QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation

2026-07-22

AI Summary

This work addresses the high communication overhead and inference latency of federated learning in medical polyp segmentation by introducing quantization-aware training into the federated learning framework for the first time. By integrating a lightweight U-Net architecture, 8-bit model quantization, and the FedAvg algorithm, the proposed method enables efficient collaborative training across hospitals while preserving data privacy. The approach substantially reduces communication costs by approximately fourfold and accelerates inference speed by up to 1.5×, all while maintaining competitive accuracy—achieving Dice scores of 0.910 and 0.930 on the Kvasir-SEG and CVC-ClinicVideoDB datasets, respectively—thus effectively balancing model efficiency and segmentation performance.

Abstract

Background and Objective: Automatic polyp segmentation supports computer-aided diagnosis and early colorectal cancer detec- tion. Centralized deep learning requires hospitals to share sensitive medical data, while federated learning preserves privacy but introduces high communication costs through repeated transmission of full-precision model parameters. We propose QFedPolyp, a communication- and inference-efficient federated learning framework for collaborative polyp segmentation. Methods: QFedPolyp combines quantization-aware training with low-precision model communication. Each hospital locally trains a lightweight U-Net on private data while simulating quantization during training. Clients transmit quantized model parameters to a central server, where they are reconstructed and aggregated using Federated Averaging. Evaluation is performed on Kvasir-SEG, CVC-ClinicVideoDB, PolypGen, and BKAI-IGH NeoPolyp. Results: Full-precision federated training achieves Dice scores of 0.910 on Kvasir-SEG and 0.930 on CVC-ClinicVideoDB. Uni- form 8-bit communication reduces transmission cost by approximately 4 times while preserving competitive segmentation accuracy. Quantized models also achieve up to 1.5 times faster inference than full-precision models. Conclusions: QFedPolyp enables privacy-preserving collaborative polyp segmentation with reduced communication overhead and faster inference. The resulting lightweight models are suitable for real-time clinical deployment.

Problem

• federated learning
• polyp segmentation
• communication efficiency
• inference efficiency
• medical privacy

Innovation

• federated learning
• quantization-aware training
• polyp segmentation
• communication efficiency
• lightweight model