imbalanced distribution of the sizes of the infection regions between COVID-19 and CAP, partially due to fast progress of COVID-19 after symptom onset. Therefore, we develop a dual-sampling strategy to mitigate the imbalanced learning. Our method is evaluated (to our best knowledge) upon the largest multi-center CT data for COVID-19 from 8 hospitals. In the training-validation stage, we collect 2186 CT scans from 1588 patients for a 5-fold cross-validation. In the testing stage, we employ another independent large-scale testing dataset including 2796 CT scans from 2057 patients. Results show that our algorithm can identify the COVID-19 images with the area under the receiver operating characteristic curve (AUC) value of 0.944, accuracy of 87.5%, sensitivity of 86.9%, specificity of 90.1%, and F1-score of 82.0%. With this performance, the proposed algorithm could potentially aid radiologists with COVID-19 diagnosis from CAP, especially in the early stage of the COVID-19 outbreak.

Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy.

Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity. Results The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (±standard deviation) was 49 years ± 15, and there were slightly more men than women (1838 vs 1484, respectively; P = .29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P < .001). The per-scan sensitivity and specificity for detecting CAP in the independent test set was 87% (152 of 175 scans) and 92% (239 of 259 scans), respectively, with an area under the receiver operating characteristic curve of 0.95 (95% CI: 0.93, 0.97). Conclusion A deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. © RSNA, 2020 Online supplemental material is available for this article.

Use of Lung Ultrasound to Differentiate Coronavirus Disease 2019 (COVID-19) Pneumonia From Community-Acquired Pneumonia.

To investigate the feasibility of lung ultrasound in evaluating coronavirus disease 2019 (COVID-19) and distinguish the sonographic features between COVID-19 and community-acquired pneumonia (CAP), a total of 12 COVID-19 patients and 20 CAP patients were selected and underwent lung ultrasound. The modified Buda scoring system for interstitial lung disease was used to evaluate the severity and treatment effect of COVID-19 on ultrasonography. The differences between modified lung ultrasound (MLUS) score and high-resolution computed tomography (HRCT) Warrick score were analyzed to evaluate their correlation. COVID-19 showed the following sonographic features: thickening (12/12), blurred (9/12), discontinuous (6/12) pleural line; rocket sign (4/12), partially diffused B-line (12/12), completely diffused B-line (10/12), waterfall sign (4/12); C-line sign (5/12); pleural effusion (1/12) and pulmonary balloon (Am line, 1/12). The last two features were rarely seen. Differences of ultrasonic features, including lesion range, lung signs and pneumonia-related complications, between COVID-19 and CAP were statistically significant (p˂ 0.05 or 0.001). MLUS scores (p = 0.006) and HRCT Warrick scores (p = 0.015) increased as the severity of COVID-19 increased. The differences between moderate (29.00 [25.75-37.50]) and severe (43.00 [38.75-47.25]) (p = 0.022) or between moderate and critical (47.50 [44.25-50.00]) (p = 0.002) type COVID-19 were statistically significant, compared with those between severe and critical types. Correlation between MLUS scores and HRCT Warrick scores was positive (r = 0.54, p = 0.048). MLUS scores (Z = 2.61, p = 0.009) and HRCT Warrick scores (Z = 2.63, p = 0.009) of five severe or critical COVID-19 patients significantly decreased as their conditions improved after treatment. The differences of sonographic features between COVID-19 and CAP patients were notable. The MLUS scoring system could be used to evaluate the severity and treatment effect of COVID-19.