New International Guidelines and Consensus on the Use of Lung Ultrasound

Integrated Multi-Organ Ultrasound

Integrated multi-organ ultrasound is increasingly used across various medical specialties. It should be performed in conjunction with history, physical examination, and other investigations in the diagnostic process to enhance the detection of conditions in the lung, heart, and abdomen. Multi-organ ultrasound has been shown to improve diagnostic accuracy in a sizeable portion of patients, potentially altering treatment plans. Specifically, it aids in assessing shock, sepsis, dyspnea, delirium, and in the perioperative setting, contributing to a more comprehensive patient assessment process.

Basic Lung Ultrasound and Clinical Applications in General Medicine

Proficiency in basic lung ultrasound is highly recommended for clinicians in general and internal medicine. This article will review and provide guidance for novice users on how to use lung ultrasound in clinical practice, through a pathology-oriented approach. The authors recommend a 12-zone protocol and describe how to perform and apply it in clinical practice while examining patients with clinical suspicion for the following diseases: pleural effusion, heart failure, pneumonia (bacterial and viral), interstitial lung disease, and pneumothorax.

WFUMB Commentary Paper on Artificial intelligence in Medical Ultrasound Imaging

Artificial intelligence (AI) is defined as the theory and development of computer systems able to perform tasks normally associated with human intelligence. At present, AI has been widely used in a variety of ultrasound tasks, including in point-of-care ultrasound, echocardiography, and various diseases of different organs. However, the characteristics of ultrasound, compared to other imaging modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), poses significant additional challenges to AI. Application of AI can not only reduce variability during ultrasound image acquisition, but can standardize these interpretations and identify patterns that escape the human eye and brain. These advances have enabled greater innovations in ultrasound AI applications that can be applied to a variety of clinical settings and disease states. Therefore, The World Federation of Ultrasound in Medicine and Biology (WFUMB) is addressing the topic with a brief and practical overview of current and potential future AI applications in medical ultrasound, as well as discuss some current limitations and future challenges to AI implementation.

[Use of clinical ultrasound in primary care: Markers in congestive heart failure]

The patient with heart failure (HF) is a frequent scenario in primary care consultations. The presence of subclinical congestion is a predictor of rehospitalization and adverse events in these patients. The assessment of congestion is complex due to the low sensitivity of classic symptoms and signs, which leads to underdiagnosis, delayed initiation of treatment and a greater likelihood of complications. The family doctor should be familiar with new techniques for congestion assessment, such as the study of venous congestion with ultrasound and pulmonary ultrasound. This makes it possible to know the existence of subclinical congestion in a more realistic way. Clinical ultrasound in the hands of the family doctor individualizes decongestive therapy in patients with HF in an accurate, fast and safe way.

The role of point-of-care ultrasound to monitor response of fluid replacement therapy in pregnancy

Fluid management in obstetrical care is crucial because of the complex physiological conditions of pregnancy, which complicate clinical manifestations and fluid balance management. This expert review examined the use of point-of-care ultrasound to evaluate and monitor the response to fluid therapy in pregnant patients. Pregnancy induces substantial physiological changes, including increased cardiac output and glomerular filtration rate, decreased systemic vascular resistance, and decreased plasma oncotic pressure. Conditions, such as preeclampsia, further complicate fluid management because of decreased intravascular volume and increased capillary permeability. Traditional methods for assessing fluid volume status, such as physical examination and invasive monitoring, are often unreliable or inappropriate. Point-of-care ultrasound provides a noninvasive, rapid, and reliable means to assess fluid responsiveness, which is essential for managing fluid therapy in pregnant patients. This review details the various point-of-care ultrasound modalities used to measure dynamic changes in fluid status, focusing on the evaluation of the inferior vena cava, lung ultrasound, and left ventricular outflow tract. Inferior vena cava ultrasound in spontaneously breathing patients determines diameter variability, predicts fluid responsiveness, and is feasible even late in pregnancy. Lung ultrasound is crucial for detecting early signs of pulmonary edema before clinical symptoms arise and is more accurate than traditional radiography. The left ventricular outflow tract velocity time integral assesses stroke volume response to fluid challenges, providing a quantifiable measure of cardiac function, which is particularly beneficial in critical care settings where rapid and accurate fluid management is essential. This expert review synthesizes current evidence and practice guidelines, suggesting the integration of point-of-care ultrasound as a fundamental aspect of fluid management in obstetrics. It calls for ongoing research to enhance techniques and validate their use in broader clinical settings, aiming to improve outcomes for pregnant patients and their babies by preventing complications associated with both under- and overresuscitation.

Lung ultrasound in children with primary ciliary dyskinesia or cystic fibrosis

INTRODUCTION

Primary ciliary dyskinesia (PCD) and cystic fibrosis (CF) are respiratory conditions requiring regular chest radiography (CXR) surveillance to monitor pulmonary disease. However, CXR is insensitive for lung disease in CF and PCD. Lung ultrasound (LU) is a radiation-free alternative showing good correlation with severity of lung disease in CF but has not been studied in PCD.

METHOD

Standardized, six-zone LU studies and CXR were performed on a convenience sample of children with PCD or CF during a single visit when well. LU studies were graded using the LU scoring system, while CXR studies received a modified Chrispin-Norman score. Scores were correlated with clinical outcomes.

RESULT

Data from 30 patients with PCD and 30 with CF (median age PCD 11.5 years, CF 9.1 years) with overall mild pulmonary disease (PCD median FEV1 90% predicted, CF FEV1 100%) were analyzed. LU abnormalities appear in 11/30 (36%) patients with PCD and 9/30 (30%) with CF. Sensitivity, specificity, positive predictive, and negative predictive values for abnormal LU compared to the gold standard of CXR are 42%, 61%, 42%, and 61% in PCD, and 44%, 81%, 50%, and 77% in CF, respectively. Correlation between LU and CXR scores are poor for both diseases (PCD r = -0.1288, p = 0.4977; CF r = 0.0343, p = 0.8571), and LU score does not correlate with clinical outcomes in PCD.

CONCLUSION

The correlation of LU findings with CXR surveillance studies is poor in patients with mild disease burdens from PCD or CF, and LU scores do not correlate with clinical outcomes in PCD.

Deep learning approaches for automated classification of neonatal lung ultrasound with assessment of human-to-AI interrater agreement

Neonatal respiratory disorders pose significant challenges in clinical settings, often requiring rapid and accurate diagnostic solutions for effective management. Lung ultrasound (LUS) has emerged as a promising tool to evaluate respiratory conditions in neonates. This evaluation is mainly based on the interpretation of visual patterns (horizontal artifacts, vertical artifacts, and consolidations). Automated interpretation of these patterns can assist clinicians in their evaluations. However, developing AI-based solutions for this purpose is challenging, primarily due to the lack of annotated data and inherent subjectivity in expert interpretations. This study aims to propose an automated solution for the reliable interpretation of patterns in LUS videos of newborns. We employed two distinct strategies. The first strategy is a frame-to-video-level approach that computes frame-level predictions from deep learning (DL) models trained from scratch (F2V-TS) along with fine-tuning pre-trained models (F2V-FT) followed by aggregation of those predictions for video-level evaluation. The second strategy is a direct video classification approach (DV) for evaluating LUS data. To evaluate our methods, we used LUS data from 34 neonatal patients comprising of 70 exams with annotations provided by three expert human operators (3HOs). Results show that within the frame-to-video-level approach, F2V-FT achieved the best performance with an accuracy of 77% showing moderate agreement with the 3HOs. while the direct video classification approach resulted in an accuracy of 72%, showing substantial agreement with the 3HOs, our proposed study lays down the foundation for reliable AI-based solutions for newborn LUS data evaluation.

The Application of Diaphragm Ultrasound in Chronic Obstructive Pulmonary Disease: A Narrative Review

Chronic Obstructive Pulmonary Disease (COPD) is a prevalent condition that poses a significant burden on individuals and society due to its high morbidity and mortality rates. The diaphragm is the main respiratory muscle, its function has a direct impact on the quality of life and prognosis of COPD patients. This article aims to review the structural measurement and functional evaluation methods through the use of diaphragmatic ultrasound and relevant research on its application in clinical practice for COPD patients. Thus, it serves to provide valuable insights for clinical monitoring of diaphragm function in COPD patients, facilitating early clinical intervention and aiding in the recovery of diaphragm function.

