EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DMFL_Net: A Federated Learning-Based Framework for the Classification of COVID-19 from Multiple Chest Diseases Using X-rays

Hassaan Malik iD, Ahmad Naeem iD, Rizwan Ali Naqvi iD, Woong-Kee Loh

Sensors · 09.01.2023 · 23 (2) · 743

DOI: 10.3390/s23020743 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.01.2023. Verfasst von Hassaan Malik und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Management and Technology, Lahore 54000, Pakistan. Hauptthemen laut MEDLINE: COVID-19, Lung Neoplasms. Die Arbeit wurde bisher 98-mal zitiert (Crossref) und nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, national research foundation (NRF), Ministry of Science and ICT (MSIT), South Korea through the Development Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coronavirus Disease 2019 (COVID-19) is still a threat to global health and safety, and it is anticipated that deep learning (DL) will be the most effective way of detecting COVID-19 and other chest diseases such as lung cancer (LC), tuberculosis (TB), pneumothorax (PneuTh), and pneumonia (Pneu). However, data sharing across hospitals is hampered by patients’ right to privacy, leading to unexpected results from deep neural network (DNN) models. Federated learning (FL) is a game-changing concept since it allows clients to train models together without sharing their source data with anybody else. Few studies, however, focus on improving the model’s accuracy and stability, whereas most existing FL-based COVID-19 detection techniques aim to maximize secondary objectives such as latency, energy usage, and privacy. In this work, we design a novel model named decision-making-based federated learning network (DMFL_Net) for medical diagnostic image analysis to distinguish COVID-19 from four distinct chest disorders including LC, TB, PneuTh, and Pneu. The DMFL_Net model that has been suggested gathers data from a variety of hospitals, constructs the model using the DenseNet-169, and produces accurate predictions from information that is kept secure and only released to authorized individuals. Extensive experiments were carried out with chest X-rays (CXR), and the performance of the proposed model was compared with two transfer learning (TL) models, i.e., VGG-19 and VGG-16 in terms of accuracy (ACC), precision (PRE), recall (REC), specificity (SPF), and F1-measure. Additionally, the DMFL_Net model is also compared with the default FL configurations. The proposed DMFL_Net + DenseNet-169 model achieves an accuracy of 98.45% and outperforms other approaches in classifying COVID-19 from four chest diseases and successfully protects the privacy of the data among diverse clients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Lung NeoplasmsHumansX-RaysRadiographyThoraxHospitals

Stichwörter der Autor:innen

COVID-19TBdata privacyfederated learninglung cancermachine learning

Autor:innen und Institutionen

  • Department of Computer Science, University of Management and Technology, Lahore 54000, Pakistan.
  • Department of Unmanned Vehicle Engineering, Sejong University, Seoul 05006, Republic of Korea.
  • School of Computing, Gachon University, Seongnam 13120, Republic of Korea.

ORCID-Profile: Hassaan Malik, Ahmad Naeem, Rizwan Ali Naqvi

Förderung

  • National Research Foundation of Korea
  • national research foundation (NRF)
  • Ministry of Science and ICT (MSIT), South Korea through the Development Research

Zitieren

APA

Malik, H., Naeem, A., Naqvi, R. A., & Loh, W. K. (2023). DMFL_Net: A Federated Learning-Based Framework for the Classification of COVID-19 from Multiple Chest Diseases Using X-rays. Sensors, 23(2), 743. https://doi.org/10.3390/s23020743

Vancouver

Malik H, Naeem A, Naqvi RA, Loh WK. DMFL_Net: A Federated Learning-Based Framework for the Classification of COVID-19 from Multiple Chest Diseases Using X-rays. Sensors. 2023;23(2):743. doi:10.3390/s23020743

BibTeX
@article{Malik2023,
  author = {Malik, Hassaan and Naeem, Ahmad and Naqvi, Rizwan Ali and Loh, Woong-Kee},
  title = {DMFL_Net: A Federated Learning-Based Framework for the Classification of COVID-19 from Multiple Chest Diseases Using X-rays},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {2},
  pages = {743},
  doi = {10.3390/s23020743}
}
Kostenlos starten →