A British Society of Thoracic Imaging statement: considerations in designing local imaging diagnostic algorithms for the COVID-19 pandemic

Lung pneumonia severity scoring in chest X-ray images using transformers

To create robust and adaptable methods for lung pneumonia diagnosis and the assessment of its severity using chest X-rays (CXR), access to well-curated, extensive datasets is crucial. Many current severity quantification approaches require resource-intensive training for optimal results. Healthcare practitioners require efficient computational tools to swiftly identify COVID-19 cases and predict the severity of the condition. In this research, we introduce a novel image augmentation scheme as well as a neural network model founded on Vision Transformers (ViT) with a small number of trainable parameters for quantifying COVID-19 severity and other lung diseases. Our method, named Vision Transformer Regressor Infection Prediction (ViTReg-IP), leverages a ViT architecture and a regression head. To assess the model's adaptability, we evaluate its performance on diverse chest radiograph datasets from various open sources. We conduct a comparative analysis against several competing deep learning methods. Our results achieved a minimum Mean Absolute Error (MAE) of 0.569 and 0.512 and a maximum Pearson Correlation Coefficient (PC) of 0.923 and 0.855 for the geographic extent score and the lung opacity score, respectively, when the CXRs from the RALO dataset were used in training. The experimental results reveal that our model delivers exceptional performance in severity quantification while maintaining robust generalizability, all with relatively modest computational requirements. The source codes used in our work are publicly available at https://github.com/bouthainas/ViTReg-IP .

Mobile imaging trailers: A scoping review of CT and MRI modalities

INTRODUCTION

Mobile Imaging Trailers enable moving diagnostic imaging equipment between locations requiring very little setup and configuration, example given CT-scanners and MRI-scanners. However, despite the apparent benefits of utilising these imaging capabilities, very little research on the subject exists. This study aims at gaining an overview of the current state of the literature, using the scoping review methodology.

METHODS

The systematic literature search was conducted in three databases: Scopus, Embase and PubMed. Included sources were extracted based on the objectives of the scoping review, and inspired by the by PRISMA-ScR.

RESULTS

29 papers were included.

CONCLUSION

The results of the review showed that three general categories of research on this subject exist - trailers used in research, trailers as the object of research and trailers as an element or tool of the research. Of these, the most prevalent one used is the latter - trailers used as an element or tool of the research. This; however, is an issue for the use of trailers in a clinical setting, as very little research has been conducted on how they might be used and how they compare to fixed installations. As seen during the recent COVID-19 pandemic, the potentials for the use of MITs are immense; however, with the current lack of knowledge and understanding, the full potential has not been realised, suggesting further research should be focused in this area.

IMPLICATIONS FOR PRACTICE

This study has shown that the limited research in the area does point towards a few benefits of MITs; however, there is a clear lack of sufficient research on the field to say this with confidence.

Simple demographic, laboratory and chest radiograph variables can identify COVID-19 patients with pulmonary thromboembolism: a retrospective multicentre United Kingdom study

OBJECTIVES

To (1) identify discriminatory demographic, laboratory and initial CXR findings; (2) explore correlation between D-dimer and radiographic severity scores; and (3) assess accuracy of published D-dimer thresholds to identify pulmonary thromboembolism (PTE) in COVID-19 patients.

METHODS

Retrospective study including all COVID-19 patients admitted from 1st to 30th April 2020 meeting inclusion criteria from 25 (blinded) hospitals. Demographics, blood results, CXR and CTPA findings were compared between positive and negative PTE cohorts using uni- and multivariable logistic regression. Published D-dimer cut-offs were applied.

RESULTS

389 patients were included [median age 63; 237 males], of which 26.2% had a PTE. Significant univariable discriminators for PTE were peak D-dimer, sex, neutrophil count at the time of the D-dimer and at admission, abnormal CXR, and CXR zonal severity score. Only neutrophil count at peak D-dimer remained significant for predicting PTE on multivariable analysis (p = 0.008). When compared with the published literature, sensitivity for PTE were lower than those published at all cut-off values, however specificity at different cut-offs was variable.

CONCLUSIONS

In this multicentre COVID-19 cohort, univariable admission factors that could indicate pulmonary thromboembolism were male sex, high neutrophil count and abnormal CXR with a greater CXR zonal severity score. The accuracy levels of published D-dimer thresholds were not reproducible in our population.

ADVANCES IN KNOWLEDGE

This is a large multicentre study looking at the discriminatory value of simple variables to determine if a patient with COVID-19 has PTE or not, in addition to comparing D-dimer cut off values against published values.

Interpretation of chest radiography in patients with known or suspected SARS-CoV-2 infection: what we learnt from comparison with computed tomography

Differently from computed tomography (CT), well-defined terminology for chest radiography (CXR) findings and standardized reporting in the setting of known or suspected COVID-19 are still lacking. We propose a revision of CXR major imaging findings in SARS-CoV-2 pneumonia derived from the comparison of CXR and CT, suggesting a precise and standardized terminology for CXR reporting. This description will consider asymptomatic patients, symptomatic patients, and patients with SARS-CoV-2-related pulmonary complications. We suggest using terms such as ground-glass opacities, consolidation, and reticular pattern for the most common findings, and characteristic chest radiographic pattern in presence of one or more of the above-mentioned findings with peripheral and mid-to-lower lung zone distribution.

Deep Neural Network Augments Performance of Junior Residents in Diagnosing COVID-19 Pneumonia on Chest Radiographs

Chest X-rays (CXRs) are essential in the preliminary radiographic assessment of patients affected by COVID-19. Junior residents, as the first point-of-contact in the diagnostic process, are expected to interpret these CXRs accurately. We aimed to assess the effectiveness of a deep neural network in distinguishing COVID-19 from other types of pneumonia, and to determine its potential contribution to improving the diagnostic precision of less experienced residents. A total of 5051 CXRs were utilized to develop and assess an artificial intelligence (AI) model capable of performing three-class classification, namely non-pneumonia, non-COVID-19 pneumonia, and COVID-19 pneumonia. Additionally, an external dataset comprising 500 distinct CXRs was examined by three junior residents with differing levels of training. The CXRs were evaluated both with and without AI assistance. The AI model demonstrated impressive performance, with an Area under the ROC Curve (AUC) of 0.9518 on the internal test set and 0.8594 on the external test set, which improves the AUC score of the current state-of-the-art algorithms by 1.25% and 4.26%, respectively. When assisted by the AI model, the performance of the junior residents improved in a manner that was inversely proportional to their level of training. Among the three junior residents, two showed significant improvement with the assistance of AI. This research highlights the novel development of an AI model for three-class CXR classification and its potential to augment junior residents' diagnostic accuracy, with validation on external data to demonstrate real-world applicability. In practical use, the AI model effectively supported junior residents in interpreting CXRs, boosting their confidence in diagnosis. While the AI model improved junior residents' performance, a decline in performance was observed on the external test compared to the internal test set. This suggests a domain shift between the patient dataset and the external dataset, highlighting the need for future research on test-time training domain adaptation to address this issue.

Chest radiograph classification and severity of suspected COVID-19 by different radiologist groups and attending clinicians: multi-reader, multi-case study

OBJECTIVES

To quantify reader agreement for the British Society of Thoracic Imaging (BSTI) diagnostic and severity classification for COVID-19 on chest radiographs (CXR), in particular agreement for an indeterminate CXR that could instigate CT imaging, from single and paired images.

