SOURCE-LINKED INTELLIGENCE

OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Federated learning enables collaborative model development without centralizing patient data, but annotation reliability at participating institutions cannot always be assumed. In ophthalmic imaging, differences in disease prevalence and class composition can resemble changes caused by corrupted supervision. We introduce OCT-FedSIR, a reliability-aware spectral framework for federated OCT classification under client-dependent annotation noise and heterogeneous data distributions. OCT-FedSIR combines class-balanced spectral estimation, Stage-I logit adjustment, complementary spectral descriptor

Read original source ↗ Open in workspace

recordType

paper

region

Global