EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Federated Learning for Thoracic Disease Classification Using Convolutional Neural Networks and Differential Privacy

Muhammad Zulqarnain, Syed Jawad Hussain, Muhammad Zeeshan Aslam, Ahsan Fiaz iD, Muhammad Islam iD

Healthcare Technology Letters · 2026-01 · 13 (1)

DOI: 10.1049/htl2.70080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 02.05.2026. Verfasst von Muhammad Zulqarnain und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science Sir Syed CASE Institute of Technology Islamabad Pakistan. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early diagnosis of thoracic diseases using chest x‐ray imaging remains a critical challenge, particularly in resource‐constrained healthcare environments where data sharing is restricted due to privacy concerns. Federated learning (FL) offers a decentralized solution by enabling collaborative model training without sharing sensitive patient data. However, integrating privacy‐preserving mechanisms such as differential privacy (DP) introduces additional challenges related to performance degradation and computational overhead. In this study, we present a unified FL framework for multi‐label thoracic disease classification using multiple convolutional neural network (CNN) architectures, including ResNet50, DenseNet169, EfficientNet variants and MobileNetV3. Unlike prior studies focusing on single‐model evaluation, this work provides a controlled comparative analysis under identical FL settings and investigates the impact of client scalability (5–10 clients) on model performance. Furthermore, we conduct a comprehensive empirical analysis of the privacy utility trade‐off by integrating DP with varying privacy budgets ( ε = 1, 15 and 30). Experimental results on the CheXpert and NIH Chest x‐ray14 datasets demonstrate that the proposed EfficientNet‐B3‐based federated model achieves a mean AUC of 0.8027, while maintaining robustness across decentralized settings. The integration of DP leads to a predictable reduction in performance, with mean AUC ranging from 0.60 to 0.64, highlighting the inherent trade‐off between privacy and diagnostic accuracy. The findings emphasize the practical viability of FL for privacy‐sensitive medical imaging applications and provide insights into model selection, scalability and privacy configuration for real‐world deployment. The source code for this study is publicly accessible at https://github.com/Zulqarnain8‐8/FEDERATED_LEARNING_FOR_THORACIC_DISEASE_CLASSIFICATION .

Schlagwörter

Stichwörter der Autor:innen

convolutional neural networks (CNNs)differential privacy (DP)federated learning (FL)healthcare AImedical imagingmulti‐label classificationremote healthcarex‐ray diagnosis

Autor:innen und Institutionen

  • Department of Computer Science Sir Syed CASE Institute of Technology Islamabad Pakistan.
  • Department of Computing Institute of Space Technology Islamabad Pakistan.
  • College of Science and Engineering James Cook University Cairns Queensland Australia.

ORCID-Profile: Ahsan Fiaz, Muhammad Islam

Zitieren

APA

Zulqarnain, M., Hussain, S. J., Aslam, M. Z., Fiaz, A., & Islam, M. (2026). Federated Learning for Thoracic Disease Classification Using Convolutional Neural Networks and Differential Privacy. Healthcare Technology Letters, 13(1). https://doi.org/10.1049/htl2.70080

Vancouver

Zulqarnain M, Hussain SJ, Aslam MZ, Fiaz A, Islam M. Federated Learning for Thoracic Disease Classification Using Convolutional Neural Networks and Differential Privacy. Healthcare Technology Letters. 2026;13(1). doi:10.1049/htl2.70080

BibTeX
@article{Zulqarnain2026,
  author = {Zulqarnain, Muhammad and Hussain, Syed Jawad and Aslam, Muhammad Zeeshan and Fiaz, Ahsan and Islam, Muhammad},
  title = {Federated Learning for Thoracic Disease Classification Using Convolutional Neural Networks and Differential Privacy},
  journal = {Healthcare Technology Letters},
  year = {2026},
  volume = {13},
  number = {1},
  doi = {10.1049/htl2.70080}
}
Kostenlos starten →