Role of Imaging in the Management of Patients with SARS-CoV-2 Lung Involvement Admitted to the Emergency Department: A Systematic Review.

During the waves of the coronavirus disease (COVID-19) pandemic, emergency departments were overflowing with patients suffering with suspected medical or surgical issues. In these settings, healthcare staff should be able to deal with different medical and surgical scenarios while protecting themselves against the risk of contamination. Various strategies were used to overcome the most critical issues and guarantee quick and efficient diagnostic and therapeutic charts. The use of saliva and nasopharyngeal swab Nucleic Acid Amplification Tests (NAAT) in the diagnosis of COVID-19 was one of the most adopted worldwide. However, NAAT results were slow to report and could sometimes create significant delays in patient management, especially during pandemic peaks. On these bases, radiology has played and continues to play an essential role in detecting COVID-19 patients and solving differential diagnosis between different medical conditions. This systematic review aims to summarize the role of radiology in the management of COVID-19 patients admitted to emergency departments by using chest X-rays (CXR), computed tomography (CT), lung ultrasounds (LUS), and artificial intelligence (AI).

Chest CT opportunistic biomarkers for phenotyping high-risk COVID-19 patients: a retrospective multicentre study.

OBJECTIVE: To assess the value of opportunistic biomarkers derived from chest CT performed at hospital admission of COVID-19 patients for the phenotypization of high-risk patients. METHODS: In this multicentre retrospective study, 1845 consecutive COVID-19 patients with chest CT performed within 72 h from hospital admission were analysed. Clinical and outcome data were collected by each center 30 and 80 days after hospital admission. Patients with unknown outcomes were excluded. Chest CT was analysed in a single core lab and behind pneumonia CT scores were extracted opportunistic data about atherosclerotic profile (calcium score according to Agatston method), liver steatosis (≤ 40 HU), myosteatosis (paraspinal muscle F < 31.3 HU, M < 37.5 HU), and osteoporosis (D12 bone attenuation < 134 HU). Differences according to treatment and outcome were assessed with ANOVA. Prediction models were obtained using multivariate binary logistic regression and their AUCs were compared with the DeLong test. RESULTS: The final cohort included 1669 patients (age 67.5 [58.5-77.4] yo) mainly men 1105/1669, 66.2%) and with reduced oxygen saturation (92% [88-95%]). Pneumonia severity, high Agatston score, myosteatosis, liver steatosis, and osteoporosis derived from CT were more prevalent in patients with more aggressive treatment, access to ICU, and in-hospital death (always p < 0.05). A multivariable model including clinical and CT variables improved the capability to predict non-critical pneumonia compared to a model including only clinical variables (AUC 0.801 vs 0.789; p = 0.0198) to predict patient death (AUC 0.815 vs 0.800; p = 0.001). CONCLUSION: Opportunistic biomarkers derived from chest CT can improve the characterization of COVID-19 high-risk patients. CLINICAL RELEVANCE STATEMENT: In COVID-19 patients, opportunistic biomarkers of cardiometabolic risk extracted from chest CT improve patient risk stratification. KEY POINTS: • In COVID-19 patients, several information about patient comorbidities can be quantitatively extracted from chest CT, resulting associated with the severity of oxygen treatment, access to ICU, and death. • A prediction model based on multiparametric opportunistic biomarkers derived from chest CT resulted superior to a model including only clinical variables in a large cohort of 1669 patients suffering from SARS- CoV2 infection. • Opportunistic biomarkers of cardiometabolic comorbidities derived from chest CT may improve COVID-19 patients' risk stratification also in absence of detailed clinical data and laboratory tests identifying subclinical and previously unknown conditions.

Liver involvement in patients with COVID-19 infection: A comprehensive overview of diagnostic imaging features.

During the first wave of the pandemic, coronavirus disease 2019 (COVID-19) infection has been considered mainly as a pulmonary infection. However, different clinical and radiological manifestations were observed over time, including involvement of abdominal organs. Nowadays, the liver is considered one of the main affected abdominal organs. Hepatic involvement may be caused by either a direct damage by the virus or an indirect damage related to COVID-19 induced thrombosis or to the use of different drugs. After clinical assessment, radiology plays a key role in the evaluation of liver involvement. Ultrasonography (US), computed tomography (CT) and magnetic resonance imaging (MRI) may be used to evaluate liver involvement. US is widely available and it is considered the first-line technique to assess liver involvement in COVID-19 infection, in particular liver steatosis and portal-vein thrombosis. CT and MRI are used as second- and third-line techniques, respectively, considering their higher sensitivity and specificity compared to US for assessment of both parenchyma and vascularization. This review aims to the spectrum of COVID-19 liver involvement and the most common imaging features of COVID-19 liver damage.

Unsupervised segmentation and quantification of COVID-19 lesions on computed Tomography scans using CycleGAN.

BACKGROUND: Lesion segmentation is a critical step in medical image analysis, and methods to identify pathology without time-intensive manual labeling of data are of utmost importance during a pandemic and in resource-constrained healthcare settings. Here, we describe a method for fully automated segmentation and quantification of pathological COVID-19 lung tissue on chest Computed Tomography (CT) scans without the need for manually segmented training data. METHODS: We trained a cycle-consistent generative adversarial network (CycleGAN) to convert images of COVID-19 scans into their generated healthy equivalents. Subtraction of the generated healthy images from their corresponding original CT scans yielded maps of pathological tissue, without background lung parenchyma, fissures, airways, or vessels. We then used these maps to construct three-dimensional lesion segmentations. Using a validation dataset, Dice scores were computed for our lesion segmentations and other published segmentation networks using ground truth segmentations reviewed by radiologists. RESULTS: The COVID-to-Healthy generator eliminated high Hounsfield unit (HU) voxels within pulmonary lesions and replaced them with lower HU voxels. The generator did not distort normal anatomy such as vessels, airways, or fissures. The generated healthy images had higher gas content (2.45 ± 0.93 vs 3.01 ± 0.84 L, P < 0.001) and lower tissue density (1.27 ± 0.40 vs 0.73 ± 0.29 Kg, P < 0.001) than their corresponding original COVID-19 images, and they were not significantly different from those of the healthy images (P < 0.001). Using the validation dataset, lesion segmentations scored an average Dice score of 55.9, comparable to other weakly supervised networks that do require manual segmentations. CONCLUSION: Our CycleGAN model successfully segmented pulmonary lesions in mild and severe COVID-19 cases. Our model's performance was comparable to other published models; however, our model is unique in its ability to segment lesions without the need for manual segmentations.

AI-SCoRE (artificial intelligence-SARS CoV2 risk evaluation): a fast, objective and fully automated platform to predict the outcome in COVID-19 patients.

PURPOSE: To develop and validate an effective and user-friendly AI platform based on a few unbiased clinical variables integrated with advanced CT automatic analysis for COVID-19 patients' risk stratification. MATERIAL AND METHODS: In total, 1575 consecutive COVID-19 adults admitted to 16 hospitals during wave 1 (February 16-April 29, 2020), submitted to chest CT within 72 h from admission, were retrospectively enrolled. In total, 107 variables were initially collected; 64 extracted from CT. The outcome was survival. A rigorous AI model selection framework was adopted for models selection and automatic CT data extraction. Model performances were compared in terms of AUC. A web-mobile interface was developed using Microsoft PowerApps environment. The platform was externally validated on 213 COVID-19 adults prospectively enrolled during wave 2 (October 14-December 31, 2020). RESULTS: The final cohort included 1125 patients (292 non-survivors, 26%) and 24 variables. Logistic showed the best performance on the complete set of variables (AUC = 0.839 ± 0.009) as in models including a limited set of 13 and 5 variables (AUC = 0.840 ± 0.0093 and AUC = 0.834 ± 0.007). For non-inferior performance, the 5 variables model (age, sex, saturation, well-aerated lung parenchyma and cardiothoracic vascular calcium) was selected as the final model and the extraction of CT-derived parameters was fully automatized. The fully automatic model showed AUC = 0.842 (95% CI: 0.816-0.867) on wave 1 and was used to build a 0-100 scale risk score (AI-SCoRE). The predictive performance was confirmed on wave 2 (AUC 0.808; 95% CI: 0.7402-0.8766). CONCLUSIONS: AI-SCoRE is an effective and reliable platform for automatic risk stratification of COVID-19 patients based on a few unbiased clinical data and CT automatic analysis.

Multiorgan Involvement in SARS-CoV-2 Infection: The Role of the Radiologist from Head to Toe.

