Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis

TLDR

Fast, safe, highly sensitive diagnostic tools are essential during the COVID‑19 pandemic, and lung ultrasound offers practical advantages but poses pattern‑recognition challenges for clinicians. The study aims to use machine learning to guide diagnosis from lung ultrasound and to evaluate deep learning methods for differentiating lung pathologies. We release the largest publicly available LUS dataset of 202 videos across four classes, train a frame‑based deep learning model, apply spatio‑temporal interpretability for biomarker localization, and incorporate uncertainty estimation, with all data and code publicly available. The model achieves high sensitivity and specificity (≈0.90/0.96 on training data, 0.81/0.96 on an independent test), correctly identifies low‑confidence cases, and the publicly released dataset and framework support community validation and rapid pulmonary disease screening.

Abstract

Care during the COVID-19 pandemic hinges upon the existence of fast, safe, and highly sensitive diagnostic tools. Considering significant practical advantages of lung ultrasound (LUS) over other imaging techniques, but difficulties for doctors in pattern recognition, we aim to leverage machine learning toward guiding diagnosis from LUS. We release the largest publicly available LUS dataset for COVID-19 consisting of 202 videos from four classes (COVID-19, bacterial pneumonia, non-COVID-19 viral pneumonia and healthy controls). On this dataset, we perform an in-depth study of the value of deep learning methods for the differential diagnosis of lung pathologies. We propose a frame-based model that correctly distinguishes COVID-19 LUS videos from healthy and bacterial pneumonia data with a sensitivity of 0.90±0.08 and a specificity of 0.96±0.04. To investigate the utility of the proposed method, we employ interpretability methods for the spatio-temporal localization of pulmonary biomarkers, which are deemed useful for human-in-the-loop scenarios in a blinded study with medical experts. Aiming for robustness, we perform uncertainty estimation and demonstrate the model to recognize low-confidence situations which also improves performance. Lastly, we validated our model on an independent test dataset and report promising performance (sensitivity 0.806, specificity 0.962). The provided dataset facilitates the validation of related methodology in the community and the proposed framework might aid the development of a fast, accessible screening method for pulmonary diseases. Dataset and all code are publicly available at: https://github.com/BorgwardtLab/covid19_ultrasound.