Automatic Detection of Lung Ultrasound Artifacts using a Deep Neural Networks approach

The COVID-19 pandemic has challenged many of the healthcare systems around the world. Many patients who have been hospitalized due to this disease develop lung damage. In low and middle-income countries, people living in rural and remote areas have very limited access to adequate health care. Ultrasound is a safe, portable and accessible alternative;however, it has limitations such as being operator-dependent and requiring a trained professional. The use of lung ultrasound volume sweep imaging is a potential solution for this lack of physicians. In order to support this protocol, image processing together with machine learning is a potential methodology for an automatic lung damage screening system. In this paper we present an automatic detection of lung ultrasound artifacts using a Deep Neural Network, identifying clinical relevant artifacts such as pleural and A-lines contained in the ultrasound examination taken as part of the clinical screening in patients with suspected lung damage. The model achieved encouraging preliminary results such as sensitivity of 94%, specificity of 81%, and accuracy of 89% to identify the presence of A-lines. Finally, the present study could result in an alternative solution for an operator-independent lung damage screening in rural areas, leading to the integration of AI-based technology as a complementary tool for healthcare professionals. © 2023 SPIE.

lungEcho - Resource Constrained Lung Ultrasound Video Analysis Tool for Faster Triaging and Active Learning

Lung ultrasound (LUS) is possibly the only medical imaging modality which could be used for continuous and periodic monitoring of the lung. This is extremely useful in tracking the lung manifestations either during the onset of lung infection or to track the effect of vaccination on lung as in pandemics such as COVID-19. There have been many attempts in automating the classification of the severity of lung involvement into various classes or automatic segmentation of various LUS landmarks and manifestations. However, all these approaches are based on training static machine learning models which require a significantly large clinically annotated dataset and are computationally heavy and are most of the time non-real time. In this work, a real-time light weight active learning-based approach is presented for faster triaging in COVID-19 subjects in resource constrained settings. The tool, based on the you look only once (YOLO) network, has the capability of providing the quality of images based on the identification of various LUS landmarks, artefacts and manifestations. This tool also predict the severity of lung infection and make use of the possibility of active learning based on the feedback from clinicians or on the image quality. The capability of this tool to summarize the significant frames which are having high severity of infection and high image quality will be helpful for clinicians to discern things more easily. The results show that the proposed object detection tool has a mean average precision (mAP) of 66% at an Intersection over Union (IoU) threshold of 0.5 for the prediction of LUS landmarks with initial training on less than 1000 images. The 14MB lightweight YOLOv5s network achieves 123 FPS while running on a Quadro P4000 GPU. The tool is available for usage and analysis upon request from the authors and details can be found online.

Evaluation of Lung Ultrasound in Assessment of Critically Ill patients in Respiratory Intensive Care Unit

Reaching a proper diagnosis for critically ill patients is like collecting pieces of puzzle and bed side lung ultrasound (LUS) becomes a crucial piece complementary to clinical and laboratory pieces. It is a bed side, real time tool for diagnosis of patients in ICU who are critical to be transferred to radiology unit especially in Covid-19 pandemic with risk of infection transmission. The aim was to evaluate the accuracy of lung ultrasound in assessment of critically ill patients admitted to Respiratory Intensive Care Unit (RICU), moreover to assess its diagnostic performance in different pulmonary diseases as compared to the gold standard approach accordingly. This observational prospective (cross sectional) study with a total 183 patients who met the inclusion criteria,were selected from patients admitted at the RICU;Chest Department, Zagazig University Hospitals, during the period from September 2019 to September 2021. LUS examination was performed to diagnose the different pulmonary diseases causing RF. All cases were examined by LUS on admission. From a total 183 patients, 111 patients 60.7% were males and 72 patients 39.3% were females, with a mean age of 56+/-12.77 years, 130 patients were breathing spontaneously received conservative management with O2 therapy, 32 patients needed NIV while 21 patients needed IMV with ETT. Exacerbated COPD was the most common disease finally diagnosed followed by bacterial pneumonia, exacerbated ILD, post Covid-19 fibrosis and pulmonary embolism in32, 29,27, 19 and 11 patients respectively with corresponding diagnostic accuracy of LUS 97.3%, AUC=0.943, 93.9% (AUC=0.922), 96.7%(AUC=0.920), 97.8%, AUC=0.895, and 97.8% respectively, while Covid-19 pneumonia was the final diagnosis in 8 patients with LUS diagnostic accuracy of 97.8% (AUC=0.869) with no statistical significant difference p-value=0.818 with bacterial pneumonia in distribution of US profiles. A profile was the commonest detected US profile among the studied patients followed by B profile, C profile, A/B profile and A' profile in 37.2%, 24.6%, 15.8% 4.9%, and 3.8% of cases respectively. Bed side LUS has a reliable, valuable diagnostic performance when integrated with clinical and laboratory data for the diagnosis of most pulmonary diseases in RICU.Copyright © 2023, Colegio de Farmaceuticos de la Provincia de Buenos Aires. All rights reserved.

