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.

The lung ultrasound "Rule of 7" in the prognosis of COVID-19 patients: Results from a prospective multicentric study.

Purpose: There is growing evidence regarding the imaging findings of coronavirus disease 2019 (COVID-19) in lung ultrasound (LUS), however the use of a combined prognostic and triage tool has yet to be explored.To determine the impact of the LUS in the prediction of the mortality of patients with highly suspected or confirmed COVID-19.The secondary outcome was to calculate a score with LUS findings with other variables to predict hospital admission and emergency department (ED) discharge. Material and methods: Prospective study performed in the ED of three academic hospitals. Patients with highly suspected or confirmed COVID-19 underwent a LUS examination and laboratory tests. Results: A total of 228 patients were enrolled between March and September 2020. The mean age was 61.9 years (Standard Deviation - SD 21.1). The most common findings in LUS was a right posteroinferior isolated irregular pleural line (53.9%, 123 patients). A logistic regression model was calculated, including age over 70 years, C-reactive protein (CRP) over 70 mg/L and a lung score over 7 to predict mortality, hospital admission and discharge from the ED. We obtained a predictive model with a sensitivity of 56.8% and a specificity of 87.6%, with an AUC of 0.813 [p < 0.001]. Conclusions: The combination of LUS, clinical and laboratory findings in this easy to apply "rule of 7" showed excellent performance to predict hospital admission and mortality.

Objetivo: Existe una evidencia creciente con respecto a los hallazgos de imagen de la enfermedad por coronavirus 2019 (COVID-19) en la ecografía pulmonar (LUS), sin embargo, aún no se ha explorado el uso de una herramienta combinada de pronóstico y triaje.El objetivo principal de este estudio fue determinar el impacto de la LUS en la predicción de la mortalidad de los pacientes con sospecha de afectación pulmonar por COVID-19. El objetivo secundario fue calcular una puntuación con los hallazgos del LUS con otras variables para predecir el ingreso hospitalario y el alta del servicio de urgencias (SU). Material y métodos: Estudio prospectivo realizado en urgencias de tres hospitales académicos, en pacientes con sospecha de COVID-19 o confirmación de esta, a los que se sometió a un examen de LUS y pruebas de laboratorio. Resultados: Se inscribieron un total de 228 pacientes entre marzo y septiembre de 2020. La edad media fue de 61,9 años (DE 21,1). El hallazgo más común en la LUS fue la irregularidad pleural posteroinferior derecha (53,9%, 123 pacientes). Se calculó un modelo de regresión logística, que incluyó la edad mayor de 70 años, proteína C reactiva (PCR) mayor de 70 mg/L y puntuación de afectación pulmonar mediante LUS score superior a 7 para predecir la mortalidad, el ingreso hospitalario y el alta del SU. Se obtuvo una sensibilidad del 56,8% y una especificidad del 87,6%, con un AUC de 0,813 [p < 0,001] para dicho modelo predictivo, en materia de mortalidad. Conclusiones: La combinación de LUS, hallazgos clínicos y de laboratorio en esta «regla de 7¼ de fácil aplicación se mostró de utilidad para predecir el ingreso hospitalario y la mortalidad.

Inter-Rater Variability in the Evaluation of Lung Ultrasound in Videos Acquired from COVID-19 Patients

Lung ultrasound (LUS) allows for the detection of a series of manifestations of COVID-19, such as B-lines and consolidations. The objective of this work was to study the inter-rater reliability (IRR) when detecting signs associated with COVID-19 in the LUS, as well as the performance of the test in a longitudinal or transverse orientation. Thirty-three physicians with advanced experience in LUS independently evaluated ultrasound videos previously acquired using the ULTRACOV system on 20 patients with confirmed COVID-19. For each patient, 24 videos of 3 s were acquired (using 12 positions with the probe in longitudinal and transverse orientations). The physicians had no information about the patients or other previous evaluations. The score assigned to each acquisition followed the convention applied in previous studies. A substantial IRR was found in the cases of normal LUS (kappa = 0.74), with only a fair IRR for the presence of individual B-lines (kappa = 0.36) and for confluent B-lines occupying < 50% (kappa = 0.26) and a moderate IRR in consolidations and B-lines > 50% (kappa = 0.50). No statistically significant differences between the longitudinal and transverse scans were found. The IRR for LUS of COVID-19 patients may benefit from more standardized clinical protocols.

Usefulness of Multi-Organ Point-of-Care Ultrasound as a Complement to the Decision-Making Process in Internal Medicine.

