Deep-learning based detection of COVID-19 using lung ultrasound imagery

Abstract

Background The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, especially in underdeveloped countries. There is a clear need to develop novel computer-assisted diagnosis tools to provide rapid and cost-effective screening in places where massive traditional testing is not feasible. Lung ultrasound is a portable, easy to disinfect, low cost and non-invasive tool that can be used to identify lung diseases. Computer-assisted analysis of lung ultrasound imagery is a relatively recent approach that has shown great potential for diagnosing pulmonary conditions, being a viable alternative for screening and diagnosing COVID-19. Objective To evaluate and compare the performance of deep-learning techniques for detecting COVID-19 infections from lung ultrasound imagery. Methods We adapted different pre-trained deep learning architectures, including VGG19, InceptionV3, Xception, and ResNet50. We used the publicly available POCUS dataset comprising 3326 lung ultrasound frames of healthy, COVID-19, and pneumonia patients for training and fine-tuning. We conducted two experiments considering three classes (COVID-19, pneumonia, and healthy) and two classes (COVID-19 versus pneumonia and COVID-19 versus non-COVID-19) of predictive models. The obtained results were also compared with the POCOVID-net model. For performance evaluation, we calculated per-class classification metrics (Precision, Recall, and F1-score) and overall metrics (Accuracy, Balanced Accuracy, and Area Under the Receiver Operating Characteristic Curve). Lastly, we performed a statistical analysis of performance results using ANOVA and Friedman tests followed by post-hoc analysis using the Wilcoxon signed-rank test with the Holm’s step-down correction. Results InceptionV3 network achieved the best average accuracy (89.1%), balanced accuracy (89.3%), and area under the receiver operating curve (97.1%) for COVID-19 detection from bacterial pneumonia and healthy lung ultrasound data. The ANOVA and Friedman tests found statistically significant performance differences between models for accuracy, balanced accuracy and area under the receiver operating curve. Post-hoc analysis showed statistically significant differences between the performance obtained with the InceptionV3-based model and POCOVID-net, VGG19-, and ResNet50-based models. No statistically significant differences were found in the performance obtained with InceptionV3- and Xception-based models. Conclusions Deep learning techniques for computer-assisted analysis of lung ultrasound imagery provide a promising avenue for COVID-19 screening and diagnosis. Particularly, we found that the InceptionV3 network provides the most promising predictive results from all AI-based techniques evaluated in this work. InceptionV3- and Xception-based models can be used to further develop a viable computer-assisted screening tool for COVID-19 based on ultrasound imagery.

Review of Machine Learning in Lung Ultrasound in COVID-19 Pandemic

“…In January 2021, they extended the dataset and trained a frame-based classifier, yielding a sensitivity of 0.806 and a specificity of 0.962 [ 61 ]. Similarly, Diaz-Escobar et al performed both three-class (COVID-19, bacterial pneumonia, and healthy) and binary (COVID-19 vs. bacterial and COVID-19 vs. healthy) classifications on POCUS, with pre-trained DL models (VGG19, InceptionV3, Xception, and ResNet50) [ 73 ]. Their results showed that InceptionV3 worked best with an AUC of 0.97 to identify COVID-19 cases from pneumonia and healthy controls.…”

Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool

“…In addition, these imaging modalities may not be available in all public healthcare services, especially for countries who are swamped with the pandemic, due to their costs and additional maintenance requirements. Most recently, researchers have utilized a safer and simpler imaging approach based on ultrasound to screen lungs for COVID-19 [ 28 ] and achieved high levels of performance (accuracy > 89%). Therefore, finding promising alternatives that are simple, fast, and cost-effective is an ultimate goal to researchers when it comes to integrating these techniques with machine learning.…”

Lung ultrasound findings following COVID-19 hospitalization: A prospective longitudinal cohort study

“…The COVID-19 worsening score including clinically relevant data in addition to LUS findings has proven to accurately identify patients who are less likely to require treatment in the intensive care unit [ 16 ]. Moreover, deep-learning based methods for LUS have also shown promising results for detecting COVID-19 pneumonia [ 17 , 18 ].…”