Lung ultrasound for the diagnosis of subpleural consolidations - a review of the veterinary and human literature

Lung ultrasound (LUS) is an imaging modality of growing importance in human medicine. LUS has been extensively applied to human patients. Guidelines have been created for internal medicine, describing ultrasonographic features of various lung pathologic processes. Such guidelines do not exist for veterinary medicine, and studies on the utility of LUS in companion animals are limited. Therefore, this review compares conclusions from veterinary studies to recommendations in human medicine for the detection of subpleural consolidations beyond the application of LUS as a point-of-care modality in emergency and critical care.

D-PRISM: a global survey-based study to assess diagnostic and treatment approaches in pneumonia managed in intensive care

BACKGROUND

Pneumonia remains a significant global health concern, particularly among those requiring admission to the intensive care unit (ICU). Despite the availability of international guidelines, there remains heterogeneity in clinical management. The D-PRISM study aimed to develop a global overview of how pneumonias (i.e., community-acquired (CAP), hospital-acquired (HAP), and Ventilator-associated pneumonia (VAP)) are diagnosed and treated in the ICU and compare differences in clinical practice worldwide.

METHODS

The D-PRISM study was a multinational, survey-based investigation to assess the diagnosis and treatment of pneumonia in the ICU. A self-administered online questionnaire was distributed to intensive care clinicians from 72 countries between September to November 2022. The questionnaire included sections on professional profiles, current clinical practice in diagnosing and managing CAP, HAP, and VAP, and the availability of microbiology diagnostic tests. Multivariable analysis using multiple regression analysis was used to assess the relationship between reported antibiotic duration and organisational variables collected in the study.

RESULTS

A total of 1296 valid responses were collected from ICU clinicians, spread between low-and-middle income (LMIC) and high-income countries (HIC), with LMIC respondents comprising 51% of respondents. There is heterogeneity across the diagnostic processes, including clinical assessment, where 30% (389) did not consider radiological evidence essential to diagnose pneumonia, variable collection of microbiological samples, and use and practice in bronchoscopy. Microbiological diagnostics were least frequently available in low and lower-middle-income nation settings. Modal intended antibiotic treatment duration was 5-7 days for all types of pneumonia. Shorter durations of antibiotic treatment were associated with antimicrobial stewardship (AMS) programs, high national income status, and formal intensive care training.

CONCLUSIONS

This study highlighted variations in clinical practice and diagnostic capabilities for pneumonia, particularly issues with access to diagnostic tools in LMICs were identified. There is a clear need for improved adherence to existing guidelines and standardized approaches to diagnosing and treating pneumonia in the ICU. Trial registration As a survey of current practice, this study was not registered. It was reviewed and endorsed by the European Society of Intensive Care Medicine.

Lung Ultrasound Findings in Children With Asthma Exacerbations

OBJECTIVE

We sought to assess whether the presence and extent of lung ultrasound (LUS) findings were associated with asthma exacerbation severity in children.

METHODS

We enrolled a convenience sample of patients aged 5-18 years presenting with acute asthma exacerbation to a tertiary care pediatric emergency department. Severity of an asthma exacerbation (mild, moderate, severe) was assessed within 1 hour of the LUS using the Hospital Asthma Severity Score, a validated asthma assessment tool. LUS was performed by trained pediatric emergency providers. The presence of LUS findings (B-lines, consolidations, pleural effusion, and pleural line abnormalities) was assessed using a standardized criterion based on consensus guidelines.

RESULTS

A total of 111 patients with a median age of 8 years (interquartile range 6-12) were enrolled. LUS was positive in 57% of patients. Pleural line abnormalities were observed in 34%, B-lines in 29%, consolidations <1 cm in 24%, and consolidations ≥1 cm in 7%. Patients with moderate and severe asthma exacerbations were more likely to have any B-lines (31% and 43%, respectively) than patients with mild exacerbations (12%; P = .021); however, the presence of ≥3 B-lines or confluent B-lines did not differ across severity groups. The presence of other findings did not differ based on asthma severity.

CONCLUSIONS

LUS findings are observed in a substantial portion of children presenting with asthma exacerbations. B-lines were the only LUS finding significantly associated with asthma severity, while lung consolidations <1 cm and >1 cm were not correlated with severity. These findings provide valuable information for the diagnostic use of LUS in pediatric patients with asthma exacerbation.

[Diagnostic comparison of bedside lung ultrasound and chest radiography in the intensive care unit]

BACKGROUND

Bedside lung ultrasound (POCUS) offers advantages over chest X-ray, including better cost-effectiveness for diagnosing certain pulmonary pathologies. This study compares the diagnostic concordance between portable chest X-rays and bedside lung ultrasounds in the intensive care unit (ICU).

METHODS

Adult ICU patients were included. POCUS was performed using the abbreviated BLUE protocol. Diagnostic results from POCUS and chest radiographies were compared using the intensivist clinical diagnosis - based on clinical examinations and lung ultrasounds - as the reference. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the ultrasounds were calculated.

RESULTS

A total of 100 patients were included, 71 with pulmonary pathologies. The average time to perform the ultrasound was 308 seconds. Ultrasound identified pathology in 20 patients with a normal chest radiographs. Diagnostic discrepancies occurred in 30 patients, highlighting ultrasound´s superior sensitivity in detecting atelectasis, pleural effusions, and pulmonary edema. Ultrasound demonstrated sensitivity (S) of 85%, specificity (E) of 100%, positive predictive value (PPV) of 100%, and negative predictive value (NPV) of 55%.

CONCLUSION

Lung point-of-care ultrasound at ICU admission detects more pathologies and does not miss significant abnormalities seen on chest X-rays. It also shows good diagnostic accuracy. These findings suggest that pulmonary POCUS, using an abbreviated protocol, could be a viable alternative to chest radiography for initial evaluation and follow-up of pulmonary pathologies in critically ill patients, potentially improving care quality and management.

Delphi Consensus Recommendations for the Development of the Emergency Medicine Point of Care Ultrasound (POCUS) Curriculum in Nepal

Introduction: Emergency Medicine Point of Care Ultrasound (EM-POCUS) is a diagnostic bedside tool for quick and accurate clinical decision-making. Comprehensive training in POCUS is a mandatory part of EM training in developed countries. In Nepal, we need to build an educational curriculum based on the local medical system, available resources, and educational environment. We used the modified Delphi method to develop a EM-POCUS curriculum. Methods: We formed an EM-POCUS core working group based on expertise in key identified areas. The core working group developed criteria for expert panelist selection and synthesized the data for panelists after each Delphi round. We recruited 46 expert panelists to participate in a series of electronic surveys. The literature review and the results of the first Delphi round identified a set of competencies. Quantitative methodology was performed for subsequent surveys. Data analysis of the frequency, percentage, median, and interquartile range of the 9-point Likert scale was performed. We deemed a minimum threshold of 80% agreement to retain items across Delphi rounds. The result of every round was disseminated before subsequent rounds for the expert panelists to review responses in light of the group's response. Results: We identified 10 specific global competency categories and 132 objectives (Round 1, response rate 85%). Rounds 2 and 3 (response rates 78% and 81% respectively) developed consensus on 45 core objectives (34%). The list of EM-POCUS competencies with the median (IQR) was finalized. Conclusion: This expert, consensus-generated EM-POCUS curriculum provides detailed guidance for EM-POCUS education and applications in clinical practice in Nepal.

A study of machine learning to predict NRDS severity based on lung ultrasound score and clinical indicators

Objective

To develop predictive models for neonatal respiratory distress syndrome (NRDS) using machine learning algorithms to improve the accuracy of severity predictions.

Methods

This double-blind cohort study included 230 neonates admitted to the neonatal intensive care unit (NICU) of Yantaishan Hospital between December 2020 and June 2023. Of these, 119 neonates were diagnosed with NRDS and placed in the NRDS group, while 111 neonates with other conditions formed the non-NRDS (N-NRDS) group. All neonates underwent lung ultrasound and various clinical assessments, with data collected on the oxygenation index (OI), sequential organ failure assessment (SOFA), respiratory index (RI), and lung ultrasound score (LUS). An independent sample test was used to compare the groups' LUS, OI, RI, SOFA scores, and clinical data. Use Least Absolute Shrinkage and Selection Operator (LASSO) regression to identify predictor variables, and construct a model for predicting NRDS severity using logistic regression (LR), random forest (RF), artificial neural network (NN), and support vector machine (SVM) algorithms. The importance of predictive variables and performance metrics was evaluated for each model.

