Diagnostic performance of standardized typical CT findings for COVID-19: a systematic review and meta-analysis.

OBJECTIVE: To meta-analyze diagnostic performance measures of standardized typical CT findings for COVID-19 and examine these measures by region and national income. METHODS: MEDLINE and Embase were searched from January 2020 to April 2022 for diagnostic studies using the Radiological Society of North America (RSNA) classification or the COVID-19 Reporting and Data System (CO-RADS) for COVID-19. Patient and study characteristics were extracted. We pooled the diagnostic performance of typical CT findings in the RSNA and CO-RADS systems and interobserver agreement. Meta-regression was performed to examine the effect of potential explanatory factors on the diagnostic performance of the typical CT findings. RESULTS: We included 42 diagnostic performance studies with 6777 PCR-positive and 9955 PCR-negative patients from 18 developing and 24 developed countries covering the Americas, Europe, Asia, and Africa. The pooled sensitivity was 70% (95% confidence interval [CI]: 65%, 74%; I2 = 92%), and the pooled specificity was 90% (95% CI 86%, 93%; I2 = 94%) for the typical CT findings of COVID-19. The sensitivity and specificity of the typical CT findings did not differ significantly by national income and the region of the study (p > 0.1, respectively). The pooled interobserver agreement from 19 studies was 0.72 (95% CI 0.63, 0.81; I2 = 99%) for the typical CT findings and 0.67 (95% CI 0.61, 0.74; I2 = 99%) for the overall CT classifications. CONCLUSION: The standardized typical CT findings for COVID-19 provided moderate sensitivity and high specificity globally, regardless of region and national income, and were highly reproducible between radiologists. CRITICAL RELEVANCE STATEMENT: Standardized typical CT findings for COVID-19 provided a reproducible high diagnostic accuracy globally. KEY POINTS: Standardized typical CT findings for COVID-19 provide high sensitivity and specificity. Typical CT findings show high diagnosability regardless of region or income. The interobserver agreement for typical findings of COVID-19 is substantial.

Artificial intelligence to predict the need for mechanical ventilation in cases of severe COVID-19.

Objective: To determinate the accuracy of computed tomography (CT) imaging assessed by deep neural networks for predicting the need for mechanical ventilation (MV) in patients hospitalized with severe acute respiratory syndrome due to coronavirus disease 2019 (COVID-19). Materials and Methods: This was a retrospective cohort study carried out at two hospitals in Brazil. We included CT scans from patients who were hospitalized due to severe acute respiratory syndrome and had COVID-19 confirmed by reverse transcription-polymerase chain reaction (RT-PCR). The training set consisted of chest CT examinations from 823 patients with COVID-19, of whom 93 required MV during hospitalization. We developed an artificial intelligence (AI) model based on convolutional neural networks. The performance of the AI model was evaluated by calculating its accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve. Results: For predicting the need for MV, the AI model had a sensitivity of 0.417 and a specificity of 0.860. The corresponding area under the ROC curve for the test set was 0.68. Conclusion: The high specificity of our AI model makes it able to reliably predict which patients will and will not need invasive ventilation. That makes this approach ideal for identifying high-risk patients and predicting the minimum number of ventilators and critical care beds that will be required.

Objetivo: Determinar a acurácia da tomografia computadorizada (TC), avaliada por redes neurais profundas, na ventilação mecânica, de pacientes hospitalizados por síndrome respiratória aguda grave por COVID-19. Materiais e Métodos: Trata-se de estudo de coorte retrospectivo, realizado em dois hospitais brasileiros. Foram incluídas TCs de pacientes hospitalizados por síndrome respiratória aguda grave e COVID-19 confirmada por RT-PCR. O treinamento consistiu em TC de tórax de 823 pacientes com COVID-19, dos quais 93 foram submetidos a ventilação mecânica na hospitalização. Nós desenvolvemos um modelo de inteligência artificial baseado em redes de convoluções neurais. A avaliação do desempenho do uso da inteligência artificial foi baseada no cálculo de acurácia, sensibilidade, especificidade e área sob a curva ROC. Resultados: A sensibilidade do modelo foi de 0,417 e a especificidade foi de 0,860. A área sob a curva ROC para o conjunto de teste foi de 0,68. Conclusão: Criamos um modelo de aprendizado de máquina com elevada especificidade, capaz de prever de forma confiável pacientes que não precisarão de ventilação mecânica. Isso significa que essa abordagem é ideal para prever com antecedência pacientes de alto risco e um número mínimo de equipamentos de ventilação e de leitos críticos.

Myocardial extracellular volume assessment at CT in hospitalized COVID-19 patients with regards to pulmonary embolism.

PURPOSE: To evaluate myocardial status through the assessment of extracellular volume (ECV) calculated at computed tomography (CT) in patients hospitalized for novel coronavirus disease (COVID-19), with regards to the presence of pulmonary embolism (PE) as a risk factor for cardiac dysfunction. METHOD: Hospitalized patients with COVID-19 who underwent contrast-enhanced CT at our institution were retrospectively included in this study and grouped with regards to the presence of PE. Unenhanced and portal venous phase scans were used to calculate ECV by placing regions of interest in the myocardial septum and left ventricular blood pool. ECV values were compared between patients with and without PE, and correlations between ECV values and clinical or technical variables were subsequently appraised. RESULTS: Ninety-four patients were included, 63/94 of whom males (67%), with a median age of 70 (IQR 56-76 years); 28/94 (30%) patients presented with PE. Patients with PE had a higher myocardial ECV than those without (33.5%, IQR 29.4-37.5% versus 29.8%, IQR 25.1-34.0%; p = 0.010). There were no correlations between ECV and patients' age (p = 0.870) or sex (p = 0.122), unenhanced scan voltage (p = 0.822), portal phase scan voltage (p = 0.631), overall radiation dose (p = 0.569), portal phase scan timing (p = 0.460), and contrast agent dose (p = 0.563). CONCLUSIONS: CT-derived ECV could help identify COVID-19 patients at higher risk of cardiac dysfunction, especially when related to PE, to potentially plan a dedicated, patient-tailored clinical approach.

A multicenter evaluation of a deep learning software (LungQuant) for lung parenchyma characterization in COVID-19 pneumonia.

BACKGROUND: The role of computed tomography (CT) in the diagnosis and characterization of coronavirus disease 2019 (COVID-19) pneumonia has been widely recognized. We evaluated the performance of a software for quantitative analysis of chest CT, the LungQuant system, by comparing its results with independent visual evaluations by a group of 14 clinical experts. The aim of this work is to evaluate the ability of the automated tool to extract quantitative information from lung CT, relevant for the design of a diagnosis support model. METHODS: LungQuant segments both the lungs and lesions associated with COVID-19 pneumonia (ground-glass opacities and consolidations) and computes derived quantities corresponding to qualitative characteristics used to clinically assess COVID-19 lesions. The comparison was carried out on 120 publicly available CT scans of patients affected by COVID-19 pneumonia. Scans were scored for four qualitative metrics: percentage of lung involvement, type of lesion, and two disease distribution scores. We evaluated the agreement between the LungQuant output and the visual assessments through receiver operating characteristics area under the curve (AUC) analysis and by fitting a nonlinear regression model. RESULTS: Despite the rather large heterogeneity in the qualitative labels assigned by the clinical experts for each metric, we found good agreement on the metrics compared to the LungQuant output. The AUC values obtained for the four qualitative metrics were 0.98, 0.85, 0.90, and 0.81. CONCLUSIONS: Visual clinical evaluation could be complemented and supported by computer-aided quantification, whose values match the average evaluation of several independent clinical experts. KEY POINTS: We conducted a multicenter evaluation of the deep learning-based LungQuant automated software. We translated qualitative assessments into quantifiable metrics to characterize coronavirus disease 2019 (COVID-19) pneumonia lesions. Comparing the software output to the clinical evaluations, results were satisfactory despite heterogeneity of the clinical evaluations. An automatic quantification tool may contribute to improve the clinical workflow of COVID-19 pneumonia.

Chest computed tomography analysis of lung sparing morphology: differentiation of COVID-19 pneumonia from influenza pneumonia and bacterial pneumonia using the arched bridge and vacuole signs.

INTRODUCTION: This study evaluated the arched bridge and vacuole signs, which constitute morphological patterns of lung sparing in coronavirus disease 2019 (COVID-19), then examined whether these signs could be used to differentiate COVID-19 pneumonia from influenza pneumonia or bacterial pneumonia. METHODS: In total, 187 patients were included: 66 patients with COVID-19 pneumonia, 50 patients with influenza pneumonia and positive computed tomography findings, and 71 patients with bacterial pneumonia and positive computed tomography findings. Images were independently reviewed by two radiologists. The incidences of the arched bridge sign and/or vacuole sign were compared among the COVID-19 pneumonia, influenza pneumonia, and bacterial pneumonia groups. RESULTS: The arched bridge sign was much more common among patients with COVID-19 pneumonia (42/66, 63.6%) than among patients with influenza pneumonia (4/50, 8.0%; P<0.001) or bacterial pneumonia (4/71, 5.6%; P<0.001). The vacuole sign was also much more common among patients with COVID-19 pneumonia (14/66, 21.2%) than among patients with influenza pneumonia (1/50, 2.0%; P=0.005) or bacterial pneumonia (1/71, 1.4%; P<0.001). The signs occurred together in 11 (16.7%) patients with COVID-19 pneumonia, but they did not occur together in patients with influenza pneumonia or bacterial pneumonia. The arched bridge and vacuole signs predicted COVID-19 pneumonia with respective specificities of 93.4% and 98.4%. CONCLUSION: The arched bridge and vacuole signs are much more common in patients with COVID-19 pneumonia and can help differentiate COVID-19 pneumonia from influenza and bacterial pneumonia.

Role of Sonography in COVID-19 Lung Imaging

The article discusses the key role played by sonography in conducting lung imaging to patients infected with Covid-19. Also cited are the use of computed tomography (CT) imaging of the chest to diagnose and manage patients with suspected or confirmed coronavirus infection, and the benefits of sonography like its lack of ionizing radiation and low price and maintenance costs.

COVID-19 and vaccination impact on radiology departments provided by Dose Archiving and Communication System.

OBJECTIVES: To study the impact of COVID-19 on chest CT practice during the different waves using Dose Archiving and Communication System (DACS). METHODS: Retrospective study including data from 86,136 chest CT acquisitions from 27 radiology centers (15 private; 12 public) between January 1, 2020, and October 13, 2021, using a centralized DACS. Daily chest CT activity and dosimetry information such as dose length product (DLP), computed tomography dose index (CTDI), and acquisition parameters were collected. Pandemic indicators (daily tests performed, incidence, and hospital admissions) and vaccination rates were collected from a governmental open-data platform. Descriptive statistics and correlation analysis were performed. RESULTS: For the first two waves, strong positive and significant correlations were found between all pandemic indicators and total chest CT activity, as high as R = 0.7984 between daily chest CT activity and hospital admissions during the second wave (p < 0.0001). We found differences between public hospitals and private imaging centers during the first wave, with private centers demonstrating a negative correlation between daily chest CT activity and hospital admissions (-0.2819, p = 0.0019). Throughout the third wave, simultaneously with the rise of vaccination rates, total chest CT activity decreased with significant negative correlations with pandemic indicators, such as R = -0.7939 between daily chest CTs and daily incidence (p < 0.0001). Finally, less than 5% of all analyzed chest CTs could be considered as low dose. CONCLUSIONS: During the first waves, COVID-19 had a strong impact on chest CT practice which was lost with the arrival of vaccination. Low-dose protocols remained marginal. KEY POINTS: • There was a significant correlation between the number of daily chest CTs and pandemic indicators throughout the first two waves. It was lost during the third wave due to vaccination arrival. • Differences were observed between public and private centers, especially during the first wave, less during the second, and were lost during the third. • During the first three waves of COVID-19 pandemic, few CT helical acquisitions could be considered as low dose with only 3.8% of the acquisitions according to CTDIvol and 4.3% according to DLP.

Utilizing Clustering FCM And Contrast Based Enhancement to Isolate Covid-19 Infected Regions in CT Lung Images

Covid-19 disease that directly affecting lungs is an acute disease caused death of many people around word, so the early detecting of it and asses the relative ratio of the lung infection is a vital need. In this work, Histogram based contrast adjustment was implemented to enhance four lung abnormal CT scan images to highlight the abnormal regions within the experimental images. Fuzzy c-mean algorithm then was applied to segment the images in order to detect and isolate the infected regions. Besides, several morphological operations were employed to extract the refined infected Covid-19 areas effectively with accuracy of 96%.

Detection Of Covid19 in Lung X-Rays Using Deep Learning Algorithms

The World Health Organization (WHO) compiled this medical imaging reference guide in response to the emergence of the COVID-19 virus. The Beijing Country Office of the World Health Organization learned on December 31 that there was an epidemic of pneumonia patients in Wuhan, China. The causative agent of the pandemic was quickly identified as a novel coronavirus. In 2019, we should anticipate seeing an increase in the prevalence of coronavirus sickness, also known as the SARS-CoV-2 virus, and the SARS-CoV-1 virus. In order to determine the presence of this virus (COVID-19), we have created two models. Finally, the distorted part of the image was located. Some of the processes that we go through regularly have been the subject of our efforts to automate them. Using Resnet-18 models in combination with Deep Convolutional Neural Network (DenseNet-121 & Resnet-18) models, we were able to successfully detect COVID-19. The Densenet-121 model did well in its training and evaluation on a dataset of 1600 chest X-ray images. Over 2700 CXR pictures may be used for model training and evaluation with Resnet18. We have separated the data into groups according to the suggested models and found widely varying degrees of precision across the board. Data from both sources showed that Densenet-121 was the most reliable model.

Role of Sonography in COVID-19 Lung Imaging

The article discusses the key role played by sonography in conducting lung imaging to patients infected with Covid-19. Also cited are the use of computed tomography (CT) imaging of the chest to diagnose and manage patients with suspected or confirmed coronavirus infection, and the benefits of sonography like its lack of ionizing radiation and low price and maintenance costs.

Diagnostic Performance in Differentiating COVID-19 from Other Viral Pneumonias on CT Imaging: Multi-Reader Analysis Compared with an Artificial Intelligence-Based Model.

Growing evidence suggests that artificial intelligence tools could help radiologists in differentiating COVID-19 pneumonia from other types of viral (non-COVID-19) pneumonia. To test this hypothesis, an R-AI classifier capable of discriminating between COVID-19 and non-COVID-19 pneumonia was developed using CT chest scans of 1031 patients with positive swab for SARS-CoV-2 (n = 647) and other respiratory viruses (n = 384). The model was trained with 811 CT scans, while 220 CT scans (n = 151 COVID-19; n = 69 non-COVID-19) were used for independent validation. Four readers were enrolled to blindly evaluate the validation dataset using the CO-RADS score. A pandemic-like high suspicion scenario (CO-RADS 3 considered as COVID-19) and a low suspicion scenario (CO-RADS 3 considered as non-COVID-19) were simulated. Inter-reader agreement and performance metrics were calculated for human readers and R-AI classifier. The readers showed good agreement in assigning CO-RADS score (Gwet's AC2 = 0.71, p < 0.001). Considering human performance, accuracy = 78% and accuracy = 74% were obtained in the high and low suspicion scenarios, respectively, while the AI classifier achieved accuracy = 79% in distinguishing COVID-19 from non-COVID-19 pneumonia on the independent validation dataset. The R-AI classifier performance was equivalent or superior to human readers in all comparisons. Therefore, a R-AI classifier may support human readers in the difficult task of distinguishing COVID-19 from other types of viral pneumonia on CT imaging.

Interleukin 18 and IL-18 BP response to Sars-CoV-2 virus infection.

The immune response to the SARS-CoV-2 infection is crucial to the patient outcome. IL-18 is involved in the lymphocyte response to the disease and it is well established its important role in the complex developing of the host response to viral infection. This study aims at the analysis of the concentrations of IL-18, IL-18BP, INF-γ at the onset of the SARS-CoV-2 infection. The serum levels of measured interleukins were obtained through enzyme-linked immunosorbent assay. Furthermore, the free fraction of IL-18 was numerically evaluated. The enrolled patients were divided in two severity groups according to a threshold value of 300 for the ratio of arterial partial pressure of oxygen and fraction of inspired oxygen fraction and according to the parenchymal involvement as evaluated by computerized tomography at the admittance. In the group of patients with a more severe disease, a significant increase of the IL-18, INF-γ and IL-18BP levels have been observed, whereas the free IL-18 component values were almost constant. The results confirm that, at the onset of the disease, the host response keep the inflammatory cytokines in an equilibrium and support the hypothesis to adopt the IL-18BP modulation as a possible and effective therapeutic approach.

Mediastinal Emphysema, Giant Bulla, and Pneumothorax Developed during the Course of COVID-19 Pneumonia.

The coronavirus disease 2019 (COVID-19) pneumonia is a recent outbreak in mainland China and has rapidly spread to multiple countries worldwide. Pulmonary parenchymal opacities are often observed during chest radiography. Currently, few cases have reported the complications of severe COVID-19 pneumonia. We report a case where serial follow-up chest computed tomography revealed progression of pulmonary lesions into confluent bilateral consolidation with lower lung predominance, thereby confirming COVID-19 pneumonia. Furthermore, complications such as mediastinal emphysema, giant bulla, and pneumothorax were also observed during the course of the disease.

2019 Novel Coronavirus (COVID-19) Pneumonia: Serial Computed Tomography Findings.

From December 2019, Coronavirus disease 2019 (COVID-19) pneumonia (formerly known as the 2019 novel Coronavirus [2019-nCoV]) broke out in Wuhan, China. In this study, we present serial CT findings in a 40-year-old female patient with COVID-19 pneumonia who presented with the symptoms of fever, chest tightness, and fatigue. She was diagnosed with COVID-19 infection confirmed by real-time reverse-transcriptase-polymerase chain reaction. CT showed rapidly progressing peripheral consolidations and ground-glass opacities in both lungs. After treatment, the lesions were shown to be almost absorbed leaving the fibrous lesions.

