A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal

To advance the automated interpretation of lung ultrasound (LUS) data, multiple deep learning (DL) models have been introduced to identify LUS patterns for differentiating COVID-19, Pneumonia, and Normal cases. While these models have generally yielded promising outcomes, they have encountered chall...

Full description

Saved in:
Bibliographic Details
Main Authors: Shereen Morsy, Neveen Abd-Elsalam, Ahmed Khandil, Ahmed Elbialy, Abou-Bakr Youssef
Format: Article
Language:English
Published: Universitas Ahmad Dahlan 2025-02-01
Series:IJAIN (International Journal of Advances in Intelligent Informatics)
Subjects:
Online Access:https://ijain.org/index.php/IJAIN/article/view/1966
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850240702304223232
author Shereen Morsy
Neveen Abd-Elsalam
Ahmed Khandil
Ahmed Elbialy
Abou-Bakr Youssef
author_facet Shereen Morsy
Neveen Abd-Elsalam
Ahmed Khandil
Ahmed Elbialy
Abou-Bakr Youssef
author_sort Shereen Morsy
collection DOAJ
description To advance the automated interpretation of lung ultrasound (LUS) data, multiple deep learning (DL) models have been introduced to identify LUS patterns for differentiating COVID-19, Pneumonia, and Normal cases. While these models have generally yielded promising outcomes, they have encountered challenges in accurately classifying each pattern across diverse cases. Therefore, this study introduces an ensemble framework that leverages multiple classification models, optimizing their contributions to the final prediction through a majority voting mechanism. After training seven different classification models, the three models with the highest accuracies were selected. The ensemble incorporates these top-performing models: EfficientNetV2-B0, EfficientNetV2-B2, and EfficientNetV2-B3, and utilizes this framework to classify patterns in LUS images. Compared to individual model performance, the ensemble approach significantly enhances classification accuracy, achieving an accuracy of 99.25% and an F1-score of 99%. In contrast, the standalone models attained accuracies of 97.8%, 97.6%, and 98.1%, with F1-score of approximately 98%. This research highlights the potential of ensemble learning for improving the accuracy and robustness of automated LUS analysis, offering a practical and scalable solution for real-world medical diagnostics. By combining the strengths of multiple models, the proposed framework paves the way for more reliable and efficient tools to assist clinicians in diagnosing lung diseases.
format Article
id doaj-art-e2ea410263ba46b9bac6697dbdeb1cb8
institution OA Journals
issn 2442-6571
2548-3161
language English
publishDate 2025-02-01
publisher Universitas Ahmad Dahlan
record_format Article
series IJAIN (International Journal of Advances in Intelligent Informatics)
spelling doaj-art-e2ea410263ba46b9bac6697dbdeb1cb82025-08-20T02:00:47ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612025-02-0111114315610.26555/ijain.v11i1.1966326A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normalShereen Morsy0Neveen Abd-Elsalam1Ahmed Khandil2Ahmed Elbialy3Abou-Bakr Youssef4Systems and Biomedical Engineering, Cairo UniversitySystems and Biomedical Engineering, Cairo UniversitySystems and Biomedical Engineering, Cairo UniversitySystems and Biomedical Engineering, Cairo University; and Shorouk AcademySystems and Biomedical Engineering, Cairo UniversityTo advance the automated interpretation of lung ultrasound (LUS) data, multiple deep learning (DL) models have been introduced to identify LUS patterns for differentiating COVID-19, Pneumonia, and Normal cases. While these models have generally yielded promising outcomes, they have encountered challenges in accurately classifying each pattern across diverse cases. Therefore, this study introduces an ensemble framework that leverages multiple classification models, optimizing their contributions to the final prediction through a majority voting mechanism. After training seven different classification models, the three models with the highest accuracies were selected. The ensemble incorporates these top-performing models: EfficientNetV2-B0, EfficientNetV2-B2, and EfficientNetV2-B3, and utilizes this framework to classify patterns in LUS images. Compared to individual model performance, the ensemble approach significantly enhances classification accuracy, achieving an accuracy of 99.25% and an F1-score of 99%. In contrast, the standalone models attained accuracies of 97.8%, 97.6%, and 98.1%, with F1-score of approximately 98%. This research highlights the potential of ensemble learning for improving the accuracy and robustness of automated LUS analysis, offering a practical and scalable solution for real-world medical diagnostics. By combining the strengths of multiple models, the proposed framework paves the way for more reliable and efficient tools to assist clinicians in diagnosing lung diseases.https://ijain.org/index.php/IJAIN/article/view/1966covid-19pneumoniadeep learningtransfer learningensemble method
spellingShingle Shereen Morsy
Neveen Abd-Elsalam
Ahmed Khandil
Ahmed Elbialy
Abou-Bakr Youssef
A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
IJAIN (International Journal of Advances in Intelligent Informatics)
covid-19
pneumonia
deep learning
transfer learning
ensemble method
title A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
title_full A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
title_fullStr A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
title_full_unstemmed A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
title_short A deep learning ensemble framework for robust classification of lung ultrasound patterns: covid-19, pneumonia, and normal
title_sort deep learning ensemble framework for robust classification of lung ultrasound patterns covid 19 pneumonia and normal
topic covid-19
pneumonia
deep learning
transfer learning
ensemble method
url https://ijain.org/index.php/IJAIN/article/view/1966
work_keys_str_mv AT shereenmorsy adeeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT neveenabdelsalam adeeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT ahmedkhandil adeeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT ahmedelbialy adeeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT aboubakryoussef adeeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT shereenmorsy deeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT neveenabdelsalam deeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT ahmedkhandil deeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT ahmedelbialy deeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal
AT aboubakryoussef deeplearningensembleframeworkforrobustclassificationoflungultrasoundpatternscovid19pneumoniaandnormal