Results

The NRDS group showed significantly higher LUS, SOFA, and RI scores and lower OI values than the N-NRDS group (p < 0.01). LUS, SOFA, and RI scores were significantly higher in the severe NRDS group compared to the mild and moderate groups, while OI was markedly lower (p < 0.01). LUS, OI, RI, and SOFA scores were the most impactful variables for the predictive efficacy of the models. The RF model performed best of the four models, with an AUC of 0.894, accuracy of 0.808, and sensitivity of 0.706. In contrast, the LR, NN, and SVM models have lower AUC values than the RF model with 0.841, 0.828, and 0.726, respectively.

Conclusion

Four predictive models based on machine learning can accurately assess the severity of NRDS. Among them, the RF model exhibits the best predictive performance, offering more effective support for the treatment and care of neonates.

[Chest ultrasound for imaging of pneumonia]

Diagnosis of pneumonia can be challenging, particularly the differential diagnosis of lower respiratory tract infection and pneumonia, acute respiratory failure, the diagnosis of nosocomial pneumonia and in case of treatment failure. As compared to conventional chest radiography and CT of the scan, sonography of the chest offers advantages. It could be demonstrated that it was even superior to chest radiography in the identification of pneumonic consolidations. Since most pneumonias affect the lower lobes and include the pleura, pneumonic substrates could be identified in up to 90% of cases despite the limited penetration depth of lung ultrasound. Sonography of the chest has become an established method in the diagnosis of both adult as well as in pediatric community-acquired pneumonia. In addition, it is particularly powerful when used within a point of care (POCUS) approach which also includes the evaluation of the heart. Finally, it appears to have significant potential also in the diagnosis of nosomomial pneumonia and in the evaluation of treatment response, both in the ward as in the ICU.

Factors associated with antibiotics for respiratory infections in Swiss long-term care facilities

BACKGROUND

Long-term care facility (LTCF) residents are twice as likely to receive antibiotics compared with elderly living in the community, and studies have reported up to half of prescriptions in LTCFs as inappropriate.

AIM

To identify factors contributing to general and inappropriate antibiotic prescription among LTCF residents with lower respiratory tract infections (LRTIs).

METHODS

In this prospective, multicentric, observational study, residents with LRTIs were recruited among 32 LTCFs in Western Switzerland during winter 2022-2023. Residents underwent lung ultrasound (LUS) within three days of LRTI onset, serving as the pneumonia diagnosis reference standard. Multivariate logistic regression and backward selection were used with P < 0.1 cut-off to identify factors among demographics, vital signs, diagnostic tests, and LTCF characteristics associated with (i) antibiotic prescription and (ii) inappropriate prescription.

FINDINGS

A total of 114 residents were included, 63% female, median age 87 years. Fifty-nine (52%) residents underwent diagnostic tests: 50 (44%) polymerase chain reaction (PCR) for respiratory viruses and 16 (14%) blood test with C-reactive protein and/or blood count. Sixty-three (55%) residents received antibiotics. Factors associated with antibiotic prescriptions were Rockwood Clinical Frailty Scale score ≥7, oxygen saturation <92%, performing a blood test, rural LTCFs, and female physician. Among residents receiving antibiotics, 48 (74%) had inappropriate prescriptions, with performance of respiratory virus PCR test as the only protective factor.

CONCLUSION

Whereas half of LRTI residents received antibiotics, falling within lower ranges of European LTCFs prescription rates (53-80%), most antibiotic prescriptions were inappropriate. Utilization of diagnostic tests correlates with lower overall and inappropriate prescription, advocating for their use to optimize prescription practices in LTCFs.

Comments and Illustrations of the European Federation of Societies for Ultrasound in Medicine (EFSUMB) Guidelines: Rare Malignant Pulmonal and Pleural Tumors: Primary Pulmonary Sarcoma and Mesothelioma, Imaging Features on Transthoracic Ultrasound

Primary pulmonary sarcoma and mesothelioma are rare malignancies. The review article discusses the appearance of these tumors in B-mode ultrasound (US), color Doppler ultrasound and contrast-enhanced ultrasound (CEUS). In particular, the article is intended to inspire the examination of thoracic wall tumors and pleural masses with the possibilities of ultrasonography and to obtain histologically evaluable material using US or CEUS-guided sampling.

Point-of-Care Ultrasound in Post-acute and Long-Term Care: A Scoping Review

OBJECTIVES

Point-of-care ultrasound (POCUS) is an emerging application of ultrasonography that is being integrated into patient care in many medical specialties. The post-acute and long-term care (PALTC) setting has opportunities to adopt POCUS as a diagnostic aid to improve patient outcomes. We aim (1) to describe the current use of POCUS in PALTC and (2) to examine how the use of POCUS can advance in PALTC settings.

DESIGN

Scoping review.

SETTING AND PARTICIPANTS

PALTC facilities and residents.

METHODS

The MEDLINE, Embase, CINAHL Complete, and Web of Science databases were searched by a medical librarian for studies on the use of POCUS in PALTC. All studies underwent dual, independent review during 2 phases of screening. We included all study designs where POCUS was obtained and interpreted by a provider at the bedside.

RESULTS

Six studies met inclusion criteria. Most studies were conducted in the setting of COVID19 outbreaks in nursing homes and communities. The organ systems examined using POCUS were lung and vasculature. Lung ultrasound was shown to have variable diagnostic and prognostic utility in assessing lung injury secondary to COVID19. Ultrasound measurements of the vasculature were not useful for predicting hydration status.

CONCLUSION AND IMPLICATIONS

Implementation of POCUS in PALTC is feasible, but current literature is limited to use in only 2 organ systems. These results suggest potential for expanding POCUS in PALTC. Further work is required to ascertain if POCUS use can improve patient outcomes in this health care setting.

Establishment of seven lung ultrasound phenotypes: a retrospective observational study of an LUS registry

BACKGROUND

Lung phenotypes have been extensively utilized to assess lung injury and guide precise treatment. However, current phenotypic evaluation methods rely on CT scans and other techniques. Although lung ultrasound (LUS) is widely employed in critically ill patients, there is a lack of comprehensive and systematic identification of LUS phenotypes based on clinical data and assessment of their clinical value.

METHODS

Our study was based on a retrospective database. A total of 821 patients were included from September 2019 to October 2020. 1902 LUS examinations were performed in this period. Using a dataset of 55 LUS examinations focused on lung injuries, a group of experts developed an algorithm for classifying LUS phenotypes based on clinical practice, expert experience, and lecture review. This algorithm underwent validation and refinement with an additional 140 LUS images, leading to five iterative revisions and the generation of 1902 distinct LUS phenotypes. Subsequently, a validated machine learning algorithm was applied to these phenotypes. To assess the algorithm's effectiveness, experts manually verified 30% of the phenotypes, confirming its efficacy. Using K-means cluster analysis and expert image selection from the 1902 LUS examinations, we established seven distinct LUS phenotypes. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities.

RESULTS

A total of 1902 LUS phenotypes were tested by randomly selecting 30% to verify the phenotypic accuracy. With the 1902 LUS phenotypes, seven lung ultrasound phenotypes were established through statistical K-means cluster analysis and expert screening. The acute respiratory distress syndrome (ARDS) exhibited gravity-dependent phenotypes, while the cardiogenic pulmonary edema exhibited nongravity phenotypes. The baseline characteristics of the 821 patients included age (66.14 ± 11.76), sex (560/321), heart rate (96.99 ± 23.75), mean arterial pressure (86.5 ± 13.57), Acute Physiology and Chronic Health Evaluation II (APACHE II)score (20.49 ± 8.60), and duration of ICU stay (24.50 ± 26.22); among the 821 patients, 78.8% were cured. In severe pneumonia patients, the gravity-dependent phenotype accounted for 42% of the cases, whereas the nongravity-dependent phenotype constituted 58%. These findings highlight the value of applying different LUS phenotypes in various diagnoses.

CONCLUSIONS

Seven sets of LUS phenotypes were established through machine learning analysis of retrospective data; these phenotypes could represent the typical characteristics of patients with different types of critical illness.

