# Low Latency Real-Time Seizure Detection Using Transfer Deep Learning

arXiv: https://arxiv.org/abs/2202.07796 · HTML: https://mlsanity.com/paper/2202.07796/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Temple University Hospital Seizure Detection Corpus](https://mlsanity.com/paper/1801.08085/) (2018)
- [Objective evaluation metrics for automatic classification of EEG events](https://mlsanity.com/paper/1712.10107/) (2017)
- [An Analysis of Two Common Reference Points for EEGs](https://mlsanity.com/paper/1801.02474/) (2018)
- [A Novel Method for Epileptic Seizure Detection Using Coupled Hidden Markov Models](https://mlsanity.com/paper/1808.03630/) (2018)

## Built on by (most cited first, 3 of 3)

- [Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis](https://mlsanity.com/paper/2208.07448/) (2022)
- [An Automated Classifier of Harmful Brain Activities for Clinical Usage Based on a Vision-Inspired Pre-trained Framework](https://mlsanity.com/paper/2507.08874/) (2025)
- [MR-EEGWaveNet: Multiresolutional EEGWaveNet for Seizure Detection from Long EEG Recordings](https://mlsanity.com/paper/2505.17972/) (2025)

## Abstract (arXiv)

Scalp electroencephalogram (EEG) signals inherently have a low signal-to-noise ratio due to the way the signal is electrically transduced. Temporal and spatial information must be exploited to achieve accurate detection of seizure events. Most popular approaches to seizure detection using deep learning do not jointly model this information or require multiple passes over the signal, which makes the systems inherently non-causal. In this paper, we exploit both simultaneously by converting the multichannel signal to a grayscale image and using transfer learning to achieve high performance. The proposed system is trained end-to-end with only very simple pre- and postprocessing operations which are computationally lightweight and have low latency, making them conducive to clinical applications that require real-time processing. We have achieved a performance of 42.05% sensitivity with 5.78 false alarms per 24 hours on the development dataset of v1.5.2 of the Temple University Hospital Seizure Detection Corpus. On a single-core CPU operating at 1.7 GHz, the system runs faster than real-time (0.58 xRT), uses 16 Gbytes of memory, and has a latency of 300 msec.