High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm

TL;DR

E4G is a deep learning framework that efficiently detects EEG artifacts and estimates uncertainty in a single pass, improving accuracy and reliability for clinical applications.

Contribution

The paper introduces E4G, a novel early exit-based deep learning approach that captures predictive uncertainty in EEG artifact detection, outperforming existing methods.

Findings

Achieves state-of-the-art classification accuracy on EEG artifact detection.

Provides well-calibrated uncertainty estimates comparable to Monte Carlo dropout.

Operates efficiently with a single forward pass, enabling real-time applications.

Abstract

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.