A semi-supervised deep learning algorithm for abnormal EEG identification

TL;DR

This paper introduces a semi-supervised deep learning method for EEG abnormality detection that effectively leverages large unlabeled datasets and minimal labeled data, reducing the need for extensive manual annotation.

Contribution

It presents a novel semi-supervised learning workflow that achieves accurate EEG classification with as few as five labeled examples, addressing data labeling challenges.

Findings

Effective use of large unlabeled EEG datasets

Accurate predictions with minimal labeled data

Reduces dependency on extensive manual labeling

Abstract

Systems that can automatically analyze EEG signals can aid neurologists by reducing heavy workload and delays. However, such systems need to be first trained using a labeled dataset. While large corpuses of EEG data exist, a fraction of them are labeled. Hand-labeling data increases workload for the very neurologists we try to aid. This paper proposes a semi-supervised learning workflow that can not only extract meaningful information from large unlabeled EEG datasets but also make predictions with minimal supervision, using labeled datasets as small as 5 examples.