Automated Lung Ultrasound B-Line Assessment Using a Deep Learning Algorithm

Abstract

Shortness of breath is a major reason that patients present to the emergency department (ED) and point-of-care ultrasound (POCUS) has been shown to aid in diagnosis, particularly through evaluation for artifacts known as B-lines. B-line identification and quantification can be a challenging skill for novice ultrasound users, and experienced users could benefit from a more objective measure of quantification. We sought to develop and test a deep learning (DL) algorithm to quantify the assessment of B-lines in lung ultrasound. We utilized ultrasound clips ( n = 400 ) from an existing database of ED patients to provide training and test sets to develop and test the DL algorithm based on deep convolutional neural networks. Interpretations of the images by algorithm were compared to expert human interpretations on binary and severity (a scale of 0-4) classifications. Our model yielded a sensitivity of 93% (95% confidence interval (CI) 81%-98%) and a specificity of 96% (95% CI 84%-99%) for the presence or absence of B-lines compared to expert read, with a kappa of 0.88 (95% CI 0.79-0.97). Model to expert agreement for severity classification yielded a weighted kappa of 0.65 (95% CI 0.56-074). Overall, the DL algorithm performed well and could be integrated into an ultrasound system in order to help diagnose and track B-line severity. The algorithm is better at distinguishing the presence from the absence of B-lines but can also be successfully used to distinguish between B-line severity. Such methods could decrease variability and provide a standardized method for improved diagnosis and outcome.