Federated prediction for scalable and privacy-preserved knowledge-based planning in radiotherapy

2025-05-20

AI Summary

Deep learning in radiotherapy suffers from poor generalizability due to limited annotated data and substantial inter-institutional heterogeneity, hindering clinical deployment. To address this, we propose FedKBP+, a novel federated learning platform enabling both centralized and fully decentralized (peer-to-peer) training modes within a unified architecture—without sharing raw patient data—thereby ensuring privacy-preserving, cross-institutional, and cross-device knowledge transfer. FedKBP+ leverages an efficient gRPC-based communication stack, incorporates a Scale-Attention Network (SA-Net) to enhance feature representation, and introduces a radiotherapy-specific federated optimization strategy tailored for clinical knowledge planning. Evaluated on three critical prediction tasks, FedKBP+ demonstrates significantly improved cross-center generalization, high training efficiency, and strong robustness against data heterogeneity and client dropouts. This work establishes a scalable, regulatory-compliant, and clinically practical paradigm for federated radiotherapy modeling.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Background: Deep learning has potential to improve the efficiency and consistency of radiation therapy planning, but clinical adoption is hindered by the limited model generalizability due to data scarcity and heterogeneity among institutions. Although aggregating data from different institutions could alleviate this problem, data sharing is a practical challenge due to concerns about patient data privacy and other technical obstacles. Purpose: This work aims to address this dilemma by developing FedKBP+, a comprehensive federated learning (FL) platform for predictive tasks in real-world applications in radiotherapy treatment planning. Methods: We implemented a unified communication stack based on Google Remote Procedure Call (gRPC) to support communication between participants whether located on the same workstation or distributed across multiple workstations. In addition to supporting the centralized FL strategies commonly available in existing open-source frameworks, FedKBP+ also provides a fully decentralized FL model where participants directly exchange model weights to each other through Peer-to-Peer communication. We evaluated FedKBP+ on three predictive tasks using scale-attention network (SA-Net) as the predictive model. Conclusions: Our results demonstrate that FedKBP+ is highly effective, efficient and robust, showing great potential as a federated learning platform for radiation therapy.

Problem

• Enhancing radiotherapy planning with federated learning for privacy
• Overcoming data scarcity and heterogeneity in multi-institutional settings
• Developing a decentralized FL platform for clinical adoption

Innovation

• Federated learning platform for radiotherapy planning
• Unified gRPC-based communication stack
• Decentralized peer-to-peer model weight exchange