Vertical Artifacts in Lung Ultrasonography: Some Common Clinician Questions and the Related Engineer Answers

Introduction: Vertical artifacts, including B lines, are frequently seen in a variety of lung diseases. Their sonomorphology varies in length, width, shape, and internal reverberations. The reason for this diversity is still unknown and is the cause of discussion between clinicians and ultrasound physics engineers. Aim: The aim of this work is to sum up the most common clinician observations and provide an explanation to each of them derived from ultrasound physics. Materials and Methods: Based on clinical and engineering experiences as well as data collected from relevant literature, the sonomorphology of vertical artifacts was analyzed. Thirteen questions and answers were prepared on the common sonomorphology of vertical artifacts, current nomenclature, and clinical observations. Conclusions: From a clinical standpoint, the analysis of vertical artifacts is very important and requires that further clinical studies be conducted in cooperation with engineers who specialize in physics.

Artificial Intelligence and Democratization of the Use of Lung Ultrasound in COVID-19: On the Feasibility of Automatic Calculation of Lung Ultrasound Score

During the COVID-19 pandemic, lung ultrasound has been revealed as a powerful technique for diagnosis and follow-up of pneumonia, the principal complication of SARS-CoV-2 infection. Nevertheless, being a relatively new and unknown technique, the lack of trained personnel has limited its application worldwide. Computer-aided diagnosis could possibly help to reduce the learning curve for less experienced physicians, and to extend such a new technique such as lung ultrasound more quickly. This work presents the preliminary results of the ULTRACOV (Ultrasound in Coronavirus disease) study, aimed to explore the feasibility of a real-time image processing algorithm for automatic calculation of the lung ultrasound score (LUS). A total of 28 patients positive on COVID-19 were recruited and scanned in 12 thorax zones following the lung score protocol, saving a 3 s video at each probe position. Those videos were evaluated by an experienced physician and by a custom developed automated detection algorithm, looking for A-Lines, B-Lines, consolidations, and pleural effusions. The agreement between the findings of the expert and the algorithm was 88.0% for B-Lines, 93.4% for consolidations and 99.7% for pleural effusion detection, and 72.8% for the individual video score. The standard deviation of the patient lung score difference between the expert and the algorithm was ±2.2 points over 36. The exam average time with the ULTRACOV prototype was 5.3 min, while with a conventional scanner was 12.6 min. Conclusion: A good agreement between the algorithm output and an experienced physician was observed, which is a first step on the feasibility of developing a real-time aided-diagnosis lung ultrasound equipment. Additionally, the examination time was reduced to less than half with regard to a conventional ultrasound exam. Acquiring a complete lung ultrasound exam within a few minutes is possible using fairly simple ultrasound machines that are enhanced with artificial intelligence, such as the one we propose. This step is critical to democratize the use of lung ultrasound in these difficult times.

THE IDEAL PROFILE (INCREASE IN B-LINES/DELTA B-LINES) ON LUNG ULTRASOUND FOR DIAGNOSING WEANING INDUCED PULMONARY EDEMA IN VENTILATED PATIENTS

Objective: To ascertain the ideal number of B-lines on lung ultrasound for the diagnosis of weaning induced pulmonary edema in ventilated patients. Study Design: Prospective observational study. Place and Duration of Study: Department of Medicine, Shifa International Hospital, Islamabad, from Jan to Aug 2020. Methodology: All the patients over the age of 18 years who were on mechanical ventilation in a medical intensive care unit were included in the study. The patients were given spontaneous breathing trials as a protocol for weaning from mechanical ventilation. Lung ultrasound was performed on 4 points of anterior chest wall before and after spontaneous breathing trials. Before and after spontaneous breathing trials counting of B lines was done on ultrasound of lung and comparison of increase in B lines (Delta-B-lines) was done with reference diagnosis of weaning induced pulmonary edema diagnosed by intensivist who was blinded to the results of lung ultrasound. Results: The study included 42 patients including 23 (54.8%) men and 19 (45.2%) women. 14 cases failed spontaneous breathing trials. Seven cases (16.7%) had weaning induced pulmonary edema. Delta-B-lines ≥6 diagnosed weaning induced pulmonary edema with 100% accuracy. Out of the remaining seven patients with weaning failure but without weaning induced pulmonary edema, 6 (28.6%) had Delta-B-lines ≥6. The ultrasound lung technique had a 100% sensitivity profile to detect weaning induced pulmonary edema and a specificity of 77.78%. Conclusion: The study indicates that Delta-B-lines ≥6 diagnosed the weaning induced pulmonary edema with the best accuracy.

