applsci-11-11697.pdf (2.54 MB)
B-line detection and localization in lung ultrasound videos using spatiotemporal attention
journal contribution
posted on 2023-06-10, 04:40 authored by Hamideh Kerdegari, Nhat T H Phung, Angela McBride, Luigi Pisani, Hao Van Nguyen, Thuy B Duong, Reza Razavi, Louise Thwaites, Sophie Yacoub, Alberto GomezThe 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.
History
Publication status
- Published
File Version
- Published version
Journal
Applied Sciences (Switzerland)ISSN
1454-5101Publisher
MDPI AGExternal DOI
Issue
24Volume
11Page range
a11697 1-14Department affiliated with
- Global Health and Infection Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2022-09-06First Open Access (FOA) Date
2022-09-06First Compliant Deposit (FCD) Date
2022-09-05Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC