ABSTRACT
Over the last 20 years, scientific literature and interest on chest/lung ultrasound (LUS) have exponentially increased. Interpreting mixed-anatomical and artifactual-pictures determined the need of a proposal of a new nomenclature of artifacts and signs to simplify learning, spread, and implementation of this technique. The aim of this review is to collect and analyze different signs and artifacts reported in the history of chest ultrasound regarding normal lung, pleural pathologies, and lung consolidations. By reviewing the possible physical and anatomical interpretation of these artifacts and signs reported in the literature, this work aims to present the AdET (Accademia di Ecografia Toracica) proposal of nomenclature and to bring order between published studies.
Subject(s)
Lung Diseases , Lung , Humans , Lung/diagnostic imaging , Lung Diseases/diagnostic imaging , Thorax , Ultrasonography/methods , ArtifactsABSTRACT
OBJECTIVES: Lung ultrasound (LUS) has sparked significant interest during COVID-19. LUS is based on the detection and analysis of imaging patterns. Vertical artifacts and consolidations are some of the recognized patterns in COVID-19. However, the interrater reliability (IRR) of these findings has not been yet thoroughly investigated. The goal of this study is to assess IRR in LUS COVID-19 data and determine how many LUS videos and operators are required to obtain a reliable result. METHODS: A total of 1035 LUS videos from 59 COVID-19 patients were included. Videos were randomly selected from a dataset of 1807 videos and scored by six human operators (HOs). The videos were also analyzed by artificial intelligence (AI) algorithms. Fleiss' kappa coefficient results are presented, evaluated at both the video and prognostic levels. RESULTS: Findings show a stable agreement when evaluating a minimum of 500 videos. The statistical analysis illustrates that, at a video level, a Fleiss' kappa coefficient of 0.464 (95% confidence interval [CI] = 0.455-0.473) and 0.404 (95% CI = 0.396-0.412) is obtained for pairs of HOs and for AI versus HOs, respectively. At prognostic level, a Fleiss' kappa coefficient of 0.505 (95% CI = 0.448-0.562) and 0.506 (95% CI = 0.458-0.555) is obtained for pairs of HOs and for AI versus HOs, respectively. CONCLUSIONS: To examine IRR and obtain a reliable evaluation, a minimum of 500 videos are recommended. Moreover, the employed AI algorithms achieve results that are comparable with HOs. This research further provides a methodology that can be useful to benchmark future LUS studies.
Subject(s)
COVID-19 , Humans , Artificial Intelligence , Reproducibility of Results , Lung/diagnostic imaging , Ultrasonography/methodsABSTRACT
Although during the last few years the lung ultrasound (LUS) technique has progressed substantially, several artifacts, which are currently observed in clinical practice, still need a solid explanation of the physical phenomena involved in their origin. This is particularly true for vertical artifacts, conventionally known as B-lines, and for their use in clinical practice. A wider consensus and a deeper understanding of the nature of these artifactual phenomena will lead to a better classification and a shared nomenclature, and, ultimately, result in a more objective correlation between anatomo-pathological data and clinical scenarios. The objective of this review is to collect and document the different signs and artifacts described in the history of chest ultrasound, with a particular focus on vertical artifacts (B-lines) and sonographic interstitial syndrome (SIS). By reviewing the possible physical and anatomical interpretation of the signs and artifacts proposed in the literature, this work also aims to bring order to the available studies and to present the AdET (Accademia di Ecografia Toracica) viewpoint in terms of nomenclature and clinical approach to the SIS.
Subject(s)
Artifacts , Lung , Humans , Lung/diagnostic imaging , Syndrome , UltrasonographyABSTRACT
Lung ultrasound (LUS) is currently being extensively used for the evaluation of patients affected by coronavirus disease 2019. In the past months, several imaging protocols have been proposed in the literature. However, how the different protocols would compare when applied to the same patients had not been investigated yet. To this end, in this multicenter study, we analyzed the outcomes of 4 different LUS imaging protocols, respectively based on 4, 8, 12, and 14 LUS acquisitions, on data from 88 patients. Results show how a 12-area acquisition system seems to be a good tradeoff between the acquisition time and accuracy.