Accumulated data show the utility of diagnostic multi-organ point-of-care ultrasound (PoCUS) in the assessment of patients admitted to an internal medicine ward. We assessed whether multi-organ PoCUS (lung, cardiac, and abdomen) provides relevant diagnostic and/or therapeutic information in patients admitted for any reason to an internal medicine ward. We conducted a prospective, observational, and single-center study, at a secondary hospital. Multi-organ PoCUS was performed during the first 24 h of admission. The sonographer had access to the patients' medical history, physical examination, and basic complementary tests performed in the Emergency Department (laboratory, X-ray, electrocardiogram). We considered a relevant ultrasound finding if it implied a significant diagnostic and/or therapeutic change. In the second semester of 2019, we enrolled 310 patients, 48.7% were male and the mean age was 70.5 years. Relevant ultrasound findings were detected in 86 patients (27.7%) and in 60 (19.3%) triggered a therapeutic change. These findings were associated with an older age (Mantel-Haenszel χ2 = 25.6; p < 0.001) and higher degree of dependency (Mantel-Haenszel χ2 = 5.7; p = 0.017). Multi-organ PoCUS provides relevant diagnostic information, complementing traditional physical examination, and facilitates therapy adjustment, regardless of the cause of admission. Multi-organ PoCUS to be useful need to be systematically integrated into the decision-making process in internal medicine.

Point-of-care ultrasonography in the initial characterization of patients with COVID-19.

BACKGROUND: There is growing evidence regarding the imaging findings of coronavirus disease 2019 (COVID-19) in chest X-rays and computed tomography scans; however, their availability during this pandemic outbreak might be compromised. Currently, the role of point-of-care ultrasonography (POCUS) has yet to be explored. OBJECTIVES: To describe the POCUS findings of COVID-19 in patients with the disease admitted to the emergency department (ED), correlating them with vital signs, laboratory and radiologic results, therapeutic decisions, and the prognosis. METHODS: Prospective study performed in the ED of 2 academic hospitals. Patients with highly suspected or confirmed COVID-19 underwent a lung ultrasonography (lung POCUS), focused cardiac ultrasound (FOCUS), and inferior vena cava (IVC) exam. RESULTS: Between March and April 2020, 96 patients were enrolled. The mean age was 68.2 years (SD 17.5). The most common findings in the lung POCUS were an irregular pleural line (63.2%), bilateral confluence (55.2%), and isolated B-lines (53.1%), which were associated with a positive RT-PCR (odds ratio 4.327; 95% CI 1.216-15.401; p < .001), and correlated with IL-6 levels (rho = 0.622; p = .002). The IVC negatively correlated with levels of expiratory pO2 (rho = -0.539; p = .014) and inspiratory pO2 (rho = -0.527; p = 0.017), and expiratory diameter positively correlated with troponin I (rho = 0.509; p = .03). After the POCUS exam, almost 20% of the patients had an associated condition that required a change in their treatment or management. CONCLUSIONS: POCUS parameters have the potential to impact the diagnosis, management, and prognosis of patients with confirmed or suspected COVID-19.

ANTECEDENTES: Existe una evidencia creciente con respecto a los hallazgos por imagen de la COVID-19, tanto en radiografías de tórax como en tomografía computarizada; sin embargo, la disponibilidad de estas técnicas durante la pandemia podría verse comprometida. OBJETIVOS: Describir los hallazgos en la ecografía en el punto de atención (POCUS) en pacientes con COVID-19 que consultaron en el servicio de urgencias (SU), correlacionándolos con signos vitales, resultados analíticos y radiológicos, decisiones terapéuticas y pronóstico. MÉTODOS: Estudio prospectivo realizado en los SU de dos hospitales académicos. Los pacientes con COVID-19 con alta sospecha o confirmada se sometieron a una ecografía pulmonar (POCUS pulmonar), una ecocardioscopia y una ecografía de la vena cava inferior (VCI). RESULTADOS: Entre marzo y abril del 2020, se reclutaron 96 pacientes. La edad media fue de 68,2 años (DE 17,5). Los hallazgos más comunes en el POCUS pulmonar fueron la línea pleural irregular (63,2%), las líneas B confluyentes bilateral (55,2%) y aisladas (53,1%), que se vincularon con una RT-PCR (odds ratio 4,327; IC 95% 1,216 a 15,401; p < 0,001), y se asoció con los niveles de interleucina-6 (IL-6) (ρ = 0,622; p = 0,002). La VCI se correlacionó negativamente con los niveles de pO2 espiratorio (ρ = − 0,539; p = 0,014) y pO2 inspiratorio (ρ = − 0,527; p = 0,017), y el diámetro espiratorio se relacionó positivamente con la troponina I (ρ = 0,509; p = 0, 03). Después del examen POCUS, casi el 20% de los pacientes tenían una condición asociada que requería un cambio en el tratamiento o manejo previo. CONCLUSIONES: Los parámetros POCUS tienen el potencial de afectar el diagnóstico, manejo y pronóstico de pacientes con sospecha o confirmación de COVID-19.

