QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
QFedPolyp：一种用于息肉分割的通信与推理高效联邦学习框架
Abstract: Background and Objective: Automatic polyp segmentation supports computer-aided diagnosis and early colorectal cancer detection. 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.
摘要： 背景与目标：自动息肉分割技术支持计算机辅助诊断及结直肠癌的早期检测。集中式深度学习要求医院共享敏感的医疗数据，而联邦学习虽然保护了隐私，但由于需要重复传输全精度模型参数，导致了高昂的通信成本。我们提出了 QFedPolyp，这是一个用于协作息肉分割的通信与推理高效的联邦学习框架。
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.
方法： QFedPolyp 将量化感知训练与低精度模型通信相结合。每家医院在私有数据上本地训练轻量级 U-Net，并在训练过程中模拟量化。客户端将量化后的模型参数传输到中央服务器，服务器通过联邦平均（Federated Averaging）算法对参数进行重构与聚合。评估工作在 Kvasir-SEG、CVC-ClinicVideoDB、PolypGen 和 BKAI-IGH NeoPolyp 数据集上进行。
Results: Full-precision federated training achieves Dice scores of 0.910 on Kvasir-SEG and 0.930 on CVC-ClinicVideoDB. Uniform 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.
结果： 全精度联邦训练在 Kvasir-SEG 上达到了 0.910 的 Dice 分数，在 CVC-ClinicVideoDB 上达到了 0.930。统一的 8 位通信在保持竞争性分割精度的同时，将传输成本降低了约 4 倍。此外，量化模型的推理速度比全精度模型快 1.5 倍。
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.
结论： QFedPolyp 实现了隐私保护下的协作息肉分割，同时降低了通信开销并加快了推理速度。由此产生的轻量级模型非常适合实时临床部署。