The Role of Lung Ultrasound in Diagnosing COVID-19-Related Multisystemic Inflammatory Disease: A Preliminary Experience

Background: To date, there are no data regarding the systematic application of Point-of-Care Lung Ultrasound (PoC-LUS) in children with Multisystem Inflammatory Syndrome in Children (MIS-C). The main aim of this study is to show the role of Point-of-Care Lung Ultrasound as an additional aid in the diagnosis of COVID-19-related Multisystem Inflammatory Syndrome in Children (MIS-C). Methods: Between April 2020 and April 2021, patients aged 0–18 years referred to our emergency department for fever, and later hospitalized without a specific diagnosis, underwent PoC-LUS. Ultrasound images of patients with a final diagnosis of MIS-C were retrospectively evaluated. Results: Ten patients were enrolled. All were described to have pleural irregularities and B-lines. In particular: 8/10 children presented with isolated B-lines in at least half of the lung areas of interest; 8/10 presented with multiple B-lines and 3/8 had them in at least 50% of lung areas; 5/10 had a white lung appearance in at least one lung area and 1/5 had them in half of the areas of interest. Pleural effusion was described in 9/10. Conclusions: During the ongoing COVID-19 pandemic, we suggest performing PoC-LUS in febrile patients with high levels of inflammatory indices and clinical suspicion of MIS-C, or without a certain diagnosis; the finding of many B-lines and pleural effusion would support the diagnosis of a systemic inflammatory disease.

Lung Ultrasound B-lines as a Surrogate Marker for High Left Ventricular Diastolic Pressures; a bed-side Diagnostic tool

Background: We studied the diagnostic accuracy of B-lines (comet-tail sign) on bedside lung US, NT-proBNP, E/e` on ECHO in differentiation of the causes of acute dyspnea in the emergency setting. Major advantages include bedside availability, no radiation, high feasibility and reproducibility, and cost efficiency. Methods: Our prospective study was performed at the alazhar university hospital, Cairo, Egypt, between July 2019 and March 2020. All patients underwent lung ultrasound examinations, along with TTE, laboratory testing, including rapid NT-proBNP testing. Results: The median E/e’ levels in patients with B-profile were 18, compared with a median of 7.4 in the subjects with A-profile (P =< 0.0001 CI = -9.649 to -7.044). It was found that the sensitivity and the specificity of detecting B-profile on ultrasound is high when E/e’ > 15.5 (95.0% and 83.0% consecutively), which concluded the high correlation between finding B profile on U/S chest and elevated left ventricle filling pressure in a patient presenting with picture of suggestive of heart failure Conclusion: Chest ultrasound can be used as screening test for the evaluation of patients with suspicion of heart failure with excellent sensitivity and good specificity.

Lung Ultrasound in Pediatric Asthma - Characterizing Baseline Findings Outside of Acute Exacerbations

Background: Lung ultrasound (LUS) has been shown to be an effective tool to rapidly diagnose certain causes of pediatric respiratory distress in the emergency department. However, very little is known about LUS findings in pediatric asthma outside of acute exacerbations. Objectives: The primary objective of this study was to characterize LUS findings in a cohort of pediatric patients with a definitive diagnosis of asthma, outside of an asthma exacerbation. Methods: Eligible patients, aged 6 to 17 years old and diagnosed with asthma, underwent LUS during an outpatient visit. LUS was conducted using a six-zone scanning protocol. A positive LUS was defined by one or more of the following: ≥3 B-lines per intercostal space, pulmonary consolidation and/or pleural anomaly. Images were interpreted by an expert sonographer blinded to patient clinical characteristics. Results: 52 patients were included. 10/52 patients had a positive LUS (19.2%, 95CI 8.3-30.1%). Of those with positive LUS findings, 8 had B lines, 7 had consolidations <1cm, 1 had a pleural line abnormality and 1 had a consolidation >1cm. Positive findings were seen in the right anterior and lateral zones in 60% of participants and were limited to 1-2 intercostal spaces within one lung zone in 100% of participants. Conclusion: To our knowledge, this is the first report of LUS findings in outpatient pediatric asthma. Positive LUS findings in asthmatic children can be seen outside of acute exacerbations. Such findings need to be taken into consideration when using LUS for the acute evaluation of a pediatric patient with asthma.