METHODS

Twenty readers (four groups of five individuals)-consultant chest (CCR), general consultant (GCR), and specialist registrar (RSR) radiologists, and infectious diseases clinicians (IDR)-assigned BSTI categories and severity in addition to modified Covid-Radiographic Assessment of Lung Edema Score (Covid-RALES), to 305 CXRs (129 paired; 2 time points) from 176 guideline-defined COVID-19 patients. Percentage agreement with a consensus of two chest radiologists was calculated for (1) categorisation to those needing CT (indeterminate) versus those that did not (classic/probable, non-COVID-19); (2) severity; and (3) severity change on paired CXRs using the two scoring systems.

RESULTS

Agreement with consensus for the indeterminate category was low across all groups (28-37%). Agreement for other BSTI categories was highest for classic/probable for the other three reader groups (66-76%) compared to GCR (49%). Agreement for normal was similar across all radiologists (54-61%) but lower for IDR (31%). Agreement for a severe CXR was lower for GCR (65%), compared to the other three reader groups (84-95%). For all groups, agreement for changes across paired CXRs was modest.

CONCLUSION

Agreement for the indeterminate BSTI COVID-19 CXR category is low, and generally moderate for the other BSTI categories and for severity change, suggesting that the test, rather than readers, is limited in utility for both deciding disposition and serial monitoring.

KEY POINTS

• Across different reader groups, agreement for COVID-19 diagnostic categorisation on CXR varies widely. • Agreement varies to a degree that may render CXR alone ineffective for triage, especially for indeterminate cases. • Agreement for serial CXR change is moderate, limiting utility in guiding management.

Attention-augmented U-Net (AA-U-Net) for semantic segmentation

Deep learning-based image segmentation models rely strongly on capturing sufficient spatial context without requiring complex models that are hard to train with limited labeled data. For COVID-19 infection segmentation on CT images, training data are currently scarce. Attention models, in particular the most recent self-attention methods, have shown to help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent attention-augmented convolution model aims to capture long range interactions by concatenating self-attention and convolution feature maps. This work proposes a novel attention-augmented convolution U-Net (AA-U-Net) that enables a more accurate spatial aggregation of contextual information by integrating attention-augmented convolution in the bottleneck of an encoder-decoder segmentation architecture. A deep segmentation network (U-Net) with this attention mechanism significantly improves the performance of semantic segmentation tasks on challenging COVID-19 lesion segmentation. The validation experiments show that the performance gain of the attention-augmented U-Net comes from their ability to capture dynamic and precise (wider) attention context. The AA-U-Net achieves Dice scores of 72.3% and 61.4% for ground-glass opacity and consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.2% points against a baseline U-Net and 3.09% points compared to a baseline U-Net with matched parameters.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11760-022-02302-3.

Noise Suppression and Edge Preservation for Low-Dose COVID-19 CT Images Using NLM and Method Noise Thresholding in Shearlet Domain

In the COVID-19 era, it may be possible to detect COVID-19 by detecting lesions in scans, i.e., ground-glass opacity, consolidation, nodules, reticulation, or thickened interlobular septa, and lesion distribution, but it becomes difficult at the early stages due to embryonic lesion growth and the restricted use of high dose X-ray detection. Therefore, it may be possible for a patient who may or may not be infected with coronavirus to consider using high-dose X-rays, but it may cause more risks. Conclusively, using low-dose X-rays to produce CT scans and then adding a rigorous denoising algorithm to the scans is the best way to protect patients from side effects or a high dose X-ray when diagnosing coronavirus involvement early. Hence, this paper proposed a denoising scheme using an NLM filter and method noise thresholding concept in the shearlet domain for noisy COVID CT images. Low-dose COVID CT images can be further utilized. The results and comparative analysis showed that, in most cases, the proposed method gives better outcomes than existing ones.

The Impact of COVID-19 Crisis on the Control and Management of Radiography Practice in the United Arab Emirates

The present study aimed to assess the impact of the COVID-19 crisis on radiology practices in Abu Dhabi, UAE. An electronic survey (Google form) was distributed among Abu Dhabi government and private hospitals. The survey included general X–ray services, which were only provided in the radiology departments. The diagnostic radiographers who reported changes in the number and type of radiology procedures (37%) reported that the changes reached 61–80% compared to the number of procedures being conducted prior to the outbreak of COVID-19. While infection control was challenging due to the shortage of personal protective equipment (PPE), 51.2% of the participants were affected. The healthcare workers in the radiology departments in Abu Dhabi are exposed to a high number of COVID-19–infection patients, which increases their chances of contracting the disease. A total of 90% of employees were infected with COVID-19 during the crisis. COVID-19 has resulted in changes in clinical working patterns, such as the type and number of procedures performed daily. Additionally, PPE shortages, staff infection during the pandemic, an increase in workplace–related difficulties, and staff well–being are common consequences of the pandemic. It is vital to enhance coping strategies in order to support staff well–being. However, the psychological effects caused as a result of the pandemic should not be ignored, and providing professional support to workers is recommended.

Correlation of Clinical Course with Computed Tomography Findings and Biochemical Parameters at the Time of Admission in COVID-19 Patients

OBJECTIVE

The primary objective of our study was to evaluate the predictive performance of serum inflammatory markers and the semiquantitative computed tomography severity scoring system on diagnosing the Covid 2019 disease and its course.

METHODS

Our study is a single-center retrospective cohort study. The data of 213 adults who were confirmed to have coronavirus disease 2019 by polymerase chain reaction tests in the period between April 2020 and August 2020 were evaluated. One hundred eighty four of these patients whose C-reactive protein, d-dimer, and ferritin levels, lymphocyte counts, and thoracic computed tomography images were obtained at the time of admission were included in the study. The semi-quantitative computed tomography severity score was calculated for all patients.

RESULTS

The median age of the 184 patients included in the study was 51.5 (19-91) years. The incidence of intensive care need and mortality was 10.3% (n=19) and 5.4% (n=10), respectively. The intensive care need and mortality rate was significantly correlated with higher thoracic computed tomography involvement scores at admission. There was a statistically significant and positive correlation between the computed tomography scores and the C-reactive protein, d-dimer, and ferritin levels. Older age (>65 years-old) and thoracic computed tomography scores of 11 and higher were independent factors correlated with need for intensive care.

CONCLUSION

Serum inflammatory markers and semi-quantitative computed tomography severity scoring system were predictive in diagnosing the Covid 2019 disease and its course.

COVID-19 and Inflammatory Markers

Coronavirus disease-2019 (COVID-19) causes mild illness to serious infection with lung involvement, thrombosis, and other complications potentially resulting in fatal outcomes. Recognised inflammatory biomarkers play important roles in managing patients with COVID-19; for example, diagnosis, follow-up, assessment of treatment response, and risk stratification. Inflammatory markers in COVID-19 disease were analysed in two categories. Well-known inflammatory markers include complete blood count, C-reactive protein, albumin, cytokines, and erythrocyte sedimentation rate. Asymmetric dimethylarginine, endocan, pentraxin 3, serum amyloid A, soluble urokinase plasminogen activator receptor, total oxidant status and total antioxidant status, and galectin-3 are considered among the emerging inflammatory markers. This brief narrative review assesses the relationship between these inflammatory markers and COVID-19 infection.

Fahr’s Syndrome for Primary Hypoparathyroidism in a Patient With COVID-19

Fahr's syndrome, recently named "primary brain calcification," is a rare disorder with a variable clinical presentation ranging from behavioral changes to seizures. It can be idiopathic or have multiple causes, hypoparathyroidism the most frequent. In the current coronavirus 2019 (COVID-19) pandemic, these electrolyte imbalances have acquired importance, and there has been a correlation between the lowest serum calcium levels and severe COVID-19 disease. It is known that calcium accomplishes many normal physiologic functions.

We present a case of a 63-year-old woman who arrived at the emergency room with a fever of 10-day duration, odynophagia, dry cough, dyspnea, and drowsiness. Upon her arrival, computed tomography of the brain and chest was performed, showing areas of calcification in the basal nuclei and infiltrates with a ground-glass pattern, respectively. In addition, laboratory studies were conducted in which hypocalcemia and hyperphosphatemia stand out. Furthermore, a positive result was obtained from acute Respiratory Syndrome Coronavirus 2 (SARS-COV2) from bronchial secretion. According to the clinical presentation data in the imaging and laboratory studies, Fahr's syndrome and COVID-19 pneumonia were diagnosed.

We consider evaluating electrolyte imbalances at case presentations essential and continuously monitoring them. Appropriate and prompt corrections were achieved in patients with hypoparathyroidism history and severe COVID-19 disease. This case shows the vital collaboration between endocrinologists and other physicians that care for patients with COVID-19 infection.

Expiratory CT scanning in COVID-19 patients: can we add useful data?

OBJECTIVE

To evaluate small airway disease in COVID-19 patients using the prevalence of air trapping (AT) and correlating it with clinical outcomes. The relationship between CT-based opacities in small blood vessels and ventilation in patients with SARS-CoV-2 pneumonia was also assessed.

METHODS

We retrospectively included 53 patients with positive RT-PCR results for SARS-CoV-2 between March and April of 2020. All subjects underwent HRCT scanning, including inspiratory and expiratory acquisitions. Subjects were divided into two groups based on visual identification of AT. Small blood vessel volumes were estimated by means of cross-sectional areas < 5 mm2 (BV5) derived from automated segmentation algorithms. Mixed-effect models were obtained to represent the BV5 as a function of CT-based lobar opacities and lobar ventilation.

RESULTS

Of the 53 participants, AT was identified in 23 (43.4%). The presence of AT was associated with increased SpO2 at admission (OR = 1.25; 95% CI, 1.07-1.45; p = 0.004) and reduced D-dimer levels (OR = 0.99; 95% CI, 0.99-0.99; p = 0.039). Patients with AT were less likely to be hospitalized (OR = 0.27; 95% CI, 0.08-0.89; p = 0.032). There was a significant but weak inverse correlation between BV5 and CT-based lobar opacities (R2 = 0.19; p = 0.03), as well as a nonsignificant and weak direct correlation between BV5 and lobar ventilation (R2 = 0.08; p = 0.54).

CONCLUSIONS

AT is a common finding in patients with COVID-19 that undergo expiratory CT scanning. The presence of AT may correlate with higher SpO2 at admission, lower D-dimer levels, and fewer hospitalizations when compared with absence of AT. Also, the volume of small pulmonary vessels may negatively correlate with CT opacities but not with lobar ventilation.

Diagnostic Accuracy of Right Bronchial Infiltration on Chest X-rays in Diagnosing COVID-19 Patients in the Early Stage of the Disease

Purpose SARS-CoV-2 has been a diagnostic challenge for healthcare setups worldwide since 2019 due to its proximity to a myriad of pathological processes. Although reverse transcription - polymerase chain reaction (RT-PCR) and high-resolution computed tomography (HRCT) have helped in the diagnosis of the disease, they are not as widely available as chest X-rays. This study aims to investigate the diagnostic accuracy of right bronchial infiltration in chest X-ray in diagnosing COVID-19. Material and methods This was a validation study conducted in a single center in Riyadh, Saudi Arabia. A total of 114 patients were enrolled according to the selection criteria of the study. Consent was waived off on the condition of confidentiality maintenance as per the ethical review board. X-rays of suspected patients were viewed and analyzed by two blinded consultant radiologists. Patients were followed for their RT-PCR reports. Data were entered and analyzed in SPSS Statistics v.23.0 (IBM Corp., Armonk, USA). Results Among the 114 patients, the mean age was 46.2±17.3 years and 85 (74.6%) were males. The total number of COVID-19-positive patients were 82 (71.9%) while the patients presenting with right bronchial infiltration (RBI) were 94 (82.5%). RBI was significantly associated with the presence and absence of COVID-19 on PCR (p<0.001) and the presence of comorbidities (p<0.001). The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the sign were 84.04%, 85.00%, 96.34%, 53.12%, and 84.21%, respectively. Conclusions RBI can be used as a diagnostic sign in X-rays for early identification of COVID-19 positive patients. This feature can be used in the triage of patients. This would decrease the spread of disease by providing early time to intervene to isolate patients.

A case-control evaluation of pulmonary and extrapulmonary findings of incidental asymptomatic COVID-19 infection on FDG PET-CT

OBJECTIVES

To describe the findings of incidental asymptomatic COVID-19 infection on FDG PET-CT using a case-control design.

METHODS

Incidental pulmonary findings suspicious of asymptomatic COVID-19 infection on FDG PET-CT were classified as a confirmed (positive RT-PCR test) or suspected case (no/negative RT-PCR test). Control cases were identified using a 4:1 control:case ratio. Pulmonary findings were re-categorised by two reporters using the BSTI classification. SUV metrics in ground glass opacification (GGO)/consolidation (where present), background lung, intrathoracic nodes, liver, spleen and bone marrow were measured.

RESULTS

7/9 confirmed and 11/15 suspected cases (COVID-19 group) were re-categorised as BSTI 1 (classic/probable COVID-19) or BSTI 2 (indeterminate COVID-19); 0/96 control cases were categorised as BSTI 1. Agreement between two reporters using the BSTI classification was almost perfect (weighted κ = 0.94). SUVmax GGO/consolidation (5.1 vs 2.2; p < 0.0001) and target-to-background ratio, normalised to liver SUVmean (2.4 vs 1.0; p < 0.0001) were higher in the BSTI 1 & 2 group vs BSTI 3 (non-COVID-19) cases. SUVmax GGO/consolidation discriminated between the BSTI 1 & 2 group vs BSTI 3 (non-COVID-19) cases with high accuracy (AUC = 0.93). SUV metrics were higher (p < 0.05) in the COVID-19 group vs control cases in the lungs, intrathoracic nodes and spleen.

CONCLUSION

Asymptomatic COVID-19 infection on FDG PET-CT is characterised by bilateral areas of FDG avid (intensity > x2 liver SUVmean) GGO/consolidation and can be identified with high interobserver agreement using the BSTI classification. There is generalised background inflammation within the lungs, intrathoracic nodes and spleen.

ADVANCES IN KNOWLEDGE

Incidental asymptomatic COVID-19 infection on FDG PET-CT, characterised by bilateral areas of ground glass opacification and consolidation, can be identified with high reproducibility using the BSTI classification. The intensity of associated FDG uptake (>x2 liver SUVmean) provides high discriminative ability in differentiating such cases from pulmonary findings in a non-COVID-19 pattern. Asymptomatic COVID-19 infection causes a generalised background inflammation within the mid-lower zones of the lungs, hilar and central mediastinal nodal stations, and spleen on FDG PET-CT.