Radiology plays a crucial role for the diagnosis and management of COVID-19 patients during the different stages of the disease, allowing for early detection of manifestations and complications of COVID-19 in the different organs. Lungs are the most common organs involved by SARS-CoV-2 and chest computed tomography (CT) represents a reliable imaging-based tool in acute, subacute, and chronic settings for diagnosis, prognosis, and management of lung disease and the evaluation of acute and chronic complications. Cardiac involvement can be evaluated by using cardiac computed tomography angiography (CCTA), considered as the best choice to solve the differential diagnosis between the most common cardiac conditions: acute coronary syndrome, myocarditis, and cardiac dysrhythmia. By using compressive ultrasound it's possible to study the peripheral arteries and veins and to exclude the deep vein thrombosis, directly linked to the onset of pulmonary embolism. Moreover, CT and especially MRI can help to evaluate the gastrointestinal involvement and assess hepatic function, pancreas involvement, and exclude causes of lymphocytopenia, thrombocytopenia, and leukopenia, typical of COVID-19 patients. Finally, radiology plays a crucial role in the early identification of renal damage in COVID-19 patients, by using both CT and US. This narrative review aims to provide a comprehensive radiological analysis of commonly involved organs in patients with COVID-19 disease.

Compressive ultrasound can predict early pulmonary embolism onset in COVID patients.

PURPOSE: To evaluate the usefulness of compressive ultrasound (CUS) for the diagnosis of deep vein thrombosis (DVT) in patients with SARS-CoV-2-related infection. METHODS: 112 hospitalized patients with confirmed SARS-CoV-2 infection were retrospectively enrolled. CUS was performed within 2 days of admission and consisted in the assessment of the proximal and distal deep venous systems. Lack of compressibility, or direct identification of an endoluminal thrombus, were the criteria used for the diagnosis of DVT. Pulmonary embolism (PE) events were investigated at computed tomography pulmonary angiography (CTPA) within 5 days of follow-up. Logistic binary regression was computed to determine which clinical and radiological parameters were independently associated with PE onset. RESULTS: Overall, the incidence of DVT in our cohort was about 43%. The most common district involved was the left lower limb (68.7%) in comparison with the right one (58.3%) while the upper limbs were less frequently involved (4.2% the right one and 2.1% the left one, respectively). On both sides, the distal tract of the popliteal vein was the most common involved (50% right side and 45.8% left side). The presence of DVT in the distal tract of the right popliteal vein (OR = 2.444 95%CIs 1.084-16.624, p = 0.038), in the distal tract of the left popliteal vein (OR = 4.201 95%CIs 1.484-11.885, p = 0.007), and D-dimer values (OR = 2.122 95%CIs 1.030-5.495, p = 0.003) were independently associated with the onset on PE within 5 days. CONCLUSIONS: CUS should be considered a useful tool to discriminate which category of patients can develop PE within 5 days from admission.

Computed tomography semi-automated lung volume quantification in SARS-CoV-2-related pneumonia.

OBJECTIVES: To evaluate a semi-automated segmentation and ventilated lung quantification on chest computed tomography (CT) to assess lung involvement in patients affected by SARS-CoV-2. Results were compared with clinical and functional parameters and outcomes. METHODS: All images underwent quantitative analyses with a dedicated workstation using a semi-automatic lung segmentation software to compute ventilated lung volume (VLV), Ground-glass opacity (GGO) volume (GGO-V), and consolidation volume (CONS-V) as absolute volume and as a percentage of total lung volume (TLV). The ratio between CONS-V, GGO-V, and VLV (CONS-V/VLV and GGO-V/VLV, respectively), TLV (CONS-V/TLV, GGO-V/TLV, and GGO-V + CONS-V/TLV respectively), and the ratio between VLV and TLV (VLV/TLV) were calculated. RESULTS: A total of 108 patients were enrolled. GGO-V/TLV significantly correlated with WBC (r = 0.369), neutrophils (r = 0.446), platelets (r = 0.182), CRP (r = 0.190), PaCO2 (r = 0.176), HCO3- (r = 0.284), and PaO2/FiO2 (P/F) values (r = - 0.344). CONS-V/TLV significantly correlated with WBC (r = 0.294), neutrophils (r = 0.300), lymphocytes (r = -0.225), CRP (r = 0.306), PaCO2 (r = 0.227), pH (r = 0.162), HCO3- (r = 0.394), and P/F (r = - 0.419) values. Statistically significant differences between CONS-V, GGO-V, GGO-V/TLV, CONS-V/TLV, GGO-V/VLV, CONS-V/VLV, GGO-V + CONS-V/TLV, VLV/TLV, CT score, and invasive ventilation by ET were found (all p < 0.05). CONCLUSION: The use of quantitative semi-automated algorithm for lung CT elaboration effectively correlates the severity of SARS-CoV-2-related pneumonia with laboratory parameters and the need for invasive ventilation. KEY POINTS: • Pathological lung volumes, expressed both as GGO-V and as CONS-V, can be considered a useful tool in SARS-CoV-2-related pneumonia. • All lung volumes, expressed themselves and as ratio with TLV and VLV, correlate with laboratory data, in particular C-reactive protein and white blood cell count. • All lung volumes correlate with patient's outcome, in particular concerning invasive ventilation.

The hidden interplay between sex and COVID-19 mortality: the role of cardiovascular calcification.

Recent clinical and demographical studies on COVID-19 patients have demonstrated that men experience worse outcomes than women. However, in most cases, the data were not stratified according to gender, limiting the understanding of the real impact of gender on outcomes. This study aimed to evaluate the disaggregated in-hospital outcomes and explore the possible interactions between gender and cardiovascular calcifications. Data was derived from the sCORE-COVID-19 registry, an Italian multicentre registry that enrolled COVID-19 patients who had undergone a chest computer tomography scan on admission. A total of 1683 hospitalized patients (mean age 67±14 years) were included. Men had a higher prevalence of cardiovascular comorbidities, a higher pneumonia extension, more coronary calcifications (63% vs.50.9%, p<0.001), and a higher coronary calcium score (391±847 vs. 171±479 mm3, p<0.001). Men experienced a significantly higher mortality rate (24.4% vs. 17%, p=0.001), but the death event tended to occur earlier in women (15±7 vs. 8±7 days, p= 0.07). Non-survivors had a higher coronary, thoracic aorta, and aortic valve calcium score. Female sex, a known independent predictor of a favorable outcome in SARS-CoV2 infection, was not protective in women with a coronary calcification volume greater than 100 mm3. There were significant differences in cardiovascular comorbidities and vascular calcifications between men and women with SARS-CoV2 pneumonia. The differences in outcomes can be at least partially explained by the different cardiovascular profiles. However, women with poor outcomes had the same coronary calcific burden as men. The presumed favorable female sex bias in COVID-19 must therefore be reviewed in the context of comorbidities, especially cardiovascular ones.

Impact of clinical and subclinical coronary artery disease as assessed by coronary artery calcium in COVID-19.

BACKGROUND AND AIMS: The potential impact of coronary atherosclerosis, as detected by coronary artery calcium, on clinical outcomes in COVID-19 patients remains unsettled. We aimed to evaluate the prognostic impact of clinical and subclinical coronary artery disease (CAD), as assessed by coronary artery calcium score (CAC), in a large, unselected population of hospitalized COVID-19 patients undergoing non-gated chest computed tomography (CT) for clinical practice. METHODS: SARS-CoV 2 positive patients from the multicenter (16 Italian hospitals), retrospective observational SCORE COVID-19 (calcium score for COVID-19 Risk Evaluation) registry were stratified in three groups: (a) "clinical CAD" (prior revascularization history), (b) "subclinical CAD" (CAC >0), (c) "No CAD" (CAC = 0). Primary endpoint was in-hospital mortality and the secondary endpoint was a composite of myocardial infarction and cerebrovascular accident (MI/CVA). RESULTS: Amongst 1625 patients (male 67.2%, median age 69 [interquartile range 58-77] years), 31%, 57.8% and 11.1% had no, subclinical and clinical CAD, respectively. Increasing rates of in-hospital mortality (11.3% vs. 27.3% vs. 39.8%, p < 0.001) and MI/CVA events (2.3% vs. 3.8% vs. 11.9%, p < 0.001) were observed for patients with no CAD vs. subclinical CAD vs clinical CAD, respectively. The association with in-hospital mortality was independent of in-study outcome predictors (age, peripheral artery disease, active cancer, hemoglobin, C-reactive protein, LDH, aerated lung volume): subclinical CAD vs. No CAD: adjusted hazard ratio (adj-HR) 2.86 (95% confidence interval [CI] 1.14-7.17, p=0.025); clinical CAD vs. No CAD: adj-HR 3.74 (95% CI 1.21-11.60, p=0.022). Among patients with subclinical CAD, increasing CAC burden was associated with higher rates of in-hospital mortality (20.5% vs. 27.9% vs. 38.7% for patients with CAC score thresholds≤100, 101-400 and > 400, respectively, p < 0.001). The adj-HR per 50 points increase in CAC score 1.007 (95%CI 1.001-1.013, p=0.016). Cardiovascular risk factors were not independent predictors of in-hospital mortality when CAD presence and extent were taken into account. CONCLUSIONS: The presence and extent of CAD are associated with in-hospital mortality and MI/CVA among hospitalized patients with COVID-19 disease and they appear to be a better prognostic gauge as compared to a clinical cardiovascular risk assessment.

