Deep learning for accurate B-line detection and localization in lung ultrasound imaging
The integration of these models into a mobile LUS screening tool provides a promising solution for B-line localization in resource-limited settings, where accessibility to trained professionals may be scarce. The YOLOv5-PBB and YOLOv8-PBB models offer high performance while addressing challenges related to inference speed and model size, making them ideal candidates for mobile deployment in such environments.
Authors
- Cosmas Mwikirize (ORCID: https://orcid.org/0000-0002-3393-2758)
- Anthony Oriekot
- Eva Nabawanuka (ORCID: https://orcid.org/0000-0002-8605-0951)
- Andrew Katumba (ORCID: https://orcid.org/0000-0001-7699-8426)
- Joyce Nakatumba‐Nabende (ORCID: https://orcid.org/0000-0002-0108-3798)
- Jonathan Serugunda (ORCID: https://orcid.org/0000-0003-3952-2546)
- Samuel Bugeza
- Sudi Murindanyi (ORCID: https://orcid.org/0009-0001-3667-5814)
- Nixson Okila (ORCID: https://orcid.org/0009-0006-2899-829X)
- Juliet Bossa
Institutions
- Mulago Hospital (UG)
- Makerere University (UG)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-04-22
- DOI
- https://doi.org/10.3389/frai.2025.1560523
- Citations
- 3
- Primary Topic
- Ultrasound in Clinical Applications
- Type
- article
- Field-Weighted Citation Impact
- 4.64
Funders
- International Development Research Centre