SARS-Net: COVID-19 detection from chest x-rays by combining graph convolutional network and convolutional neural network

COVID-19 has emerged as one of the deadliest pandemics that has ever crept on humanity. Screening tests are currently the most reliable and accurate steps in detecting severe acute respiratory syndrome coronavirus in a patient, and the most used is RT-PCR testing. Various researchers and early studies implied that visual indicators (abnormalities) in a patient's Chest X-Ray (CXR) or computed tomography (CT) imaging were a valuable characteristic of a COVID-19 patient that can be leveraged to find out virus in a vast population. Motivated by various contributions to open-source community to tackle COVID-19 pandemic, we introduce SARS-Net, a CADx system combining Graph Convolutional Networks and Convolutional Neural Networks for detecting abnormalities in a patient's CXR images for presence of COVID-19 infection in a patient. In this paper, we introduce and evaluate the performance of a custom-made deep learning architecture SARS-Net, to classify and detect the Chest X-ray images for COVID-19 diagnosis. Quantitative analysis shows that the proposed model achieves more accuracy than previously mentioned state-of-the-art methods. It was found that our proposed model achieved an accuracy of 97.60% and a sensitivity of 92.90% on the validation set.

Chest radiographic findings and their correlation with disease progression in COVID-19 patients in northern India

Introduction:

The present study was undertaken to describe and quantify the spectrum of radiographic findings on coronavirus disease 2019 (COVID-19) patients. The study also aimed to analyse the changes in chest X-ray (CXR) with disease progression.

Methods:

COVID-19 patients admitted between the period of 15 March 2020 and 1 July 2020 were retrospectively enrolled. CXR images were assessed and reported as ‘Normal’ or ‘Abnormal’. A severity score was calculated using Warren et al.’s Radiographic Assessment of Lung Edema scoring. Correlations of the severity score thus calculated were sought with age, sex, clinical manifestations and presence of comorbidities.

Results:

Five hundred patients (342 males, 158 females) were enrolled, median age being 35 years. Fever and cough were the most common symptoms but significant correlation of an abnormal CXR was found with dyspnoea. CXRs were normal in 67% and abnormal in 33% patients. The commonest comorbidities were diabetes mellitus and cardiovascular disease including hypertension, coronary artery disease and congestive heart failure. Predominant pattern was ground glass opacities, reticular alteration and consolidation peaking in the second week from symptom onset. The most frequent distribution was bilateral, peripheral with middle/lower predominance. Increasing age, male sex, presence of dyspnoea and comorbidities correlated with abnormal findings on CXR. Critical illness and mortality correlated strongly with increasing age, male sex and presence of dyspnoea, less so with presence of comorbidities.

Conclusion:

In the current scenario with clinicians and radiologists working in tandem, CXR seems to be a promising tool in providing relevant information in a simplified way.

Building Resilient Health Systems Intelligence: Adapting Indicators of Compromise for the Cyber-Bionexus

The health sector is an underutilized source of actionable health intelligence for responding to threats across the "cyber-bionexus," defined as the convergence of threats from the biological and cybersecurity domains to produce harms with widespread societal consequences. The escalation of concerns about such threats-related to misinformation and disinformation; chemical, biological, radiological, and nuclear events; cyberattacks; natural disease outbreaks; and disasters of various kinds-places health system concerns squarely at the forefront of national critical systems and broader security imperatives. Events such as the COVID-19 pandemic have highlighted the dearth of systems available for generating real-time intelligence in relation to critical functions of health sector operations amidst an unfolding crisis. Drawing on principles from the field of cyberthreat intelligence, and building on existing scholarship in health security intelligence, we propose a model for applying health system indicators of compromise for cyberbio events. We further discuss the relevance of this approach within the broader landscape of the cyber-bionexus to signal new pathways for research, practice, and policy engagement.

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.

Development and prospective validation of COVID-19 chest X-ray screening model for patients attending emergency departments

Chest X-rays (CXRs) are the first-line investigation in patients presenting to emergency departments (EDs) with dyspnoea and are a valuable adjunct to clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to facilitate rapid triage of CXRs for further patient testing and/or isolation. In this work we develop an AI algorithm, CovIx, to differentiate normal, abnormal, non-COVID-19 pneumonia, and COVID-19 CXRs using a multicentre cohort of 293,143 CXRs. The algorithm is prospectively validated in 3289 CXRs acquired from patients presenting to ED with symptoms of COVID-19 across four sites in NHS Greater Glasgow and Clyde. CovIx achieves area under receiver operating characteristic curve for COVID-19 of 0.86, with sensitivity and F1-score up to 0.83 and 0.71 respectively, and performs on-par with four board-certified radiologists. AI-based algorithms can identify CXRs with COVID-19 associated pneumonia, as well as distinguish non-COVID pneumonias in symptomatic patients presenting to ED. Pre-trained models and inference scripts are freely available at https://github.com/beringresearch/bravecx-covid.

Fine-Tuning Convolutional Neural Networks for COVID-19 Detection from Chest X-ray Images

As the COVID-19 pandemic continues to ravage the world, the use of chest X-ray (CXR) images as a complementary screening strategy to reverse transcription-polymerase chain reaction (RT-PCR) testing continues to grow owing to its routine clinical application to respiratory diseases. We performed extensive convolutional neural network (CNN) fine-tuning experiments and identified that models pretrained on larger out-of-domain datasets show an improved performance. This suggests that a priori knowledge of models from out-of-field training should also apply to X-ray images. With appropriate hyperparameters selection, we found that higher resolution images carry more clinical information, and the use of mixup in training improved the performance of the model. The experimental showed that our proposed transfer learning present state-of-the-art results. Furthermore, we evaluated the performance of our model with a small amount of downstream training data and found that the model still performed well in COVID-19 identification. We also explored the mechanism of model detection using a gradient-weighted class activation mapping (Grad-CAM) method for CXR imaging to interpret the detection of radiology images. The results helped us understand how the model detects COVID-19, which can be used to discover new visual features and assist radiologists in screening.

Current limitations to identify covid-19 using artificial intelligence with chest x-ray imaging (part ii). The shortcut learning problem

Since the outbreak of the COVID-19 pandemic, computer vision researchers have been working on automatic identification of this disease using radiological images. The results achieved by automatic classification methods far exceed those of human specialists, with sensitivity as high as 100% being reported. However, prestigious radiology societies have stated that the use of this type of imaging alone is not recommended as a diagnostic method. According to some experts the patterns presented in these images are unspecific and subtle, overlapping with other viral pneumonias. This report seeks to evaluate the analysis the robustness and generalizability of different approaches using artificial intelligence, deep learning and computer vision to identify COVID-19 using chest X-rays images. We also seek to alert researchers and reviewers to the issue of "shortcut learning". Recommendations are presented to identify whether COVID-19 automatic classification models are being affected by shortcut learning. Firstly, papers using explainable artificial intelligence methods are reviewed. The results of applying external validation sets are evaluated to determine the generalizability of these methods. Finally, studies that apply traditional computer vision methods to perform the same task are considered. It is evident that using the whole chest X-Ray image or the bounding box of the lungs, the image regions that contribute most to the classification appear outside of the lung region, something that is not likely possible. In addition, although the investigations that evaluated their models on data sets external to the training set, the effectiveness of these models decreased significantly, it may provide a more realistic representation as how the model will perform in the clinic. The results indicate that, so far, the existing models often involve shortcut learning, which makes their use less appropriate in the clinical setting.

