Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG

• URL: http://arxiv.org/abs/2301.03470v1
• Date: Tue, 3 Jan 2023 15:57:13 GMT
• Title: Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG
• Authors: \.Ilkay Y{\i}ld{\i}z Potter, George Zerveas, Carsten Eickhoff, Dominique Duncan
• Abstract summary: Epileptic seizures are commonly monitored through electroencephalogram (EEG) recordings. We present an unsupervised transformer-based model for seizure identification on raw EEG. We train an autoencoder involving a transformer encoder via an unsupervised loss function, incorporating a novel masking strategy.
• Score: 9.338549413542948
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Epilepsy is one of the most common neurological disorders, typically observed via seizure episodes. Epileptic seizures are commonly monitored through electroencephalogram (EEG) recordings due to their routine and low expense collection. The stochastic nature of EEG makes seizure identification via manual inspections performed by highly-trained experts a tedious endeavor, motivating the use of automated identification. The literature on automated identification focuses mostly on supervised learning methods requiring expert labels of EEG segments that contain seizures, which are difficult to obtain. Motivated by these observations, we pose seizure identification as an unsupervised anomaly detection problem. To this end, we employ the first unsupervised transformer-based model for seizure identification on raw EEG. We train an autoencoder involving a transformer encoder via an unsupervised loss function, incorporating a novel masking strategy uniquely designed for multivariate time-series data such as EEG. Training employs EEG recordings that do not contain any seizures, while seizures are identified with respect to reconstruction errors at inference time. We evaluate our method on three publicly available benchmark EEG datasets for distinguishing seizure vs. non-seizure windows. Our method leads to significantly better seizure identification performance than supervised learning counterparts, by up to 16% recall, 9% accuracy, and 9% Area under the Receiver Operating Characteristics Curve (AUC), establishing particular benefits on highly imbalanced data. Through accurate seizure identification, our method could facilitate widely accessible and early detection of epilepsy development, without needing expensive label collection or manual feature extraction.

Related papers

• From Epilepsy Seizures Classification to Detection: A Deep Learning-based Approach for Raw EEG Signals [0.8182812460605992]
  One-third of people suffering from mesial temporal lobe epilepsy exhibit drug resistance. Key part in anti-seizure medication development is the capability of detecting and quantifying epileptic seizures. In this study, we introduced a seizure detection pipeline based on deep learning models applied to raw EEG signals.
  arXiv  Detail & Related papers  (2024-10-04T12:52:37Z)
• SincVAE: a New Approach to Improve Anomaly Detection on EEG Data Using SincNet and Variational Autoencoder [0.0]
  This work proposes a semi-supervised approach for detecting epileptic seizures from EEG data, utilizing a novel Deep Learning-based method called SincVAE. Results indicate that SincVAE improves seizure detection in EEG data and is capable of identifying early seizures during the preictal stage as well as monitoring patients throughout the postictal stage.
  arXiv  Detail & Related papers  (2024-06-25T13:21:01Z)
• ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges [7.726017342725144]
  We propose an invariant scattering transform-based hierarchical Transformer that specifically pays attention to subtle features. In particular, the disentangled frequency-aware attention (FAA) enables the Transformer to capture clinically informative high-frequency components. Our proposed model achieves median AUCROC and accuracy of 98.14%, 96.39% in patients with Rolandic epilepsy.
  arXiv  Detail & Related papers  (2023-04-26T10:10:58Z)
• Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis [4.1372815372396525]
  We propose to detect seizure channels and clips in a self-supervised manner where no access to the seizure data is needed. The proposed method considers local structural and contextual information embedded in EEG graphs by employing positive and negative sub-graphs. We conduct an extensive set of experiments on the largest seizure dataset and demonstrate that our proposed framework outperforms the state-of-the-art methods in the EEG-based seizure study.
  arXiv  Detail & Related papers  (2022-08-15T21:56:30Z)
• Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography [51.45515911920534]
  A task-oriented self-supervised learning approach is proposed to train a more effective anomaly detector. A specific two branch convolutional neural network with larger kernels is designed as the feature extractor. The effectively designed and trained feature extractor has shown to be able to extract better feature representations from EEGs.
  arXiv  Detail & Related papers  (2022-07-04T13:15:08Z)
• SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
  Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-11-25T03:53:43Z)
• SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection Classifier [68.8204255655161]
  Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures. For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts. SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
  arXiv  Detail & Related papers  (2021-10-01T23:01:20Z)
• High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm [70.50499513259322]
  Current artifact detection pipelines are resource-hungry and rely heavily on hand-crafted features. 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.
  arXiv  Detail & Related papers  (2021-07-21T07:05:42Z)
• Uncovering the structure of clinical EEG signals with self-supervised learning [64.4754948595556]
  Supervised learning paradigms are often limited by the amount of labeled data that is available. This phenomenon is particularly problematic in clinically-relevant data, such as electroencephalography (EEG) By extracting information from unlabeled data, it might be possible to reach competitive performance with deep neural networks.
  arXiv  Detail & Related papers  (2020-07-31T14:34:47Z)
• Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning [59.74684475991192]
  Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old. PD symptoms include tremor, rigidity and braykinesia. We present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device.
  arXiv  Detail & Related papers  (2020-05-06T09:02:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.