Lung Ultrasound Spectroscopy Applied to the Differential Diagnosis of Pulmonary Diseases: An In Vivo Multicenter Clinical Study

Lung ultrasound (LUS) is an important imaging modality to assess the state of the lung surface. However, current LUS approaches are based on subjective interpretation of imaging artifacts, which results in poor specificity as quantitative evaluation lacks. The latter could be improved by adopting LUS spectroscopy of vertical artifacts. Indeed, parameterizing these artifacts with native frequency, bandwidth, and total intensity ( [Formula: see text]) already showed potentials in differentiating pulmonary fibrosis (PF). In this study, we acquired radio frequency (RF) data from 114 patients. These data (representing the largest LUS RF dataset worldwide) were acquired by utilizing a multifrequency approach, implemented with an ULtrasound Advanced Open Platform (ULA-OP). Convex (CA631) and linear (LA533) probes (Esaote, Florence, Italy) were utilized to acquire RF data at three (2, 3, and 4 MHz), and four (3, 4, 5, and 6 MHz) imaging frequencies. A multifrequency analysis was conducted on vertical artifacts detected in patients having cardiogenic pulmonary edema (CPE), pneumonia, or PF. These artifacts were characterized by the three abovementioned parameters, and their mean values were used to project each patient into a feature space having up to three dimensions. Binary classifiers were used to evaluate the performance of these three mean features in differentiating patients affected by CPE, pneumonia, and PF. Acquisitions of multifrequency data performed with linear probe lead to accuracies up to 85.43% in the differential diagnosis of these diseases (convex probes' maximum accuracy was 74.51%). Moreover, the results showed high potentials of mean [Formula: see text] (by itself or combined with other features) in improving LUS specificity.

Role of Lung Ultrasound in the Detection of Lung Sequelae in Post-COVID-19 Patients: A Systematic Review and Meta-Analysis

Background: During the COVID-19 pandemic, several studies demonstrated the effectiveness of lung ultrasound (LUS) as a frontline tool in diagnosing and managing acute SARS-CoV-2 pneumonia. However, its role in detecting post-COVID-19 lung sequelae remains to be fully determined. This study aims to evaluate the diagnostic accuracy of LUS in identifying lung parenchymal damage, particularly fibrotic-like changes, following COVID-19 pneumonia, comparing its performance to that of CT. Methods: Relevant studies published before July 2024 were identified through a comprehensive search of PubMed, Embase, and Cochrane library. The search terms were combinations of the relevant medical subject heading (MeSH) terms, key words and word variants for "lung", "post-COVID", "long-COVID", and "ultrasound". The pooled sensitivity, specificity, diagnostic odds ratio (DOR), and summary receiver-operating characteristic (SROC) curve were used to examine the accuracy of CEUS. The selected works used different thresholds for the detection and counting of B-lines by ultrasound. This led to dividing our analysis into two models, the first based on the lower thresholds for detection of B-lines found in the works, and the second on data obtained using a higher detection threshold. Results: In terms of the diagnostic accuracy of LUS in detecting residual fibrotic-like changes in patients post-COVID-19 infection, a low-threshold model displayed a pooled sensitivity of 0.98 [95% confidence interval (CI): 0.95-0.99] and a pooled specificity of 0.54 (95% CI: 0.49-0.59). The DOR was 44.9 (95% CI: 10.8-187.1). The area under the curve (AUC) of SROC was 0.90. In the second analysis, the model with the higher threshold to detect B-lines showed a pooled sensitivity of 0.90 (95% CI: 0.85-0.94) and a pooled specificity of 0.88 (95% CI: 0.84-0.91). The DOR was 50.4 (95% CI: 15.9-159.3). The AUC of SROC was 0.93. Conclusions: In both analyses (even using the high threshold for the detection of B-lines), excellent sensitivity (98% in model 1 and 90% in model 2) is maintained. The specificity has a significant variation between the two models from 54 (model 1) to 87% (model 2). The model with the highest threshold for the detection of B-lines displayed the best diagnostic accuracy, as confirmed by the AUC values of the SROC (0.93).

The LUSBI Protocol (Lung Ultrasound/BREST Score/Inferior Vena Cava)-Its Role in a Differential Diagnostic Approach to Dyspnea of Cardiogenic and Non-Cardiogenic Origin

Background and Objectives: PoCUS ultrasound applications are widely used in everyday work, especially in the field of emergency medicine. The main goal of this research was to create a diagnostic and therapeutic protocol that will integrate ultrasound examination of the lungs, ultrasound measurements of the inferior vena cava (assessment of central venous pressure) and BREST scores (risk stratification for heart failure), with the aim of establishing a more effective differential diagnostic approach for dyspneic patients. Materials and Methods: A cross-sectional study was conducted in the emergency medicine department with the educational center of the community health center of Banja Luka. Eighty patients of both sexes were included and divided into experimental and control groups based on the presence or absence of dyspnea as a dominant subjective complaint. Based on the abovementioned variables, the LUSBI protocol (lung ultrasound/BREST score/inferior vena cava) was created, including profiles to determine the nature of the origin of complaints. The biochemical marker of heart failure NT pro-BNP served as a laboratory confirmation of the cardiac origin of the complaints. Results: The distribution of NT pro BNP values in the experimental group showed statistically significant differences between individual profiles of the LUSBI protocol (p < 0.001). Patients assigned to group B PLAPS 2 had significantly higher average values of NT pro-BNP (20159.00 ± 3114.02 pg/mL) compared to other LUSBI profiles. Patients from the experimental group who had a high risk of heart failure according to their BREST scores also had a significantly higher average maximum expiratory diameter compared to those without heart failure (p = 0.004). A statistically significant difference (p = 0.001) in LUSBI profiles was observed between the groups of patients divided according to CVP categories. Conclusion: The integration of the LUSBI protocol into the differential diagnosis of dyspnea has been shown to be very effective in confirming or excluding a cardiac cause of the disease in patients.

A versatile role for lung ultrasound in systemic autoimmune rheumatic diseases related pulmonary involvement: a narrative review

Systemic autoimmune rheumatic diseases (SARDs) related pulmonary disease is highly prevalent, with variable clinical presentation and behavior, and thus is associated with poor outcomes and negatively impacts quality of life. Chest high resolution computed tomography (HRCT) is still considered a fundamental imaging tool in the screening, diagnosis, and follow-up of pulmonary disease in patients with SARDs. However, radiation exposure, economic burden, as well as lack of point-of-care CT equipment limits its application in some clinical situation. Ultrasound has found a place in numerous aspects of the rheumatic diseases, including the vasculature, skin, muscle, joints, kidneys and in screening for malignancies. Likewise it has found increasing use in the lungs. In the past two decades, lung ultrasound has started to be used for pulmonary parenchymal diseases such as pneumonia, pulmonary edema, lung fibrosis, pneumothorax, and pleural lesions, although the lung parenchymal was once considered off-limits to ultrasound. Lung ultrasound B-lines and irregularities of the pleural line are now regarded two important sonographic artefacts related to diffuse parenchymal lung disease and they could reflect the lesion extent and severity. However, its role in the management of SARDs related pulmonary involvement has not been fully investigated. This review article will focus on the potential applications of lung ultrasound in different pulmonary scenarios related with SARDs, such as interstitial lung disease, diffuse alveolar hemorrhage, diaphragmatic involvement, and pulmonary infection, in order to explore its value in clinical daily practice.

RATTUS (Rat Thoracic Ultrasound): diagnosis of pneumothorax in pet rats

Introduction

Rat thoracic ultrasound (RATTUS) is a non-invasive, easy-to-perform method for the evaluation of the pleural space and lungs in pet rats. The aim of the article is to present species-specific differences in the sonographic diagnosis of pneumothorax (PTX) in pet rats.

Methods

In total, 158 client-owned pet rats were examined during the period from July 2023 to January 2024. PTX was diagnosed in 20 of the examined rats (13.25%, the age of the animals ranged from 2 months to 32 months (19.08 ± 6.93 months; mean ± SD) and their body weight ranged from 97 g to 885 g (461.27 ± 138.97 g; mean ± SD). Radiographic confirmation of PTX was performed in all these 20 rats, in the control group radiography was used to confirm that PTX was not present.

Results

The lung point and the barcode sign was found in 7/20 animals with sensitivity of 33.3% (95% CI, 0.16-0.59) and specificity of 100% (95% CI, 0.97-1.0). The abnormal curtain sign was found in 19/20 of animals with the sensitivity of 95% (95% CI, 0.73-0.99.7) and the specificity of 89% (95% CI, 0.82-0.93). The abnormalities in the substernal access were in 17/20 of animals with the sensitivity of 85% (95% CI, 0.61-0.96) and the specificity of 71% (95% CI, 0.62-0.78).