Long-term survival of mechanically ventilated patients with severe COVID-19: an observational cohort study

Background

Information is lacking regarding long-term survival and predictive factors for mortality in patients with acute hypoxemic respiratory failure due to coronavirus disease 2019 (COVID-19) and undergoing invasive mechanical ventilation. We aimed to estimate 180-day mortality of patients with COVID-19 requiring invasive ventilation, and to develop a predictive model for long-term mortality.

Methods

Retrospective, multicentre, national cohort study between March 8 and April 30, 2020 in 16 intensive care units (ICU) in Spain. Participants were consecutive adults who received invasive mechanical ventilation for COVID-19. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection detected in positive testing of a nasopharyngeal sample and confirmed by real time reverse-transcriptase polymerase chain reaction (rt-PCR). The primary outcomes was 180-day survival after hospital admission. Secondary outcomes were length of ICU and hospital stay, and ICU and in-hospital mortality. A predictive model was developed to estimate the probability of 180-day mortality.

Results

868 patients were included (median age, 64 years [interquartile range [IQR], 56–71 years]; 72% male). Severity at ICU admission, estimated by SAPS3, was 56 points [IQR 50–63]. Prior to intubation, 26% received some type of noninvasive respiratory support. The unadjusted overall 180-day survival rates was 59% (95% CI 56–62%). The predictive factors measured during ICU stay, and associated with 180-day mortality were: age [Odds Ratio [OR] per 1-year increase 1.051, 95% CI 1.033–1.068)), SAPS3 (OR per 1-point increase 1.027, 95% CI 1.011–1.044), diabetes (OR 1.546, 95% CI 1.085–2.204), neutrophils to lymphocytes ratio (OR per 1-unit increase 1.008, 95% CI 1.001–1.016), failed attempt of noninvasive positive pressure ventilation prior to orotracheal intubation (OR 1.878 (95% CI 1.124–3.140), use of selective digestive decontamination strategy during ICU stay (OR 0.590 (95% CI 0.358–0.972) and administration of low dosage of corticosteroids (methylprednisolone 1 mg/kg) (OR 2.042 (95% CI 1.205–3.460).

Conclusion

The long-term survival of mechanically ventilated patients with severe COVID-19 reaches more than 50% and may help to provide individualized risk stratification and potential treatments.

Trial registration: ClinicalTrials.gov Identifier: NCT04379258. Registered 10 April 2020 (retrospectively registered)

Supplementary Information

The online version contains supplementary material available at 10.1186/s13613-021-00929-y.

Chest computed tomography versus RT-PCR in early diagnostics of COVID-19 - a systematic review with meta-analysis

The purpose of this study was to compare the sensitivity and specificity of computed tomography (CT) scans of the chests of patients with the reference reverse-transcription real-time polymerase chain reaction (RT-PCR) in early diagnosis of COVID-19. A systematic review with meta-analysis for numerical outcomes was performed, including 10 studies (6528 patients). High risk of systematic bias (spectrum bias) was demonstrated in all studies, while in several studies research information bias was found to be possible. The sensitivity of CT examination ranged from 72% to 98%, and the specificity from 22% to 96%. The overall sensitivity of the CT scan was 91% and the specificity 87% (95% CI). Overall sensitivity of the RT-PCR reference test was lower (87%) than its specificity (99%) (95% CI). No clear conclusion could be drawn on the rationale of using CT scanning in the early diagnosis of COVID-19 in situations when specific clinical symptoms and epidemiological history would indicate coronavirus infection. The sensitivity of the CT test seems to be higher than that of the RT-PCR reference test, but this may be related to the mode of analysis and type of material analysed in genetic tests. CT scanning could be performed in symptomatic patients, with a defined time interval from symptom onset to performing CT or RT-PCR, and it should be explicitly included as an additional procedure when initial coronavirus genetic test results are negative, while clinical symptoms and epidemiological history indicate possible infection. However, a reference test showing the presence of coronavirus genetic material is essential throughout the diagnostic and treatment process.

Radiological profile of patients undergoing Chest X-ray and computed tomography scans during COVID-19 outbreak

BACKGROUND & OBJECTIVE

Radiology has played a significant role in the diagnosis and quantifying the severity of COVID 19 pulmonary disease. This study was conducted to assess patterns and severity of COVID-19 pulmonary disease based on radiological imaging.

METHODS

A prospective observational study was conducted in a large tertiary care public sector teaching hospital of Karachi, Pakistan from June 2020 till August 2020. All confirmed and suspected COVID-19 patients referred for chest X-rays and computed tomography (CT) scans were evaluated along with RT-PCR results. Suspected patients were followed for RT-PCR. Radiological features and severity of imaging studies were determined.

RESULTS

Of 533 patients in whom X-rays were performed, majority had severe/critical findings, i.e., 304 (57.03%). Of 97 patients in whom CT scan was performed, mild/moderate findings were observed in 63 (64.94%) patients. Of 472 patients with abnormal X-rays, majority presented with alveolar pattern 459 (97.2%), bilateral lung involvement 453 (89.6%), and consolidation 356 (75.4%). Moreover, lobar predominance showed lower zone preponderance in 446 (94.5%) patients. Of 88 patients with abnormal CT findings, ground-glass opacity (GGO) 87 (98.9%) and crazy paving 69 (78.4%) were the most common findings. An insignificantly higher association of PCR positive cases was observed with severe/critical X-rays (p-value 0.076) and CT scan findings (p-value 0.431).

CONCLUSION

Most common patterns on CT scans were GGO and crazy paving. While on chest radiographs, bilateral lung involvement with alveolar pattern and consolidation were most common findings. On X-rays, majority had severe/critical whereas CT scan had mild/moderate findings.

EDL-COVID: Ensemble Deep Learning for COVID-19 Case Detection From Chest X-Ray Images

Effective screening of COVID-19 cases has been becoming extremely important to mitigate and stop the quick spread of the disease during the current period of COVID-19 pandemic worldwide. In this article, we consider radiology examination of using chest X-ray images, which is among the effective screening approaches for COVID-19 case detection. Given deep learning is an effective tool and framework for image analysis, there have been lots of studies for COVID-19 case detection by training deep learning models with X-ray images. Although some of them report good prediction results, their proposed deep learning models might suffer from overfitting, high variance, and generalization errors caused by noise and a limited number of datasets. Considering ensemble learning can overcome the shortcomings of deep learning by making predictions with multiple models instead of a single model, we propose EDL-COVID, an ensemble deep learning model employing deep learning and ensemble learning. The EDL-COVID model is generated by combining multiple snapshot models of COVID-Net, which has pioneered in an open-sourced COVID-19 case detection method with deep neural network processed chest X-ray images, by employing a proposed weighted averaging ensembling method that is aware of different sensitivities of deep learning models on different classes types. Experimental results show that EDL-COVID offers promising results for COVID-19 case detection with an accuracy of 95%, better than COVID-Net of 93.3%.

On the Use of Deep Learning for Imaging-Based COVID-19 Detection Using Chest X-rays

The global COVID-19 pandemic that started in 2019 and created major disruptions around the world demonstrated the imperative need for quick, inexpensive, accessible and reliable diagnostic methods that would allow the detection of infected individuals with minimal resources. Radiography, and more specifically, chest radiography, is a relatively inexpensive medical imaging modality that can potentially offer a solution for the diagnosis of COVID-19 cases. In this work, we examined eleven deep convolutional neural network architectures for the task of classifying chest X-ray images as belonging to healthy individuals, individuals with COVID-19 or individuals with viral pneumonia. All the examined networks are established architectures that have been proven to be efficient in image classification tasks, and we evaluated three different adjustments to modify the architectures for the task at hand by expanding them with additional layers. The proposed approaches were evaluated for all the examined architectures on a dataset with real chest X-ray images, reaching the highest classification accuracy of 98.04% and the highest F1-score of 98.22% for the best-performing setting.

