Lung Ultrasound for Pleural Line Abnormalities, Confluent B-Lines, and Consolidation: Expert Reproducibility and a Method of Standardization

Deep learning for real-time multi-class segmentation of artefacts in lung ultrasound

Lung ultrasound (LUS) has emerged as a safe and cost-effective modality for assessing lung health, particularly during the COVID-19 pandemic. However, interpreting LUS images remains challenging due to its reliance on artefacts, leading to operator variability and limiting its practical uptake. To address this, we propose a deep learning pipeline for multi-class segmentation of objects (ribs, pleural line) and artefacts (A-lines, B-lines, B-line confluence) in ultrasound images of a lung training phantom. Lightweight models achieved a mean Dice Similarity Coefficient (DSC) of 0.74, requiring fewer than 500 training images. Applying this method in real-time, at up to 33.4 frames per second in inference, allows enhanced visualisation of these features in LUS images. This could be useful in providing LUS training and helping to address the skill gap. Moreover, the segmentation masks obtained from this model enable the development of explainable measures of disease severity, which have the potential to assist in the triage and management of patients. We suggest one such semi-quantitative measure called the B-line Artefact Score, which is related to the percentage of an intercostal space occupied by B-lines and in turn may be associated with the severity of a number of lung conditions. Moreover, we show how transfer learning could be used to train models for small datasets of clinical LUS images, identifying pathologies such as simple pleural effusions and lung consolidation with DSC values of 0.48 and 0.32 respectively. Finally, we demonstrate how such DL models could be translated into clinical practice, implementing the phantom model alongside a portable point-of-care ultrasound system, facilitating bedside assessment and improving the accessibility of LUS.

Inspiratory-expiratory variation of pleural line thickness in neonates with and without acute respiratory failure

BACKGROUND

There are relatively few data about the ultrasound evaluation of pleural line in patients with respiratory failure. We measured the pleural line thickness during different phases of the respiratory cycle in neonates with and without acute respiratory failure as we hypothesized that this can significantly change.

METHODS

Prospective, observational, cohort study performed in an academic tertiary neonatal intensive care unit recruiting neonates with transient tachypnoea of the neonate (TTN), respiratory distress syndrome (RDS) or neonatal acute respiratory distress syndrome (NARDS). Neonates with no lung disease (NLD) were also recruited as controls. Pleural line thickness was measured with high-frequency ultrasound at end-inspiration and end-expiration by two different raters.

RESULTS

Pleural line thickness was slightly but significantly higher at end-expiration (0.53 [0.43-0.63] mm) than at end-inspiration (0.5 [0.4-0.6] mm; p = 0.001) for the whole population. End-inspiratory (NLD: 0.45 [0.38-0.53], TTN: 0.49 [0.43-0.59], RDS: 0.53 [0.41-0.62], NARDS: 0.6 [0.5-0.7] mm) and -expiratory (NLD: 0.47 [0.42-0.56], TTN: 0.48 [0.43-0.61], RDS: 0.53 [0.46-0.65], NARDS: 0.61 [0.54-0.72] mm) thickness were significantly different (overall p = 0.021 for both), between the groups although the absolute differences were small. The inter-rater agreement was optimal (ICC: 0.95 (0.94-0.96)). Coefficient of variation was 2.8% and 2.5% for end-inspiratory and end-expiratory measurements, respectively. These findings provide normative data of pleural line thickness for the most common forms of neonatal acute respiratory failure and are useful to design future studies to investigate possible clinical applications.

Diagnosis and Prognosis Evaluation of Severe Pneumonia by Lung Ultrasound Score Combined with Serum Inflammatory Markers

Introduction

To analyze the significance of lung ultrasound score (LUS) combined with serum inflammatory indexes in different severities of severe pneumonia and its clinical value on prognosis.

Methods

100 patients with severe pneumonia treated in the Gansu Provincial Hospital from June 2017 to June 2021 were selected as the research objects. According to the acute physiology and chronic health (APACHE II) score, they were divided into a low-risk group (28 cases), a medium-risk group (39 cases) and a high-risk group (33 cases). The general clinical data of the patients (age, gender, smoking history, and underlying diseases) were collected, the lung ultrasound score (LUS) of the patients was measured, and the serum inflammatory indicators (IL-6, IL-10, TNF-α, CRP and NLR) levels; Pearson correlation analysis to evaluate the correlation between LUS score, serum inflammatory index levels and disease severity; receiver operating characteristic (ROC) curve analysis to evaluate the prognostic value of the combined diagnosis of LUS score and serum inflammatory index for the severity of severe pneumonia.

