Accurate assessment of the lung sliding artefact on lung ultrasonography using a deep learning approach

Blake VanBerlo; Derek Wu; Brian Li; Marwan A Rahman; Gregory Hogg; Bennett VanBerlo; Jared Tschirhart; Alex Ford; Jordan Ho; Joseph McCauley; Benjamin Wu; Jason Deglint; Jaswin Hargun; Rushil Chaudhary; Chintan Dave; Robert Arntfield

doi:10.1016/j.compbiomed.2022.105953

Accurate assessment of the lung sliding artefact on lung ultrasonography using a deep learning approach

Comput Biol Med. 2022 Sep:148:105953. doi: 10.1016/j.compbiomed.2022.105953. Epub 2022 Aug 9.

Authors

Affiliations

¹ Faculty of Mathematics, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
² Department of Medicine, Western University, London, ON N6A 5C1, Canada.
³ Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
⁴ Faculty of Engineering, University of Western Ontario, London, ON N6A 5C1, Canada.
⁵ Schulich School of Medicine and Dentistry, Western University, London, ON N6A 5C1, Canada.
⁶ Lawson Health Research Institute, London, ON N6C 2R5, Canada.
⁷ Department of Family Medicine, Western University, London, ON N6A 5C1, Canada.
⁸ Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada.
⁹ Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada. Electronic address: robert.arntfield@lhsc.on.ca.

PMID: 35985186
DOI: 10.1016/j.compbiomed.2022.105953

Abstract

Pneumothorax is a potentially life-threatening condition that can be rapidly and accurately assessed via the lung sliding artefact generated using lung ultrasound (LUS). Access to LUS is challenged by user dependence and shortage of training. Image classification using deep learning methods can automate interpretation in LUS and has not been thoroughly studied for lung sliding. Using a labelled LUS dataset from 2 academic hospitals, clinical B-mode (also known as brightness or two-dimensional mode) videos featuring both presence and absence of lung sliding were transformed into motion (M) mode images. These images were subsequently used to train a deep neural network binary classifier that was evaluated using a holdout set comprising 15% of the total data. Grad-CAM explanations were examined. Our binary classifier using the EfficientNetB0 architecture was trained using 2535 LUS clips from 614 patients. When evaluated on a test set of data uninvolved in training (540 clips from 124 patients), the model performed with a sensitivity of 93.5%, specificity of 87.3% and an area under the receiver operating characteristic curve (AUC) of 0.973. Grad-CAM explanations confirmed the model's focus on relevant regions on M-mode images. Our solution accurately distinguishes between the presence and absence of lung sliding artefacts on LUS.

Keywords: Classification; Deep learning; Explainable AI; Lung sliding; Machine learning; POCUS; Pneumothorax; Point-of care-ultrasound; Ultrasound.

MeSH terms

Artifacts
Deep Learning*
Humans
Lung
Pneumothorax*
Ultrasonography