Next Article in Journal
A Local Search Maximum Likelihood Parameter Estimator of Chirp Signal
Next Article in Special Issue
Does Two-Class Training Extract Real Features? A COVID-19 Case Study
Previous Article in Journal
Object-Wise Video Editing
Previous Article in Special Issue
Hybrid Deep Learning-Based Epidemic Prediction Framework of COVID-19: South Korea Case
Open AccessArticle

Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis

1
Department of Biosystems Science and Engineering, ETH Zurich, 4058 Basel, Switzerland
2
Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland
3
Department of Mathematics and Computer Science, University of Barcelona, 08007 Barcelona, Spain
4
Brandenburg Medical School Theodor Fontane, 16816 Neuruppin, Germany
5
Pediatric Emergency Department, Hirslanden Clinique des Grangettes, 1224 Geneva, Switzerland
6
Department of Philosophy, University of Vienna, 1010 Vienna, Austria
7
Northumbria Specialist Emergency Care Hospital, Cramlington NE23 6NZ, UK
8
SIB Swiss Institute of Bioinformatics, 1015 Lausanne, Switzerland
*
Authors to whom correspondence should be addressed.
Shared first-authors.
Appl. Sci. 2021, 11(2), 672; https://doi.org/10.3390/app11020672
Received: 19 December 2020 / Revised: 7 January 2021 / Accepted: 8 January 2021 / Published: 12 January 2021
Care during the COVID-19 pandemic hinges upon the existence of fast, safe, and highly sensitive diagnostic tools. Considering significant practical advantages of lung ultrasound (LUS) over other imaging techniques, but difficulties for doctors in pattern recognition, we aim to leverage machine learning toward guiding diagnosis from LUS. We release the largest publicly available LUS dataset for COVID-19 consisting of 202 videos from four classes (COVID-19, bacterial pneumonia, non-COVID-19 viral pneumonia and healthy controls). On this dataset, we perform an in-depth study of the value of deep learning methods for the differential diagnosis of lung pathologies. We propose a frame-based model that correctly distinguishes COVID-19 LUS videos from healthy and bacterial pneumonia data with a sensitivity of 0.90±0.08 and a specificity of 0.96±0.04. To investigate the utility of the proposed method, we employ interpretability methods for the spatio-temporal localization of pulmonary biomarkers, which are deemed useful for human-in-the-loop scenarios in a blinded study with medical experts. Aiming for robustness, we perform uncertainty estimation and demonstrate the model to recognize low-confidence situations which also improves performance. Lastly, we validated our model on an independent test dataset and report promising performance (sensitivity 0.806, specificity 0.962). The provided dataset facilitates the validation of related methodology in the community and the proposed framework might aid the development of a fast, accessible screening method for pulmonary diseases. Dataset and all code are publicly available at: https://github.com/BorgwardtLab/covid19_ultrasound. View Full-Text
Keywords: computer vision; Convolutional neural network; COVID-19; deep learning; interpretability; pneumonia; Lung imaging; machine learning; medical imaging; ultrasound; supervised learning computer vision; Convolutional neural network; COVID-19; deep learning; interpretability; pneumonia; Lung imaging; machine learning; medical imaging; ultrasound; supervised learning
Show Figures

Figure 1

MDPI and ACS Style

Born, J.; Wiedemann, N.; Cossio, M.; Buhre, C.; Brändle, G.; Leidermann, K.; Aujayeb, A.; Moor, M.; Rieck, B.; Borgwardt, K. Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis. Appl. Sci. 2021, 11, 672. https://doi.org/10.3390/app11020672

AMA Style

Born J, Wiedemann N, Cossio M, Buhre C, Brändle G, Leidermann K, Aujayeb A, Moor M, Rieck B, Borgwardt K. Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis. Applied Sciences. 2021; 11(2):672. https://doi.org/10.3390/app11020672

Chicago/Turabian Style

Born, Jannis; Wiedemann, Nina; Cossio, Manuel; Buhre, Charlotte; Brändle, Gabriel; Leidermann, Konstantin; Aujayeb, Avinash; Moor, Michael; Rieck, Bastian; Borgwardt, Karsten. 2021. "Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis" Appl. Sci. 11, no. 2: 672. https://doi.org/10.3390/app11020672

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop