Next Article in Journal
YOLOv4-MN3 for PCB Surface Defect Detection
Next Article in Special Issue
Ultrasound Localization Microscopy in Liquid Metal Flows
Previous Article in Journal
Static and Seismic Responses of Eco-Friendly Buried Concrete Pipes with Various Dosages of Fly Ash
Previous Article in Special Issue
Reflection-Mode Ultrasound Computed Tomography Based on Wavelet Processing for High-Contrast Anatomical and Morphometric Imaging
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 11
Issue 24
10.3390/app112411697
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention

by
Hamideh Kerdegari
1,*,
Nhat Tran Huy Phung
1,2,
Angela McBride
2,
Luigi Pisani
3,
Hao Van Nguyen
4,
Thuy Bich Duong
4,
Reza Razavi
1,
Louise Thwaites
2,
Sophie Yacoub
2,
Alberto Gomez
1 and
VITAL Consortium
†
1
School of Biomedical Engineering & Imaging Sciences, King’s College London, London SE1 7EU, UK
2
Oxford University Clinical Research Unit (OUCRU), Ho Chi Minh City 700000, Vietnam
3
Mahidol Oxford Tropical Medicine Research Unit (MORU), Bangkok 10400, Thailand
4
Hospital of Tropical Diseases, Ho Chi Minh City 700000, Vietnam
*
Author to whom correspondence should be addressed.
†
Membership of the VITAL Consortium is provided in the Acknowledgments.
Appl. Sci. 2021, 11(24), 11697; https://doi.org/10.3390/app112411697
Submission received: 11 November 2021 / Revised: 26 November 2021 / Accepted: 30 November 2021 / Published: 9 December 2021
(This article belongs to the Special Issue Computational Ultrasound Imaging and Applications)
Browse Figures
Versions Notes

Abstract

The presence of B-line artefacts, the main artefact reflecting lung abnormalities in dengue patients, is often assessed using lung ultrasound (LUS) imaging. Inspired by human visual attention that enables us to process videos efficiently by paying attention to where and when it is required, we propose a spatiotemporal attention mechanism for B-line detection in LUS videos. The spatial attention allows the model to focus on the most task relevant parts of the image by learning a saliency map. The temporal attention generates an attention score for each attended frame to identify the most relevant frames from an input video. Our model not only identifies videos where B-lines show, but also localizes, within those videos, B-line related features both spatially and temporally, despite being trained in a weakly-supervised manner. We evaluate our approach on a LUS video dataset collected from severe dengue patients in a resource-limited hospital, assessing the B-line detection rate and the model’s ability to localize discriminative B-line regions spatially and B-line frames temporally. Experimental results demonstrate the efficacy of our approach for classifying B-line videos with an F1 score of up to 83.2% and localizing the most salient B-line regions both spatially and temporally with a correlation coefficient of 0.67 and an IoU of 69.7%, respectively.
Keywords: lung ultrasound (LUS) imaging; b-lines; spatiotemporal attention; classification; video analysis lung ultrasound (LUS) imaging; b-lines; spatiotemporal attention; classification; video analysis

Share and Cite

MDPI and ACS Style

Kerdegari, H.; Phung, N.T.H.; McBride, A.; Pisani, L.; Nguyen, H.V.; Duong, T.B.; Razavi, R.; Thwaites, L.; Yacoub, S.; Gomez, A.; et al. B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention. Appl. Sci. 2021, 11, 11697. https://doi.org/10.3390/app112411697

AMA Style

Kerdegari H, Phung NTH, McBride A, Pisani L, Nguyen HV, Duong TB, Razavi R, Thwaites L, Yacoub S, Gomez A, et al. B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention. Applied Sciences. 2021; 11(24):11697. https://doi.org/10.3390/app112411697

Chicago/Turabian Style

Kerdegari, Hamideh, Nhat Tran Huy Phung, Angela McBride, Luigi Pisani, Hao Van Nguyen, Thuy Bich Duong, Reza Razavi, Louise Thwaites, Sophie Yacoub, Alberto Gomez, and et al. 2021. "B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention" Applied Sciences 11, no. 24: 11697. https://doi.org/10.3390/app112411697

APA Style

Kerdegari, H., Phung, N. T. H., McBride, A., Pisani, L., Nguyen, H. V., Duong, T. B., Razavi, R., Thwaites, L., Yacoub, S., Gomez, A., & VITAL Consortium. (2021). B-Line Detection and Localization in Lung Ultrasound Videos Using Spatiotemporal Attention. Applied Sciences, 11(24), 11697. https://doi.org/10.3390/app112411697

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop