Evaluating deep learning approaches for AI-assisted lung ultrasound diagnosis: an international multi-center and multi-scanner study.
Authors
Affiliations (7)
Affiliations (7)
- Institute for Physical and Information Technologies, Spanish National Research Council, Madrid, Spain. [email protected].
- Electronic Department, Universidad de Alcalá, Madrid, Spain. [email protected].
- Department of Information Engineering and Computer Science, University of Trento, Trento, Italy.
- Institute for Physical and Information Technologies, Spanish National Research Council, Madrid, Spain.
- Medicina Interna e Medicina d'Urgenza, Humanitas Gavazzeni, Bergamo, Italia.
- Dipartimento Neuroscienze, Organi di Senso e Torace, UOC Pneumologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
- Department of Internal Medicine, Hospital Universitario La Paz, Madrid, Spain.
Abstract
Lung ultrasound (LUS) interpretation is often subjective and operator-dependent, motivating the development of automated, artificial intelligence (AI)-based methods. This international, multi-center study evaluated two distinct deep learning approaches for automated LUS severity scoring for pulmonary infections caused by COVID-19: a pre-trained classification model (CM) and a segmentation model based method (SM); assessing performance at video, exam, and prognostic levels. Two datasets were analyzed: one comprising data from multiple scanners and another using data from a single scanner. Results showed that the SM achieved prognostic-level agreement with expert clinicians comparable to that of the CM. Furthermore, at the exam level, over 84% of examinations were classified with acceptable error (≤ 10 score difference) across both models and datasets, reaching both methods an agreement higher than 95% on the dataset acquired by a single scanner. The obtained results demonstrate the potential of AI-assisted LUS for reliable prognostic assessment and highlight that image quality and acquisition technique are key factors in achieving consistent and generalizable model performance, as well as the potential for international clinical translations.