The Role of Chest Imaging in Patient Management During the COVID-19 Pandemic: A Multinational Consensus Statement From the Fleischner Society

Dissociation between the clinical course and chest imaging in severe COVID-19 pneumonia: A series of five cases

BACKGROUND

Although an RT-PCR test is the "gold standard" tool for diagnosing an infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), chest imaging can be used to support a diagnosis of coronavirus disease 2019 (COVID-19) - albeit with fairly low specificity. However, if the chest imaging findings do not faithfully reflect the patient's clinical course, one can question the rationale for relying on these imaging data in the diagnosis of COVID-19.

AIMS

To compare clinical courses with changes over time in chest imaging findings among patients admitted to an ICU for severe COVID-19 pneumonia.

METHODS

We retrospectively reviewed the medical charts of all adult patients admitted to our intensive care unit (ICU) between March 1, 2020, and April 15, 2020, for a severe COVID-19 lung infection and who had a positive RT-PCR test. Changes in clinical, laboratory and radiological variables were compared, and patients with discordant changes over time (e.g. a clinical improvement with stable or worse radiological findings) were analyzed further.

RESULTS

Of the 46 included patients, 5 showed an improvement in their clinical status but not in their chest imaging findings. On admission to the ICU, three of the five were mechanically ventilated and the two others received high-flow oxygen therapy or a non-rebreather mask. Even though the five patients' radiological findings worsened or remained stable, the mean ± standard deviation partial pressure of arterial oxygen to the fraction of inspired oxygen (PaO₂:FiO₂) ratio increased significantly in all cases (from 113.2 ± 59.7 mmHg at admission to 259.8 ± 59.7 mmHg at a follow-up evaluation; p=0.043).

INTERPRETATION

Our results suggest that in cases of clinical improvement with worsened or stable chest imaging variables, the PaO2:FiO2 ratio might be a good marker of the resolution of COVID-19-specific pulmonary vascular insult.

Thoracic imaging outcomes in COVID-19 survivors

The coronavirus disease 2019 (COVID-19) pandemic presents a significant global public health challenge. One in five individuals with COVID-19 presents with symptoms that last for weeks after hospital discharge, a condition termed "long COVID". Thus, efficient follow-up of patients is needed to assess the resolution of lung pathologies and systemic involvement. Thoracic imaging is multimodal and involves using different forms of waves to produce images of the organs within the thorax. In general, it includes chest X-ray, computed tomography, lung ultrasound and magnetic resonance imaging techniques. Such modalities have been useful in the diagnosis and prognosis of COVID-19. These tools have also allowed for the follow-up and assessment of long COVID. This review provides insights on the effectiveness of thoracic imaging techniques in the follow-up of COVID-19 survivors who had long COVID.

Imaging in the COVID-19 era: Lessons learned during a pandemic

The first year of the coronavirus disease 2019 (COVID-19) pandemic has been a year of unprecedented changes, scientific breakthroughs, and controversies. The radiology community has not been spared from the challenges imposed on global healthcare systems. Radiology has played a crucial part in tackling this pandemic, either by demonstrating the manifestations of the virus and guiding patient management, or by safely handling the patients and mitigating transmission within the hospital. Major modifications involving all aspects of daily radiology practice have occurred as a result of the pandemic, including workflow alterations, volume reductions, and strict infection control strategies. Despite the ongoing challenges, considerable knowledge has been gained that will guide future innovations. The aim of this review is to provide the latest evidence on the role of imaging in the diagnosis of the multifaceted manifestations of COVID-19, and to discuss the implications of the pandemic on radiology departments globally, including infection control strategies and delays in cancer screening. Lastly, the promising contribution of artificial intelligence in the COVID-19 pandemic is explored.

Evaluation of initial chest computed tomography (CT) findings of COVID-19 pneumonia in 117 deceased patients: a retrospective study

Background/aim

There is no study in the literature in which only chest computed tomography (CT) findings of deceased cases obtained at admission were examined, and the relationship between these findings and mortality was evaluated.

Materials and methods

In this retrospective study, a total of 117 deceased patients with COVID-19 infection confirmed by positive polymerase chain reaction and undergone chest CT were enrolled. We evaluated initial chest CT findings and their relationship, location, prevalence, and the frequency with mortality.

Results

The mean age of patients was 73 ±18 years; 71 of all patients were male and 46 were female. The predominant feature was pure ground-glass opacity (GGO) lesion (82.0%), and 59.8% of cases had pure consolidation. There was no cavitation or architectural distorsion. Pericardial effusion was found in 9.4% the patients, and pleural effusions were found in 15.3% of them. Mediastinal lymphadenopathy was only 11.9% in total.

Conclusion

In deceased patients, on admission CTs, pure consolidation, pleural and pericardial effusion, mediastinal LAP were more common than ordinary cases. It was these findings that should also raise the concern when they were seen on chest CT; therefore, these radiologic features have the potential to represent prognostic imaging markers in patients with COVID-19 pneumonia.

COVID-19 imaging: Diagnostic approaches, challenges, and evolving advances

The role of radiology and the radiologist have evolved throughout the coronavirus disease-2019 (COVID-19) pandemic. Early on, chest computed tomography was used for screening and diagnosis of COVID-19; however, it is now indicated for high-risk patients, those with severe disease, or in areas where polymerase chain reaction testing is sparsely available. Chest radiography is now utilized mainly for monitoring disease progression in hospitalized patients showing signs of worsening clinical status. Additionally, many challenges at the operational level have been overcome within the field of radiology throughout the COVID-19 pandemic. The use of teleradiology and virtual care clinics greatly enhanced our ability to socially distance and both are likely to remain important mediums for diagnostic imaging delivery and patient care. Opportunities to better utilize of imaging for detection of extrapulmonary manifestations and complications of COVID-19 disease will continue to arise as a more detailed understanding of the pathophysiology of the virus continues to be uncovered and identification of predisposing risk factors for complication development continue to be better understood. Furthermore, unidentified advancements in areas such as standardized imaging reporting, point-of-care ultrasound, and artificial intelligence offer exciting discovery pathways that will inevitably lead to improved care for patients with COVID-19.

Diagnostic Performance of COVID-19 Reporting and Data System Classification Across Residents and Radiologists: A Retrospective Study

OBJECTIVE

The aim of the study was to evaluate the interobserver agreement and diagnostic accuracy of COVID-19 Reporting and Data System (CO-RADS), in patients suspected COVID-19 pneumonia.

METHODS

Two hundred nine nonenhanced chest computed tomography images of patients with clinically suspected COVID-19 pneumonia were included. The images were evaluated by 2 groups of observers, consisting of 2 residents-radiologists, using CO-RADS. Reverse transcriptase-polymerase chain reaction (PCR) was used as a reference standard for diagnosis in this study. Sensitivity, specificity, area under receiver operating characteristic curve (AUC), and intraobserver/interobserver agreement were calculated.

RESULTS

COVID-19 Reporting and Data System was able to distinguish patients with positive PCR results from those with negative PCR results with AUC of 0.796 in the group of residents and AUC of 0.810 in the group of radiologists. There was moderate interobserver agreement between residents and radiologist with κ values of 0.54 and 0.57.

CONCLUSIONS

The diagnostic performance of CO-RADS for predicting COVID-19 pneumonia showed moderate interobserver agreement between residents and radiologists.

A multicentre roadmap to restart elective cardiac surgery after COVID-19 peak in an Italian epicenter

BACKGROUND

During the Italian Phase-2 of the coronavirus pandemic, it was possible to restart elective surgeries. Because hospitals were still burdened with coronavirus disease 2019 (COVID-19) patients, it was focal to design a separate "clean path" for the surgical candidates and determine the possible effects of major surgery on previously infected patients.

METHODS

From May to July 2020 (postpandemic peak), 259 consecutive patients were scheduled for elective cardiac surgery in three different centers. Our original roadmap with four screening steps included: a short item questionnaire (STEP-1), nasopharyngeal swab (NP) (STEP-2), computed tomography (CT)-scan using COVID-19 reporting and data system (CO-RADS) scoring (STEP-3), and final NP swab before discharge (STEP-4).

RESULTS

Two patients (0.8%) resulted positive at STEP-2: one patient was discharged home for quarantine, the other performed a CT-scan (CO-RADS: <2), and underwent surgery for unstable angina. Chest-CT was positive in 6.3% (15/237) with mean CO-RADS of 2.93 ± 0.8. Mild-moderate lung inflammation (CO-RADS: 2-4) did not delay surgery. Perioperative mortality was 1.15% (3/259), and cumulative incidence of pulmonary complications was 14.6%. At multivariable analysis, only age and cardiopulmonary bypass (CPB) time were independently related to pulmonary complications composite outcome (age >75 years: odds ratio [OR]: 2.6; 95% confidence interval [CI]: 1.25-5.57; p = 0.011; CPB >90 min. OR: 4.3; 95% CI: 1.84-10.16; p = 0.001). At 30 days, no periprocedural contagion and rehospitalization for COVID-19 infections were reported.

CONCLUSIONS

Our structured roadmap supports the safe restarting of an elective cardiac surgery list after a peak of a still ongoing COVID-19 pandemic in an epicenter area. Mild to moderate CT residuals of coronavirus pneumonia do not justify elective cardiac surgery procrastination.

Coronavirus Disease (COVID-19): The Value of Chest Radiography for Patients Greater Than Age 50 Years at an Earlier Timepoint of Symptoms Compared With Younger Patients

Background: A relative paucity of data exists regarding chest radiography (CXR) in diagnosis of coronavirus disease (COVID-19) compared to computed tomography. We address the use of a strict pattern of CXR findings for COVID-19 diagnosis, specifically during early onset of symptoms with respect to patient age. Methods: We performed a retrospective study of patients under investigation for COVID-19 who presented to the emergency department during the COVID-19 outbreak of 2020 and had CXR within 1 week of symptoms. Only reverse transcription polymerase chain reaction (RT-PCR)-positive patients were included. Two board-certified radiologists, blinded to RT-PCR results, assessed 60 CXRs in consensus and assigned 1 of 3 patterns: characteristic, atypical, or negative. Atypical patterns were subdivided into more suspicious or less suspicious for COVID-19. Results: Sixty patients were included: 30 patients aged 52 to 88 years and 30 patients aged 19 to 48 years. Ninety-three percent of the older group demonstrated an abnormal CXR and were more likely to have characteristic and atypical-more suspicious findings in the first week after symptom onset than the younger group. The relationship between age and CXR findings was statistically significant (χ² [2, n=60]=15.70; P=0.00039). The relationship between negative and characteristic COVID-19 CXR findings between the 2 age cohorts was statistically significant with Fisher exact test resulting in a P value of 0.001. Conclusion: COVID-19 positive patients >50 years show earlier, characteristic patterns of statistically significant CXR changes than younger patients, suggesting that CXR is useful in the early diagnosis of infection. CXR can be useful in early diagnosis of COVID-19 in patients older than 50 years.

Covid-19 imaging: A narrative review

Background

The 2019 novel coronavirus disease (COVID-19) imaging data is dispersed in numerous publications. A cohesive literature review is to be assembled.

Objective

To summarize the existing literature on Covid-19 pneumonia imaging including precautionary measures for radiology departments, Chest CT's role in diagnosis and management, imaging findings of Covid-19 patients including children and pregnant women, artificial intelligence applications and practical recommendations.

Methods

A systematic literature search of PubMed/med line electronic databases.

Results

The radiology department's staff is on the front line of the novel coronavirus outbreak. Strict adherence to precautionary measures is the main defense against infection's spread. Although nucleic acid testing is Covid-19's pneumonia diagnosis gold standard; kits shortage and low sensitivity led to the implementation of the highly sensitive chest computed tomography amidst initial diagnostic tools. Initial Covid-19 CT features comprise bilateral, peripheral or posterior, multilobar ground-glass opacities, predominantly in the lower lobes. Consolidations superimposed on ground-glass opacifications are found in few cases, preponderantly in the elderly. In later disease stages, GGO transformation into multifocal consolidations, thickened interlobular and intralobular lines, crazy paving, traction bronchiectasis, pleural thickening, and subpleural bands are reported. Standardized CT reporting is recommended to guide radiologists. While lung ultrasound, pulmonary MRI, and PET CT are not Covid-19 pneumonia's first-line investigative diagnostic modalities, their characteristic findings and clinical value are outlined. Artificial intelligence's role in strengthening available imaging tools is discussed.

Conclusion

This review offers an exhaustive analysis of the current literature on imaging role and findings in COVID-19 pneumonia.

•

Chest computed tomography is a highly sensitive Covid −19 pneumonia's diagnostic tool.

•

Initial Covid-19 CT features are bilateral, multifocal, peripheral or posterior ground-glass opacities, mainly in the lower lobes.

•

Multifocal consolidations, bronchiectasis, pleural thickening, and subpleural bands are late disease stages features.

•

Standardized CT reporting is recommended to guide radiologists.

•

Artificial intelligence could strengthen available imaging tools.

Automatic lung segmentation in COVID-19 patients: Impact on quantitative computed tomography analysis

Purpose

To assess the impact of lung segmentation accuracy in an automatic pipeline for quantitative analysis of CT images.

Methods

Four different platforms for automatic lung segmentation based on convolutional neural network (CNN), region-growing technique and atlas-based algorithm were considered. The platforms were tested using CT images of 55 COVID-19 patients with severe lung impairment. Four radiologists assessed the segmentations using a 5-point qualitative score (QS). For each CT series, a manually revised reference segmentation (RS) was obtained. Histogram-based quantitative metrics (QM) were calculated from CT histogram using lung segmentationsfrom all platforms and RS. Dice index (DI) and differences of QMs (ΔQMs) were calculated between RS and other segmentations.

Results

Highest QS and lower ΔQMs values were associated to the CNN algorithm. However, only 45% CNN segmentations were judged to need no or only minimal corrections, and in only 17 cases (31%), automatic segmentations provided RS without manual corrections. Median values of the DI for the four algorithms ranged from 0.993 to 0.904. Significant differences for all QMs calculated between automatic segmentations and RS were found both when data were pooled together and stratified according to QS, indicating a relationship between qualitative and quantitative measurements. The most unstable QM was the histogram 90th percentile, with median ΔQMs values ranging from 10HU and 158HU between different algorithms.

Conclusions

None of tested algorithms provided fully reliable segmentation. Segmentation accuracy impacts differently on different quantitative metrics, and each of them should be individually evaluated according to the purpose of subsequent analyses.

Enhance Portable Radiograph for Fast and High Accurate COVID-19 Monitoring

This work aimed to assist physicians by improving their speed and diagnostic accuracy when interpreting portable CXRs as well as monitoring the treatment process to see whether a patient is improving or deteriorating with treatment. These objectives are in especially high demand in the setting of the ongoing COVID-19 pandemic. With the recent progress in the development of artificial intelligence (AI), we introduce new deep learning frameworks to align and enhance the quality of portable CXRs to be more consistent, and to more closely match higher quality conventional CXRs. These enhanced portable CXRs can then help the doctors provide faster and more accurate diagnosis and treatment planning. The contributions of this work are four-fold. Firstly, a new database collection of subject-pair radiographs is introduced. For each subject, we collected a pair of samples from both portable and conventional machines. Secondly, a new deep learning approach is presented to align the subject-pairs dataset to obtain a pixel-pairs dataset. Thirdly, a new PairFlow approach is presented, an end-to-end invertible transfer deep learning method, to enhance the degraded quality of portable CXRs. Finally, the performance of the proposed system is evaluated by UAMS doctors in terms of both image quality and topological properties. This work was undertaken in collaboration with the Department of Radiology at the University of Arkansas for Medical Sciences (UAMS) to enhance portable/mobile COVID-19 CXRs, to improve the speed and accuracy of portable CXR images and aid in urgent COVID-19 diagnosis, monitoring and treatment.

On the role of artificial intelligence in medical imaging of COVID-19

Although a plethora of research articles on AI methods on COVID-19 medical imaging are published, their clinical value remains unclear. We conducted the largest systematic review of the literature addressing the utility of AI in imaging for COVID-19 patient care. By keyword searches on PubMed and preprint servers throughout 2020, we identified 463 manuscripts and performed a systematic meta-analysis to assess their technical merit and clinical relevance. Our analysis evidences a significant disparity between clinical and AI communities, in the focus on both imaging modalities (AI experts neglected CT and ultrasound, favoring X-ray) and performed tasks (71.9% of AI papers centered on diagnosis). The vast majority of manuscripts were found to be deficient regarding potential use in clinical practice, but 2.7% (n = 12) publications were assigned a high maturity level and are summarized in greater detail. We provide an itemized discussion of the challenges in developing clinically relevant AI solutions with recommendations and remedies.

Quality of and Recommendations for Relevant Clinical Practice Guidelines for COVID-19 Management: A Systematic Review and Critical Appraisal

Background: The morbidity and mortality of coronavirus disease 2019 (COVID-19) are still increasing. This study aimed to assess the quality of relevant COVID-19 clinical practice guidelines (CPGs) and to compare the similarities and differences between recommendations. Methods: A comprehensive search was conducted using electronic databases (PubMed, Embase, and Web of Science) and representative guidelines repositories from December 1, 2019, to August 11, 2020 (updated to April 5, 2021), to obtain eligible CPGs. The Appraisal of Guidelines for Research and Evaluation (AGREE II) tool was used to evaluate the quality of CPGs. Four authors extracted relevant information and completed data extraction forms. All data were analyzed using R version 3.6.0 software. Results: In total, 39 CPGs were identified and the quality was not encouragingly high. The median score (interquartile range, IQR) of every domain from AGREE II for evidence-based CPGs (EB-CPGs) versus (vs.) consensus-based CPG (CB-CPGs) was 81.94% (75.00-84.72) vs. 58.33% (52.78-68.06) in scope and purpose, 59.72% (38.89-75.00) vs. 36.11% (33.33-36.11) in stakeholder involvement, 64.58% (32.29-71.88) vs. 22.92% (16.67-26.56) in rigor of development, 75.00% (52.78-86.81) vs. 52.78% (50.00-63.89) in clarity of presentation, 40.63% (22.40-62.50) vs. 20.83% (13.54-25.00) in applicability, and 58.33% (50.00-100.00) vs. 50.00% (50.00-77.08) in editorial independence, respectively. The methodological quality of EB-CPGs were significantly superior to the CB-CPGs in the majority of domains (P < 0.05). There was no agreement on diagnosis criteria of COVID-19. But a few guidelines show Remdesivir may be beneficial for the patients, hydroxychloroquine +/- azithromycin may not, and there were more consistent suggestions regarding discharge management. For instance, after discharge, isolation management and health status monitoring may be continued. Conclusions: In general, the methodological quality of EB-CPGs is greater than CB-CPGs. However, it is still required to be further improved. Besides, the consistency of COVID-19 recommendations on topics such as diagnosis criteria is different. Of them, hydroxychloroquine +/- azithromycin may be not beneficial to treat patients with COVID-19, but remdesivir may be a favorable risk-benefit in severe COVID-19 infection; isolation management and health status monitoring after discharge may be still necessary. Chemoprophylaxis, including SARS-CoV 2 vaccines and antiviral drugs of COVID-19, still require more trials to confirm this.

Could chest CT findings taken on admission in symptomatic patients with COVID-19 be related to the prognosis and clinical outcome of the disease?

AIM

Initial chest CT findings of patients were compared by grouping them according to the clinical outcome of the infection and those which could predict clinical outcome, prognosis and mortality were investigated.

BACKGROUND

Published studies on chest CT in COVID-19 infection do not go beyond describing the characteristics of the current period. Nevertheless, comparative analysis of chest CT findings on hospital admission among patients in different clinical outcomes is scarce.

OBJECTIVE

198 consecutive symptomatic patients with COVID-19 infection confirmed by positive polymerase chain reaction (PCR) and who had undergone chest CT were enrolled in this retrospective study.

METHOD

According to their clinical outcomes, we divided them (n:98) into 3 groups. Group 1 (n: 62) involved patients discharged from the service, group 2 (n: 60) included patients hospitalized in the intensive care unit, and group 3 (n: 76) comprised patients who died despite any treatment.

RESULTS

Clinical characteristics involving age, dyspnea, hypertension, and chest CT findings of mediastinal lymphadenopathy, pleural effusion, and pericardial effusion, were determined as poor prognosis and mortality predictors, and halo sign in chest CT finding was a good prognosis predictor in multivariate analysis.

CONCLUSION

It was seen that some CT findings were significantly correlated to the patients' endpoints, such as discharge, hospitalization in the intensive care unit, and as a worst consequence, death. These findings support the role of CT imaging for potentially predicting the clinical outcomes of these patients with COVID-19.

Risk Stratification for ECMO Requirement in COVID-19 ICU Patients Using Quantitative Imaging Features in CT Scans on Admission

(1) Background: Extracorporeal membrane oxygenation (ECMO) therapy in intensive care units (ICUs) remains the last treatment option for Coronavirus disease 2019 (COVID-19) patients with severely affected lungs but is highly resource demanding. Early risk stratification for the need of ECMO therapy upon admission to the hospital using artificial intelligence (AI)-based computed tomography (CT) assessment and clinical scores is beneficial for patient assessment and resource management; (2) Methods: Retrospective single-center study with 95 confirmed COVID-19 patients admitted to the participating ICUs. Patients requiring ECMO therapy (n = 14) during ICU stay versus patients without ECMO treatment (n = 81) were evaluated for discriminative clinical prediction parameters and AI-based CT imaging features and their diagnostic potential to predict ECMO therapy. Reported patient data include clinical scores, AI-based CT findings and patient outcomes; (3) Results: Patients subsequently allocated to ECMO therapy had significantly higher sequential organ failure (SOFA) scores (p < 0.001) and significantly lower oxygenation indices on admission (p = 0.009) than patients with standard ICU therapy. The median time from hospital admission to ECMO placement was 1.4 days (IQR 0.2-4.0). The percentage of lung involvement on AI-based CT assessment on admission to the hospital was significantly higher in ECMO patients (p < 0.001). In binary logistic regression analyses for ECMO prediction including age, sex, body mass index (BMI), SOFA score on admission, lactate on admission and percentage of lung involvement on admission CTs, only SOFA score (OR 1.32, 95% CI 1.08-1.62) and lung involvement (OR 1.06, 95% CI 1.01-1.11) were significantly associated with subsequent ECMO allocation. Receiver operating characteristic (ROC) curves showed an area under the curve (AUC) of 0.83 (95% CI 0.73-0.94) for lung involvement on admission CT and 0.82 (95% CI 0.72-0.91) for SOFA scores on ICU admission. A combined parameter of SOFA on ICU admission and lung involvement on admission CT yielded an AUC of 0.91 (0.84-0.97) with a sensitivity of 0.93 and a specificity of 0.84 for ECMO prediction; (4) Conclusions: AI-based assessment of lung involvement on CT scans on admission to the hospital and SOFA scoring, especially if combined, can be used as risk stratification tools for subsequent requirement for ECMO therapy in patients with severe COVID-19 disease to improve resource management in ICU settings.

Assessing COVID-19 pneumonia-Clinical extension and risk with point-of-care ultrasound: A multicenter, prospective, observational study

BACKGROUND

Assessing the extent of lung involvement is important for the triage and care of COVID-19 pneumonia. We sought to determine the utility of point-of-care ultrasound (POCUS) for characterizing lung involvement and, thereby, clinical risk determination in COVID-19 pneumonia.

METHODS

This multicenter, prospective, observational study included patients with COVID-19 who received 12-zone lung ultrasound and chest computed tomography (CT) scanning in the emergency department (ED). We defined lung disease severity using the lung ultrasound score (LUS) and chest CT severity score (CTSS). We assessed the association between the LUS and poor outcome (ICU admission or 30-day all-cause mortality). We also assessed the association between the LUS and hospital length of stay. We examined the ability of the LUS to differentiate between disease severity groups. Lastly, we estimated the correlation between the LUS and CTSS and the interrater agreement for the LUS. We handled missing data by multiple imputation with chained equations and predictive mean matching.

RESULTS

We included 114 patients treated between March 19, 2020, and May 4, 2020. An LUS ≥12 was associated with a poor outcome within 30 days (hazard ratio [HR], 5.59; 95% confidence interval [CI], 1.26-24.80; P = 0.02). Admission duration was shorter in patients with an LUS <12 (adjusted HR, 2.24; 95% CI, 1.47-3.40; P < 0.001). Mean LUS differed between disease severity groups: no admission, 6.3 (standard deviation [SD], 4.4); hospital/ward, 13.1 (SD, 6.4); and ICU, 18.0 (SD, 5.0). The LUS was able to discriminate between ED discharge and hospital admission excellently, with an area under the curve of 0.83 (95% CI, 0.75-0.91). Interrater agreement for the LUS was strong: κ = 0.88 (95% CI, 0.77-0.95). Correlation between the LUS and CTSS was strong: κ = 0.60 (95% CI, 0.48-0.71).

CONCLUSIONS

We showed that baseline lung ultrasound - is associated with poor outcomes, admission duration, and disease severity. The LUS also correlates well with CTSS. Point-of-care lung ultrasound may aid the risk stratification and triage of patients with COVID-19 at the ED.

Impact of SARS-CoV-2 Pandemic on "Stroke Code" Imaging Utilization and Yield

BACKGROUND AND PURPOSE

Indirect consequences of the Severe Acute Respiratory Syndrome coronavirus 2 (SARS-CoV-2) pandemic include those related to failure of patients to seek or receive timely medical attention for seemingly unrelated disease. We report our experience with stroke code imaging during the early pandemic months of 2020.

MATERIALS AND METHODS

Retrospective review of stroke codes during the 2020 pandemic and both 2020 and matched 2019 prepandemic months was performed. Patient variables were age, sex, hospital location, and severity of symptoms based on the NIHSS. We reviewed the results of CT of the head, CTA, CTP, and MR imaging examinations and classified a case as imaging-positive if any of the imaging studies yielded a result that related to the clinical indication for the study. Both year-to-year and sequential comparisons were performed between pandemic and prepandemic months.

RESULTS

A statistically significant decrease was observed in monthly stroke code volumes accompanied by a statistically significant increased proportion of positive imaging findings during the pandemic compared with the same months in the prior year (P < .001) and prepandemic months in the same year (P < .001). We also observed statistically significant increases in average NIHSS scores (P = .045 and P = .03) and the proportion of inpatient stroke codes (P = .003 and P = .03).

CONCLUSIONS

During our pandemic period, there was a significantly decreased number of stroke codes but simultaneous increases in positivity rates, symptom severity, and inpatient codes. We postulate that this finding reflects the documented reluctance of patients to seek medical care during the pandemic, with the shift toward a greater proportion of inpatient stroke codes potentially reflecting the neurologic complications of the virus itself.

Chest-CT mimics of COVID-19 pneumonia-a review article

Coronavirus disease 2019 (COVID-19) emerged in early December 2019 in China, as an acute lower respiratory tract infection and spread rapidly worldwide being declared a pandemic in March 2020. Chest-computed tomography (CT) has been utilized in different clinical settings of COVID-19 patients; however, COVID-19 imaging appearance is highly variable and nonspecific. Indeed, many pulmonary infections and non-infectious diseases can show similar CT findings and mimic COVID-19 pneumonia. In this review, we discuss clinical conditions that share a similar imaging appearance with COVID-19 pneumonia, in order to identify imaging and clinical characteristics useful in the differential diagnosis.

Comparing CT scan and chest X-ray imaging for COVID-19 diagnosis

People suspected of having COVID-19 need to know quickly if they are infected, so they can receive appropriate treatment, self-isolate, and inform those with whom they have been in close contact. Currently, the formal diagnosis of COVID-19 requires a laboratory test (RT-PCR) on samples taken from the nose and throat. The RT-PCR test requires specialized equipment and takes at least 24 h to produce a result. Chest imaging has demonstrated its valuable role in the development of this lung disease. Fast and accurate diagnosis of COVID-19 is possible with the chest X-ray (CXR) and computed tomography (CT) scan images. Our manuscript aims to compare the performances of chest imaging techniques in the diagnosis of COVID-19 infection using different convolutional neural networks (CNN). To do so, we have tested Resnet-18, InceptionV3, and MobileNetV2, for CT scan and CXR images. We found that the ResNet-18 has the best overall precision and sensitivity of 98.5% and 98.6%, respectively, the InceptionV3 model has achieved the best overall specificity of 97.4%, and the MobileNetV2 has obtained a perfect sensitivity for COVID-19 cases. All these performances have occurred with CT scan images.

COVID-19 in CXR: From Detection and Severity Scoring to Patient Disease Monitoring

This work estimates the severity of pneumonia in COVID-19 patients and reports the findings of a longitudinal study of disease progression. It presents a deep learning model for simultaneous detection and localization of pneumonia in chest Xray (CXR) images, which is shown to generalize to COVID-19 pneumonia. The localization maps are utilized to calculate a "Pneumonia Ratio" which indicates disease severity. The assessment of disease severity serves to build a temporal disease extent profile for hospitalized patients. To validate the model's applicability to the patient monitoring task, we developed a validation strategy which involves a synthesis of Digital Reconstructed Radiographs (DRRs - synthetic Xray) from serial CT scans; we then compared the disease progression profiles that were generated from the DRRs to those that were generated from CT volumes.

The usage of deep neural network improves distinguishing COVID-19 from other suspected viral pneumonia by clinicians on chest CT: a real-world study

OBJECTIVES

Based on the current clinical routine, we aimed to develop a novel deep learning model to distinguish coronavirus disease 2019 (COVID-19) pneumonia from other types of pneumonia and validate it with a real-world dataset (RWD).

METHODS

A total of 563 chest CT scans of 380 patients (227/380 were diagnosed with COVID-19 pneumonia) from 5 hospitals were collected to train our deep learning (DL) model. Lung regions were extracted by U-net, then transformed and fed to pre-trained ResNet-50-based IDANNet (Identification and Analysis of New covid-19 Net) to produce a diagnostic probability. Fivefold cross-validation was employed to validate the application of our model. Another 318 scans of 316 patients (243/316 were diagnosed with COVID-19 pneumonia) from 2 other hospitals were enrolled prospectively as the RWDs to testify our DL model's performance and compared it with that from 3 experienced radiologists.

RESULTS

A three-dimensional DL model was successfully established. The diagnostic threshold to differentiate COVID-19 and non-COVID-19 pneumonia was 0.685 with an AUC of 0.906 (95% CI: 0.886-0.913) in the internal validation group. In the RWD cohort, our model achieved an AUC of 0.868 (95% CI: 0.851-0.876) with the sensitivity of 0.811 and the specificity of 0.822, non-inferior to the performance of 3 experienced radiologists, suggesting promising clinical practical usage.

CONCLUSIONS

The established DL model was able to achieve accurate identification of COVID-19 pneumonia from other suspected ones in the real-world situation, which could become a reliable tool in clinical routine.

KEY POINTS

• In an internal validation set, our DL model achieved the best performance to differentiate COVID-19 from non-COVID-19 pneumonia with a sensitivity of 0.836, a specificity of 0.800, and an AUC of 0.906 (95% CI: 0.886-0.913) when the threshold was set at 0.685. • In the prospective RWD cohort, our DL diagnostic model achieved a sensitivity of 0.811, a specificity of 0.822, and AUC of 0.868 (95% CI: 0.851-0.876), non-inferior to the performance of 3 experienced radiologists. • The attention heatmaps were fully generated by the model without additional manual annotation and the attention regions were highly aligned with the ROIs acquired by human radiologists for diagnosis.

Validation of Remote Dielectric Sensing (ReDS) in Monitoring Adult Patients Affected by COVID-19 Pneumonia

Remote dielectric sensing (ReDS) is a non-invasive electromagnetic wave technology which provides an accurate reading of lung fluid content, and it has been reported as a valid tool in monitoring heart failure patients. Considering that morphological alterations in COVID-19 include pulmonary edema, the purpose of the present study was to evaluate the reliability of ReDS technology in assessing the excess of lung fluid status in COVID-19 pneumonia, as compared to CT scans. In this pilot single center study, confirmed COVID-19 patients were enrolled on admission to an intermediate care unit. Measurements with the ReDS system and CT scans were performed on admission and at weeks 1 and 2. Eleven patients were recruited. The average change in ReDS was −3.1 ± 1.7 after one week (p = 0.001) and −4.6 ± 2.9 after two weeks (p = 0.006). A similar trend was seen in total CT score (−3.3 ± 2.1, p = 0.001). The level of agreement between ReDS and CT changes yielded a perfect result. Statistically significant changes were observed in lactate dehydrogenase, lymphocytes, and c-reactive protein over 2 weeks. This pilot study shows that ReDS can track changes in lung involvement according to the severity of COVID-19. Further studies to detect early clinical deterioration are needed.

Coronavirus Disease 2019 in Children

Since its appearance in Wuhan in mid-December 2019, acute respiratory syndrome coronavirus 2 (SARS-CoV-2) related 19 coronavirus disease (COVID-19) has spread dramatically worldwide. It soon became apparent that the incidence of pediatric COVID-19 was much lower than the adult form. Morbidity in children is characterized by a variable clinical presentation and course. Symptoms are similar to those of other acute respiratory viral infections, the upper airways being more affected than the lower airways. Thus far, over 90% of children who tested positive for the virus presented mild or moderate symptoms and signs. Most children were asymptomatic, and only a few cases were severe, unlike in the adult population. Deaths have been rare and occurred mainly in children with underlying morbidity. Factors as reduced angiotensin-converting enzyme receptor expression, increased activation of the interferon-related innate immune response, and trained immunity have been implicated in the relative resistance to COVID-19 in children, however the underlying pathogenesis and mechanism of action remain to be established. While at the pandemic outbreak, mild respiratory manifestations were the most frequently described symptoms in children, subsequent reports suggested that the clinical course of COVID-19 is more complex than initially thought. Thanks to the experience acquired in adults, the diagnosis of pediatric SARS-CoV-2 infection has improved with time. Data on the treatment of children are sparse, however, several antiviral trials are ongoing. The purpose of this narrative review is to summarize current understanding of pediatric SARS-CoV-2 infection and provide more accurate information for healthcare workers and improve the care of patients.

Role of Chest Computed Tomography versus Real Time Reverse Transcription Polymerase Chain Reaction for Diagnosis of COVID-19: A Systematic Review and Meta-Analysis

Background

The current global pandemic of COVID-19 is considered a public health emergency. The diagnosis of COVID-19 depends on detection of the viral nucleic acid by real time reverse transcription polymerase chain reaction (RT-PCR). However, false-negative RT-PCR tests are reported and could hinder the control of the pandemic. Chest computed tomography could achieve a more reliable diagnosis and represent a complementary diagnostic tool.

Aim

To perform a meta-analysis and systematic review to find out the role of chest computed tomography versus RT-PCR for precise diagnosis of COVID-19 infection.

Methods

We searched three electronic databases (PubMed, ScienceDirect, and Scopus) from April 1 to April 20, 2020, to find out articles including the accuracy of chest computed tomography scan versus RT-PCR for diagnosis of SARS-CoV-2 infection. Observational studies, case series, and case reports were included.

Results

A total of 238 articles were retrieved from the search strategy. Following screening, 39 articles were chosen for full text assessment and finally 35 articles were included for qualitative and quantitative analysis. Chest computed tomography showed a wide range of sensitivity varied from 12%–100%.

Conclusion

Chest computed tomography is playing a key role for diagnosis and detection of COVID-19 infection. Computed tomography image findings may precede the initially positive RT-PCR assay.

Atypical chest CT findings of COVID-19 pneumonia: a pictorial review

Coronavirus disease 2019 (COVID-19) first emerged in China and rapidly spread in the world causing a pandemic. Chest computed tomography (CT) continues to play an important role in the diagnosis and follow-up of the disease due to shortcomings of the real-time reverse transcription-polymerase chain reaction test, which is the gold standard in the diagnosis of this disease. Typical chest CT findings of COVID-19 pneumonia have been widely reported in the literature. However, atypical findings such as central involvement, peribronchovascular involvement, isolated upper lobe involvement, nodular involvement, lobar consolidation, solitary involvement, pleural and pericardial fluid, and subpleural sparing can also be seen. Knowing these atypical findings is important to avoid misdiagnosis. This review summarizes the atypical findings that can be seen in the course of the disease and may be confused with other diseases.

Diagnostic yield, safety, and advantages of ultra-low dose chest CT compared to chest radiography in early stage suspected SARS-CoV-2 pneumonia: A retrospective observational study

ABSTRACT

To determine the role of ultra-low dose chest computed tomography (uld CT) compared to chest radiographs in patients with laboratory-confirmed early stage SARS-CoV-2 pneumonia.Chest radiographs and uld CT of 12 consecutive suspected SARS-CoV-2 patients performed up to 48 hours from hospital admission were reviewed by 2 radiologists. Dosimetry and descriptive statistics of both modalities were analyzed.On uld CT, parenchymal abnormalities compatible with SARS-CoV-2 pneumonia were detected in 10/12 (83%) patients whereas on chest X-ray in, respectively, 8/12 (66%) and 5/12 (41%) patients for reader 1 and 2. The average increment of diagnostic performance of uld CT compared to chest X-ray was 29%. The average effective dose was, respectively, of 0.219 and 0.073 mSv.Uld CT detects substantially more lung injuries in symptomatic patients with suspected early stage SARS-CoV-2 pneumonia compared to chest radiographs, with a significantly better inter-reader agreement, at the cost of a slightly higher equivalent radiation dose.

Relative Sparing of the Left Upper Zone on Chest Radiography in Severe COVID-19 Pneumonia

The radiological findings of COVID-19 are well-described, including its evolution. In an earlier report of admission chest radiographs of patients with COVID-19, we anecdotally noted relative sparing of the left upper zone (LUZ). We subsequently aimed to describe the main chest radiograph findings in another cohort, focusing on zonal predominance. The admission chest radiographs of 111 patients with CO-VID-19 pneumonia requiring intensive care admission were reviewed by 2 thoracic radiologists and categorized according to the predominant pattern into either ground-glass opacities (GGOs), alveolar infiltrates and/or consolidation, or reticular and/or nodular infiltrates or an equal combination of both, and the extent of disease involvement of each of the zones using a modified Radiologic Assessment of Lung Edema (RALE) score. Parenchymal changes were detected in all. In total, 106 radiographs showed GGOs, alveolar infiltrates, and/or consolidation, and 5 had a combination of reticular/nodular infiltrates as well as GGOs, alveolar infiltrates, and/or consolidation. The LUZ had a significant lower grading score than the right upper zone: 1 versus 2 (p < 0.001). Likewise, the upper zones had a significant lower score than the mid and lower zones (p < 0.001). Our findings confirmed the relative sparing of the LUZ in severe COVID-19 pneumonia.

An optimized transfer learning-based approach for automatic diagnosis of COVID-19 from chest x-ray images

Accurate and fast detection of COVID-19 patients is crucial to control this pandemic. Due to the scarcity of COVID-19 testing kits, especially in developing countries, there is a crucial need to rely on alternative diagnosis methods. Deep learning architectures built on image modalities can speed up the COVID-19 pneumonia classification from other types of pneumonia. The transfer learning approach is better suited to automatically detect COVID-19 cases due to the limited availability of medical images. This paper introduces an Optimized Transfer Learning-based Approach for Automatic Detection of COVID-19 (OTLD-COVID-19) that applies an optimization algorithm to twelve CNN architectures to diagnose COVID-19 cases using chest x-ray images. The OTLD-COVID-19 approach adapts Manta-Ray Foraging Optimization (MRFO) algorithm to optimize the network hyperparameters' values of the CNN architectures to improve their classification performance. The proposed dataset is collected from eight different public datasets to classify 4-class cases (COVID-19, pneumonia bacterial, pneumonia viral, and normal). The experimental result showed that DenseNet121 optimized architecture achieves the best performance. The evaluation results based on Loss, Accuracy, F1-score, Precision, Recall, Specificity, AUC, Sensitivity, IoU, and Dice values reached 0.0523, 98.47%, 0.9849, 98.50%, 98.47%, 99.50%, 0.9983, 0.9847, 0.9860, and 0.9879 respectively.

Ending the Pandemic: Are Rapid COVID-19 Tests a Step Forward or Back?

Some experts have promoted the use of rapid testing for COVID-19. However, with the current technologies available, continuing to replace laboratory-based, real-time reverse transcription polymerase chain reaction tests with rapid (point-of-care) tests may lead to an increased number of false negative tests. Moreover, the more rapid dissemination of false negative results that can occur with the use of rapid tests for COVID-19 may lead to increased spread of the novel coronavirus if patients do not understand the concept of false negative tests. One means of combatting this would be to tell patients who have a "negative" rapid COVID-19 test that their test result was "indeterminate."

CT visual quantitative evaluation of hypertensive patients with coronavirus disease (COVID-19): Potential influence of angiotensin converting enzyme inhibitors / angiotensin receptor blockers on severity of lung involvement

OBJECTIVE

There is not enough data on the effect of angiotensin-converting enzyme inhibitors (ACEIs)/angiotensin receptor blockers (ARBs) on lung involvement in patients with COVID-19 pneumonia and hypertension (HT). Our aim was to compare the lung involvement of the HT patients hospitalized for COVID-19 using ACEIs/ARBs with the patients taking other anti-HT medications.

METHODS

: Patients who have a diagnosis of HT among the patients treated for laboratory-confirmed COVID-19 between 31 March 2020 and 28 May 2020 were included in the study. One hundred and twenty-four patients were divided into two as ACEIs/ARBs group (n = 75) and non-ACEIs/ARBs group (n = 49) according to the anti-HT drug used. The chest CT involvement areas of these two groups were evaluated quantitatively by two observers including all lobes, and total severity score (TSS) was calculated. These TSS values were compared between drug groups and clinical groups.

RESULTS

In clinical classification; there were 4 (%3.2) asymptomatic, 5 (4.0%) mild type, 92 (74.1%) common type, 14 (11.3%) severe type, 9 (7.3%) critical type patients. ACEI/ARB group's TSS (mean±SD, 7.74 ± 3.54) was statistically higher than other anti-HT medication group (mean±SD, 4.40 ± 1.89) (p < .001). Likewise, severe-critical clinical type's TSS (mean±SD, 9.17 ± 3.44) was statistically higher than common type (mean±SD, 5.76 ± 3.07) (p < .001). Excellent agreement was established between the two blinded observers in the TSS measurements.

CONCLUSIONS

Quantitative evaluation of CT and TSS score can give an idea about the clinical classification of the patient. TSS is higher in ACEI/ARB group than non-ACEIs/ARBs group.

Low Dose Chest CT and Lung Ultrasound for the Diagnosis and Management of COVID-19

BACKGROUND

The COVID-19 pandemic has provided an opportunity to use low- and non-radiating chest imaging techniques on a large scale in the context of an infectious disease, which has never been done before. Previously, low-dose techniques were rarely used for infectious diseases, despite the recognised danger of ionising radiation.

METHOD

To evaluate the role of low-dose computed tomography (LDCT) and lung ultrasound (LUS) in managing COVID-19 pneumonia, we performed a review of the literature including our cases.

RESULTS

Chest LDCT is now performed routinely when diagnosing and assessing the severity of COVID-19, allowing patients to be rapidly triaged. The extent of lung involvement assessed by LDCT is accurate in terms of predicting poor clinical outcomes in COVID-19-infected patients. Infectious disease specialists are less familiar with LUS, but this technique is also of great interest for a rapid diagnosis of patients with COVID-19 and is effective at assessing patient prognosis.

CONCLUSIONS

COVID-19 is currently accelerating the transition to low-dose and "no-dose" imaging techniques to explore infectious pneumonia and their long-term consequences.

An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department

During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745-0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

The value of computed tomography in assessing the risk of death in COVID-19 patients presenting to the emergency room

Objective

The aims of this study were to develop a multiparametric prognostic model for death in COVID-19 patients and to assess the incremental value of CT disease extension over clinical parameters.

Methods

Consecutive patients who presented to all five of the emergency rooms of the Reggio Emilia province between February 27 and March 23, 2020, for suspected COVID-19, underwent chest CT, and had a positive swab within 10 days were included in this retrospective study. Age, sex, comorbidities, days from symptom onset, and laboratory data were retrieved from institutional information systems. CT disease extension was visually graded as < 20%, 20–39%, 40–59%, or ≥ 60%. The association between clinical and CT variables with death was estimated with univariable and multivariable Cox proportional hazards models; model performance was assessed using k-fold cross-validation for the area under the ROC curve (cvAUC).

Results

Of the 866 included patients (median age 59.8, women 39.2%), 93 (10.74%) died. Clinical variables significantly associated with death in multivariable model were age, male sex, HDL cholesterol, dementia, heart failure, vascular diseases, time from symptom onset, neutrophils, LDH, and oxygen saturation level. CT disease extension was also independently associated with death (HR = 7.56, 95% CI = 3.49; 16.38 for ≥ 60% extension). cvAUCs were 0.927 (bootstrap bias-corrected 95% CI = 0.899–0.947) for the clinical model and 0.936 (bootstrap bias-corrected 95% CI = 0.912–0.953) when adding CT extension.

Conclusions

A prognostic model based on clinical variables is highly accurate in predicting death in COVID-19 patients. Adding CT disease extension to the model scarcely improves its accuracy.

Key Points

• Early identification of COVID-19 patients at higher risk of disease progression and death is crucial; the role of CT scan in defining prognosis is unclear.

• A clinical model based on age, sex, comorbidities, days from symptom onset, and laboratory results was highly accurate in predicting death in COVID-19 patients presenting to the emergency room.

• Disease extension assessed with CT was independently associated with death when added to the model but did not produce a valuable increase in accuracy.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-07993-9.

Clinical and Laboratory Findings of COVID-19 in High-Altitude Inhabitants of Saudi Arabia

Background: SARS-CoV-2, the causative agent of COVID-19, continues to cause a worldwide pandemic, with more than 147 million being affected globally as of this writing. People's responses to COVID-19 range from asymptomatic to severe, and the disease is sometimes fatal. Its severity is affected by different factors and comorbidities of the infected patients. Living at a high altitude could be another factor that affects the severity of the disease in infected patients.

Methods: In the present study, we have analyzed the clinical, laboratory, and radiological findings of COVID-19-infected patients in Taif, a high-altitude region of Saudi Arabia. In addition, we compared matched diseased subjects to those living at sea level. We hypothesized that people living in high-altitude locations are prone to develop a more severe form of COVID-19 than those living at sea level.

Results: Age and a high Charlson comorbidity score were associated with increased numbers of intensive care unit (ICU) admissions and mortality among COVID-19 patients. These ICU admissions and fatalities were found mainly in patients with comorbidities. Rates of leukocytosis, neutrophilia, higher D-dimer, ferritin, and highly sensitive C-reactive protein (CRP) were significantly higher in ICU patients. CRP was the most independent of the laboratory biomarkers found to be potential predictors of death. COVID-19 patients who live at higher altitude developed a less severe form of the disease and had a lower mortality rate, in comparison to matched subjects living at sea level.

Conclusion: CRP and Charlson comorbidity scores can be considered predictive of disease severity. People living at higher altitudes developed less severe forms of COVID-19 disease than those living at sea level, due to a not-yet-known mechanism.

Sustainable Closed-Loop Mask Supply Chain Network Design Using Mathematical Modeling and a Fuzzy Multi-Objective Approach

The outbreak of the deadly coronavirus, which is increasing the number of victims every day, has created many changes in today’s world. The use of various masks is the most important social tool against this virus. Given the importance of rapid and quality supply of masks in the current situation, it is necessary to study supply chain in particular. In this research, the design of a closed chain supply chain network for different types of masks is assessed. The studied supply chain includes suppliers, manufacturers, distributors, and retailers in the forward flow and collection centers, separate centers, recycling centers, and disposal centers in the backward flow. In this regard, a multi-objective mathematical model with the objectives of increasing the total profit and reducing the total environmental impact, and maximizing social responsibility is presented. The optimization of this mathematical model has been done using a fuzzy optimization approach in GAMS software. The results of this study show that maximizing the total profit and minimizing the environmental effects and maximizing social responsibility are in contrast to each other. In addition, the sensitivity analysis indicated that the customers’ demand can affect all aspects of the sustainable supply chain simultaneously.

Radiologists versus Deep Convolutional Neural Networks: A Comparative Study for Diagnosing COVID-19

The reverse transcriptase polymerase chain reaction (RT-PCR) is still the routinely used test for the diagnosis of SARS-CoV-2 (COVID-19). However, according to several reports, RT-PCR showed a low sensitivity and multiple tests may be required to rule out false negative results. Recently, chest computed tomography (CT) has been an efficient tool to diagnose COVID-19 as it is directly affecting the lungs. In this paper, we investigate the application of pre-trained models in diagnosing patients who are positive for COVID-19 and differentiating it from normal patients, who tested negative for coronavirus. The study aims to compare the generalization capabilities of deep learning models with two thoracic radiologists in diagnosing COVID-19 chest CT images. A dataset of 3000 images was obtained from the Near East Hospital, Cyprus, and used to train and to test the three employed pre-trained models. In a test set of 250 images used to evaluate the deep neural networks and the radiologists, it was found that deep networks (ResNet-18, ResNet-50, and DenseNet-201) can outperform the radiologists in terms of higher accuracy (97.8%), sensitivity (98.1%), specificity (97.3%), precision (98.4%), and F1-score (198.25%), in classifying COVID-19 images.

COVID-19 pneumonia: current evidence of chest imaging features, evolution and prognosis

COVID-19 pneumonia represents a global threatening disease, especially in severe cases. Chest imaging, with X-ray and high-resolution computed tomography (HRCT), plays an important role in the initial evaluation and follow-up of patients with COVID-19 pneumonia. Chest imaging can also help in assessing disease severity and in predicting patient’s outcome, either as an independent factor or in combination with clinical and laboratory features. This review highlights the current knowledge of imaging features of COVID-19 pneumonia and their temporal evolution over time, and provides recent evidences on the role of chest imaging in the prognostic assessment of the disease.

Case Report: Incidental Finding of COVID-19 Infection after Positron Emission Tomography/CT Imaging in a Patient with a Diagnosis of Histoplasmosis and Recurring Fever

This is a case report of a 37-year-old woman evaluated with 18F-fludeoxyglucose (18F-FDG) positron emission computed tomography/CT with recurrent fever after treatment with itraconazole for 6 weeks for histoplasmosis. The examination demonstrated a decrease in the dimensions of the pulmonary opacities previously identified in the left lower lobe and attributed to histoplasmosis. In addition to these pulmonary opacities, increased FDG uptake was also observed in lymph nodes present in the cervical region, mediastinum, left lung hilum, and hepatic hilum. Notably, other pulmonary opacities with ground-glass pattern that were not present in the previous computed tomography were detected in the right lower lobe, with mild 18F-FDG uptake. Nasal swab performed shortly after the examination was positive for COVID-19. In this case, the 18F-FDG positron emission computed tomography/CT study demonstrated findings consistent with active COVID-19 infection coexisting with inflammatory changes associated with histoplasmosis infection.

Pathophysiology and Imaging Findings of COVID-19 Infection: An Organ-system Based Review

BACKGROUND

COVID-19 commonly presents with upper respiratory symptoms; however, studies have shown that SARS-CoV-2 infection affects multiple organ systems. Here, we review the pathophysiology and imaging characteristics of SARS-CoV-2 infection in organ systems throughout the body and explore commonalities.

OBJECTIVE

Familiarity with the underlying pathophysiology and imaging characteristics is essential for the radiologist to recognize these findings in patients with COVID-19 infection. Though pulmonary findings are the most prevalent presentation, COVID-19 may have multiple manifestations and recognition of the extrapulmonary manifestations is especially important because of the potential serious and long-term effects of COVID-19 on multiple organ systems.

Artificial intelligence-based approaches for COVID-19 patient management

During the highly infectious pandemic of coronavirus disease 2019 (COVID-19), artificial intelligence (AI) has provided support in addressing challenges and accelerating achievements in controlling this public health crisis. It has been applied in fields varying from outbreak forecasting to patient management and drug/vaccine development. In this paper, we specifically review the current status of AI-based approaches for patient management. Limitations and challenges still exist, and further needs are highlighted.

COVID-19 and pulmonary fibrosis: therapeutics in clinical trials, repurposing, and potential development

In 2019, an unprecedented disease named coronavirus disease 2019 (COVID-19) emerged and spread across the globe. Although the rapid transmission of COVID-19 has resulted in thousands of deaths and severe lung damage, conclusive treatment is not available. However, three COVID-19 vaccines have been authorized, and two more will be approved soon, according to a World Health Organization report on December 12, 2020. Many COVID-19 patients show symptoms of acute lung injury that eventually leads to pulmonary fibrosis. Our aim in this article is to present the relationship between pulmonary fibrosis and COVID-19, with a focus on angiotensin converting enzyme-2. We also evaluate the radiological imaging methods computed tomography (CT) and chest X-ray (CXR) for visualization of patient lung condition. Moreover, we review possible therapeutics for COVID-19 using four categories: treatments related and unrelated to lung disease and treatments that have and have not entered clinical trials. Although many treatments have started clinical trials, they have some drawbacks, such as short-term and small-group testing, that need to be addressed as soon as possible.

Diagnostic value of lung ultrasonography in children with COVID-19

BACKGROUND

Lung ultrasound (LUS) has been successfully used in the diagnosis of different pulmonary diseases. Present study design to determine the diagnostic value of LUS in the evaluation of children with novel coronavirus disease 2019 (COVID-19).

METHODS AND OBJECTIVES

Prospective multicenter study, 40 children with confirmed COVID-19 were included. LUS was performed to all patients at admission. The chest X-ray and computed tomography (CT) were performed according to the decision of the primary physicians. LUS results were compared with chest X-ray and CT findings and diagnostic performance was determined.

