High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm
This work addresses the need for uncertainty-aware artifact detection in EEG monitoring to support clinicians-in-the-loop frameworks, representing an incremental improvement over existing methods.
The paper tackles the problem of detecting artifacts in high-frequency EEG signals, which are often obscured by non-cerebral noise, by proposing E4G, a deep learning framework that achieves state-of-the-art classification results on the Temple University Hospital EEG Artifact Corpus (v2.0) and provides well-calibrated uncertainty metrics comparable to Monte Carlo dropout in a single forward pass.
Electroencephalography (EEG) is crucial for the monitoring and diagnosis of brain disorders. However, EEG signals suffer from perturbations caused by non-cerebral artifacts limiting their efficacy. Current artifact detection pipelines are resource-hungry and rely heavily on hand-crafted features. Moreover, these pipelines are deterministic in nature, making them unable to capture predictive uncertainty. We propose E4G, a deep learning framework for high frequency EEG artifact detection. Our framework exploits the early exit paradigm, building an implicit ensemble of models capable of capturing uncertainty. We evaluate our approach on the Temple University Hospital EEG Artifact Corpus (v2.0) achieving state-of-the-art classification results. In addition, E4G provides well-calibrated uncertainty metrics comparable to sampling techniques like Monte Carlo dropout in just a single forward pass. E4G opens the door to uncertainty-aware artifact detection supporting clinicians-in-the-loop frameworks.