Development of an acquisition system to monitoring asynchronous tele-ultrasound for lung patients

Lung ultrasound imaging allows the detection and evaluation of the lung damage generated by COVID-19. However, several infrastructure and logistical limitations prevent them from being carried out in isolated and remote areas. In this work, a system for the acquisition of medical images through asynchronous tele-ultrasounds was developed. The system is based on a graphical user interface, which records the three video cameras, the ultrasound image and the accelerometer simultaneously. The interface was developed according to the Volume Sweep Imaging acquisition protocol. The translational and rotational movement of the transducer are tracked and monitored by the accelerometer and the position of the transducer is obtained from the images acquired by the three video cameras. The results show a correct functioning of the system overall, being viable to be implemented for data acquisition and calculation of error, although in order to validate the error calculation there is still more research to be done. © 2023 SPIE.

[Use of thoracic and lung ultrasound in general anesthesia]. / A mellkas és a tüdo ultrahangvizsgálatának szerepe az általános érzéstelenítés során.

The use of ultrasound became an essential tool in the everyday practice of anesthesiology and intensive care as an indispensable prerequisite for the precise guidance of invasive procedures and also as a point-of-care diagnostic method. Despite the limitations of imaging the lung and thoracic structures, the COVID-19 pandemic and recent advances made this technology an evolving field. The intensive therapy applies these methods with important experience for differential diagnosis and assessment of disease severity or prognosis. Minor modifications of these results make the method beneficial for anesthesia and perioperative medicine. In the present review, the authors accentuate the most important imaging artefacts of lung ultrasonography and the principles of lung ultrasound diagnostic steps. Methods and artefacts of high importance supported by evidence for the assessment of airway management, attuning of intraoperative mechanical ventilation, respiratory disorders during surgery, and postoperative prognosis are articulated. This review intends to focus on evolving subfields in which technological or scientific novelties are expected. Orv Hetil. 2023; 164(22): 864-870.

The role of Lung Ultrasound in the diagnosis of SARS-COV-2 disease in pregnant women.

AIM: To evaluate the role of lung ultrasound (LUS) in recognizing lung abnormalities in pregnant women affected by COVID-19 pneumonia. MATERIALS AND METHODS: An observational study analyzing LUS patterns in 60 consecutively enrolled pregnant women affected by COVID-19 infection was performed. LUS was performed by using a standardized protocol by Soldati et al. The scoring system of LUS findings ranged from 0 to 3 in increasing alteration severity. The highest score obtained from each landmark was reported and the sum of the 12 zones examined was calculated. RESULTS: Patients were divided into two groups: 26 (43.3%) patients with respiratory symptoms and 32 (53.3%) patients without respiratory symptoms; 2 patients were asymptomatic (3.3%). Among the patients with respiratory symptoms 3 (12.5%) had dyspnea that required a mild Oxygen therapy. A significant correlation was found between respiratory symptoms and LUS score (p < 0.001) and between gestational weeks and respiratory symptoms (p = 0.023). Regression analysis showed that age and respiratory symptoms were risk factors for highest LUS score (p < 0.005). DISCUSSION: LUS can affect the clinical decision course and can help in stratifying patients according to its findings. The lack of ionizing radiation and its repeatability makes it a reliable diagnostic tool in the management of pregnant women.

CORONA (COre ultRasOund of covid in iNtensive care and Acute medicine) study: National service evaluation of lung and heart ultrasound in intensive care patients with suspected or proven COVID-19.

