Temporal Graph Convolutional Networks for Automatic Seizure Detection

by   Ian Covert, et al.

Seizure detection from EEGs is a challenging and time consuming clinical problem that would benefit from the development of automated algorithms. EEGs can be viewed as structural time series, because they are multivariate time series where the placement of leads on a patient's scalp provides prior information about the structure of interactions. Commonly used deep learning models for time series don't offer a way to leverage structural information, but this would be desirable in a model for structural time series. To address this challenge, we propose the temporal graph convolutional network (TGCN), a model that leverages structural information and has relatively few parameters. TGCNs apply feature extraction operations that are localized and shared over both time and space, thereby providing a useful inductive bias in tasks where one expects similar features to be discriminative across the different sequences. In our experiments we focus on metrics that are most important to seizure detection, and demonstrate that TGCN matches the performance of related models that have been shown to be state of the art in other tasks. Additionally, we investigate interpretability advantages of TGCN by exploring approaches for helping clinicians determine when precisely seizures occur, and the parts of the brain that are most involved.


page 1

page 2

page 3

page 4


Network of Tensor Time Series

Co-evolving time series appears in a multitude of applications such as e...

ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information

In healthcare applications, temporal variables that encode movement, hea...

cs-net: structural approach to time-series forecasting for high-dimensional feature space data with limited observations

In recent years, deep-learning-based approaches have been introduced to ...

Focusing on What is Relevant: Time-Series Learning and Understanding using Attention

This paper is a contribution towards interpretability of the deep learni...

Structural time series grammar over variable blocks

A structural time series model additively decomposes into generative, se...

Structured Time Series Prediction without Structural Prior

Time series prediction is a widespread and well studied problem with app...

Please sign up or login with your details

Forgot password? Click here to reset