Automatically Scoring Lung Ultrasound Videos of COVID-19 and post-COVID-19 Patients

Lung ultrasound (LUS) imaging is playing an important role in the current pandemic, allowing the evaluation of patients affected by COVID-19 pneumonia. However, LUS is limited to the visual inspection of ultrasound data, which negatively affects the reproducibility and reliability of the findings. For these reasons, we were the first to propose a standardized imaging protocol and a scoring system, from which we developed the first artificial intelligence (AI) models able to evaluate LUS videos. Furthermore, we demonstrated prognostic value of our approach and its utility for patients' stratification. In this study, we report on the level of agreement between AI and LUS clinical experts (MD) on LUS data acquired from both COVID-19 patients and post-COVID-19 patients.

Automated summary

Lung ultrasound imaging is crucial in evaluating patients with COVID-19 pneumonia. To enhance the reliability and reproducibility of the results, we proposed a standardized imaging protocol and scoring system, and developed artificial intelligence models capable of assessing lung ultrasound videos.