Lung ultrasound interpretation using deep learning for the detection of B-lines in dogs.
Authors
Affiliations (3)
Affiliations (3)
- 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.
Abstract
Deep learning (DL) shows promise for interpretation of lung ultrasound (LUS) images in humans, but its performance in animals remains underexplored. Assess performance of a B-line detection algorithm (BLDA) trained on LUS images from humans when applied to images from dogs. A total of 1,950 clips collected from 201 LUS examinations in 90 dogs across 4 studies. 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. 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. A LUS model trained on images from humans maintained strong performance when applied to dogs, supporting cross-species generalization to accelerate veterinary diagnostic innovations.