Automated lung ultrasound scoring for evaluation of coronavirus disease 2019 pneumonia using two-stage cascaded deep learning model

Abstract

Coronavirus disease 2019 (COVID-19) pneumonia has erupted worldwide, causing massive population deaths and huge economic losses. In clinic, lung ultrasound (LUS) plays an important role in the auxiliary diagnosis of COVID-19 pneumonia. However, the lack of medical resources leads to the low using efficiency of the LUS, to address this problem, a novel automated LUS scoring system for evaluating COVID-19 pneumonia based on the two-stage cascaded deep learning model was proposed in this paper. 18,330 LUS images collected from 26 COVID-19 pneumonia patients were successfully assigned scores by two experienced doctors according to the designed four-level scoring standard for training the model. At the first stage, we made a secondary selection of these scored images through five ResNet-50 models and five-fold cross validation to obtain the available 12,949 LUS images which were highly relevant to the initial scoring results. At the second stage, three deep learning models including ResNet-50, Vgg-19, and GoogLeNet were formed the cascaded scored model and trained using the new dataset, whose predictive result was obtained by the voting mechanism. In addition, 1000 LUS images collected another 5 COVID-19 pneumonia patients were employed to test the model. Experiments results showed that the automated LUS scoring model was evaluated in terms of accuracy, sensitivity, specificity, and F1-score, being 96.1%, 96.3%, 98.8%, and 96.1%, respectively. They proved the proposed two-stage cascaded deep learning model could automatically score an LUS image, which has great potential for application to the clinics on various occasions.

Diagnosing COVID-19 using artificial intelligence: a comprehensive review

“…Besides, they are known to be even more accurate than MRIs. Xing et al (2022) used lung ultrasound (LUS) to perform the auxiliary detection of coronavirus. A LUS scoring device was built, which used a cascaded deep learning classifier.…”

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

“…The changes of various indicators in LUS images were closely related to the severity of pulmonary diseases, such as COVID-19 pneumonia. Most researches [19], [21], [22] mainly focused on the entire LUS images and used deep learning methods to score the LUS for evaluating the clinical severities of some lung diseases. However, these deep learning methods commonly required a large amount of LUS images which are usually unpractical to obtain.…”

“…When using lung ultrasound (LUS) to analyze lung diseases, the commonly used clinical indicators include pleural line, A-line, B-line, and consolidation [15], [16], [17]. Previously, some researchers designed corresponding scoring standards according to these indicators, and then analyzed the LUS image as a whole to realize the auxiliary diagnosis of pneumonia severities [18], [19], [20], [21], [22], [23], [24]. Most of these methods were designed based on deep learning models.…”

“…They cannot analyze the correlation between specific indicators and clinical severities, which may not provide effective help for specific clinical problems related to lung diseases, such as pleural line thickness monitoring. Therefore, how to effectively extract and analyze independent indicators is also of great significance for clinical application of lung diseases [22].…”

Multiclass Classification for Detection of COVID-19 Infection in Chest X-Rays Using CNN

“…In more severe cases, COVID-19 patients are hospitalized and must be given extensive care to prevent death. In fact, until January 2022, the World Health Organization recorded over 334 million cases of corona infections worldwide, with over 5 million deaths [7]. ese statistics clearly re ect the impact of the coronavirus spread on public health in all countries without exceptions.…”