UFPS: A unified framework for partially-annotated federated segmentation in heterogeneous data distribution
This work addresses segmentation challenges in medical imaging under privacy constraints, but it is incremental as it builds on existing federated and partially supervised methods.
The authors tackled the problem of partially supervised segmentation in federated learning, where data privacy and heterogeneity hinder real-world medical applications, and proposed the UFPS framework to address class collision and client drift, achieving better deconflicting and generalization on real medical datasets.
Partially supervised segmentation is a label-saving method based on datasets with fractional classes labeled and intersectant. However, it is still far from landing on real-world medical applications due to privacy concerns and data heterogeneity. As a remedy without privacy leakage, federated partially supervised segmentation (FPSS) is formulated in this work. The main challenges for FPSS are class heterogeneity and client drift. We propose a Unified Federated Partially-labeled Segmentation (UFPS) framework to segment pixels within all classes for partially-annotated datasets by training a totipotential global model without class collision. Our framework includes Unified Label Learning and sparsed Unified Sharpness Aware Minimization for unification of class and feature space, respectively. We find that vanilla combinations for traditional methods in partially supervised segmentation and federated learning are mainly hampered by class collision through empirical study. Our comprehensive experiments on real medical datasets demonstrate better deconflicting and generalization ability of UFPS compared with modified methods.