Medical imaging and computational image analysis in COVID-19 diagnosis: A review

Coronavirus disease (COVID-19) is an infectious disease caused by a newly discovered coronavirus. The disease presents with symptoms such as shortness of breath, fever, dry cough, and chronic fatigue, amongst others. The disease may be asymptomatic in some patients in the early stages, which can lead to increased transmission of the disease to others. This study attempts to review papers on the role of imaging and medical image computing in COVID-19 diagnosis. For this purpose, PubMed, Scopus and Google Scholar were searched to find related studies until the middle of 2021. The contribution of this study is four-fold: 1) to use as a tutorial of the field for both clinicians and technologists, 2) to comprehensively review the characteristics of COVID-19 as presented in medical images, 3) to examine automated artificial intelligence-based approaches for COVID-19 diagnosis, 4) to express the research limitations in this field and the methods used to overcome them. Using machine learning-based methods can diagnose the disease with high accuracy from medical images and reduce time, cost and error of diagnostic procedure. It is recommended to collect bulk imaging data from patients in the shortest possible time to improve the performance of COVID-19 automated diagnostic methods.

Deep Supervised Domain Adaptation for Pneumonia Diagnosis from Chest X-ray Images

Pneumonia is one of the most common treatable causes of death, and early diagnosis allows for early intervention. Automated diagnosis of pneumonia can therefore improve outcomes. However, it is challenging to develop high performance deep learning models due to the lack of well-annotated data for training. This paper proposes a novel method, called Deep Supervised Domain Adaptation (DSDA), to automatically diagnose pneumonia from chest X-ray images. Specifically, we propose to transfer the knowledge from a publicly available large-scale source dataset (ChestX-ray14) to a well-annotated but small-scale target dataset (the TTSH dataset). DSDA aligns the distributions of the source domain and the target domain according to the underlying semantics of the training samples. It includes two task-specific sub-networks for the source domain and the target domain, respectively. These two sub-networks share the feature extraction layers and are trained in an end-to-end manner. Unlike most existing domain adaptation approaches that perform the same tasks in the source domain and the target domain, we attempt to transfer the knowledge from a multi-label classification task in the source domain to a binary classification task in the target domain. To evaluate the effectiveness of our method, we compare it with several existing peer methods. The experimental results show that our method can achieve promising performance for automated pneumonia diagnosis.

Coexistence of neurological diseases with Covid-19 pneumonia during the pandemic period

Although clinical findings are related to respiration in the Covid-19 pandemic, the number of patients with neurological symptoms and signs is increasing. The purpose of this study was to assess the prevalence of Covid-19 pneumonia using thoracic CT in patients who presented to the emergency room with neurological complaints during the pandemic. We retrospectively examined the files of 1093 patients who admitted to the emergency room and had a Neurology consultation. The research involved patients who had a neurological diagnosis and had typical findings of COVID-19 pneumonia on thorax computed tomography (CT). The thoracic CT scans of 68 (6.2%) of 1093 patients with neurological disorders at the time of admission revealed results consistent with Covid-19 pneumonia. The “real-time reverse transcription polymerase chain reaction” (RT-PCR) was positive in 42 of the 68 patients (62%), and the patients were diagnosed with Covid-19. Ground glass opacity was the most common finding in thoracic CT in patients diagnosed with Covid-19 pneumonia, with a rate of 92.9% (n = 39). Ischemic stroke (n = 26, 59.5%), cerebral haemorrhage (n = 11, 28.6%), epilepsy (n = 3, 7.1%), transient ischaemic attack (TIA; n = 1, 2.4%), and acute inflammatory demyelinating polyneuropathy (n = 1, 2.4%) were the most common neurological diagnoses among the patients. Even though Covid-19 affects the central and peripheral nervous systems, eliminating the possibility of Covid-19 pneumonia with thorax CT is critical for early treatment and patient prognosis.

Diagnostic performance of chest radiography in high COVID-19 prevalence setting: experience from a European reference hospital

Purpose

The study’s aim is to analyse the diagnostic performance of chest radiography (CXR) in patients with suspected coronavirus disease 19 (COVID-19).

Methods

We retrospectively considered 826 consecutive patients with suspected COVID-19 presenting to our emergency department (ED) from February 21 to March 31, 2020, in a high disease prevalence setting. We enrolled patients who underwent CXR and rhino-oropharyngeal swab for real-time reverse transcription-polymerase chain reaction (rRT-PCR). CXRs were evaluated by an expert radiologist; a second independent analysis was performed by two residents in consensus. All readers, blinded to rRT-PCR results, classified CXRs positive/negative depending on presence/absence of typical findings of COVID-19, using rRT-PCR as reference standard.

Results

We finally analysed 680 patients (median age 58); 547 (80%) tested positive for COVID-19. The diagnostic performance of CXR, interpreted by the expert reader, was as follows: sensitivity (79.0%; 95% CI: 75.3–82.3), specificity (81.2%; 95% CI: 73.5–87.5), PPV (94.5%;95% CI: 92.0–96.4), NPV (48.4%; 95% CI: 41.7–55.2), and accuracy (79.3%; 95% CI: 76.0–82.2). For the residents: sensitivity (75.1%; 95% CI: 71.2–78.7), specificity (57.9%; 95% CI: 49.9–66.4), PPV (88.0%; 95% CI: 84.7–90.8), NPV (36.2%; 95% CI: 29.7–43.0), and accuracy (71.6%; 95% CI: 68.1–75.0). We found a significant difference between the reporting sensitivity (p = 0.013) and specificity (p < 0.0001) of expert radiologist vs residents. CXR sensitivity was higher in patients with symptom onset > 5 days before ED presentation compared to ≤ 5 days (84.4% vs 70.7%).

Conclusions

CXR showed a sensitivity of 79% and a specificity of 81% in diagnosing viral pneumonia in symptomatic patients with clinical suspicion of COVID-19. Further studies in lower prevalence settings are needed.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10140-021-01946-x.

A comprehensive review of imaging findings in COVID-19 - status in early 2021

Medical imaging methods are assuming a greater role in the workup of patients with COVID-19, mainly in relation to the primary manifestation of pulmonary disease and the tissue distribution of the angiotensin-converting-enzyme 2 (ACE 2) receptor. However, the field is so new that no consensus view has emerged guiding clinical decisions to employ imaging procedures such as radiography, computer tomography (CT), positron emission tomography (PET), and magnetic resonance imaging, and in what measure the risk of exposure of staff to possible infection could be justified by the knowledge gained. The insensitivity of current RT-PCR methods for positive diagnosis is part of the rationale for resorting to imaging procedures. While CT is more sensitive than genetic testing in hospitalized patients, positive findings of ground glass opacities depend on the disease stage. There is sparse reporting on PET/CT with [18F]-FDG in COVID-19, but available results are congruent with the earlier literature on viral pneumonias. There is a high incidence of cerebral findings in COVID-19, and likewise evidence of gastrointestinal involvement. Artificial intelligence, notably machine learning is emerging as an effective method for diagnostic image analysis, with performance in the discriminative diagnosis of diagnosis of COVID-19 pneumonia comparable to that of human practitioners.