Nitrogen dioxide component of air pollution increases pulmonary congestion assessed by lung ultrasound in patients with chronic coronary syndromes

Pulmonary congestion is an intermediate biomarker and long-term predictor of acute decompensated heart failure.To evaluate the effects of air pollution on pulmonary congestion assessed by lung ultrasound.In a single-center, prospective, observational study design, we enrolled 1292 consecutive patients with chronic coronary syndromes referred for clinically indicated ABCDE-SE, with dipyridamole (n = 1207), dobutamine (n = 84), or treadmill exercise (n = 1). Pulmonary congestion was evaluated with lung ultrasound and a 4-site simplified scan. Same day values of 4 pollutants were obtained on the morning of testing (average of 6 h) from publicly available data sets of the regional authority of environmental protection. Assessment of air pollution included fine (< 2.5 µm diameter) and coarse (< 10 µm) particulate matter (PM), ozone and nitrogen dioxide (NO2).NO2 concentration was weakly correlated with rest (r = .089; p = 0.001) and peak stress B-lines (r = .099; p < 0.001). A multivariable logistic regression analysis, NO2 values above the median (23.1 µg/m3) independently predicted stress B-lines with odds ratio = 1.480 (95% CI 1.118–1.958) together with age, hypertension, diabetes, and reduced (< 50%) ejection fraction. PM2.5 values were higher in 249 patients with compared to those without B-lines (median and IQR, 22.0 [9.1–23.5] vs 17.6 [8.6–22.2] µg/m3, p < 0.001). No other pollutant correlated with other (A-C-D-E) SE steps.Higher concentration of NO2 is associated with more pulmonary congestion mirrored by B-lines at lung ultrasound. Local inflammation mediated by NO2 well within legally allowed limits may increase the permeability of the alveolar-capillary barrier and therefore pulmonary congestion in susceptible subjects.ClinicalTrials.gov Identifier: NCT030.49995.

B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention

The presence of B-line artefacts, the main artefact reflecting lung abnormalities in dengue patients, is often assessed using lung ultrasound (LUS) imaging. Inspired by human visual attention that enables us to process videos efficiently by paying attention to where and when it is required, we propose a spatiotemporal attention mechanism for B-line detection in LUS videos. The spatial attention allows the model to focus on the most task relevant parts of the image by learning a saliency map. The temporal attention generates an attention score for each attended frame to identify the most relevant frames from an input video. Our model not only identifies videos where B-lines show, but also localizes, within those videos, B-line related features both spatially and temporally, despite being trained in a weakly-supervised manner. We evaluate our approach on a LUS video dataset collected from severe dengue patients in a resource-limited hospital, assessing the B-line detection rate and the model’s ability to localize discriminative B-line regions spatially and B-line frames temporally. Experimental results demonstrate the efficacy of our approach for classifying B-line videos with an F1 score of up to 83.2% and localizing the most salient B-line regions both spatially and temporally with a correlation coefficient of 0.67 and an IoU of 69.7%, respectively.

The Prognostic Value of Lung Ultrasound in Patients With Newly Diagnosed Heart Failure With Preserved Ejection Fraction in the Ambulatory Setting

Background: Heart failure with preserved ejection fraction (HFpEF) is a growing healthcare burden, and its prevalence is steadily increasing. Lung ultrasound (LUS) is a promising screening and prognostic tool in the heart failure population. However, more information on its value in predicting outcome is needed.Aims: The aim of our study was to assess the prognostic performance of LUS B-lines compared to traditional and novel clinical and echocardiographic parameters and natriuretic peptide levels in patients with newly diagnosed HFpEF in an ambulatory setting.Methods: In our prospective cohort study, all ambulatory patients with clinical suspicion of HFpEF underwent comprehensive echocardiography, lung ultrasound and NT-proBNP measurement during their first appointment at our cardiology outpatient clinic. Our endpoint was a composite of worsening heart failure symptoms requiring hospitalization or loop diuretic dose escalation and death.Results: We prospectively enrolled 75 consecutive patients with HFpEF who matched our inclusion and exclusion criteria. We detected 11 events on a 26 ± 10-months follow-up. We found that the predictive value of B-lines is similar to the predictive value of NT-proBNP (AUC 0.863 vs. 0.859), with the best cut-off at &gt;15 B-lines. Having more B-lines than 15 significantly increased the likelihood of adverse events with a hazard ratio of 20.956 (p = 0.004). The number of B-lines remained an independent predictor of events at multivariate modeling. Having more than 15 B-lines lines was associated with a significantly worse event-free survival (Log-rank: 16.804, p &lt; 0.001).Conclusion: The number of B-lines seems to be an independent prognostic factor for adverse outcomes in HFpEF. Since it is an easy-to-learn, feasible and radiation-free method, it may add substantial value to the commonly used diagnostic and risk stratification models.