RESULTS

Of the 40 children median (range) was 10.5 (0.4-17.8) years. Chest X-ray and LUS were performed on all and chest CT was performed on 28 (70%) patients at the time of diagnosis. Sixteen (40%) patients had no apparent chest CT abnormalities suggestive of COVID-19, whereas 12 (30%) had abnormalities. LUS confirmed the diagnosis of pulmonary involvement in 10 of 12 patients with positive CT findings. LUS demonstrated normal lung patterns among 15 of 16 patients who had normal CT features. The sensitivity and the area under the receiver operating characteristics (ROC) curve (area under the ROC curve) identified by the chest X-ray and LUS tests were compared and statistically significantly different (McNemar's test: p = .016 and p = .001 respectively) detected. Chest X-ray displayed false-negative results for pulmonary involvement in 75% whereas for LUS it was 16.7%.

CONCLUSIONS

LUS might be a useful tool in the diagnostic steps of children with COVID-19. A reduction in chest CT assessments may be possible when LUS is used in the initial diagnostic steps for these children.

Correlation between Chest X-Ray Severity in COVID-19 and Age in Mexican-Mestizo Patients: An Observational Cross-Sectional Study

Introduction

Chest X-ray (CXR) is used for the initial triage of patients with suspected COVID-19. Studies of CXR scoring in the European population found a higher score in males than in females and significantly correlated with age. Because there have not been studies in the Mexican-mestizo community, we aimed to compare the differences in CXR scores between males and females and their correlation with age after controlling comorbidities like diabetes and hypertension.

Materials and Methods

A retrospective study of 1000 CXR of Mexican-mestizo patients with SARS-CoV-2 infection, confirmed by RT-PCR. Significant differences between age, age groups, symptoms, comorbidities, and CXR scores between males and females used the Mann-Whitney U, Chi-square tests (χ ²), and Kruskal-Wallis tests. The relationship between the total CXR score and age was measured with the Spearman rank correlation coefficient (Rs); partial correlation analysis controlled the effect of symptoms, risk factors, and comorbidities.

Results

The total CXR score did not show a difference between males and females grouped by age. There was a positive, low correlation between the total CXR score and age in males, Rs = 0.260, p < 0.001 (N = 616), and in females, Rs = 0.170, p = 0.001 (N = 384). Age only explained a <9% variance of CXR severity. Rs decreased its magnitude (from Rs = 0.152 to Rs = 0.046) and lost its significance (change in p value from p < 0.001 to p = 0.145) after controlling the effect of hypertension.

Conclusions

There is no significant difference in CXR score between males and females in the Mexican-mestizo population grouped by age. Hypertension cancels the significance of CXR severity with age pointing to its role in the pathophysiology of COVID-19. Further research using stratified groups by age and gender in other populations needs to be published.

Computed Tomography Image Processing Analysis in COVID-19 Patient Follow-Up Assessment

The rapid worldwide spread of the COVID-19 pandemic has infected patients around the world in a short space of time. Chest computed tomography (CT) images of patients who are infected with COVID-19 can offer early diagnosis and efficient forecast monitoring at a low cost. The diagnosis of COVID-19 on CT in an automated way can speed up many tasks and the application of medical treatments. This can help complement reverse transcription-polymerase chain reaction (RT-PCR) diagnosis. The aim of this work is to develop a system that automatically identifies ground-glass opacity (GGO) and pulmonary infiltrates (PIs) on CT images from patients with COVID-19. The purpose is to assess the disease progression during the patient's follow-up assessment and evaluation. We propose an efficient methodology that incorporates oversegmentation mean shift followed by superpixel-SLIC (simple linear iterative clustering) algorithm on CT images with COVID-19 for pulmonary parenchyma segmentation. To identify the pulmonary parenchyma, we described each superpixel cluster according to its position, grey intensity, second-order texture, and spatial-context-saliency features to classify by a tree random forest (TRF). Second, by applying the watershed segmentation to the mean-shift clusters, only pulmonary parenchyma segmentation-identified zones showed GGO and PI based on the description of each watershed cluster of its position, grey intensity, gradient entropy, second-order texture, Euclidean position to the border region of the PI zone, and global saliency features, after using TRF. Our classification results for pulmonary parenchyma identification on CT images with COVID-19 had a precision of over 92% and recall of over 92% on twofold cross validation. For GGO, the PI identification showed 96% precision and 96% recall on twofold cross validation.

Towards computer-aided severity assessment via deep neural networks for geographic and opacity extent scoring of SARS-CoV-2 chest X-rays

A critical step in effective care and treatment planning for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause for the coronavirus disease 2019 (COVID-19) pandemic, is the assessment of the severity of disease progression. Chest x-rays (CXRs) are often used to assess SARS-CoV-2 severity, with two important assessment metrics being extent of lung involvement and degree of opacity. In this proof-of-concept study, we assess the feasibility of computer-aided scoring of CXRs of SARS-CoV-2 lung disease severity using a deep learning system. Data consisted of 396 CXRs from SARS-CoV-2 positive patient cases. Geographic extent and opacity extent were scored by two board-certified expert chest radiologists (with 20+ years of experience) and a 2nd-year radiology resident. The deep neural networks used in this study, which we name COVID-Net S, are based on a COVID-Net network architecture. 100 versions of the network were independently learned (50 to perform geographic extent scoring and 50 to perform opacity extent scoring) using random subsets of CXRs from the study, and we evaluated the networks using stratified Monte Carlo cross-validation experiments. The COVID-Net S deep neural networks yielded R[Formula: see text] of [Formula: see text] and [Formula: see text] between predicted scores and radiologist scores for geographic extent and opacity extent, respectively, in stratified Monte Carlo cross-validation experiments. The best performing COVID-Net S networks achieved R[Formula: see text] of 0.739 and 0.741 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively. The results are promising and suggest that the use of deep neural networks on CXRs could be an effective tool for computer-aided assessment of SARS-CoV-2 lung disease severity, although additional studies are needed before adoption for routine clinical use.

Discrepancies in the clinical and radiological profiles of COVID-19: A case-based discussion and review of literature

The current gold standard for the diagnosis of coronavirus disease-19 (COVID-19) is a positive reverse transcriptase polymerase chain reaction (RT-PCR) test, on the background of clinical suspicion. However, RT-PCR has its limitations; this includes issues of low sensitivity, sampling errors and appropriate timing of specimen collection. As pulmonary involvement is the most common manifestation of severe COVID-19, early and appropriate lung imaging is important to aid diagnosis. However, gross discrepancies can occur between the clinical and imaging findings in patients with COVID-19, which can mislead clinicians in their decision making. Although chest X-ray (CXR) has a low sensitivity for the diagnosis of COVID-19 associated lung disease, especially in the earlier stages, a positive CXR increases the pre-test probability of COVID-19. CXR scoring systems have shown to be useful, such as the COVID-19 opacification rating score which helps to predict the need of tracheal intubation. Furthermore, artificial intelligence-based algorithms have also shown promise in differentiating COVID-19 pneumonia on CXR from other lung diseases. Although costlier than CXR, unenhanced computed tomographic (CT) chest scans have a higher sensitivity, but lesser specificity compared to RT-PCR for the diagnosis of COVID-19 pneumonia. A semi-quantitative CT scoring system has been shown to predict short-term mortality. The routine use of CT pulmonary angiography as a first-line imaging modality in patients with suspected COVID-19 is not justifiable due to the risk of contrast nephropathy. Scoring systems similar to those pioneered in CXR and CT can be used to effectively plan and manage hospital resources such as ventilators. Lung ultrasound is useful in the assessment of critically ill COVID-19 patients in the hands of an experienced operator. Moreover, it is a convenient tool to monitor disease progression, as it is cheap, non-invasive, easily accessible and easy to sterilise. Newer lung imaging modalities such as magnetic resonance imaging (MRI) for safe imaging among children, adolescents and pregnant women are rapidly evolving. Imaging modalities are also essential for evaluating the extra-pulmonary manifestations of COVID-19: these include cranial imaging with CT or MRI; cardiac imaging with ultrasonography (US), CT and MRI; and abdominal imaging with US or CT. This review critically analyses the utility of each imaging modality to empower clinicians to use them appropriately in the management of patients with COVID-19 infection.