EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Lung ultrasound interpretation using deep learning for the detection of B-lines in dogs

Jessica L Ward iD, Blake VanBerlo iD, Benjamin Huggard iD, Delaney Smith iD, Robert Arntfield iD

Journal of Veterinary Internal Medicine · 01.07.2026 · 40 (4)

DOI: 10.1093/jvimsj/aalag152 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Veterinary Internal Medicine, online erschienen am 22.07.2026. Verfasst von Jessica L Ward und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Veterinary Clinical Sciences, College of Veterinary Medicine, Iowa State University, Ames, IA 50011, United States. Hauptthemen laut MEDLINE: Deep Learning, Lung, Dog Diseases. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Deep learning (DL) shows promise for interpretation of lung ultrasound (LUS) images in humans, but its performance in animals remains underexplored. Hypothesis/Objectives Assess performance of a B-line detection algorithm (BLDA) trained on LUS images from humans when applied to images from dogs. Animals A total of 1,950 clips collected from 201 LUS examinations in 90 dogs across 4 studies.

Methods

Ultrasound clips were collated and labeled with A-line or B-line profiles by an expert reviewer. A DL model previously trained on LUS images from humans was applied to detect presence of B-lines at a framewise level. A clip classification algorithm was calibrated to maximize clip-level performance of the BLDA using a calibration data set. Performance of the DL model and BLDA was assessed on a held-out test set of LUS images. A heatmap-based explainability method was used to visualize regions most utilized by the model for predictions.

Results

When applied to the test set, the BLDA showed an overall accuracy of 87%, with sensitivity of 73% and specificity of 93%. The algorithm performed best when identifying images with strong (versus weak) B-line profiles. Assessing raw model predictions, zero-shot performance for identification of B-lines was excellent (area under the curve, 0.96). Heatmaps suggested that the DL model utilized image areas that were plausibly relevant for LUS interpretation. Conclusions and clinical importance A LUS model trained on images from humans maintained strong performance when applied to dogs, supporting cross-species generalization to accelerate veterinary diagnostic innovations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningLungDog DiseasesAnimalsDogsUltrasonographySensitivity and SpecificityAlgorithmsDetection Algorithms

Stichwörter der Autor:innen

artificial intelligencecaninecardiologyrespiratory

Autor:innen und Institutionen

  • Department of Veterinary Clinical Sciences, College of Veterinary Medicine, Iowa State University, Ames, IA 50011, United States.
  • Deep Breathe, London, ON N6A 1B8, Canada.
  • Division of Critical Care Medicine, Schulich School of Medicine and Dentistry, Western University, London, ON N6A 5W9, Canada.

ORCID-Profile: Jessica L Ward, Blake VanBerlo, Benjamin Huggard, Delaney Smith, Robert Arntfield

Zitieren

APA

Ward, J. L., VanBerlo, B., Huggard, B., Smith, D., & Arntfield, R. (2026). Lung ultrasound interpretation using deep learning for the detection of B-lines in dogs. Journal of Veterinary Internal Medicine, 40(4). https://doi.org/10.1093/jvimsj/aalag152

Vancouver

Ward JL, VanBerlo B, Huggard B, Smith D, Arntfield R. Lung ultrasound interpretation using deep learning for the detection of B-lines in dogs. Journal of Veterinary Internal Medicine. 2026;40(4). doi:10.1093/jvimsj/aalag152

BibTeX
@article{Ward2026,
  author = {Ward, Jessica L and VanBerlo, Blake and Huggard, Benjamin and Smith, Delaney and Arntfield, Robert},
  title = {Lung ultrasound interpretation using deep learning for the detection of B-lines in dogs},
  journal = {Journal of Veterinary Internal Medicine},
  year = {2026},
  volume = {40},
  number = {4},
  doi = {10.1093/jvimsj/aalag152}
}
Kostenlos starten →