Semi-supervised Ensemble Learning for Automatic Interpretation of Lung Ultrasound Videos
Journal of Imaging Informatics in Medicine · 2024
DOI: 10.1007/s10278-024-01344-y ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2024. Verfasst von Bárbara Malainho und 7 weiteren Autor:innen. Beteiligte Einrichtung: Life and Health Sciences Research Institute, School of Medicine, University of Minho, Braga, Portugal. Hauptthemen laut MEDLINE: Lung, Deep Learning, Image Interpretation, Computer-Assisted, Supervised Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação para a Ciência e a Tecnologia.
Abstract (Originalsprache)
Point-of-care ultrasound (POCUS) stands as a safe, portable, and cost-effective imaging modality for swift bedside patient examinations. Specifically, lung ultrasonography (LUS) has proven useful in evaluating both acute and chronic pulmonary conditions. Despite its clinical value, automatic LUS interpretation remains relatively unexplored, particularly in multi-label contexts. This work proposes a novel deep learning (DL) framework tailored for interpreting lung POCUS videos, whose outputs are the finding(s) present in these videos (such as A-lines, B-lines, or consolidations). The pipeline, based on a residual (2+1)D architecture, initiates with a pre-processing routine for video masking and standardisation, and employs a semi-supervised approach to harness available unlabeled data. Additionally, we introduce an ensemble modeling strategy that aggregates outputs from models trained to predict distinct label sets, thereby leveraging the hierarchical nature of LUS findings. The proposed framework and its building blocks were evaluated through extensive experiments with both multi-class and multi-label models, highlighting its versatility. In a held-out test set, the categorical proposal, suited for expedite triage, achieved an average F1-score of 92.4%, while the multi-label proposal, helpful for patient management and referral, achieved an average F1-score of 70.5% across five relevant LUS findings. Overall, the semi-supervised methodology contributed significantly to improved performance, while the proposed hierarchy-aware ensemble provided moderate additional gains.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Life and Health Sciences Research Institute, School of Medicine, University of Minho, Braga, Portugal.
- ICVS/3B's - PT Government Associate Laboratory, Braga/Guimarães, Portugal.
- Algoritmi Center, School of Engineering, University of Minho, Guimarães, Portugal.
- Department of Internal Medicine, Hospital Clínicas de Porto Alegre, Porto Alegre, Brazil.
- Institute of Computing, University of Campinas, São Paulo, Brazil.
- Wenckebach Institute, Research program LEARN, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
Förderung
- Fundação para a Ciência e a Tecnologia
Zitieren
APA
Malainho, B., Freitas, J., Rodrigues, C., Tonelli, A. C., Santanchè, A., Carvalho-Filho, M. A., Fonseca, J. C., & Queirós, S. (2024). Semi-supervised Ensemble Learning for Automatic Interpretation of Lung Ultrasound Videos. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-024-01344-y
Vancouver
Malainho B, Freitas J, Rodrigues C, Tonelli AC, Santanchè A, Carvalho-Filho MA, et al. Semi-supervised Ensemble Learning for Automatic Interpretation of Lung Ultrasound Videos. Journal of Imaging Informatics in Medicine. 2024. doi:10.1007/s10278-024-01344-y
BibTeX
@article{Malainho2024,
author = {Malainho, Bárbara and Freitas, João and Rodrigues, Catarina and Tonelli, Ana Claudia and Santanchè, André and Carvalho-Filho, Marco A and Fonseca, Jaime C and Queirós, Sandro},
title = {Semi-supervised Ensemble Learning for Automatic Interpretation of Lung Ultrasound Videos},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
doi = {10.1007/s10278-024-01344-y}
}
EUVIMED