DANCE: Detect and Classify Events in EEG

TL;DR

DANCE is a deep learning pipeline that detects and classifies events directly from raw EEG signals, outperforming existing methods across various datasets and tasks, including seizure monitoring and BCI applications.

Contribution

It introduces a novel set-prediction approach for neural decoding that operates on unaligned signals, advancing end-to-end asynchronous EEG analysis.

Findings

Outperforms existing methods on ten diverse datasets.

Establishes new state-of-the-art in seizure monitoring.

Matches accuracy of onset-informed models in BCI tasks.

Abstract

Event identification in continuous neural recordings is a critical task in neuroscience. Decoding in EEG is dominated by classifying windows aligned to known event onsets. However, while available in controlled experiments, such onsets are absent in continuous real-world monitoring. Here, we introduce DANCE, a deep learning pipeline that frames neural decoding as a set-prediction problem and jointly detects and classifies events directly from raw, unaligned signals. Evaluated separately on ten datasets curated from the literature with a wide variety of event types (ranging from milliseconds to minutes in duration), our model outperforms existing methods on a broad range of cognitive, clinical and BCI tasks. This single architecture establishes a new state of the art in the competitive task of seizure monitoring and matches the accuracy of onset-informed models for BCI tasks. Overall, our method marks a step towards end-to-end asynchronous neural decoding models