Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19
Open Access
- 16 August 2023
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 13 (16) , 2692
Abstract
COVID-19 is an ongoing global health pandemic. Although COVID-19 can be diagnosed with various tests such as PCR, these tests do not establish pulmonary disease burden. Whereas point-of-care lung ultrasound (POCUS) can directly assess the severity of characteristic pulmonary findings of COVID-19, the advantage of using US is that it is inexpensive, portable, and widely available for use in many clinical settings. For automated assessment of pulmonary findings, we have developed an unsupervised learning technique termed the calculated lung ultrasound (CLU) index. The CLU can quantify various types of lung findings, such as A or B lines, consolidations, and pleural effusions, and it uses these findings to calculate a CLU index score, which is a quantitative measure of pulmonary disease burden. This is accomplished using an unsupervised, patient-specific approach that does not require training on a large dataset. The CLU was tested on 52 lung ultrasound examinations from several institutions. CLU demonstrated excellent concordance with radiologist findings in different pulmonary disease states. Given the global nature of COVID-19, the CLU would be useful for sonographers and physicians in resource-strapped areas with limited ultrasound training and diagnostic capacities for more accurate assessment of pulmonary status.Keywords
Funding Information
- Radiological Society of North America (RSCH2028, 1034096, 5P30CA006973, U01CA140204)
- American Lung Association COVID-19 and Emerging Respiratory Viruses Research Award (RSCH2028, 1034096, 5P30CA006973, U01CA140204)
- National Institutes of Health (RSCH2028, 1034096, 5P30CA006973, U01CA140204)
This publication has 35 references indexed in Scilit:
- Can Lung US Help Critical Care Clinicians in the Early Diagnosis of Novel Coronavirus (COVID-19) Pneumonia?Radiology, 2020
- Findings of lung ultrasonography of novel corona virus pneumonia during the 2019–2020 epidemicIntensive Care Medicine, 2020
- ESR statement on portable ultrasound devicesInsights into Imaging, 2019
- A simplified lung ultrasound for the diagnosis of interstitial lung disease in connective tissue disease: a meta-analysisArthritis Research & Therapy, 2019
- Perceived barriers in the use of ultrasound in developing countriesThe Ultrasound Journal, 2015
- BLUE-Protocol and FALLS-ProtocolChest, 2015
- Lung ultrasound: Present and futureLung India, 2015
- Comparative analysis of nonlinear dimensionality reduction techniques for breast MRI segmentationMedical Physics, 2012
- Topographic distance and watershed linesSignal Processing, 1994
- A Threshold Selection Method from Gray-Level HistogramsIEEE Transactions on Systems, Man, and Cybernetics, 1979