Coronary and total thoracic calcium scores predict mortality and provides pathophysiologic insights in COVID-19 patients.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has spread worldwide determining dramatic impacts on healthcare systems. Early identification of high-risk parameters is required in order to provide the best therapeutic approach. Coronary, thoracic aorta and aortic valve calcium can be measured from a non-gated chest computer tomography (CT) and are validated predictors of cardiovascular events and all-cause mortality. However, their prognostic role in acute systemic inflammatory diseases, such as COVID-19, has not been investigated. OBJECTIVES: The aim was to evaluate the association of coronary artery calcium and total thoracic calcium on in-hospital mortality in COVID-19 patients. METHODS: 1093 consecutive patients from 16 Italian hospitals with a positive swab for COVID-19 and an admission chest CT for pneumonia severity assessment were included. At CT, coronary, aortic valve and thoracic aorta calcium were qualitatively and quantitatively evaluated separately and combined together (total thoracic calcium) by a central Core-lab blinded to patients' outcomes. RESULTS: Non-survivors compared to survivors had higher coronary artery [Agatston (467.76 â€‹± â€‹570.92 vs 206.80 â€‹± â€‹424.13 â€‹mm2, p â€‹< â€‹0.001); Volume (487.79 â€‹± â€‹565.34 vs 207.77 â€‹± â€‹406.81, p â€‹< â€‹0.001)], aortic valve [Volume (322.45 â€‹± â€‹390.90 vs 98.27 â€‹± â€‹250.74 mm2, p â€‹< â€‹0.001; Agatston 337.38 â€‹± â€‹414.97 vs 111.70 â€‹± â€‹282.15, p â€‹< â€‹0.001)] and thoracic aorta [Volume (3786.71 â€‹± â€‹4225.57 vs 1487.63 â€‹± â€‹2973.19 mm2, p â€‹< â€‹0.001); Agatston (4688.82 â€‹± â€‹5363.72 vs 1834.90 â€‹± â€‹3761.25, p â€‹< â€‹0.001)] calcium values. Coronary artery calcium (HR 1.308; 95% CI, 1.046-1.637, p â€‹= â€‹0.019) and total thoracic calcium (HR 1.975; 95% CI, 1.200-3.251, p â€‹= â€‹0.007) resulted to be independent predictors of in-hospital mortality. CONCLUSION: Coronary, aortic valve and thoracic aortic calcium assessment on admission non-gated CT permits to stratify the COVID-19 patients in-hospital mortality risk.

Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia.

We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia.

Helmet CPAP to treat hypoxic pneumonia outside the ICU: an observational study during the COVID-19 outbreak.

BACKGROUND: Respiratory failure due to COVID-19 pneumonia is associated with high mortality and may overwhelm health care systems, due to the surge of patients requiring advanced respiratory support. Shortage of intensive care unit (ICU) beds required many patients to be treated outside the ICU despite severe gas exchange impairment. Helmet is an effective interface to provide continuous positive airway pressure (CPAP) noninvasively. We report data about the usefulness of helmet CPAP during pandemic, either as treatment, a bridge to intubation or a rescue therapy for patients with care limitations (DNI). METHODS: In this observational study we collected data regarding patients failing standard oxygen therapy (i.e., non-rebreathing mask) due to COVID-19 pneumonia treated with a free flow helmet CPAP system. Patients' data were recorded before, at initiation of CPAP treatment and once a day, thereafter. CPAP failure was defined as a composite outcome of intubation or death. RESULTS: A total of 306 patients were included; 42% were deemed as DNI. Helmet CPAP treatment was successful in 69% of the full treatment and 28% of the DNI patients (P < 0.001). With helmet CPAP, PaO2/FiO2 ratio doubled from about 100 to 200 mmHg (P < 0.001); respiratory rate decreased from 28 [22-32] to 24 [20-29] breaths per minute, P < 0.001). C-reactive protein, time to oxygen mask failure, age, PaO2/FiO2 during CPAP, number of comorbidities were independently associated with CPAP failure. Helmet CPAP was maintained for 6 [3-9] days, almost continuously during the first two days. None of the full treatment patients died before intubation in the wards. CONCLUSIONS: Helmet CPAP treatment is feasible for several days outside the ICU, despite persistent impairment in gas exchange. It was used, without escalating to intubation, in the majority of full treatment patients after standard oxygen therapy failed. DNI patients could benefit from helmet CPAP as rescue therapy to improve survival. TRIAL REGISTRATION: NCT04424992.

CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network.

The purpose of this study was to develop a fully-automated segmentation algorithm, robust to various density enhancing lung abnormalities, to facilitate rapid quantitative analysis of computed tomography images. A polymorphic training approach is proposed, in which both specifically labeled left and right lungs of humans with COPD, and nonspecifically labeled lungs of animals with acute lung injury, were incorporated into training a single neural network. The resulting network is intended for predicting left and right lung regions in humans with or without diffuse opacification and consolidation. Performance of the proposed lung segmentation algorithm was extensively evaluated on CT scans of subjects with COPD, confirmed COVID-19, lung cancer, and IPF, despite no labeled training data of the latter three diseases. Lobar segmentations were obtained using the left and right lung segmentation as input to the LobeNet algorithm. Regional lobar analysis was performed using hierarchical clustering to identify radiographic subtypes of COVID-19. The proposed lung segmentation algorithm was quantitatively evaluated using semi-automated and manually-corrected segmentations in 87 COVID-19 CT images, achieving an average symmetric surface distance of [Formula: see text] mm and Dice coefficient of [Formula: see text]. Hierarchical clustering identified four radiographical phenotypes of COVID-19 based on lobar fractions of consolidated and poorly aerated tissue. Lower left and lower right lobes were consistently more afflicted with poor aeration and consolidation. However, the most severe cases demonstrated involvement of all lobes. The polymorphic training approach was able to accurately segment COVID-19 cases with diffuse consolidation without requiring COVID-19 cases for training.

Machine learning applied on chest x-ray can aid in the diagnosis of COVID-19: a first experience from Lombardy, Italy.

BACKGROUND: We aimed to train and test a deep learning classifier to support the diagnosis of coronavirus disease 2019 (COVID-19) using chest x-ray (CXR) on a cohort of subjects from two hospitals in Lombardy, Italy. METHODS: We used for training and validation an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals (Centres 1 and 2). We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19 patients. Real-time polymerase chain reaction served as the reference standard. RESULTS: At 10-fold cross-validation, our deep learning model classified COVID-19 and non-COVID-19 patients with 0.78 sensitivity (95% confidence interval [CI] 0.74-0.81), 0.82 specificity (95% CI 0.78-0.85), and 0.89 area under the curve (AUC) (95% CI 0.86-0.91). For the independent dataset, deep learning showed 0.80 sensitivity (95% CI 0.72-0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73-0.87), and 0.81 AUC (95% CI 0.73-0.87). Radiologists' reading obtained 0.63 sensitivity (95% CI 0.52-0.74) and 0.78 specificity (95% CI 0.61-0.90) in Centre 1 and 0.64 sensitivity (95% CI 0.52-0.74) and 0.86 specificity (95% CI 0.71-0.95) in Centre 2. CONCLUSIONS: This preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of deep learning for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance.

Acute pulmonary embolism in hospitalized patients with SARS-CoV-2-related pneumonia: multicentric experience from Italian endemic area.

