A comparison between centralized and asynchronous federated learning approaches for survival outcome prediction using clinical and PET data from non-small cell lung cancer patients

Thi Tuong Vi Vo, Tae-ho Shin, Hyung-Jeong Yang, Sae-Ryung Kang, Soo-Hyung Kim

Abstract: Highlights•The feasibility and effectiveness of FedSurv, a federated learning (FL) approach, for survival time prediction.•The effectiveness of a combination of PET-based features and clinical features for multimodal survival prediction.•We further explored the adoption of FL in multimodal domains, specifically combining PET and clinical data.