Discussion

In conclusion, RATTUS is a non-invasive method for the diagnosis of PTX in rats. Lung point and barcode sign are specific but not easily diagnosed signs. The curtain sign in RATTUS is not specific for PTX, as there are e.g. geriatric rats (rats older than 1,5 years) in which the abnormal curtain sign is visible without the presence of PTX. The presence of moderate to severe PTX can be assessed by the substernal approach based on the presence of cardiac displacement toward the collapsed lung lobe, and on evaluation of the lung inflation symmetry. This sign is not specific for PTX but in conjunction with other ultrasonic signs described makes the RATTUS a feasible tool for PTX diagnosis in rats.

FLUEnT: Transformer for detecting lung consolidations in videos using fused lung ultrasound encodings

Pneumonia is the leading cause of death among children around the world. According to WHO, a total of 740,180 lives under the age of five were lost due to pneumonia in 2019. Lung ultrasound (LUS) has been shown to be particularly useful for supporting the diagnosis of pneumonia in children and reducing mortality in resource-limited settings. The wide application of point-of-care ultrasound at the bedside is limited mainly due to a lack of training for data acquisition and interpretation. Artificial Intelligence can serve as a potential tool to automate and improve the LUS data interpretation process, which mainly involves analysis of hyper-echoic horizontal and vertical artifacts, and hypo-echoic small to large consolidations. This paper presents, Fused Lung Ultrasound Encoding-based Transformer (FLUEnT), a novel pediatric LUS video scoring framework for detecting lung consolidations using fused LUS encodings. Frame-level embeddings from a variational autoencoder, features from a spatially attentive ResNet-18, and encoded patient information as metadata combiningly form the fused encodings. These encodings are then passed on to the transformer for binary classification of the presence or absence of consolidations in the video. The video-level analysis using fused encodings resulted in a mean balanced accuracy of 89.3 %, giving an average improvement of 4.7 % points in comparison to when using these encodings individually. In conclusion, outperforming the state-of-the-art models by an average margin of 8 % points, our proposed FLUEnT framework serves as a benchmark for detecting lung consolidations in LUS videos from pediatric pneumonia patients.

Feline friendly POCUS: how to implement it into your daily practice

PRACTICAL RELEVANCE

Cats are great pretenders; they often hide illness until they are critical. This makes patients of this species challenging to assess and manage in the emergency setting where quick and stress-free diagnosis and treatment are necessary. Veterinary point-of-care ultrasound (POCUS) is a rapid, evidence-based, non-invasive, repeatable, cage-side ultrasonographic examination designed to answer clinically driven questions without compromising feline wellbeing. Integrating feline friendly POCUS as an extension of the physical examination to streamline diagnostic and therapeutic interventions, thereby limiting stress and improving overall patient care, is advocated by the authors of this article.

EQUIPMENT

Given the multitude of ultrasound machines and probes available that are portable, meaning they can be moved around the clinic and used patient-side, it should be possible for most practitioners to integrate POCUS into daily practice. The authors' preferred equipment for feline POCUS is a microconvex probe and a portable machine with a fixed pre-set. This set-up allows the clinician to complete all POCUS (abdominal, lung and pleural space, and heart) without needing to move the patient, change probes or restrain the patient in a particular position, ultimately saving time, personnel and cost while maintaining patient comfort and safety.

AIM

This review aims to serve as a valuable resource for veterinarians seeking to improve their feline patient care through the judicious utilisation of POCUS. In this article, the complex challenges posed by cats are addressed, and the different POCUS techniques, applications and clinical recommendations are discussed.

EVIDENCE BASE

This review draws on the published literature, as well as the authors' own collective experience when providing recommendations.

Knowledge fused latent representation from lung ultrasound examination for COVID-19 pneumonia severity assessment

COVID-19 pneumonia severity assessment is of great clinical importance, and lung ultrasound (LUS) plays a crucial role in aiding the severity assessment of COVID-19 pneumonia due to its safety and portability. However, its reliance on qualitative and subjective observations by clinicians is a limitation. Moreover, LUS images often exhibit significant heterogeneity, emphasizing the need for more quantitative assessment methods. In this paper, we propose a knowledge fused latent representation framework tailored for COVID-19 pneumonia severity assessment using LUS examinations. The framework transforms the LUS examination into latent representation and extracts knowledge from regions labeled by clinicians to improve accuracy. To fuse the knowledge into the latent representation, we employ a knowledge fusion with latent representation (KFLR) model. This model significantly reduces errors compared to approaches that lack prior knowledge integration. Experimental results demonstrate the effectiveness of our method, achieving high accuracy of 96.4 % and 87.4 % for binary-level and four-level COVID-19 pneumonia severity assessments, respectively. It is worth noting that only a limited number of studies have reported accuracy for clinically valuable exam level assessments, and our method surpass existing methods in this context. These findings highlight the potential of the proposed framework for monitoring disease progression and patient stratification in COVID-19 pneumonia cases.

Integration of Diagnostic Lung Ultrasound Into Clinical Practice by Hospitalists in an Academic Medical Center: A Retrospective Chart Review

Background Point-of-care lung ultrasound (LUS) is a guideline-recommended imaging modality that has been shown to be more accurate than chest radiography for multiple causes of dyspnea. This study was conducted to understand the impact of LUS on real-world clinical decision-making among hospitalists. Methods  A retrospective chart review was conducted of patients who received a LUS while hospitalized at a quaternary care academic medical center between July 2020 and June 2022. Data was extracted from the electronic health record (EHR) into a standardized REDCap form. Cases were defined as patients who had received a LUS that (1) had images archived and accessible to viewing through the EHR and (2) had an imaging report documented in the EHR. Results Of the 820 LUSs reviewed, 297 (36.2%) were performed to evaluate for appropriateness of thoracentesis, 205 (25%) for diagnosing or monitoring of pneumonia related to COVID-19, 169 (20.6%) for volume status assessment, 136 (16.6%) for worsening respiratory status, 114 (13.9%) for monitoring pleural effusions, 64 (7.8%) for diagnosing or monitoring of pneumonia not related to COVID-19, and 12 (1.5%) for monitoring of diuresis. Documentation was sufficient to determine clinical decision-making in 730 (89%) of LUSs reviewed, 739 (90.1%) were considered to be diagnostically useful, and 327 (39.9%) changed management. Conclusions These findings suggest LUS was diagnostically useful and routinely changed management in hospitalist practice. Further, documentation in the EHR was sufficient to allow for the evaluation of real-world clinical decision-making using LUS, which is an important gap in both the education and health services research literature.

Pregnancy-Related Thromboembolism-Current Challenges at the Emergency Department

Thrombotic events during pregnancy are burdened by an increased risk of morbidity and mortality, despite innovations in their diagnosis and treatment. Given their multifactorial etiology, it is important to understand all the pathophysiological mechanisms but especially to achieve correct and timely diagnosis. Pulmonary embolism (PE) during pregnancy represents a rare event, with an incidence of 1 per 1000 pregnancies, but it is also one of the leading causes of death during pregnancy. Managing PE in the acute setting is even more challenging and complex due to the attempt to maintain a balance between hemorrhagic and thrombotic complications while ensuring an optimal outcome for both the mother and the baby. In this review, our aim is to analyze the most significant challenges of acute PE during pregnancy and identify suitable management approaches for specific situations in order to improve the prognosis of pregnant women.

Molecular Diagnostic Yield and Safety Profile of Ultrasound-Guided Lung Biopsies: A Cross-Sectional Study

BACKGROUND

The recent advances in precision oncology for lung cancer treatment has focused attention on the importance of obtaining appropriate specimens for tissue diagnosis as well as comprehensive molecular profiling. CT scan-guided biopsies and bronchoscopy are currently the main procedures employed for tissue sampling. However, growing evidence suggests that ultrasound-guided biopsies may represent an effective as well as safe approach in this diagnostic area. This study explores the safety and the diagnostic yield for cancer molecular profiling in ultrasound-guided percutaneous lung lesion biopsies (US-PLLB).

METHODS

One hundred consecutive patients with suspected lung cancer, between January 2021 and May 2024, who had ultrasound-guided lung biopsies have been retrospectively analyzed. Molecular profiling was conducted with next-generation sequencing Genexus using Oncomine precision assay or polymerase chain reaction according to specimen quality. Qualitative immunohistochemical assay of programmed death ligand 1 (PD-L1) expression was evaluated by the Dako PD-L1 immunohistochemistry 22C3 pharmDx assay. The co-primary endpoints were the molecular diagnostic yield and the safety profile of US-guided lung biopsies.