Impact of Lung Ultrasound during the SARS-CoV-2 Pandemic: Distinction Between Viral and Bacterial Pneumonia⋆ Impacto de la ecografía pulmonar durante la pandemia por SARS-CoV-2: distinción entre la neumonía viral y la bacteriana

Introduction Lung Ultrasound is an accessible, low-cost technique that has demonstrated its usefulness in the prognostic stratification of COVID-19 patients. In addition, according to previous studies, it can guide us towards the potential aetiology, especially in epidemic situations such as the current one. Patients and methods 40 patients were prospectively recruited, 30 with confirmed SARS-CoV-2 pneumonia and 10 with community-acquired pneumonia (CAP). The patients included underwent both a chest X-ray and ultrasound. Results There were no differences in the 2 groups in terms of clinical and laboratory characteristics. The main ultrasound findings in the SARS-CoV-2 group were the presence of confluent B lines and subpleural consolidations and hepatinization in the CAP group. Pleural effusion was more frequent in the CAP group. There were no normal lung ultrasound exams. Analysis of the area under the curve (AUC) curves showed an area under the curve for Lung Ultrasound of 89.2% (95% CI: 75.0-100%, p < .001) in the identification of SARS-CoV-2 pneumonia. The cut-off value for the lung score of 10 had a sensitivity of 93.3% and a specificity of 80.0% (p < .001). Discussion The combination of the findings of the Lung Ultrasound, with a Lung Score greater than 10, added to the rest of the additional tests, can be an excellent tool to predict the aetiology of the pneumonia.

Impact of lung ultrasound during the SARS-CoV-2 pandemic: Distinction between viral and bacterial pneumonia.

INTRODUCTION: Lung Ultrasound is an accessible, low-cost technique that has demonstrated its usefulness in the prognostic stratification of COVID-19 patients. In addition, according to previous studies, it can guide us towards the potential aetiology, especially in epidemic situations such as the current one. PATIENTS AND METHODS: 40 patients were prospectively recruited, 30 with confirmed SARS-CoV-2 pneumonia and 10 with community-acquired pneumonia (CAP). The patients included underwent both a chest X-ray and ultrasound. RESULTS: There were no differences in the 2 groups in terms of clinical and laboratory characteristics. The main ultrasound findings in the SARS-CoV-2 group were the presence of confluent B lines and subpleural consolidations and hepatinization in the CAP group. Pleural effusion was more frequent in the CAP group. There were no normal lung ultrasound exams. Analysis of the area under the curve (AUC) curves showed an area under the curve for Lung Ultrasound of 89.2% (95% CI: 75%.0-100%, p < .001) in the identification of SARS-CoV-2 pneumonia. The cut-off value for the lung score of 10 had a sensitivity of 93.3% and a specificity of 80.0% (p < .001). DISCUSSION: The combination of the findings of the Lung Ultrasound, with a Lung Score greater than 10, added to the rest of the additional tests, can be an excellent tool to predict the aetiology of the pneumonia.

Mortality by COVID-19 Before Vaccination - One Year Experience of Hospitalized Patients in Madrid.

OBJECTIVES: The aim of the study was to analyze the mortality and characteristics of deceased patients with COVID-19 during the first year of the pandemic. METHODS: All admissions owing to COVID-19 at a tertiary hospital in Madrid were analyzed. Three waves were considered: March 2020 to June 2020, July 2020 to November 2020, and December 2020 to April 2021. RESULTS: A total of 3,676 patients were identified. Among inpatients, no differences regarding age, sex, length of admission, or mortality were found between the 3 waves (p >0.05). The overall mortality rate was 12.9%. Among deceased patients, the median age was 82 years and the median Charlson Comorbidity Index was 6. Considering the main predictors for mortality by COVID-19 (age, sex, and concomitant comorbidities), only patients with previous lung disease were more prevalent in the third period (p <0.01). Finally, higher intensive care unit admission rates, a lower rate of patients coming from nursing homes, and a lower rate of patients with dementia were noted in the third period (p <0.05) among deceased patients. CONCLUSION: One year after the onset of the pandemic, the mortality rate of hospitalized patients and the profile of non-survivors have not changed significantly. In the absence of vaccine benefits, advanced age and multiple pathologies are uniform characteristics of non-survivors.

A Case of Restrictive Lung Disease Masquerading as SARS-CoV-2 Pneumonia: the Complexity of Integrating Lung Ultrasound in Clinical Management

This report aims to highlight the importance of integrating the lung ultrasound findings in the clinical judgment, and to integrate its findings, exemplified in this patient, thought to have COVID-19 bilateral pneumonia, and turn out to have an infectious spondylodiscitis and secondary, a restrictive lung disease. As ultrasound devices become increasingly portable and affordable, the future potential of lung ultrasound relies on a not lesser degree of clinical skills acquisition.