Thoracic Surgery in the COVID-19 Pandemic: A Novel Approach to Reach Guideline Consensus

The COVID-19 pandemic challenges international and national healthcare systems. In the field of thoracic surgery, procedures may be deferred due to mandatory constraints of the access to diagnostics, staff and follow-up facilities. There is a lack of prospective data on the management of benign and malignant thoracic conditions in the pandemic. Therefore, we derived recommendations from 14 thoracic societies to address key questions on the topic of COVID-19 in the field of thoracic surgery. Respective recommendations were extracted and the degree of consensus among different organizations was calculated. A high degree of consensus was found to temporarily suspend non-critical elective procedures or procedures for benign conditions and to prioritize patients with symptomatic or advanced cancer. Prior to hospitalization, patients should be screened for respiratory symptoms indicating possible COVID-19 infection and most societies recommended to screen all patients for COVID-19 prior to admission. There was a weak consensus on the usage of serology tests and CT scans for COVID-19 diagnostics. Nearly all societies suggested to postpone elective procedures in patients with suspected or confirmed COVID-19 and recommended constant reevaluation of these patients. Additionally, we summarized recommendations focusing on precautions in the theater and the management of chest drains. This study provides a novel approach to informed guidance for thoracic surgeons during the COVID-19 pandemic in the absence of scientific evidence-based data.

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.

Point of care detection of COVID-19: Advancement in biosensing and diagnostic methods

The recent outbreak of COVID-19 has created much inconvenience and fear that the virus can seriously affect humans, causing health hazards and death. This pandemic has created much worry and as per the report by World Health Organization (WHO), more than 43 million individuals in 215 countries and territories were affected. People around the world are still struggling to overcome the problems associated with this pandemic. Of all the available methods, reverse-transcriptase polymerase chain reaction (RT-PCR) has been widely practiced for the pandemic detection even though several diagnostic tools are available having varying accuracy and sensitivity. The method offers many advantages making it a life-saving tool, but the method has the limitation of transporting to the nearest pathology lab, thus limiting its application in resource limited settings. This has a risen a crucial need for point-of-care devices for on-site detection. In this venture, biosensors have been used, since they can be applied immediately at the point-of-care. This review will discuss about the available diagnostic methods and biosensors for COVID-19 detection.

A narrative review of coronavirus disease 2019 (COVID-19): clinical, epidemiological characteristics, and systemic manifestations

Coronavirus disease 2019 (COVID-19) is an emerging infectious disease which has had a rapid surge in cases and deaths since it is first documented in Wuhan, China, in December 2019. COVID-19 is caused by the Betacoronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). SARS-CoV-2 uses angiotensin-converting enzyme 2, which is highly expressed in the human lower respiratory tract but also in other tissues, as the cellular entry receptor. Thus, COVID-19 mainly affects the respiratory system but can cause damage to other body systems, including the cardiovascular, gastrointestinal, hepatobiliary, renal, and central nervous systems. We review the pathogenesis and clinical manifestations of the infection, focusing on our current understanding of the disease mechanisms and their translation to clinical outcomes, as well as adverse effects on different body systems. We also discuss the epidemiology pathogenesis, clinical, and multi-organ consequences, and highlight some of the research gaps regarding COVID-19.

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."

The Role of Medical Imaging in COVID-19

The coronavirus disease 2019 (COVID-19) pandemic launched in the third decade of the twenty-first century and continued to present time to cause the worst challenges the modern medicine has ever encountered. Medical imaging is an essential part of the universal fight against this pandemic. In the absence of documented treatment and vaccination, early accurate diagnosis of infected patients is the backbone of this pandemic management. This chapter reviews different aspects of medical imaging in the context of COVID-19.

Impact of the COVID-19 pandemic on clinical radiography practice in low resource settings: The Ghanaian radiographers' perspective

INTRODUCTION

The COVID-19 pandemic has altered the professional practice of all healthcare workers, including radiographers. In the pandemic, clinical practice of radiographers was centred mostly on chest imaging of COVID-19 patients and radiotherapy treatment care delivery to those with cancer. This study aimed to assess the radiographers' perspective on the impact of the pandemic on their wellbeing and imaging service delivery in Ghana.

METHODS

A cross-sectional survey of practising radiographers in Ghana was conducted online from March 26th to May 6th, 2020. A previously validated questionnaire that sought information regarding demographics, general perspectives on personal and professional impact of the pandemic was used as the research instrument. Data obtained was analysed using Microsoft Excel® 2016.

RESULTS

A response rate of 57.3% (134/234) was obtained. Of the respondents, 75.4% (n = 101) reported to have started experiencing high levels of workplace-related stress after the outbreak. Three-quarters (n = 98, 73.1%) of respondents reported limited access to any form of psychosocial support systems at work during the study period. Half (n = 67, 50%) of the respondents reported a decline in general workload during the study period while only a minority (n = 18, 13.4%) reported an increase in workload due to COVID-19 cases.

CONCLUSION

This national survey indicated that majority of the workforce started experiencing coronavirus-specific workplace-related stress after the outbreak. Albeit speculative, low patient confidence and fear of contracting the COVID-19 infection on hospital attendance contributed to the decline in general workload during the study period.

IMPLICATIONS FOR PRACTICE

In order to mitigate the burden of workplace-related stress on frontline workers, including radiographers, and in keeping to standard practices for staff mental wellbeing and patient safety, institutional support structures are necessary in similar future pandemics.

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.

Sensitivity of SARS-CoV-2 RNA polymerase chain reaction using a clinical and radiological reference standard

OBJECTIVES

Diagnostic tests for SARS-CoV-2 are important for epidemiology, clinical management, and infection control. Limitations of oro-nasopharyngeal real-time PCR sensitivity have been described based on comparisons of single tests with repeated sampling. We assessed SARS-CoV-2 PCR clinical sensitivity using a clinical and radiological reference standard.

METHODS

Between March-May 2020, 2060 patients underwent thoracic imaging and SARS-CoV-2 PCR testing. Imaging was independently double- or triple-reported (if discordance) by blinded radiologists according to radiological criteria for COVID-19. We excluded asymptomatic patients and those with alternative diagnoses that could explain imaging findings. Associations with PCR-positivity were assessed with binomial logistic regression.

RESULTS

901 patients had possible/probable imaging features and clinical symptoms of COVID-19 and 429 patients met the clinical and radiological reference case definition. SARS-CoV-2 PCR sensitivity was 68% (95% confidence interval 64-73), was highest 7-8 days after symptom onset (78% (68-88)) and was lower among current smokers (adjusted odds ratio 0.23 (0.12-0.42) p < 0.001).

CONCLUSIONS

In patients with clinical and imaging features of COVID-19, PCR test sensitivity was 68%, and was lower among smokers; a finding that could explain observations of lower disease incidence and that warrants further validation. PCR tests should be interpreted considering imaging, symptom duration and smoking status.