Subject(s)
COVID-19 , Humans , Lung/diagnostic imaging , Multicenter Studies as Topic , SARS-CoV-2 , UltrasonographyABSTRACT
OBJECTIVES: The 2019 novel coronavirus (severe acute respiratory syndrome coronavirus 2) is causing cases of severe pneumonia. Lung ultrasound (LUS) could be a useful tool for physicians detecting a bilateral heterogeneous patchy distribution of pathologic findings in a symptomatic suggestive context. The aim of this study was to focus on the implications of limiting LUS examinations to specific regions of the chest. METHODS: Patients were evaluated with a standard sequence of LUS scans in 14 anatomic areas. A scoring system of LUS findings was reported, ranging from 0 to 3 (worst score, 3). The scores reported on anterior, lateral, and posterior landmarks were analyzed separately and compared with each other and with the global findings. RESULTS: Thirty-eight patients were enrolled. A higher prevalence of score 0 was observed in the anterior region (44.08%). On the contrary, 21.05% of posterior regions and 13.62% of lateral regions were evaluated as score 3, whereas only 5.92% of anterior regions were classified as score 3. Findings from chest computed tomography performed in 16 patients with coronavirus disease 2019 correlated with and matched the distribution of findings from LUS. CONCLUSIONS: To assess the quantity and severity of lung disease, a comprehensive LUS examination is recommended. Omitting areas of the chest misses involved lung.
Subject(s)
COVID-19/diagnostic imaging , Lung/diagnostic imaging , Ultrasonography/methods , Female , Humans , Male , Middle Aged , Reproducibility of Results , SARS-CoV-2 , Severity of Illness IndexABSTRACT
Ultrasound in point-of-care lung assessment is becoming increasingly relevant. This is further reinforced in the context of the COVID-19 pandemic, where rapid decisions on the lung state must be made for staging and monitoring purposes. The lung structural changes due to severe COVID-19 modify the way ultrasound propagates in the parenchyma. This is reflected by changes in the appearance of the lung ultrasound images. In abnormal lungs, vertical artifacts known as B-lines appear and can evolve into white lung patterns in the more severe cases. Currently, these artifacts are assessed by trained physicians, and the diagnosis is qualitative and operator dependent. In this article, an automatic segmentation method using a convolutional neural network is proposed to automatically stage the progression of the disease. 1863 B-mode images from 203 videos obtained from 14 asymptomatic individual,14 confirmed COVID-19 cases, and 4 suspected COVID-19 cases were used. Signs of lung damage, such as the presence and extent of B-lines and white lung areas, are manually segmented and scored from zero to three (most severe). These manually scored images are considered as ground truth. Different test-training strategies are evaluated in this study. The results shed light on the efficient approaches and common challenges associated with automatic segmentation methods.
Subject(s)
COVID-19 , Humans , Image Processing, Computer-Assisted , Lung/diagnostic imaging , Pandemics , SARS-CoV-2 , Tomography, X-Ray ComputedABSTRACT
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.