RESULTS

From January 2021 to May 2024, 100 US-guided lung biopsies were carried out and 95 were considered for inclusion in the study. US-PLLB provided informative tissue for a histological evaluation in 93 of 95 patients with an overall diagnostic accuracy of 96.84% [Sensitivity: 92.63%; Specificity: 96.84%; PPV: 100%; NPV: 100%]. Sixty-Six patients were diagnosed with NSCLC (69.47%) and were considered for molecular diagnostic yield evaluation and PD-L1 testing. Four patients had malignant lymphoid lesions. US-PLLB was not adequate to achieve a final diagnosis in three patients (3.16%). Complete molecular profiling and PD-L1 evaluation were achieved in all patients with adenocarcinoma (molecular diagnostic yield: 100%). PD-L1 evaluation was achieved in 28 of 29 patients (96.55%) with either SCC or NOS lung cancer. The overall complication rate was 9.47% (n = 9). Six patients (6.31%) developed pneumothorax, while three patients (3.16%) suffered mild haemoptysis without desaturation.

CONCLUSIONS

According to our findings, US-guided lung biopsy is a safe, minimally invasive procedure in patients with suspected lung malignancies, providing an excellent diagnostic yield for both comprehensive molecular profiling and PD-L1 testing. In addition, our results suggest that US-guided biopsy may also be an effective diagnostic approach in patients with suspected lung lymphoma.

Point-of-care Ultrasound in Infectious Diseases: Current Insights and Future Perspectives

Point-of-care ultrasound (POCUS) is a safe, noninvasive technique performed at the patient's bedside, providing immediate results to the operator. It complements physical examination and facilitates clinical decision-making. In infectious diseases, POCUS is particularly valuable, offering an initial assessment in cases of suspected infection. It often leads to an early tentative diagnosis enabling the prompt initiation of antimicrobial treatment without the delay associated with traditional radiology. POCUS provides direct visualization of affected organs, assists in evaluating fluid balance, and facilitates various interventions, all while reducing patient discomfort. For infectious disease specialists, becoming proficient in POCUS is a critical future challenge, requiring dedicated training for effective utilization.

Thoracic ultrasound in guiding management of respiratory disease

INTRODUCTION

The use of ultrasound in respiratory disease has evolved substantially over the past two decades. From a test done to confirm the safe site of pleural fluid drainage, thoracic ultrasound has become a point-of-care test that guides the management of patients on respiratory wards, in clinics and endoscopy.

AREAS COVERED

This review overviews the process of ultrasound examination in the chest. It then delves into specific disease areas (pleural disease, lung disease, diaphragm disease, and invasive procedures) to highlight how thoracic ultrasound is being used to refine management. The review concludes with discussion on the training curricula and assessment tools for competency in thoracic ultrasound. Being a scoping review, literature searches were conducted on PubMed using relevant search terms.

EXPERT OPINION

In addition to its current uses, there are many avenues where thoracic ultrasound will soon be beneficial. Recent studies show promising roles in areas such as patient-tailored guidance of pleurodesis and non-invasively predicting lung re-expansion after pleural fluid drainage. In addition, auxiliary tools such as contrast-enhanced ultrasound and elastography are proving useful in identifying the etiology and directing the successful sampling of pleural and lung lesions. Studies are also exploring the utility of sonographic biomarkers such as echogenicity and septations to predict outcomes in pleural disease.

Ultrasound and Intrapleural Enzymatic Therapy for Complicated Pleural Effusion: A Case Series with a Literature Review

Pleural effusion is the most common manifestation of pleural disease, and chest ultrasound is crucial for diagnostic workup and post-treatment monitoring. Ultrasound helps distinguish the various types of pleural effusion and enables the detection of typical manifestations of empyema, which presents as a complicated, septated effusion. This may benefit from drainage and the use of intrapleural enzyme therapy or may require more invasive approaches, such as medical or surgical thoracoscopy. The mechanism of action of intrapleural enzymatic therapy (IPET) is the activation of plasminogen to plasmin, which breaks down fibrin clots that form septa or the loculation of effusions and promotes their removal. In addition, IPET has anti-inflammatory properties and can modulate the immune response in the pleural space, resulting in reduced pleural inflammation and improved fluid reabsorption. In this article, we briefly review the literature on the efficacy of IPET and describe a case series in which most practical applications of IPET are demonstrated, i.e., as a curative treatment but also as an alternative, propaedeutic, or subsequent treatment to surgery.

Effect of lung volume preservation during spontaneous breathing trial on successful extubation in patients receiving mechanical ventilation: protocol for a multicenter clinical trial

BACKGROUND

In standard weaning from mechanical ventilation, a successful spontaneous breathing test (SBT) consisting of 30 min 8 cmH2O pressure-support ventilation (PSV8) without positive end-expiratory pressure (PEEP) is followed by extubation with continuous suctioning; however, these practices might promote derecruitment. Evidence supports the feasibility and safety of extubation without suctioning. Ultrasound can assess lung aeration and respiratory muscles. We hypothesize that weaning aiming to preserve lung volume can yield higher rates of successful extubation.

METHODS

This multicenter superiority trial will randomly assign eligible patients to receive either standard weaning [SBT: 30-min PSV8 without PEEP followed by extubation with continuous suctioning] or lung-volume-preservation weaning [SBT: 30-min PSV8 + 5 cmH2O PEEP followed by extubation with positive pressure without suctioning]. We will compare the rates of successful extubation and reintubation, ICU and hospital stays, and ultrasound measurements of the volume of aerated lung (modified lung ultrasound score), diaphragm and intercostal muscle thickness, and thickening fraction before and after successful or failed SBT. Patients will be followed for 90 days after randomization.

DISCUSSION

We aim to recruit a large sample of representative patients (N = 1600). Our study cannot elucidate the specific effects of PEEP during SBT and of positive pressure during extubation; the results will show the joint effects derived from the synergy of these two factors. Although universal ultrasound monitoring of lungs, diaphragm, and intercostal muscles throughout weaning is unfeasible, if derecruitment is a major cause of weaning failure, ultrasound may help clinicians decide about extubation in high-risk and borderline patients.

TRIAL REGISTRATION

The Research Ethics Committee (CEIm) of the Fundació Unió Catalana d'Hospitals approved the study (CEI 22/67 and 23/26). Registered at ClinicalTrials.gov in August 2023. Identifier: NCT05526053.

Relationship between neonatal respiratory distress syndrome pulmonary ultrasonography and respiratory distress score, oxygenation index, and chest radiography grading

BACKGROUND

Accurate condition assessment is critical for improving the prognosis of neonatal respiratory distress syndrome (RDS), but current assessment methods for RDS pose a cumulative risk of harm to neonates. Thus, a less harmful method for assessing the health of neonates with RDS is needed.

AIM

To analyze the relationships between pulmonary ultrasonography and respiratory distress scores, oxygenation index, and chest X-ray grade of neonatal RDS to identify predictors of neonatal RDS severity.

METHODS

This retrospective study analyzed the medical information of 73 neonates with RDS admitted to the neonatal intensive care unit of Liupanshui Maternal and Child Care Service Center between April and December 2022. The pulmonary ultrasonography score, respiratory distress score, oxygenation index, and chest X-ray grade of each newborn before and after treatment were collected. Spearman correlation analysis was performed to determine the relationships among these values and neonatal RDS severity.

RESULTS

The pulmonary ultrasonography score, respiratory distress score, oxygenation index, and chest X-ray RDS grade of the neonates were significantly lower after treatment than before treatment (P < 0.05). Spearman correlation analysis showed that before and after treatment, the pulmonary ultrasonography score of neonates with RDS was positively correlated with the respiratory distress score, oxygenation index, and chest X-ray grade (ρ = 0.429-0.859, P < 0.05). Receiver operating characteristic curve analysis indicated that pulmonary ultrasonography screening effectively predicted the severity of neonatal RDS (area under the curve = 0.805-1.000, P < 0.05).

CONCLUSION

The pulmonary ultrasonography score was significantly associated with the neonatal RDS score, oxygenation index, and chest X-ray grade. The pulmonary ultrasonography score was an effective predictor of neonatal RDS severity.

