Background: The purpose of this study is to provide evidence-based and expert consensus recommendations for lung ultrasound with focus on emergency and critical care settings. Methods: A multidisciplinary panel of 28 experts from eight countries was involved. Literature was reviewed from January 1966 to June 2011. Consensus members searched multiple databases including Pubmed, Medline, OVID, Embase, and others. The process used to develop these evidence-based recommendations involved two phases: determining the level of quality of evidence and developing the recommendation. The quality of evidence is assessed by the grading of recommendation, assessment, development, and evaluation (GRADE) method. However, the GRADE system does not enforce a specific method on how the panel should reach decisions during the consensus process. Our methodology committee decided to utilize the RAND appropriateness method for panel judgment and decisions/consensus. Results: Seventythree proposed statements were examined and discussed in three conferences held in Bologna, Pisa, and Rome. Each conference included two rounds of face-to-face modified Delphi technique. Anonymous panel voting followed each round. The panel did not reach an agreement and therefore did not adopt any recommendations for six statements. Weak/ conditional recommendations were made for 2 statements, and strong recommendations were made for the remaining 65 statements. The statements were then recategorized and grouped to their current format. Internal and external peer-review processes took place before submission of the recommendations. Updates will occur at least every 4 years or whenever significant major changes in evidence appear. Conclusions: This document reflects the overall results of the first consensus conference on ''point-of-care'' lung ultrasound. Statements were discussed and elaborated by experts who published the vast majority of papers on clinical use of lung ultrasound in the last 20 years. Recommendations were produced to guide implementation, development, and standardization of lung ultrasound in all relevant settings.

Growing evidence is showing the usefulness of lung ultrasound in patients with the 2019 new coronavirus disease (COVID‐19). Severe acute respiratory syndrome coronavirus 2 has now spread in almost every country in the world. In this study, we share our experience and propose a standardized approach to optimize the use of lung ultrasound in patients with COVID‐19. We focus on equipment, procedure, classification, and data sharing.

No abstract

Background: Differential diagnosis between acute cardiogenic pulmonary edema (APE) and acute lung injury/acute respiratory distress syndrome (ALI/ARDS) may often be difficult. We evaluated the ability of chest sonography in the identification of characteristic pleuropulmonary signs useful in the diagnosis of ALI/ARDS and APE.

Deep learning (DL) has proved successful in medical imaging and, in the wake of the recent COVID-19 pandemic, some works have started to investigate DLbased solutions for the assisted diagnosis of lung diseases. While existing works focus on CT scans, this paper studies the application of DL techniques for the analysis of lung ultrasonography (LUS) images. Specifically, we present a novel fully-annotated dataset of LUS images collected from several Italian hospitals, with labels indicating the degree of disease severity at a frame-level, videolevel, and pixel-level (segmentation masks). Leveraging these data, we introduce several deep models that address relevant tasks for the automatic analysis of LUS images. In particular, we present a novel deep network, derived from Spatial Transformer Networks, which simultaneously predicts the disease severity score associated to a input frame and provides localization of pathological artefacts in a weakly-supervised way. Furthermore, we introduce a new method based on uninorms for effective frame score aggregation at a video-level. Finally, we benchmark state of the art deep models for estimating pixel-level segmentations of COVID-19 imaging biomarkers. Experiments on the proposed dataset demonstrate satisfactory results on all the considered tasks, paving the way to future research on DL for the assisted diagnosis of COVID-19 from LUS data.