Subject(s)
Betacoronavirus , Coronavirus Infections/diagnostic imaging , Lung/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Ultrasonography/standards , Anatomic Landmarks , Artificial Intelligence , COVID-19 , Databases, Factual , Forecasting , Humans , Image Processing, Computer-Assisted , Internationality , Pandemics , Point-of-Care Systems , Reproducibility of Results , SARS-CoV-2Subject(s)
COVID-19 , Pneumonia , Humans , Lung/diagnostic imaging , Pneumonia/diagnostic imaging , SARS-CoV-2 , UltrasonographySubject(s)
Artifacts , Thorax , Humans , Ultrasonography , Lung/diagnostic imaging , Surveys and QuestionnairesSubject(s)
COVID-19 , Coronavirus Infections , Female , Humans , Pregnancy , Pregnant Women , SARS-CoV-2 , UltrasonographySubject(s)
Lung , Point-of-Care Systems , Humans , Lung/diagnostic imaging , Point-of-Care Testing , UltrasonographySubject(s)
Betacoronavirus , Coronavirus Infections , Pandemics , Pneumonia, Viral , COVID-19 , Humans , Lung/diagnostic imaging , SARS-CoV-2 , UltrasonographyABSTRACT
Automated ultrasound imaging assessment of the effect of CoronaVirus disease 2019 (COVID-19) on lungs has been investigated in various studies using artificial intelligence-based (AI) methods. However, an extensive analysis of state-of-the-art Convolutional Neural Network-based (CNN) models for frame-level scoring, a comparative analysis of aggregation techniques for video-level scoring, together with a thorough evaluation of the capability of these methodologies to provide a clinically valuable prognostic-level score is yet missing within the literature. In addition to that, the impact on the analysis of the posterior probability assigned by the network to the predicted frames as well as the impact of temporal downsampling of LUS data are topics not yet extensively investigated. This paper takes on these challenges by providing a benchmark analysis of methods from frame to prognostic level. For frame-level scoring, state-of-the-art deep learning models are evaluated with additional analysis of best performing model in transfer-learning settings. A novel cross-correlation based aggregation technique is proposed for video and exam-level scoring. Results showed that ResNet-18, when trained from scratch, outperformed the existing methods with an F1-Score of 0.659. The proposed aggregation method resulted in 59.51%, 63.29%, and 84.90% agreement with clinicians at the video, exam, and prognostic levels, respectively; thus, demonstrating improved performances over the state of the art. It was also found that filtering frames based on the posterior probability shows higher impact on the LUS analysis in comparison to temporal downsampling. All of these analysis were conducted over the largest standardized and clinically validated LUS dataset from COVID-19 patients.
Subject(s)
Artificial Intelligence , COVID-19 , Humans , Prognosis , Benchmarking , UltrasonographyABSTRACT
Lung ultrasound (LUS) is a cheap, safe and non-invasive imaging modality that can be performed at patient bed-side. However, to date LUS is not widely adopted due to lack of trained personnel required for interpreting the acquired LUS frames. In this work we propose a framework for training deep artificial neural networks for interpreting LUS, which may promote broader use of LUS. When using LUS to evaluate a patient's condition, both anatomical phenomena (e.g., the pleural line, presence of consolidations), as well as sonographic artifacts (such as A- and B-lines) are of importance. In our framework, we integrate domain knowledge into deep neural networks by inputting anatomical features and LUS artifacts in the form of additional channels containing pleural and vertical artifacts masks along with the raw LUS frames. By explicitly supplying this domain knowledge, standard off-the-shelf neural networks can be rapidly and efficiently finetuned to accomplish various tasks on LUS data, such as frame classification or semantic segmentation. Our framework allows for a unified treatment of LUS frames captured by either convex or linear probes. We evaluated our proposed framework on the task of COVID-19 severity assessment using the ICLUS dataset. In particular, we finetuned simple image classification models to predict per-frame COVID-19 severity score. We also trained a semantic segmentation model to predict per-pixel COVID-19 severity annotations. Using the combined raw LUS frames and the detected lines for both tasks, our off-the-shelf models performed better than complicated models specifically designed for these tasks, exemplifying the efficacy of our framework.
