Federated Active Learning with Transfer Learning: Empowering Edge Intelligence for Enhanced Lung Cancer Diagnosis

Federated Learning has emerged as a promising paradigm for collaborative model training in healthcare. FL allows institutions to share knowledge without compromising patient privacy. However, data annotation remains a bottleneck, especially in medical image studies. This work proposes a Federated Active Learning with a Transfer Learning framework for efficient labeling in lung cancer diagnosis. Using ensemble entropy-based uncertainty assessment, FAL-TL streamlines sample annotation, optimizing training across distributed healthcare institutions while safeguarding patient privacy. Using the IQOTH/NCCD Lung Cancer and Chest CT-Scan images Dataset, our FAL-TL framework achieves an impressive 99.20% accuracy, surpassing traditional machine learning models. By integrating transfer learning, FAL-TL adapts pre-trained models to healthcare datasets, significantly enhancing diagnostic accuracy. This research contributes to advancing FL techniques in healthcare, offering a scalable and privacy-preserving solution with transformative implications for diagnostics and patient care.