Atypical Pneumonia: Definition, Causes, and Imaging Features

Pneumonia is among the most common causes of death worldwide. The epidemiologic and clinical heterogeneity of pneumonia results in challenges in diagnosis and treatment. There is inconsistency in the definition of the group of microorganisms that cause "atypical pneumonia." Nevertheless, the use of this term in the medical and radiologic literature is common. Among the causes of community-acquired pneumonia, atypical bacteria are responsible for approximately 15% of cases. Zoonotic and nonzoonotic bacteria, as well as viruses, have been considered among the causes of atypical pneumonia in a patient who is immunocompetent and have been associated with major community outbreaks of respiratory infection, with relevant implications in public health policies. Considering the difficulty of isolating atypical microorganisms and the significant overlap in clinical manifestations, a targeted empirical therapy is not possible. Imaging plays an important role in the diagnosis and management of atypical pneumonia, as in many cases its findings may first suggest the possibility of an atypical infection. Clarifying and unifying the definition of atypical pneumonia among the medical community, including radiologists, are of extreme importance. The prompt diagnosis and prevention of community spread of some atypical microorganisms can have a relevant impact on local, regional, and global health policies. ^©RSNA, 2021.

Diagnostic accuracy of physician's gestalt in suspected COVID-19: Prospective bicentric study

OBJECTIVES

Physicians' gestalt is central in the diagnostic pipeline of suspected COVID-19, due to the absence of a single tool allowing conclusive rule in or rule out. The aim of this study was to estimate the diagnostic test characteristics of physician's gestalt for COVID-19 in the emergency department (ED), based on clinical findings or on a combination of clinical findings and bedside imaging results.

METHODS

From April 1 to April 30, 2020, patients with suspected COVID-19 were prospectively enrolled in two EDs. Physicians prospectively dichotomized patients in COVID-19 likely or unlikely twice: after medical evaluation of clinical features (clinical gestalt [CG]) and after evaluation of clinical features and results of lung ultrasound or chest x-ray (clinical and bedside imaging-integrated gestalt [CBIIG]). The final diagnosis was adjudicated after independent review of 30-day follow-up data.

RESULTS

Among 838 ED enrolled patients, 193 (23%) were finally diagnosed with COVID-19. The area under the curve (AUC), sensitivity, and specificity of CG and CBIIG for COVID-19 were 80.8% and 91.6% (p < 0.01), 82.9% and 91.4% (p = 0.01), and 78.6% and 91.8% (p < 0.01), respectively. CBIIG had similar AUC and sensitivity to reverse transcription-polymerase chain reaction (RT-PCR) for SARS-CoV-2 on the first nasopharyngeal swab per se (93.5%, p = 0.24; and 87%, p = 0.17, respectively). CBIIG plus RT-PCR had a sensitivity of 98.4% for COVID-19 (p < 0.01 vs. RT-PCR alone) compared to 95.9% for CG plus RT-PCR (p = 0.05).

CONCLUSIONS

In suspected COVID-19, CG and CBIIG have fair diagnostic accuracy, in line with physicians' gestalt for other acute conditions. Negative RT-PCR plus low probability based on CBIIG can rule out COVID-19 with a relatively low number of false-negative cases.

Chest radiography predictor of COVID-19 adverse outcomes. A lesson learnt from the first wave

AIM

To assess the role of a severity score based on chest radiography (CXR) in predicting the risk of adverse outcomes in coronavirus disease 2019 (COVID-19).

MATERIALS AND METHODS

Of the patients who presented to L. Sacco Hospital (Milan, Italy) between 21 February and 31 March 2020, patients with a laboratory confirmation of COVID-19 who also underwent a CXR were included in the study. To quantify the extent of lung involvement, each CXR image was given a score (Milan score), ranging from 0 to 24, depending on the presence of reticular pattern and/or ground-glass opacities and/or extensive consolidations in each of the 12 areas in which the lungs were divided. The score was calculated by an expert radiologist, blinded to laboratory tests. The ability of the Milan score to predict hospital admission and mortality, after adjusting for some variables (age; gender; comorbidities; time between symptoms onset and admission), using univariate and multivariate statistical analysis was investigated retrospectively.

RESULTS

Among the 554 patients, 115 of which (21%) had a negative CXR, the in-hospital mortality was 16% (90/554). At univariate analysis, age, gender, and comorbidities were significant predictors of mortality and hospital admission. At multivariate analysis, adjusting for age and gender, the Milan score was an independent predictor of mortality and hospitalisation. In particular, patients with a Milan score ≥ 9 had a mortality risk five-times higher than those with a lower score. Other independent predictors of mortality were gender and age.

CONCLUSIONS

The CXR Milan score was an independent predictive factor of both in-hospital mortality and hospital admission.

A Pictorial Review of the Role of Imaging in the Detection, Management, Histopathological Correlations, and Complications of COVID-19 Pneumonia

Imaging plays an important role in the detection of coronavirus (COVID-19) pneumonia in both managing the disease and evaluating the complications. Imaging with chest computed tomography (CT) can also have a potential predictive and prognostic role in COVID-19 patient outcomes. The aim of this pictorial review is to describe the role of imaging with chest X-ray (CXR), lung ultrasound (LUS), and CT in the diagnosis and management of COVID-19 pneumonia, the current indications, the scores proposed for each modality, the advantages/limitations of each modality and their role in detecting complications, and the histopathological correlations.

Quantitative and semi-quantitative CT assessments of lung lesion burden in COVID-19 pneumonia

This study aimed to clarify and provide clinical evidence for which computed tomography (CT) assessment method can more appropriately reflect lung lesion burden of the COVID-19 pneumonia. A total of 244 COVID-19 patients were recruited from three local hospitals. All the patients were assigned to mild, common and severe types. Semi-quantitative assessment methods, e.g., lobar-, segmental-based CT scores and opacity-weighted score, and quantitative assessment method, i.e., lesion volume quantification, were applied to quantify the lung lesions. All four assessment methods had high inter-rater agreements. At the group level, the lesion load in severe type patients was consistently observed to be significantly higher than that in common type in the applications of four assessment methods (all the p < 0.001). In discriminating severe from common patients at the individual level, results for lobe-based, segment-based and opacity-weighted assessments had high true positives while the quantitative lesion volume had high true negatives. In conclusion, both semi-quantitative and quantitative methods have excellent repeatability in measuring inflammatory lesions, and can well distinguish between common type and severe type patients. Lobe-based CT score is fast, readily clinically available, and has a high sensitivity in identifying severe type patients. It is suggested to be a prioritized method for assessing the burden of lung lesions in COVID-19 patients.

QIBA guidance: Computed tomography imaging for COVID-19 quantitative imaging applications

As the COVID-19 pandemic impacts global populations, computed tomography (CT) lung imaging is being used in many countries to help manage patient care as well as to rapidly identify potentially useful quantitative COVID-19 CT imaging biomarkers. Quantitative COVID-19 CT imaging applications, typically based on computer vision modeling and artificial intelligence algorithms, include the potential for better methods to assess COVID-19 extent and severity, assist with differential diagnosis of COVID-19 versus other respiratory conditions, and predict disease trajectory. To help accelerate the development of robust quantitative imaging algorithms and tools, it is critical that CT imaging is obtained following best practices of the quantitative lung CT imaging community. Toward this end, the Radiological Society of North America's (RSNA) Quantitative Imaging Biomarkers Alliance (QIBA) CT Lung Density Profile Committee and CT Small Lung Nodule Profile Committee developed a set of best practices to guide clinical sites using quantitative imaging solutions and to accelerate the international development of quantitative CT algorithms for COVID-19. This guidance document provides quantitative CT lung imaging recommendations for COVID-19 CT imaging, including recommended CT image acquisition settings for contemporary CT scanners. Additional best practice guidance is provided on scientific publication reporting of quantitative CT imaging methods and the importance of contributing COVID-19 CT imaging datasets to open science research databases.