Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 7, 2026International Journal of Advanced Computer Science and ApplicationsOpen Access

Privacy-Preserving Federated Learning for Multi-Institutional Lung Cancer Severity Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

CSCh. SrividyaKRK. RamasubramanianMBMyneni.Madhu Bala

Discussion

Loading...

Member takes

Overview

Develops a privacy-preserving framework for lung cancer severity detection across institutions, suggesting robust AI collaboration is achievable while maintaining patient data privacy.

Key Points

  • To develop a framework for accurate lung cancer severity detection while ensuring data privacy across multiple clinical institutions.
  • Introduced a privacy-preserving federated neural ensemble model (PP-FNE).
  • Developed a gradient boosting-based federated learning strategy (MIF-GBF).
  • Created a hybrid convolutional-transformer network (CF-CTN).
  • Established a semi-adaptive federated attention-aggregated model (SAFAM).
  • Evaluated the framework using a synthetic dataset representing clinical heterogeneity.
  • The SAFAM model achieved an overall classification accuracy of 93.4%.
  • The model demonstrated robustness with only a 1.3% accuracy degradation under noise.
  • Strong privacy protection was maintained using encrypted model updates.
  • All models exhibited effective interpretability and adherence to HIPAA and GDPR data principles.

Cite This Study

Srividya et al. (2026) studied this question.

synapsesocial.com/papers/69abc1765af8044f7a4ea1ffhttps://doi.org/10.14569/ijacsa.2026.0170258
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Enhancing Lung Cancer Detection with Advanced Federated Learning Aggregation Techniques2025
  2. 2Federated Learning Frameworks for Privacy-Preserving Diagnostic Imaging in Multi-Site Hospital Clusters2026
  3. 3Adaptive homomorphic federated learning framework for multi-institutional medical imaging with optimized diagnostic accuracy2026 · 1 citations
  4. 4A Collaborative Federated Learning Framework for Lung and Colon Cancer Classifications2024 · 9 citations
  5. 5Regulatory-orientedDeep federated learning framework for multi-hospital medical imaging: privacy-preserving, explainable, and generalizable diagnosis2026