ABSTRACT
Knowledge of gas volume, tissue mass and recruitability measured by the quantitative CT scan analysis (CT-qa) is important when setting the mechanical ventilation in acute respiratory distress syndrome (ARDS). Yet, the manual segmentation of the lung requires a considerable workload. Our goal was to provide an automatic, clinically applicable and reliable lung segmentation procedure. Therefore, a convolutional neural network (CNN) was used to train an artificial intelligence (AI) algorithm on 15 healthy subjects (1,302 slices), 100 ARDS patients (12,279 slices), and 20 COVID-19 (1,817 slices). Eighty percent of this populations was used for training, 20% for testing. The AI and manual segmentation at slice level were compared by intersection over union (IoU). The CT-qa variables were compared by regression and Bland Altman analysis. The AI-segmentation of a single patient required 5-10 s vs. 1-2 h of the manual. At slice level, the algorithm showed on the test set an IOU across all CT slices of 91.3 ± 10.0, 85.2 ± 13.9, and 84.7 ± 14.0%, and across all lung volumes of 96.3 ± 0.6, 88.9 ± 3.1, and 86.3 ± 6.5% for normal lungs, ARDS and COVID-19, respectively, with a U-shape in the performance: better in the lung middle region, worse at the apex and base. At patient level, on the test set, the total lung volume measured by AI and manual segmentation had a R 2 of 0.99 and a bias -9.8 ml [CI: +56.0/-75.7 ml]. The recruitability measured with manual and AI-segmentation, as change in non-aerated tissue fraction had a bias of +0.3% [CI: +6.2/-5.5%] and -0.5% [CI: +2.3/-3.3%] expressed as change in well-aerated tissue fraction. The AI-powered lung segmentation provided fast and clinically reliable results. It is able to segment the lungs of seriously ill ARDS patients fully automatically.
ABSTRACT
PURPOSE: The COVID-19 pandemic poses new challenges for the medical community due to its large number of patients presenting with varying symptoms. Chest ultrasound (ChUS) may be particularly useful in the early clinical management in suspected COVID-19 patients due to its broad availability and rapid application. We aimed to investigate patterns of ChUS in COVID-19 patients and compare the findings with results from chest X-ray (CRX). MATERIALS AND METHODS: 24 patients (18 symptomatic, 6 asymptomatic) with confirmed SARS-CoV-2 by polymerase chain reaction underwent bedside ChUS in addition to CRX following admission. Subsequently, the results of ChUS and CRX were compared. RESULTS: 94% (n=17/18) of patients with respiratory symptoms demonstrated lung abnormalities on ChUS. ChUS was especially useful to detect interstitial syndrome compared to CXR in COVID-19 patients (17/18 vs. 11/18; p<0.02). Of note, ChUS also detected lung consolidations very effectively (14/18 for ChUS vs. 7/18 cases for CXR; p<0.02). Besides pathological B-lines and subpleural consolidations, pleural line abnormality (89%; n=16/18) was the third most common feature in patients with respiratory manifestations of COVID-19 detected by ChUS. CONCLUSION: Our findings support the high value of ChUS in the management of COVID-19 patients.