PURPOSE: To analyze pulmonary embolism (PE) on chest computed tomography pulmonary angiography (CTPA) in hospitalized patients affected by SARS-CoV-2, according to the severity of lung disease based both on temporal CT features changes and on CT-severity lung involvement (CT-severity score), along with the support of clinical and laboratory findings. METHODS: We retrospectively enrolled a total of 170 patients with confirmed SARS-CoV-2 infection who underwent CTPA examination for PE suspicion. Pulmonary arteries diameters, right ventricle/left ventricle (RV/LV) ratio, presence, absence, and distribution of PE, pulmonary artery obstructive index (PAO index), and lobe involvement were recorded. All CT scans were reviewed to assess temporal CT changes and the COVID CT-severity score. RESULTS: A total of 76 out of 170 patients (44.7%) developed PE without having any major risk factors for venous thromboembolism. The most severe pulmonary arteries involvement, expressed in terms of PAO Index, occurred in those patients with markedly elevated D-dimer and C-reactive protein (CRP) values and those patients with an advanced temporal stage of lung disease. The majority PE-positive patients were hospitalized in non-intensive wards. PE-positive patients showed a slightly higher hospitalization time in comparison with PE-negative ones. In the three months of study, overall 85.9% of patients were discharged while 14.1% died, of whom 13 PE-positive (54.2%). CONCLUSIONS: Patients hospitalized for SARS-CoV-2 infection present a higher cumulative incidence of PE compared to the general population of hospitalized patients, regardless of the severity of lung inflammation or the temporal stage of the disease.

Chest CT-derived pulmonary artery enlargement at the admission predicts overall survival in COVID-19 patients: insight from 1461 consecutive patients in Italy.

OBJECTIVES: Enlarged main pulmonary artery diameter (MPAD) resulted to be associated with pulmonary hypertension and mortality in a non-COVID-19 setting. The aim was to investigate and validate the association between MPAD enlargement and overall survival in COVID-19 patients. METHODS: This is a cohort study on 1469 consecutive COVID-19 patients submitted to chest CT within 72 h from admission in seven tertiary level hospitals in Northern Italy, between March 1 and April 20, 2020. Derivation cohort (n = 761) included patients from the first three participating hospitals; validation cohort (n = 633) included patients from the remaining hospitals. CT images were centrally analyzed in a core-lab blinded to clinical data. The prognostic value of MPAD on overall survival was evaluated at adjusted and multivariable Cox's regression analysis on the derivation cohort. The final multivariable model was tested on the validation cohort. RESULTS: In the derivation cohort, the median age was 69 (IQR, 58-77) years and 537 (70.6%) were males. In the validation cohort, the median age was 69 (IQR, 59-77) years with 421 (66.5%) males. Enlarged MPAD (≥ 31 mm) was a predictor of mortality at adjusted (hazard ratio, HR [95%CI]: 1.741 [1.253-2.418], p < 0.001) and multivariable regression analysis (HR [95%CI]: 1.592 [1.154-2.196], p = 0.005), together with male gender, old age, high creatinine, low well-aerated lung volume, and high pneumonia extension (c-index [95%CI] = 0.826 [0.796-0.851]). Model discrimination was confirmed on the validation cohort (c-index [95%CI] = 0.789 [0.758-0.823]), also using CT measurements from a second reader (c-index [95%CI] = 0.790 [0.753;0.825]). CONCLUSION: Enlarged MPAD (≥ 31 mm) at admitting chest CT is an independent predictor of mortality in COVID-19. KEY POINTS: • Enlargement of main pulmonary artery diameter at chest CT performed within 72 h from the admission was associated with a higher rate of in-hospital mortality in COVID-19 patients. • Enlargement of main pulmonary artery diameter (≥ 31 mm) was an independent predictor of death in COVID-19 patients at adjusted and multivariable regression analysis. • The combined evaluation of clinical findings, lung CT features, and main pulmonary artery diameter may be useful for risk stratification in COVID-19 patients.

Chest CT in the emergency department for suspected COVID-19 pneumonia.

PURPOSE: In overwhelmed emergency departments (EDs) facing COVID-19 outbreak, a swift diagnosis is imperative. CT role was widely debated for its limited specificity. Here we report the diagnostic role of CT in two EDs in Lombardy, epicenter of Italian outbreak. MATERIAL AND METHODS: Admitting chest CT from 142 consecutive patients with suspected COVID-19 were retrospectively analyzed. CT scans were classified in "highly likely," "likely," and "unlikely" COVID-19 pneumonia according to the presence of typical, indeterminate, and atypical findings, or "negative" in the absence of findings, or "alternative diagnosis" when a different diagnosis was found. Nasopharyngeal swab results, turnaround time, and time to positive results were collected. CT diagnostic performances were assessed considering RT-PCR as reference standard. RESULTS: Most of cases (96/142, 68%) were classified as "highly likely" COVID-19 pneumonia. Ten (7%) and seven (5%) patients were classified as "likely" and "unlikely" COVID-19 pneumonia, respectively. In 21 (15%) patients a differential diagnosis was provided, including typical pneumonia, pulmonary edema, neoplasia, and pulmonary embolism. CT was negative in 8/142 (6%) patients. Mean turnaround time for the first COVID-19 RT-PCR was 30 ± 13 h. CT diagnostic accuracy in respect of the first test swab was 79% and increased to 91.5% after repeated swabs and/or BAL, for 18 false-negative first swab. CT performance was good with 76% specificity, 99% sensitivity, 90% positive predictive value and 97% negative predictive value. CONCLUSION: Chest CT was useful to streamline patients' triage while waiting for RT-PCR in the ED, supporting the clinical suspicion of COVID-19 or providing alternative diagnosis.