Results

With the increase in the severity of severe pneumonia, the LUS score and the level of inflammation in the body continued to increase, and LUS combined with serum inflammatory indexes could distinguish the severity of low-risk, medium-risk and high-risk severe pneumonia and had high diagnostic value. In addition, the combined diagnosis of LUS and serum inflammatory markers is also closely related to the prognosis of patients with severe pneumonia, which can distinguish the prognosis.

Conclusion

LUS combined with serum inflammatory indicators (IL-6, IL-10, TNF-α, CRP and NLR) can differentiate the severity and prognosis of severe pneumonia, which may be a new direction for diagnosing severe pneumonia and guide early clinical intervention.

Ultrasonographic Presentation and Anatomic Distribution of Lung Involvement in Patients with Rheumatoid Arthritis

BACKGROUND

Rheumatoid arthritis (RA) is a chronic auto-immune disease, typically affecting the joints, which can also present with lung involvement (pleuritis, interstitial lung disease, pulmonary nodules, etc.). Lung ultrasound (LUS) is an upcoming tool in the detection of these pulmonary manifestations.

METHODS

We performed a 72-window LUS in 75 patients presenting to the outpatient rheumatology clinic and describe the abnormalities (presence of B-lines (vertical comet-tail artefacts), pleural abnormalities, pleural effusions, and subpleural nodules) on lung ultrasound. We created a topological mapping of the number of B-lines per intercostal zone.

RESULTS

We observed pleural effusions, pleural abnormalities, and pleural nodules in, respectively, 1.3%, 45.3%, and 14% of patients. There were 35 (46.7%) patients who had less than 5 B-lines, 15 (20%) patients who had between 5 and 10 B-lines, 11 (14.6%) between 10 and 20, 10 (13.3%) between 20 and 50, 1 (1.3%) between 50 and 100, and 3 (4%) of patients who had more than 100 B-lines.

CONCLUSIONS

LUS in patients with RA shows an array of abnormalities ranging from interstitial syndromes to pleural abnormalities, subpleural nodules, and pleural effusions. Hotspots for the presence of B-lines are situated bilaterally in the posterior subscapular regions, as well as the anterior right mid-clavicular region.

Point-of-Care Ultrasound of Post-acute COVID-19 Syndrome: A Prospective Cohort Study

Introduction Acute COVID-19 patients can suffer from chronic symptoms known as post-acute sequelae of SARS-CoV-2 infection (PASC). Point-of-care ultrasound (POCUS) is established in acute COVID, but its utility in PASC is unclear. We sought to determine the incidence of cardiac and pulmonary abnormalities with POCUS in patients with PASC in a COVID-19 recovery clinic. Methods This prospective cohort study included adults (>18 years old) presenting with cardiopulmonary symptoms to the COVID-19 recovery clinic. A lung ultrasound and standard bedside echocardiogram were performed by ultrasound-trained physicians. Images were interpreted in real time by the performing sonographer and independently by a blinded ultrasound faculty member. Discrepancies in interpretation were addressed by consensus review. A modified Soldati score was calculated by the sum of the scores in each of the 12 lung zones, with each zone score ranging from 0 to 3 (maximum score of 36). The score was then compared to clinical outcomes and outpatient testing.  Results Between April and July 2021, 41 patients received POCUS examinations, with 24 of those included in the study. In all, 15 out of 24 (62.5%) had a normal lung ultrasound. Of the nine subjects with lung abnormalities, the median modified Soldati score was 2. Three patients had trivial pericardial effusions, and all had normal left and right ventricular size and function. Conclusion The majority (62.5%) of patients presenting to the PASC clinic had a normal pulmonary ultrasound, and the vast majority (87.5%) had normal cardiac ultrasounds. These findings suggest that cardiopulmonary symptoms in PASC may be from etiologies not well evaluated by POCUS.

Machine Learning Algorithm Detection of Confluent B-Lines

OBJECTIVE

B-lines are a ring-down artifact of lung ultrasound that arise with increased alveolar water in conditions such as pulmonary edema and infectious pneumonitis. Confluent B-line presence may signify a different level of pathology compared with single B-lines. Existing algorithms aimed at B-line counting do not distinguish between single and confluent B-lines. The objective of this study was to test a machine learning algorithm for confluent B-line identification.

METHODS

This study used a subset of 416 clips from 157 subjects, previously acquired in a prospective study enrolling adults with shortness of breath at two academic medical centers, using a hand-held tablet and a 14-zone protocol. After exclusions, random sampling generated a total of 416 clips (146 curvilinear, 150 sector and 120 linear) for review. A group of five experts in point-of-care ultrasound blindly evaluated the clips for presence/absence of confluent B-lines. Ground truth was defined as majority agreement among the experts and used for comparison with the algorithm.