Subject(s)
COVID-19 , COVID-19/diagnostic imaging , Humans , Lung/diagnostic imaging , Neural Networks, Computer , SARS-CoV-2 , Ultrasonography/methodsABSTRACT
Background: Current available therapeutic options for Coronavirus Disease-2019 (COVID-19) are primarily focused on treating hospitalized patients, and there is a lack of oral therapeutic options to treat mild to moderate outpatient COVID-19 and prevent clinical progression. Raloxifene was found as a promising molecule to treat COVID-19 due to its activity to modulate the replication of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and act as an immunomodulator to decrease proinflammatory cytokines. Methods: This was a phase 2 multicenter, randomized, placebo-controlled trial to evaluate the efficacy and safety of raloxifene in adult patients with mild to moderate COVID-19 between October 2020 to June 2021 in five centers located in Italy. This was a planned 2/3 adaptive study, but due to operational difficulties, the study was discontinued during the phase 2 study segment. Participants were randomized 1:1:1 to receive oral placebo, raloxifene 60 mg, or raloxifene 120 mg by self-administration for a maximum of two weeks. The primary outcomes were the proportion of patients with undetectable SARS-CoV-2 via nasopharyngeal swabs at day 7 and the proportion of patients who did not require supplemental oxygen therapy or mechanical ventilation on day 14. Safety was assessed. The trial is registered (EudraCT 2021-002,476-39, and ClinicalTrials.gov: NCT05172050). Findings: A total of 68 participants were enrolled and randomized to placebo (n = 21), raloxifene 60 mg (n = 24), and raloxifene 120 mg (n = 23). The proportion of participants with undetectable SARS-CoV-2 after seven days of treatment with raloxifene 60 mg [36.8%, 7/19 vs. 0.0%, 0/14] and 120 mg [22.2%, 4/18 vs. 0.0%, 0/14] was better compared to placebo, [risk difference (RD) = 0·37 (95% C.I.:0·09-0·59)] and [RD = 0·22 (95% C.I.: -0·03-0·45)], respectively. There was no evidence of effect for requirement of supplemental oxygen and/or mechanical ventilation with effects for raloxifene 60 mg and raloxifene 120 mg over placebo, [RD = 0·09 (95% C.I.: -0·22-0·37)], and [RD = 0·03 (95% C.I.: -0·28-0·33)], respectively. Raloxifene was well tolerated at both doses, and there was no evidence of any difference in the occurrence of serious adverse events. Interpretation: Raloxifene showed evidence of effect in the primary virologic endpoint in the treatment of early mild to moderate COVID-19 patients shortening the time of viral shedding. The safety profile was consistent with that reported for other indications. Raloxifene may represent a promising pharmacological option to prevent or mitigate COVID-19 disease progression. Funding: The study was funded by Dompé Farmaceutici SpA and supported by the funds from the European Commission - Health and Consumers Directorate General, for the Action under the Emergency Support Instrument- Grant to support clinical testing of repurposed medicines to treat SARS-COV-2 patients (PPPA-ESI-CTRM-2020-SI2.837140), and by the COVID-2020-12,371,675 Ricerca finalizzata and line 1 Ricerca Corrente COVID both funded by Italian Ministry of Health.
ABSTRACT
Recent works highlighted the significant potential of lung ultrasound (LUS) imaging in the management of subjects affected by COVID-19. In general, the development of objective, fast, and accurate automatic methods for LUS data evaluation is still at an early stage. This is particularly true for COVID-19 diagnostic. In this article, we propose an automatic and unsupervised method for the detection and localization of the pleural line in LUS data based on the hidden Markov model and Viterbi Algorithm. The pleural line localization step is followed by a supervised classification procedure based on the support vector machine (SVM). The classifier evaluates the healthiness level of a patient and, if present, the severity of the pathology, i.e., the score value for each image of a given LUS acquisition. The experiments performed on a variety of LUS data acquired in Italian hospitals with both linear and convex probes highlight the effectiveness of the proposed method. The average overall accuracy in detecting the pleura is 84% and 94% for convex and linear probes, respectively. The accuracy of the SVM classification in correctly evaluating the severity of COVID-19 related pleural line alterations is about 88% and 94% for convex and linear probes, respectively. The results as well as the visualization of the detected pleural line and the predicted score chart, provide a significant support to medical staff for further evaluating the patient condition.
Subject(s)
Coronavirus Infections/diagnostic imaging , Image Interpretation, Computer-Assisted/methods , Lung/diagnostic imaging , Pleura/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Ultrasonography/methods , Algorithms , COVID-19 , Humans , Pandemics , Signal Processing, Computer-Assisted , Support Vector MachineABSTRACT
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 DL-based 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, video-level, 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.