EEG-MACS: Manifold Attention and Confidence Stratification for EEG-based Cross-Center Brain Disease Diagnosis under Unreliable Annotations

arXiv:2405.00734v1 Announce Type: cross
Abstract: Cross-center data heterogeneity and annotation unreliability significantly challenge the intelligent diagnosis of diseases using brain signals. A notable example is the EEG-based diagnosis of neurodegenerative diseases, which features subtler abnormal neural dynamics typically observed in small-group settings. To advance this area, in this work, we introduce a transferable framework employing Manifold Attention and Confidence Stratification (MACS) to diagnose neurodegenerative disorders based on EEG signals sourced from four centers with unreliable annotations. The MACS framework's effectiveness …

abstract advance annotation annotations arxiv attention brain brain signals center challenge confidence cs.ai cs.lg data diagnosis disease disease diagnosis diseases dynamics eeg eess.sp example features intelligent manifold small type