Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Oct 16;12(1):1647.
doi: 10.1038/s41597-025-05854-4.

Lung Ultrasound Imaging Dataset for Accurate Detection and Localization of LUS Vertical Artifact

Nixson Okila  1 , Andrew Katumba  2   3 , Joyce Nakatumba-Nabende  1   4 , Sudi Murindanyi  1   4 , Cosmas Mwikirize  5 , Jonathan Serugunda  5 , Samuel Bugeza  6 , Anthony Oriekot  7 , Juliet Bossa  8 , Eva Nabawanuka  8
Affiliations

Lung Ultrasound Imaging Dataset for Accurate Detection and Localization of LUS Vertical Artifact

Nixson Okila et al. Sci Data. .

Abstract

Lung ultrasound (LUS) vertical artifacts are critical sonographic markers commonly used in evaluating pulmonary conditions such as pulmonary edema, interstitial lung disease, pneumonia, and COVID-19. Accurate detection and localization of these artifacts are vital for informed clinical decision-making. However, interpreting LUS images remains highly operator-dependent, leading to variability in diagnosis. While deep learning (DL) models offer promising potential to automate LUS interpretation, their development is limited by the scarcity of annotated datasets specifically focused on vertical artifacts. This study introduces a curated dataset of 401 high-resolution LUS images, each annotated with polygonal bounding boxes to indicate vertical artifact locations. The images were collected from 152 patients with pulmonary conditions at Mulago and Kiruddu National Referral Hospitals in Uganda. This dataset serves as a valuable resource for training and evaluating DL models designed to accurately detect and localize LUS vertical artifacts, contributing to the advancement of AI-driven diagnostic tools for early detection and monitoring of respiratory diseases.

PubMed Disclaimer

Conflict of interest statement

Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Workflow for LUS-BALD dataset collection and curation. The process begins with ethical approval and data acquisition, followed by sequential stages of data filtering, image preprocessing, and detailed annotation.
Fig. 2
Fig. 2
Preprocessing step for removal of overlaid measurement scales and text labels from lung ultrasound images. (a) Input image with overlaid measurement scale and text labels. (b) Cropped image containing only the text labels, with the measurement scale removed.
Fig. 3
Fig. 3
Text label removal from lung ultrasound images. (a) Cropped image with overlaid text labels. (b) Processed image after text detection, masking, and inpainting, resulting in an image free of text labels.
Fig. 4
Fig. 4
Annotation using the VGG Image Annotator. The figure illustrates two instances of annotated lung ultrasound vertical artifacts.
Fig. 5
Fig. 5
Directory structure of the LUS-BALD dataset. The figure presents the hierarchical organization of files and folders within the LUS-BALD dataset.
See this image and copyright information in PMC

References

    1. Demi, L. et al. New international guidelines and consensus on the use of lung ultrasound. J. Ultrasound Med.42, 309–344 (2023). - PMC - PubMed
    1. Corradi, F., Via, G., Forfori, F., Brusasco, C. & Tavazzi, G. Lung ultrasound and LUS vertical artfacts quantification inaccuracy: B sure to have the right solution. Intensive Care Med.46, 1081–1083 (2020). - PMC - PubMed
    1. Mento, F., Soldati, G., Prediletto, R., Demi, M. & Demi, L. Quantitative lung ultrasound spectroscopy applied to the diagnosis of pulmonary fibrosis: The first clinical study. IEEE Trans. Ultrason. Ferroelectr. Freq. Control67, 2265–2273 (2020). - PubMed
    1. Baloescu, C. et al. Automated lung ultrasound B-line assessment using a deep learning algorithm. IEEE Trans. Ultrason. Ferroelectr. Freq. Control67, 2312–2320 (2020). - PubMed
    1. Lerchbaumer, M. H. et al. Lung ultrasound for early diagnosis and severity assessment of acute respiratory distress syndrome in the critically ill. Sci. Rep.11, 10678 (2021). - PMC - PubMed

LinkOut - more resources