Background: Combined Lung Ultrasound (LUS) and Focused UltraSound for Intensive Care heart (FUSIC Heart - formerly Focused Intensive Care Echocardiography, FICE) can aid diagnosis, risk stratification and management in COVID-19. However, data on its application and results are limited to small studies in varying countries and hospitals. This United Kingdom (UK) national service evaluation study assessed how combined LUS and FUSIC Heart were used in COVID-19 Intensive Care Unit (ICU) patients during the first wave of the pandemic. Method: Twelve trusts across the UK registered for this prospective study. LUS and FUSIC Heart data were obtained, using a standardised data set including scoring of abnormalities, between 1st February 2020 to 30th July 2020. The scans were performed by intensivists with FUSIC Lung and Heart competency as a minimum standard. Data was anonymised locally prior to transfer to a central database. Results: 372 studies were performed on 265 patients. There was a small but significant relationship between LUS score >8 and 30-day mortality (OR 1.8). Progression of score was associated with an increase in 30-day mortality (OR 1.2). 30-day mortality was increased in patients with right ventricular (RV) dysfunction (49.4% vs 29.2%). Severity of LUS score correlated with RV dysfunction (p < 0.05). Change in management occurred in 65% of patients following a combined scan. Conclusions: In COVID-19 patients, there is an association between lung ultrasound score severity, RV dysfunction and mortality identifiable by combined LUS and FUSIC Heart. The use of 12-point LUS scanning resulted in similar risk score to 6-point imaging in the majority of cases. Our findings suggest that serial combined LUS and FUSIC Heart on COVID-19 ICU patients may aid in clinical decision making and prognostication.

COVID-19 Lung Ultrasound Scores and Lessons from the Pandemic: A Narrative Review.

The WHO recently declared that COVID-19 no longer constitutes a public health emergency of international concern; however, lessons learned through the pandemic should not be left behind. Lung ultrasound was largely utilized as a diagnostic tool thanks to its feasibility, easy application, and the possibility to reduce the source of infection for health personnel. Lung ultrasound scores consist of grading systems used to guide diagnosis and medical decisions, owning a good prognostic value. In the emergency context of the pandemic, several lung ultrasound scores emerged either as new scores or as modifications of pre-existing ones. Our aim is to clarify the key aspects of lung ultrasound and lung ultrasound scores to standardize their clinical use in a non-pandemic context. The authors searched on PubMed for articles related to "COVID-19", "ultrasound", and "Score" until 5 May 2023; other keywords were "thoracic", "lung", "echography", and "diaphragm". A narrative summary of the results was made. Lung ultrasound scores are demonstrated to be an important tool for triage, prediction of severity, and aid in medical decisions. Ultimately, the existence of numerous scores leads to a lack of clarity, confusion, and an absence of standardization.

Lung ultrasound in the COVID-19 era: a lesson to be learned for the future.

Lung Ultrasound (LUS) is a reliable, radiation free and bedside imaging technique to assess several pulmonary diseases. Although the diagnosis of COVID-19 is made with the nasopharyngeal swab, detection of pulmonary involvement is key for a safe patient management. LUS is a valid alternative to explore, in paucisymptomatic self-presenting patients, the presence and extension of pneumonia compared to High Resolution Computed Tomography (HRCT) that represent the gold standard. This is a single-centre prospective study with 131 patients enrolled. Twelve lung areas were explored reporting a semiquantitative assessment to obtain the LUS score. Each patient performed reverse-transcription polymerase chain reaction test (rRT-PCR), hemogasanalysis and HRCT. We observed an inverse correlation between LUSs and pO2, P/F, SpO2, AaDO2 (p value < 0.01), a direct correlation with LUSs and AaDO2 (p value < 0.01). Compared with HRCT, LUS showed sensitivity and specificity of 81.8% and 55.4%, respectively, and VPN 75%, VPP 65%. Therefore, LUS can represent an effective alternative tool to detect pulmonary involvement in COVID-19 compared to HRCT.

Determinants of point-of-care ultrasound lung sliding amplitude in mechanically ventilated patients.

BACKGROUND: Although lung sliding seen by point-of-care ultrasound (POCUS) is known to be affected to varying degrees by different physiologic and pathologic processes, it is typically only reported qualitatively in the critical care setting. Lung sliding amplitude quantitatively expresses the amount of pleural movement seen by POCUS but its determinants in mechanically ventilated patients are largely unknown. METHODS: This was a single-center, prospective, observational pilot study examining 40 hemithoraces in 20 adult patients receiving mechanical ventilation. Each subject had lung sliding amplitude measured in both B-mode and by pulsed wave Doppler at their bilateral lung apices and bases. Differences in lung sliding amplitude were correlated with anatomical location (apex vs base) as well as physiologic parameters including positive end expiratory pressure (PEEP), driving pressure, tidal volume and the ratio of arterial partial pressure of oxygen (PaO2) to fraction of inspired oxygen (FiO2). RESULTS: POCUS lung sliding amplitude was significantly lower at the lung apex compared to the lung base in both B-mode (3.6 ± 2.0 mm vs 8.6 ± 4.3 mm; p < 0.001) and the pulsed wave Doppler mode (10.3 ± 4.6 cm/s vs 13.9 ± 5.5 cm/s; p < 0.001) corresponding to expected distribution of ventilation to the lung bases. Inter-rater reliability of B-mode measurements was excellent (ICC = 0.91) and distance traversed in B-mode had a significant positive correlation with pleural line velocity (r2 = 0.32; p < 0.001). There was a non-statistically significant trend towards lower lung sliding amplitude for PEEP ≥ 10 cmH2O, as well as for driving pressure ≥ 15 cmH2O in both ultrasound modes. CONCLUSION: POCUS lung sliding amplitude was significantly lower at the lung apex than the lung base in mechanically ventilated patients. This was true when using both B-mode and pulsed wave Doppler. Lung sliding amplitude did not correlate with PEEP, driving pressure, tidal volume or PaO2:FiO2 ratio. Our findings suggest that lung sliding amplitude can be quantified in mechanically ventilated patients in a physiologically predictable way and with high inter-rater reliability. A better understanding of POCUS derived lung sliding amplitude and its determinants may aid in the more accurate diagnosis of lung pathologies, including pneumothorax, and could serve as a means of further reducing radiation exposure and improving outcomes in critically ill patients.

Efficient Lung Ultrasound Classification.

A machine learning method for classifying lung ultrasound is proposed here to provide a point of care tool for supporting a safe, fast, and accurate diagnosis that can also be useful during a pandemic such as SARS-CoV-2. Given the advantages (e.g., safety, speed, portability, cost-effectiveness) provided by the ultrasound technology over other examinations (e.g., X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest public lung ultrasound dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art models by at least 5%. The complexity is restrained by adopting specific design choices: ensembling with an adaptive combination layer, ensembling performed on the deep features, and minimal ensemble using two weak models only. In this way, the number of parameters has the same order of magnitude of a single EfficientNet-b0 and the computational cost (FLOPs) is reduced at least by 20%, doubled by parallelization. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where an inaccurate weak model focuses its attention versus an accurate one.

State-of-the-Art in Lung Ultrasound Processing - Brief Review

This paper explains the basic principles of ultrasound and its use in the medical examination mainly in chest ultrasound. We provide an overview of methods that address various aspects of classification and semantic segmentation of pathological symptoms in ultrasound videos. Also, we review the availability of the lung ultrasound data for the development of the machine learning models. Finally, we introduce our ongoing research in the field. This article serves as a theoretical basis for the introduction to lung ultrasound and the processing of ultrasonography data mainly with convolutional neural networks.

Development and interobserver reliability of a rating scale for lung ultrasound pathology in lower respiratory tract infection

Objectives The purpose of this study was to develop a severity rating scale for lung ultrasound pathology in lower respiratory tract infection based on multicenter expert consensus, and to test inter-rater reliability. Methods Ten point-of-care ultrasound experts from three academic institutions developed the scale iteratively through literature review, expert opinion, and pilot testing. Clips were prospectively collected from adults suspected of COVID-19 using a 14-zone scanning protocol. Blinded reviewers independently rated four data subsets. The rating scale was refined through eight consensus-building discussions reviewing challenging cases from the first three subsets. The final scale consisted of a set of ordinal scores from 0 to 4, for five sonographic findings: B-lines, pleural line abnormalities, consolidations, pleural effusions, and overall lung aeration. Ratings from the fourth subset were analyzed to determine reliability based on intraclass correlation coefficient (ICC). A total of 11,126 cine clips from 220 patients were acquired. Discussion After excluding uninterpretable clips, the test dataset contained 81 clips and yielded an average ICC of 0.70 across the five sonographic findings (0.76 for B-lines, 0.52 for pleural line abnormalities, 0.71 for consolidations, 0.80 for pleural effusions, and 0.70 for overall lung aeration). Improvements in agreement were observed with each successive review session and dataset rating. Conclusion The lung ultrasound severity scale established by multicenter expert consensus achieved moderate to good inter-rater reliability. The scale could be used clinically to standardize assessment of lower respiratory tract infection and in future studies to develop methods for automated interpretation of lung ultrasound pathology.

Ultrasound examination of the lungs in pneumonia in HIV-infected patients

The aim - to study was to assess the condition of the lungs and pleural cavities in HIV-infected patients with community-acquired pneumonia by ultrasound examination. Material and methods. During the period from May 2020 to February 2021, 7 HIV-infected patients with community-acquired pneumonia were observed, who underwent ultrasound of the lungs and pleural cavities. Results and discussion. Ultrasound of the lungs is the most affordable method of diagnosis in outpatient settings, at the pre-hospital stage to solve the issue of patient routing. Ultrasound is mandatory for quick triage of patients with suspected pneumonia in the emergency department. Given that ultrasound is not associated with radiation exposure to the patient, the examination of pregnant women, newborns and children with suspected pneumonia of any etiology should begin with ultrasound of the lungs, pleural cavities and mediastinum. Ultrasound of the lungs can be performed after pneumonia in order to monitor rehabilitation to assess the nature of changes in the chest cavity and determine the prognosis of the disease. The article presents a clinical example of lung ultrasound in an HIV-infected patient with pneumonia of unknown etiology.Copyright © 2021 Infectious Diseases: News, Opinions, Training. All rights reserved.

Role of Point-of-Care Ultrasound in the Management of Mechanical Ventilation

Ultrasound (US) became an essential tool in the hands of the intensivist and is now recommended both for procedural guidance and diagnostic purposes. Point-of-care ultrasound (POCUS) is an immediately available and repeatable, non-irradiating bedside tool integrating the clinical examination. Recent years were characterized by a growing interest in the fields of lung ultrasound (LUS) and diaphragm ultrasound (DUS). The combination of these two ultrasound techniques with critical care echocardiography (CCE) may integrate the classical approach to mechanically ventilated patients, both for monitoring and diagnostic purposes, finally contributing to the titration of mechanical ventilation and to the management of respiratory disease. Lung, diaphragm, and cardiac US provide significant information to improve the management of the critical patient under mechanical ventilation, from the initial assessment, through the ventilation setting (like PEEP) and its complication diagnosis (like pneumothorax, atelectasis), until the weaning process. LUS is of particular help in COVID-19 patients. It is potentially able to distinguish between the two phenotypes (type H and type L) of COVID-19, based on the different signs and patterns and also the assessment of prone positioning effects and lung recruitment maneuvers in these patients. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Radiological Patterns and Lung Ultrasound

The early diagnosis of coronavirus disease 2019 (COVID-19) is one of the crucial points in order to reduce virus spread, also containing morbidity and mortality of the pandemic. Despite the utility of specific molecular tests (such as real time polymerase chain reaction, RT-PCR), imaging is considered one of the key strategies for an early diagnostic typing of the disease, and to individualize patient management [1-3]. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Lung Ultrasound in Critical Care and Emergency Medicine: Clinical Review.

Lung ultrasound has become a part of the daily examination of physicians working in intensive, sub-intensive, and general medical wards. The easy access to hand-held ultrasound machines in wards where they were not available in the past facilitated the widespread use of ultrasound, both for clinical examination and as a guide to procedures; among point-of-care ultrasound techniques, the lung ultrasound saw the greatest spread in the last decade. The COVID-19 pandemic has given a boost to the use of ultrasound since it allows to obtain a wide range of clinical information with a bedside, not harmful, repeatable examination that is reliable. This led to the remarkable growth of publications on lung ultrasounds. The first part of this narrative review aims to discuss basic aspects of lung ultrasounds, from the machine setting, probe choice, and standard examination to signs and semiotics for qualitative and quantitative lung ultrasound interpretation. The second part focuses on how to use lung ultrasound to answer specific clinical questions in critical care units and in emergency departments.

Lung ultrasound scoring system vs ROX index as a predictor for progression to the invasive mechanical ventilation in COVID-19 patients

Background: During the outbreak of the highly contagious Coronavirus disease 19 (COVID19), rapid and simple prognostic tools were needed to support clinical decisions and predict the need of invasive mechanical ventilation. the ROX index, and the lung ultrasound score (LUSS) were proposed to objectively predict patient prognosis in addition to the subjective clinical assessment Aim: This study aimed to compare lung ultrasound score with ROX index in predicting the need of invasive ventilation in COVID-19 patients requiring advanced oxygen therapy. Patients and Methods: We studied 50 patients with severe COVID-19 pneumonia in the intensive care unit in the isolated area at Kasr Al-Ainy hospital. Complete Medical history, physical examination and laboratory investigations were obtained on admission. All patients underwent bedside lung ultrasonography scan and LUSS was calculated at the 2nd and the 12th hours, also ROX index was calculated at the 2nd, 6th and 12th hours from initiating the advanced oxygen therapy. Result(s): From a total of fifty patients with COVID-19, 56.0% were males, with mean age of 65.98 + 11.68 years, and mortality rate was 68%. The optimal cut off value of the ROX index at (2, 6, 12 hour) is (2.495, 2.675, 3.06) respectively, (p <0.001) with sensitivity 90.9% and specificity 76.5% at the 12 hour. Also the optimal cut off point of LUSS is 25.50 (p <0.001) with sensitivity 93.9% and specificity 88.2% for prediction of the invasive mechanical ventilation. Conclusion and recommendations: The study concluded that LUSS is more sensitive in predicting the need of invasive mechanical ventilation than ROX index.Copyright © 2023, Codon Publications. All rights reserved.

Thoracic UltrasONOgraphy Reporting: The TUONO Consensus.

The widespread use of the lung ultrasound (LUS) has not been followed by the development of a comprehensive standardized tool for its reporting in the intensive care unit (ICU) which could be useful to promote consistency and reproducibility during clinical examination. This work aims to define the essential features to be included in a standardized reporting tool and provides a structured model form to fully express the diagnostic potential of LUS and facilitate intensivists in the use of a LUS in everyday clinical ICU examination. We conducted a modified Delphi process to build consensus on the items to be integrated in a standardized report form and on its structure. A committee of 19 critical care physicians from 19 participating ICUs in Italy was formed, including intensivists experienced in ultrasound from both teaching hospitals and referral hospitals, and internationally renowned experts on the LUS. The consensus for 31 statements out of 33 was reached at the third Delphi round. A structured model form was developed based on the approved statements. The development of a standardized model as a backbone to report a LUS may facilitate the guidelines' application in clinical practice and increase inter-operator agreement. Further studies are needed to evaluate the effects of standardized reports in critically ill patients.

Role of Lung Ultrasound in the Follow-Up of Children with Previous SARS-CoV-2 Infection: A Case-Control Assessment of Children with Long COVID or Fully Recovered.

Lung ultrasound (LUS) can detect lower respiratory tract involvement in children with acute SARS-CoV-2 infection. However, its role in follow-up assessments is still unclear. To describe LUS findings in children after SARS-CoV-2 infection, we conducted a prospective study in a population of pediatric patients referred to the post-COVID unit in a tertiary center during the study period from February 2021 to May 2022. Children were classified as recovered from acute infection or with persisting symptoms. LUS was performed in all children and a LUS score (ranging from 0 to 36 points) was calculated according to the Italian Academy of Thoracic Ultrasound. Six hundred forty-seven children (304 females, 47%) were enrolled. The median follow-up evaluation was two months. The median age was 7.9 (IQR: 6) years. At the follow-up evaluation, 251 patients (38.8%) had persistent symptoms, of whom 104 (16.1%) had at least one respiratory symptom. The median LUS level was 2 (IQR: 4). LUS findings and LUS scores did not differ in children with Long COVID compared to the group of children fully recovered from the initial infection. In conclusion, after SARS-CoV-2 infection, LUS was mostly normal or showed minimal artifacts in all groups of children.