RESULTS

Confluent B-lines were present in 206 of 416 clips (49.5%). Sensitivity and specificity of confluent B-line detection by algorithm compared with expert determination were 83% (95% confidence interval [CI]: 0.77-0.88) and 92% (95% CI: 0.88-0.96). Sensitivity and specificity did not statistically differ between transducers. Agreement between algorithm and expert for confluent B-lines measured by unweighted κ was 0.75 (95% CI: 0.69-0.81) for the overall set.

CONCLUSION

The confluent B-line detection algorithm had high sensitivity and specificity for detection of confluent B-lines in lung ultrasound point-of-care clips, compared with expert determination.

Assessment of lung injury severity using ultrasound in critically ill COVID-19 patients in resource limited settings

BACKGROUND

Lung ultrasound is a non-invasive tool available at the bedside for the assessment of critically ill patients. The objective of this study was to evaluate the usefulness of lung ultrasound in assessing the severity of SARS-CoV-2 infection in critically-ill patients in a low-income setting.

METHODS

We conducted a 12-month observational study in a university hospital intensive care unit (ICU) in Mali, on patients admitted for COVID-19 as diagnosed by a positive polymerase chain reaction for SARS-CoV-2 and/or typical lung computed tomography scan findings.

RESULTS

The inclusion criteria was met by 156 patients with a median age of 59 years. Almost all patients (96%) had respiratory failure at admission and many needed respiratory support (121/156, 78%). The feasibility of lung ultrasound was very good, with 1802/1872 (96%) quadrants assessed. The reproducibility was good with an intra-class correlation coefficient of elementary patterns of 0.74 (95% CI 0.65, 0.82) and a coefficient of repeatability of lung ultrasound score < 3 for an overall score of 24. Confluent B lines were the most common lesions found in patients (155/156). The overall mean ultrasound score was 23 ± 5.4, and was significantly correlated with oxygen saturation (Pearson correlation coefficient of - 0.38, p < 0.001). More than half of the patients died (86/156, 55.1%). The factors associated with mortality, as shown by multivariable analysis, were: the patients' age; number of organ failures; therapeutic anticoagulation, and lung ultrasound score.

CONCLUSION

Lung ultrasound was feasible and contributed to characterize lung injury in critically-ill COVID-19 patients in a low income setting. Lung ultrasound score was associated with oxygenation impairment and mortality.

Emergency Department Point-Of-Care Echocardiography and Lung Ultrasound in Predicting COVID-19 Severity

OBJECTIVES

We sought to determine if point-of-care ultrasound (POCUS) performed on patients with COVID-19 in the emergency department (ED) can help predict disease course, severity, or identify complications.

METHODS

This was a retrospective cohort study of adult ED patients who tested positive for COVID-19 at hospital admission or within 2 weeks of presentation and received heart or lung POCUS. Clips were reviewed for presence of decreased left ventricular ejection fraction (LVEF), right ventricular dilation, presence of B-lines, and pleural line abnormalities. Patients with worsening hypoxemic respiratory failure or shock requiring higher level of care and patients who expired were considered to have developed severe COVID-19. Regression analysis was performed to determine if there was a correlation between ED POCUS findings and development of severe COVID-19.

RESULTS

A total of 155 patients met study criteria; 148 patients had documented cardiac views and 116 patients had documented lung views (113 with both). Mean age was 66.5 years old (±18.6) and 53% of subjects were female. Subjects with decreased LVEF that was not previously documented had increased odds of having severe COVID during their hospitalization compared to those with old or no dysfunction (OR 5.66, 95% CI: 1.55-19.95, P = .08). The presence of pleural line abnormalities was also predictive for development of severe COVID (OR 2.68, 95% CI: 1.04-6.92, P = .04).

CONCLUSION

POCUS findings of previously unidentified decreased LVEF and pleural line abnormalities in patients with COVID-19 evaluated in the ED were correlated to a more severe clinical course and worse prognosis.

The Mechanisms Underlying Vertical Artifacts in Lung Ultrasound and Their Proper Utilization for the Evaluation of Cardiogenic Pulmonary Edema

The recent advances in lung ultrasound for the diagnosis of cardiogenic pulmonary edema are outstanding; however, the mechanism of vertical artifacts known as B-lines used for the diagnosis has not yet been fully elucidated. The theory of “acoustic trap” is useful when considering the generation of vertical artifacts. Basic research in several studies supports the theory. Published studies with pilot experiments indicate that clarification of the relationship between the length and intensity of vertical artifacts and physical or acoustic composition of sources may be useful for differentiating cardiogenic pulmonary edema from lung diseases. There is no international consensus with regard to the optimal settings of ultrasound machines even though their contribution to the configuration of vertical artifacts is evident. In the clinical setting, the configuration is detrimentally affected by the use of spatial compound imaging, the placement of the focal point at a deep level, and the use of multiple focus. Simple educational materials using a glass microscope slide also show the non-negligible impact of the ultrasound machine settings on the morphology of vertical artifacts.