FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-supervised Medical Image Segmentation

arXiv:2402.17502v1 Announce Type: new
Abstract: Federated learning (FL) effectively mitigates the data silo challenge brought about by policies and privacy concerns, implicitly harnessing more data for deep model training. However, traditional centralized FL models grapple with diverse multi-center data, especially in the face of significant data heterogeneity, notably in medical contexts. In the realm of medical image segmentation, the growing imperative to curtail annotation costs has amplified the importance of weakly-supervised techniques which utilize sparse annotations such as points, scribbles, …

abstract aggregation arxiv center challenge concerns cs.cv data data silo diverse eess.iv face federated learning image medical personalized privacy prompt segmentation training type weakly-supervised