Evaluation of Lung Involvement in COVID-19 Pneumonia Based on Ultrasound Images

Abstract

Background: Lung ultrasound (LUS) can be an important imaging tool for the diagnosis and assessment of lung involvement. Ultrasound sonograms have been confirmed to illustrate damage to a person’s lungs, which means that the correct classification and scoring of a patient’s sonogram can be used to assess lung involvement.Methods: The purpose of this study was to establish a lung involvement assessment model based on deep learning. A novel multimodal channel and receptive field attention network combined with ResNeXt (MCRFNet) was proposed to classify sonograms, and the network can automatically fuse shallow features and determine the importance of different channels and respective fields. Finally, sonogram classes were transformed into scores to evaluate lung involvement from the initial diagnosis to rehabilitation.Results and conclusion: Using multicenter and multimodal ultrasound data from 104 patients, the diagnostic model achieved 94.39% accuracy, 82.28% precision, 76.27% sensitivity, and 96.44% specificity. The lung involvement severity and the trend of COVID-19 pneumonia were evaluated quantitatively.

Lung ultrasound as a predictor of mortality of patients with COVID-19

“…(5) Several studies have shown that LUS can detect interstitial disease, subpleural consolidations, and respiratory distress of any aetiology, with sensitivity and specificity superior to chest radiography and comparable to CT. (6)(7)(8) Indeed, LUS has already been recommended in past viral pandemics (9) and growing evidence demonstrates its effectiveness in patients with COVID-19, (10) which allows identifying the degree of lung involvement, its course, and the possible association between the initial lung involvement and its prognosis. (11)(12)(13)(14)(15) Our objective was to evaluate the performance of LUS through the lung ultrasound score (LUS score) to determine the severity of pneumonia and the short-term outcomes of patients with COVID-19 admitted to the intensive care unit. We hypothesize that the Lung Ultrasound Score (LUS) correlates with clinical evolution and predicts mortality in critically ill COVID-19 pneumonia patients.…”