Developing a generalized segmentation model capable of simultaneously delineating multiple organs and diseases is highly desirable. Federated learning (FL) is a key technology enabling the collaborative development of a model without exchanging training data. However, the limited access to fully annotated training data poses a major challenge to training generalizable models. We propose "ConDistFL", a framework to solve this problem by combining FL with knowledge distillation. Local models can extract the knowledge of unlabeled organs and tumors from partially annotated data from the global model with an adequately designed conditional probability representation. We validate our framework on four distinct partially annotated abdominal CT datasets from the MSD and KiTS19 challenges. The experimental results show that the proposed framework significantly outperforms FedAvg and FedOpt baselines. Moreover, the performance on an external test dataset demonstrates superior generalizability compared to models trained on each dataset separately. Our ablation study suggests that ConDistFL can perform well without frequent aggregation, reducing the communication cost of FL. Our implementation will be available at https://github.com/NVIDIA/NVFlare/tree/dev/research/condist-fl.

翻译：开发一种能够同时分割多个器官和病灶的通用分割模型极具价值。联邦学习（FL）是实现跨中心协作训练模型且无需交换训练数据的关键技术。然而，完全标注训练数据的有限获取对训练可泛化模型构成了重大挑战。我们提出"ConDistFL"框架，通过将联邦学习与知识蒸馏相结合来解决该问题。本地模型可利用全局模型提供的条件概率表示，从部分标注数据中提取未标注器官和肿瘤的知识。我们在MSD和KiTS19挑战赛中的四个不同部分标注腹部CT数据集上验证了该框架。实验结果表明，所提框架显著优于FedAvg和FedOpt基线方法。此外，在外部测试数据集上的性能证明了其相比各数据集单独训练的模型具有更强的泛化能力。消融研究表明，ConDistFL无需频繁聚合即可取得良好性能，从而降低了联邦学习的通信成本。我们将在https://github.com/NVIDIA/NVFlare/tree/dev/research/condist-fl 公开代码实现。