Gamified Crowdsourcing as a Novel Approach to Lung Ultrasound Data Set Labeling: Prospective Analysis

BACKGROUND

Machine learning (ML) models can yield faster and more accurate medical diagnoses; however, developing ML models is limited by a lack of high-quality labeled training data. Crowdsourced labeling is a potential solution but can be constrained by concerns about label quality.

OBJECTIVE

This study aims to examine whether a gamified crowdsourcing platform with continuous performance assessment, user feedback, and performance-based incentives could produce expert-quality labels on medical imaging data.

METHODS

In this diagnostic comparison study, 2384 lung ultrasound clips were retrospectively collected from 203 emergency department patients. A total of 6 lung ultrasound experts classified 393 of these clips as having no B-lines, one or more discrete B-lines, or confluent B-lines to create 2 sets of reference standard data sets (195 training clips and 198 test clips). Sets were respectively used to (1) train users on a gamified crowdsourcing platform and (2) compare the concordance of the resulting crowd labels to the concordance of individual experts to reference standards. Crowd opinions were sourced from DiagnosUs (Centaur Labs) iOS app users over 8 days, filtered based on past performance, aggregated using majority rule, and analyzed for label concordance compared with a hold-out test set of expert-labeled clips. The primary outcome was comparing the labeling concordance of collated crowd opinions to trained experts in classifying B-lines on lung ultrasound clips.

RESULTS

Our clinical data set included patients with a mean age of 60.0 (SD 19.0) years; 105 (51.7%) patients were female and 114 (56.1%) patients were White. Over the 195 training clips, the expert-consensus label distribution was 114 (58%) no B-lines, 56 (29%) discrete B-lines, and 25 (13%) confluent B-lines. Over the 198 test clips, expert-consensus label distribution was 138 (70%) no B-lines, 36 (18%) discrete B-lines, and 24 (12%) confluent B-lines. In total, 99,238 opinions were collected from 426 unique users. On a test set of 198 clips, the mean labeling concordance of individual experts relative to the reference standard was 85.0% (SE 2.0), compared with 87.9% crowdsourced label concordance (P=.15). When individual experts' opinions were compared with reference standard labels created by majority vote excluding their own opinion, crowd concordance was higher than the mean concordance of individual experts to reference standards (87.4% vs 80.8%, SE 1.6 for expert concordance; P<.001). Clips with discrete B-lines had the most disagreement from both the crowd consensus and individual experts with the expert consensus. Using randomly sampled subsets of crowd opinions, 7 quality-filtered opinions were sufficient to achieve near the maximum crowd concordance.

CONCLUSIONS

Crowdsourced labels for B-line classification on lung ultrasound clips via a gamified approach achieved expert-level accuracy. This suggests a strategic role for gamified crowdsourcing in efficiently generating labeled image data sets for training ML systems.

The Burden of Interstitial Lung Involvement in Rheumatoid Arthritis: Could Lung Ultrasound Have a Role in Its Detection? A Literature Review

Lung involvement represents a fearful complication in rheumatoid arthritis (RA), potentially involving all compartments of the pulmonary system. Regarding interstitial lung disease (ILD), the HRCT represents the gold standard technique for its diagnosis; however, the examination is burdened by radiation exposure and high costs. In addition, although some risk factors for ILD are known, no algorithms exist to know which patients to submit to HRCT and when. In this context, lung ultrasound (LUS) showed promising results for at least 10 years, demonstrating correlation with high resolution computed tomography (HRCT) findings in other rheumatic diseases. Here, LUS may represent a screening test providing additional information to clinical examination and pulmonary function tests. The data deriving from LUS experience in other rheumatic diseases could steer the future towards the use of this technique also in RA patients, and in this review, we report the most relevant literature regarding LUS in RA-ILD.

Efficacy of an online lung ultrasound module on skill acquisition by clinician: a new paradigm

Introduction

Lung ultrasound (LUS) as an assessment tool has seen significant expansion in adult, paediatric, and neonatal populations due to advancements in point-of-care ultrasound over the past two decades. However, with fewer experts and learning platforms available in low- and middle-income countries and the lack of a standardised supervised training programme, LUS is not currently effectively used to the best of its potential in neonatal units.

Methodology

A cross-sectional survey assessed the efficacy of learning LUS via a mentor-based online teaching module (NEOPOCUS). The questionnaire comprised the clinicians' demographic profile, pre-course skills, and self-assessment of skill acquisition after course completion with ongoing hands-on practice.

Results

A total of 175 clinicians responded to the survey, with the majority (87.9%) working in level 3 and 4 neonatal intensive care units. Clinicians had variable clinical experience. Of them, 53.2% were consultant paediatricians/neonatologists with over 10 years of experience. After the course, there was a significant increase in clinician confidence levels in diagnosing and assessing all LUS pathology, as evidenced by the increase in median cumulative scores [from baseline 6 (interquartile range, IQR, 6-9) to 20 (IQR 16-24), p < 0.001] with half of them gaining confidence within 3 months of the course.

Conclusion

An online curriculum-based neonatal lung ultrasound training programme with clinician image demonstration and peer review of images for image optimisation increases self-reported confidence in diagnosing and managing neonatal lung pathology. Web-based online training in neonatal lung ultrasound has merits that can help with the delivery of training globally, and especially in low- and middle-income countries.

Lung Ultrasonography in the Evaluation of Late Sequelae of COVID-19 Pneumonia-A Comparison with Chest Computed Tomography: A Prospective Study

The onset of the COVID-19 pandemic allowed physicians to gain experience in lung ultrasound (LUS) during the acute phase of the disease. However, limited data are available on LUS findings during the recovery phase. The aim of this study was to evaluate the utility of LUS to assess lung involvement in patients with post-COVID-19 syndrome. This study prospectively enrolled 72 patients who underwent paired LUS and chest CT scans (112 pairs including follow-up). The most frequent CT findings were ground glass opacities (83.3%), subpleural lines (72.2%), traction bronchiectasis (37.5%), and consolidations (31.9%). LUS revealed irregular pleural lines as a common abnormality initially (56.9%), along with subpleural consolidation >2.5 mm ≤10 mm (26.5%) and B-lines (26.5%). A strong correlation was found between LUS score, calculated by artificial intelligence percentage involvement in ground glass opacities described in CT (r = 0.702, p < 0.05). LUS score was significantly higher in the group with fibrotic changes compared to the non-fibrotic group with a mean value of 19.4 ± 5.7 to 11 ± 6.6, respectively (p < 0.0001). LUS might be considered valuable for examining patients with persistent symptoms after recovering from COVID-19 pneumonia. Abnormalities identified through LUS align with CT scan findings; thus, LUS might potentially reduce the need for frequent chest CT examinations.

Bedside ultrasound in post-anaesthetic care unit for the diagnosis of post-extubation negative pressure pulmonary oedema: A paediatric case

BACKGROUND

Post-extubation negative pressure pulmonary oedema is a rare, potentially life-threatening complication associated with general anaesthesia. Chest radiography is used as a diagnostic tool, but it implies a non-negligible radiation exposure, a very important consideration, especially for the paediatric population. However, lung ultrasound can overcome this problem and can be used to detect postoperative pulmonary complications.

CASE REPORT

A 16-year-old male was scheduled for tympanoplasty. General anaesthesia was conducted, and after extubation, the patient developed a laryngospasm. On arrival at the post-anaesthetic care unit, the patient started to cough, a pink frothy sputum and hypoxemia were noticed, and auscultation revealed crepitations. A bedside lung ultrasound showed more than three B-lines per intercostal window, suggesting an alveolar-interstitial syndrome.

DISCUSSION

With this case report, we would like to raise awareness to this clinical entity and demonstrate bedside ultrasound has an important role in the diagnostic and therapeutic assessment during the perioperative period.

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification

Deep learning (DL) models for medical image classification frequently struggle to generalize to data from outside institutions. Additional clinical data are also rarely collected to comprehensively assess and understand model performance amongst subgroups. Following the development of a single-center model to identify the lung sliding artifact on lung ultrasound (LUS), we pursued a validation strategy using external LUS data. As annotated LUS data are relatively scarce-compared to other medical imaging data-we adopted a novel technique to optimize the use of limited external data to improve model generalizability. Externally acquired LUS data from three tertiary care centers, totaling 641 clips from 238 patients, were used to assess the baseline generalizability of our lung sliding model. We then employed our novel Threshold-Aware Accumulative Fine-Tuning (TAAFT) method to fine-tune the baseline model and determine the minimum amount of data required to achieve predefined performance goals. A subgroup analysis was also performed and Grad-CAM++ explanations were examined. The final model was fine-tuned on one-third of the external dataset to achieve 0.917 sensitivity, 0.817 specificity, and 0.920 area under the receiver operator characteristic curve (AUC) on the external validation dataset, exceeding our predefined performance goals. Subgroup analyses identified LUS characteristics that most greatly challenged the model's performance. Grad-CAM++ saliency maps highlighted clinically relevant regions on M-mode images. We report a multicenter study that exploits limited available external data to improve the generalizability and performance of our lung sliding model while identifying poorly performing subgroups to inform future iterative improvements. This approach may contribute to efficiencies for DL researchers working with smaller quantities of external validation data.

A lung disease diagnosis algorithm based on 2D spectral features of ultrasound RF signals

Lung diseases are commonly diagnosed based on clinical pathological indications criteria and radiological imaging tools (e.g., X-rays and CT). During a pandemic like COVID-19, the use of ultrasound imaging devices has broadened for emergency examinations by taking their unique advantages such as portability, real-time detection, easy operation and no radiation. This provides a rapid, safe, and cost-effective imaging modality for screening lung diseases. However, the current pulmonary ultrasound diagnosis mainly relies on the subjective assessments of sonographers, which has high requirements for the operator's professional ability and clinical experience. In this study, we proposed an objective and quantifiable algorithm for the diagnosis of lung diseases that utilizes two-dimensional (2D) spectral features of ultrasound radiofrequency (RF) signals. The ultrasound data samples consisted of a set of RF signal frames, which were collected by professional sonographers. In each case, a region of interest of uniform size was delineated along the pleural line. The standard deviation curve of the 2D spatial spectrum was calculated and smoothed. A linear fit was applied to the high-frequency segment of the processed data curve, and the slope of the fitted line was defined as the frequency spectrum standard deviation slope (FSSDS). Based on the current data, the method exhibited a superior diagnostic sensitivity of 98% and an accuracy of 91% for the identification of lung diseases. The area under the curve obtained by the current method exceeded the results obtained that interpreted by professional sonographers, which indicated that the current method could provide strong support for the clinical ultrasound diagnosis of lung diseases.

Comparison of lung ultrasound scoring systems for the prognosis of COVID-19 in the emergency department: An international prospective cohort study

Purpose

The purpose of this study was to evaluate whether the lung ultrasound (LUS) scores applied to an international cohort of patients presenting to the emergency department (ED) with suspected COVID-19, and subsequently admitted with proven disease, could prognosticate clinical outcomes.

Methods

This was an international, multicentre, prospective, observational cohort study of patients who received LUS and were followed for the composite primary outcome of intubation, intensive care unit (ICU) admission or death. LUS scores were later applied including two 12-zone protocols ('de Alencar score' and 'CLUE score'), a 12-zone protocol with lung and pleural findings ('Ji score') and an 11-zone protocol ('Tung-Chen score'). The primary analysis comprised logistic regression modelling of the composite primary outcome, with the LUS scores analysed individually as predictor variables.

Results

Between April 2020 to April 2022, 129 patients with COVID-19 had LUS performed according to the protocol and 24 (18.6%) met the composite primary endpoint. No association was seen between the LUS score and the composite primary end point for the de Alencar score [odds ratio (OR) = 1.04; 95% confidence interval (CI): 0.97-1.11; P = 0.29], the CLUE score (OR = 1.03; 95% CI: 0.96-1.10; P = 0.40), the Ji score (OR = 1.02; 95% CI: 0.97-1.07; P = 0.40) or the Tung-Chen score (OR = 1.02; 95% CI: 0.97-1.08).

Discussion

Compared to these earlier studies performed at the start of the pandemic, the negative outcome of our study could reflect the changing scenario of the COVID-19 pandemic, including patient, disease, and system factors. The analysis suggests that the study may have been underpowered to detect a weaker association between a LUS score and the primary outcome.

Conclusion

In an international cohort of adult patients presenting to the ED with suspected COVID-19 disease who had LUS performed and were subsequently admitted to hospital, LUS severity scores did not prognosticate the need for invasive ventilation, ICU admission or death.

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.

Diagnostic Accuracy of Ultrasound Guided Percutaneous Pleural Needle Biopsy for Malignant Pleural Mesothelioma

Background/Objectives: Ultrasound (US) has been progressively spreading as the most useful technique for guiding biopsies and fine-needle aspirations that are performed percutaneously. Malignant pleural mesothelioma (MPM) represents the most common malignant pleural tumour. Thoracoscopy represents the gold standard for diagnosis, although conditions hampering such diagnostic approach often coexist. The Objective was to determine whether ultrasound-guided percutaneous needle biopsy (US-PPNB) has a high diagnostic accuracy and represents a safe option for diagnosis of MPM. Methods: US-PPNB of pleural lesions suspected for MPM in patients admitted from January 2021 to June 2023 have been retrospectively analyzed. An 18-gauge semi-automatic spring-loaded biopsy system (Medax Velox 2®) was used by experienced pneumologists. The obtained specimens were histologically evaluated and defined as adequate or non-adequate for diagnosis according to whether the material was considered appropriate or not for immunohistochemistry (IHC) analysis. The primary objective of the study was the diagnostic yield for a tissue diagnosis. Results: US-PPNB was diagnostic of MPM in 15 out of 18 patients (sensitivity: 83.39%; specificity: 100%; PPV: 100%). Three patients with non-adequate US-PPNB underwent thoracoscopy for diagnosis. We found significant differences in terms of mean pleural lesion thickness between patients with adequate and not-adequate biopsy (15.4 mm (SD: 9.19 mm) and 3.77 mm (SD: 0.60 mm), p < 0.0010. In addition, a significant positive correlation has been observed between diagnostic accuracy and FDG-PET avidity value. Conclusions: US-PPNB performed by a pneumologist represents a valid procedure with a high diagnostic yield and accuracy for the diagnosis of MPM, and may be considered as an alternative option in patients who are not suitable for thoracoscopy.

Prognostic Significance of Lung Ultrasound for Heart Failure Patient Management in Primary Care: A Systematic Review

Background: Heart failure (HF) affects around 60 million individuals worldwide. The primary aim of this study was to evaluate the efficacy of lung ultrasound (LUS) in managing HF with the goal of reducing hospital readmission rates. Methods: A systematic search was conducted on PubMed, Embase, Google Scholar, Web of Science, and Scopus, covering clinical trials, meta-analyses, systematic reviews, and original articles published between 1 January 2019 and 31 December 2023, focusing on LUS for HF assessment in out-patient settings. There is a potential for bias as the effectiveness of interventions may vary depending on the individuals administering them. Results: The PRISMA method synthesized the findings. Out of 873 articles identified, 33 were selected: 19 articles focused on prognostic assessment of HF, 11 centred on multimodal diagnostic assessments, and two addressed therapeutic guidance for HF diagnosis. LUS demonstrates advantages in detecting subclinical congestion, which holds prognostic significance for readmission and mortality during out-patient follow-up post-hospital-discharge, especially in complex scenarios, but there is a lack of standardization. Conclusions: there are considerable uncertainties in their interpretation and monitoring changes. The need for an updated international consensus on the use of LUS seems obvious.

Combining quantitative and qualitative analysis for scoring pleural line in lung ultrasound

Objective.Accurate assessment of pleural line is crucial for the application of lung ultrasound (LUS) in monitoring lung diseases, thereby aim of this study is to develop a quantitative and qualitative analysis method for pleural line.Approach.The novel cascaded deep learning model based on convolution and multilayer perceptron was proposed to locate and segment the pleural line in LUS images, whose results were applied for quantitative analysis of textural and morphological features, respectively. By using gray-level co-occurrence matrix and self-designed statistical methods, eight textural and three morphological features were generated to characterize the pleural lines. Furthermore, the machine learning-based classifiers were employed to qualitatively evaluate the lesion degree of pleural line in LUS images.Main results.We prospectively evaluated 3770 LUS images acquired from 31 pneumonia patients. Experimental results demonstrated that the proposed pleural line extraction and evaluation methods all have good performance, with dice and accuracy of 0.87 and 94.47%, respectively, and the comparison with previous methods found statistical significance (P< 0.001 for all). Meanwhile, the generalization verification proved the feasibility of the proposed method in multiple data scenarios.Significance.The proposed method has great application potential for assessment of pleural line in LUS images and aiding lung disease diagnosis and treatment.