Facilitating standardized COVID-19 suspicion prediction based on computed tomography radiomics in a multi-demographic setting.

OBJECTIVE: To develop an automatic COVID-19 Reporting and Data System (CO-RADS)-based classification in a multi-demographic setting. METHODS: This multi-institutional review boards-approved retrospective study included 2720 chest CT scans (mean age, 58 years [range 18-100 years]) from Italian and Russian patients. Three board-certified radiologists from three countries assessed randomly selected subcohorts from each population and provided CO-RADS-based annotations. CT radiomic features were extracted from the selected subcohorts after preprocessing steps like lung lobe segmentation and automatic noise reduction. We compared three machine learning models, logistic regression (LR), multilayer perceptron (MLP), and random forest (RF) for the automated CO-RADS classification. Model evaluation was carried out in two scenarios, first, training on a mixed multi-demographic subcohort and testing on an independent hold-out dataset. In the second scenario, training was done on a single demography and externally validated on the other demography. RESULTS: The overall inter-observer agreement for the CO-RADS scoring between the radiologists was substantial (k = 0.80). Irrespective of the type of validation test scenario, suspected COVID-19 CT scans were identified with an accuracy of 84%. SHapley Additive exPlanations (SHAP) interpretation showed that the "wavelet_(LH)_GLCM_Imc1" feature had a positive impact on COVID prediction both with and without noise reduction. The application of noise reduction improved the overall performance between the classifiers for all types. CONCLUSION: Using an automated model based on the COVID-19 Reporting and Data System (CO-RADS), we achieved clinically acceptable performance in a multi-demographic setting. This approach can serve as a standardized tool for automated COVID-19 assessment. KEYPOINTS: • Automatic CO-RADS scoring of large-scale multi-demographic chest CTs with mean AUC of 0.93 ± 0.04. • Validation procedure resembles TRIPOD 2b and 3 categories, enhancing the quality of experimental design to test the cross-dataset domain shift between institutions aiding clinical integration. • Identification of COVID-19 pneumonia in the presence of community-acquired pneumonia and other comorbidities with an AUC of 0.92.

Concomitant COVID-19 and pulmonary tuberculosis: computed tomography aspects.

OBJECTIVE: To describe the relationship between coronavirus disease 2019 (COVID-19) and pulmonary tuberculosis during the current pandemic, as well as to describe the main computed tomography (CT) findings in patients suffering from both diseases simultaneously. MATERIALS AND METHODS: This was a retrospective, cross-sectional observational study of the chest CT scans of 360 patients with COVID-19, as confirmed by RT-PCR. RESULTS: In four (1.1%) of the patients, changes suggestive of COVID-19 and tuberculosis were observed on the initial CT scan of the chest. On chest CT scans performed for the follow-up of COVID-19, cavitary lesions with bronchogenic spread were observed in two of the four patients, whereas alterations consistent with the progression of fibrous scarring related to previous tuberculosis were observed in the two other patients. The diagnosis of tuberculosis was confirmed by the isolation of Mycobacterium tuberculosis. CONCLUSION: Albeit rare, concomitant COVID-19 and tuberculosis can be suggested on the basis of the CT aspects. Radiologists should be aware of this possibility, because initial studies indicate that mortality rates are higher in patients suffering from both diseases simultaneously.

OBJETIVO: Descrever a associação entre COVID-19 e tuberculose pulmonar durante a pandemia atual e descrever os principais achados tomográficos. MATERIAIS E MÉTODOS: Estudo retrospectivo transversal e observacional de tomografias computadorizadas de tórax realizadas em 360 pacientes com COVID-19 confirmada por RT-PCR. RESULTADOS: Em quatro pacientes (1,1%) foram encontradas alterações tomográficas sugestivas de associação entre COVID-19 e tuberculose. Em dois pacientes observaram-se escavações com disseminação broncogênica e em outros dois, alterações compatíveis com progressão de lesões fibrocicatriciais relacionadas a tuberculose prévia, em exames de controle para COVID-19. O diagnóstico foi confirmado pelo isolamento do Mycobacterium tuberculosis. CONCLUSÃO: Apesar de incomum, a associação entre COVID-19 e tuberculose pode ser sugerida com base em aspectos tomográficos, devendo os radiologistas estar atentos a esta possibilidade, pois estudos iniciais indicam aumento da mortalidade nesses pacientes.