A Distributed Federated Learning Approach for Accurate Lung Cancer Detection

DOI

10.2991/978-94-6239-756-9_20How to use a DOI?

Keywords

Cancer detection; ML Models; Federated Learning framework

Abstract

Across the world, Cancer is one of the most dangerous diseases and which may cause death. Early and accurate diagnosis of the cancer may reduce the effect on patient health. For lung cancer prediction, machine learning models have historically depended on centralized datasets. Because of data governance regulations, institutional silos, and privacy restrictions centralized datasets are extremely challenging to consolidate data. For both diagnostic purposes and lung cancer screening the dataset of PET-CT DICOM and thoracic computed tomography (CT) images is intended. Using a thoracic PET-CT DICOM and computed tomography images dataset we propose a Federated Learning (FL) framework tailored for lung cancer classification and detection. Compared to the traditional centralized training model our results shows that the Federated Learning model produces improved detection accuracy and reliability and also respect data privacy regulations like Europe’s General Data Protection Regulation (GDPR) and US’s Health Insurance Portability and Accountability Act (HIPAA). In terms of metrics such as accuracy, sensitivity and specificity experimental results demonstrate that FL-based models exhibit comparable performance to centralized models and also maintain robust privacy safeguards. For lung cancer, this work demonstrates the feasibility and clinical significance of Federated Learning (FL), paving the way for secure, collaborative AI development that can accelerate early detection, treatment personalization, and improved survival outcomes in patients.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nilesh Sonawane
AU  - Madhuri Hiwale
PY  - 2026
DA  - 2026/08/31
TI  - A Distributed Federated Learning Approach for Accurate Lung Cancer Detection
BT  - Proceedings of the Conference on Bioengineering for Global Health (SYMRESEARCH 2.0 2025)
PB  - Atlantis Press
SP  - 282
EP  - 294
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6239-756-9_20
DO  - 10.2991/978-94-6239-756-9_20
ID  - Sonawane2026
ER  -