Early Lung Ultrasound Findings in Patients With COVID-19 Pneumonia: A Retrospective Multicenter Study of 479 Patients.

OBJECTIVES: Lung ultrasound (LUS) holds the promise of an accurate, radiation-free, and affordable diagnostic and monitoring tool in coronavirus disease 2019 (COVID-19) pneumonia. We sought to evaluate the usefulness of LUS in the diagnosis of patients with respiratory distress and suspicion of interstitial severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pneumonia, in comparison to other imaging modalities. METHODS: This was a multicenter, retrospective study. LUS was performed, on Emergency Department (ED) arrival of patients presenting for possible COVID-19 evaluation, by trained emergency physicians, before undergoing conventional radiologic examination or while waiting for the report. Scans were performed using longitudinal transducer orientation of the lung regions. CXR was interpreted by radiologists staffing ED radiology. Subjects were divided into two group based on molecular test results. LUS findings were compared to COVID test results, nonlaboratory data, and other imaging for each patient. Categorical variables were expressed as percentages and continuous variables as median ± standard error. RESULTS: A total of 479 patients were enrolled, 87% diagnosed with SARS-CoV-2 by molecular testing. COVID positive and COVID negative patients differed with respect to sex, presence of fever, and white blood cells count. Most common findings on lung point of care ultrasound (POCUS) for COVID-positive patients were B-lines, irregular pleural lines, and small consolidation. Normal chest X-ray was found in 17.89% of cases. CONCLUSIONS: This 479 patient cohort, with COVID-19, found LUS to be noninferior to chest X-ray (CXR) for diagnostic accuracy. In this study, COVID-positive patients are most likely to show B lines and sub-pleural consolidations on LUS examination.

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

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

The Impact of Different Lung Ultrasound Protocols in the Assessment of Lung Lesions in COVID-19 Patients: Is There an Ideal Lung Ultrasound Protocol?

BACKGROUND: In the past months, several lung ultrasonography (LUS) protocols have been proposed, mainly on previously validated schemes independent of coronavirus disease 2019 (COVID-19). OBJECTIVES: The main purpose of this study was to determine the impact and accuracy of different LUS protocols proposed in COVID-19. METHODS: Patients were evaluated with a standard sequence of LUS scans in 72 intercostal spaces along 14 anatomic lines in the chest. A scoring system of LUS findings was reported and then analyzed separately according to each proposed LUS protocol zones. This score was then correlated to a validated Pulmonary Inflammation Index (PII) on chest Computed Tomography (CT). RESULTS: Thirty-two patients were enrolled. The most frequent pattern was ground-glass opacities in the chest X-ray (53.1%), chest CT (59.1%) and subpleural or lobar consolidations (40.8%) in the posteroinferior areas (p < 0.001) on LUS. The Interclass Correlation Coefficient (ICC) was significantly correlated with almost every protocol analyzed except the 8-zone (p = 0.119) and the 10-zone protocol that only included one posterior point (p = 0.052). The highest ICC was obtained with a 12-zone protocol (ICC 0.500; p = 0.027) and decreased as more points were included. CONCLUSIONS: In conclusion, our study results suggest that performing an ultrasound protocol with 12-zone scanning, including the superior and inferior areas of the anterior, lateral and posterior regions of the chest was consistent with higher ICC and higher degree of concordance with CT. We emphasize the need of a more standardization technique to further implement and develop this imaging modality in COVID-19.

Usefulness of lung ultrasound in the early identification of severe COVID-19: results from a prospective study.

AIM: There is growing evidence regarding the imaging findings of coronavirus disease 2019 (COVID-19) in lung ultrasound (LUS); however, its role in predicting the prognosis has yet to be explored. The aim of the study was to assess the relationship between lung ultrasound findings with the degree of respiratory failure measured by the PaO2/FiO2 ratio (PaFi) andthe prognosis of these patients: need for non-invasive mechanical ventilation (NIMV), admission to the Intensive Care Unit (ICU) and mortality. MATERIAL AND METHOD: Prospective, longitudinal and observational study performed in patients with confirmed COVID-19 underwent a LUS examination and laboratory tests. RESULTS: A total of 107 patients were enrolled: 93.4% with bilateral involvement and 73.83% presented at least one consolidation. A good inverse correlation (Rho Spearman coefficient -0.897) between the ultrasound score and PaFi was obtained. The AUC for identification of patients with more severe respiratory failure, a moderate and severe ARDS, was 0.97 (CI 95%: 0.95-1) and a cut-off score of 34.5 showed a sensitivity of 0.94 and a specificity of 0.91. The Kappa index showed a high concordance (0.83) of the classification by ultrasound lunginvolvement and ARDS. CONCLUSIONS: The combination of the ultrasound score and the presence of respiratory failure can easily identify patients with a higher risk to present complications.