Chest X-ray features of SARS-CoV-2 in the emergency department: a multicenter experience from northern Italian hospitals.

OBJECTIVES: To evaluate the imaging features of routine admission chest X-ray in patients referred for novel Coronavirus 2019 infection. METHODS: All patients referred to the emergency departments, RT-PCR positive for SARS-CoV-2 infection were evaluated. Demographic and clinical data were recorded. Two radiologists (8 and 15 years of experience) reviewed all the X-ray images and evaluated the following findings: interstitial opacities, alveolar opacities (AO), AO associated with consolidation, consolidation and/or pleural effusion. We stratified patients in groups according to the time interval between symptoms onset (cut-off 5 days) and X-ray imaging and according to age (cut-off 60 years old). Computed tomography was performed in case of a discrepancy between clinical symptoms, laboratory and X-ray findings, and/or suspicion of complications. RESULTS: A total of 468 patients were tested positive for SARS-CoV-2. Lung lesions primarily manifested as interstitial opacities (71.7%) and AO opacities (60.5%), more frequently bilateral (64.5%) and with a peripheral predominance (62.5%). Patients admitted to the emergency radiology department after 5 days from symptoms onset, more frequently had interstitial and AO opacities, in comparison to those admitted within 5 days, and lung lesions were more frequently bilateral and peripheral. Older patients more frequently presented interstitial and AO opacities in comparison to younger ones. Sixty-eight patients underwent CT that principally showed the presence of ground-glass opacities and consolidations. CONCLUSIONS: The most common X-ray pattern is multifocal and peripheral, associated with interstitial and alveolar opacities. Chest X-ray, compared to CT, can be considered a reliable diagnostic tool, especially in the Emergency setting.

Diagnostic impact of bedside chest X-ray features of 2019 novel coronavirus in the routine admission at the emergency department: case series from Lombardy region.

PURPOSE: To evaluate the diagnostic accuracy and the imaging features of routine admission chest X-ray in patients suspected for novel Coronavirus 2019 (SARS-CoV-2) infection. METHOD: We retrospectively evaluated clinical and X-ray features in all patients referred to the emergency department for suspected SARS-CoV-2 infection between March 1st and March 13th. A single radiologist with more than 15 years of experience in chest-imaging evaluated the presence and extent of alveolar opacities, reticulations, and/or pleural effusion. The percentage of lung involvement (range <25 % to 75-100 %) was also calculated. We stratified patients in groups according to the time interval between symptoms onset and X-ray imaging (≤ 5 and > 5 days) and according to age (≤ 50 and > 50 years old). RESULTS: A total of 518 patients were enrolled. Overall 314 patients had negative and 204 had positive RT-PCR results. Lung lesions in patients with SARS-Cov2 pneumonia primarily manifested as alveolar and interstitial opacities and were mainly bilateral (60.8 %). Lung abnormalities were more frequent and more severe by symptom duration and by increasing age. The sensitivity and specificity of chest X-ray at admission in the overall cohort were 57 % (95 % CI = 47-67) and 89 % (83-94), respectively. Sensitivity was higher for patients with symptom onset > 5 days compared to ≤ 5 days (76 % [62-87] vs 37 % [24-52]) and in patients > 50 years old compared to ≤ 50 years (59 % [48-69] vs 47 % [23-72]), at the expense of a slightly lower specificity (68 % [45-86] and 82 % [73-89], respectively). CONCLUSIONS: Overall chest X-ray sensitivity for SARS-CoV-2 pneumonia was 57 %. Sensitivity was higher when symptoms had started more than 5 days before, at the expense of lesser specificity, while slightly higher in older patients in comparison to younger ones.