English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Federated learning (FL) has emerged as a promising paradigm for trainingsegmentation models on decentralized medical data, owing to itsprivacy-preserving property. However, existing research overlooks the prevalentannotation noise encountered in real-world medical datasets, which limits theperformance ceilings of FL. In this paper, we, for the first time, identify andtackle this problem. For problem formulation, we propose a contour evolutionfor modeling non-independent and identically distributed (Non-IID) noise acrosspixels within each client and then extend it to the case of multi-source datato form a heterogeneous noise model (i.e., Non-IID annotation noise acrossclients). For robust learning from annotations with such two-level Non-IIDnoise, we emphasize the importance of data quality in model aggregation,allowing high-quality clients to have a greater impact on FL. To achieve this,we propose Federated learning with Annotation quAlity-aware AggregatIon, namedFedA3I, by introducing a quality factor based on client-wise noise estimation.Specifically, noise estimation at each client is accomplished through theGaussian mixture model and then incorporated into model aggregation in alayer-wise manner to up-weight high-quality clients. Extensive experiments ontwo real-world medical image segmentation datasets demonstrate the superiorperformance of FedA$^3$I against the state-of-the-art approaches in dealingwith cross-client annotation noise. The code is available athttps://github.com/wnn2000/FedAAAI.

FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise