# Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture

arXiv: https://arxiv.org/abs/2105.13854 · HTML: https://mlsanity.com/paper/2105.13854/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 28 May 2021.

## Builds on (most cited first, 13 of 13)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Deep learning-based electroencephalography analysis: a systematic review](https://mlsanity.com/paper/1901.05498/) (2019)
- [Who Said What: Modeling Individual Labelers Improves Classification](https://mlsanity.com/paper/1703.08774/) (2017)
- [Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms](https://mlsanity.com/paper/1703.01789/) (2017)
- [Audio Event Detection using Weakly Labeled Data](https://mlsanity.com/paper/1605.02401/) (2016)
- [Neonatal Seizure Detection using Convolutional Neural Networks](https://mlsanity.com/paper/1709.05849/) (2017)
- [Investigating the Impact of CNN Depth on Neonatal Seizure Detection Performance](https://mlsanity.com/paper/1806.03044/) (2018)
- [Neonatal EEG Interpretation and Decision Support Framework for Mobile Platforms](https://mlsanity.com/paper/1806.04037/) (2018)

## Built on by (most cited first, 12 of 12)

- [EEGMamba: Bidirectional State Space Model with Mixture of Experts for EEG Multi-task Classification](https://mlsanity.com/paper/2407.20254/) (2024)
- [REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates](https://mlsanity.com/paper/2406.16906/) (2024)
- [A Meta-GNN approach to personalized seizure detection and classification](https://mlsanity.com/paper/2211.02642/) (2022)
- [Scaling convolutional neural networks achieves expert-level seizure detection in neonatal EEG](https://mlsanity.com/paper/2405.09911/) (2024)
- [Towards trustworthy seizure onset detection using workflow notes](https://mlsanity.com/paper/2306.08728/) (2023)
- [Validating an SVM-based neonatal seizure detection algorithm for generalizability, non-inferiority and clinical efficacy](https://mlsanity.com/paper/2202.12023/) (2022)
- [Ensemble learning using individual neonatal data for seizure detection](https://mlsanity.com/paper/2204.07043/) (2022)
- [Improving self-supervised pretraining models for epileptic seizure detection from EEG data](https://mlsanity.com/paper/2207.06911/) (2022)
- [Honest and Reliable Evaluation and Expert Equivalence Testing of Automated Neonatal Seizure Detection](https://mlsanity.com/paper/2508.04899/) (2025)
- [LookAroundNet: Extending Temporal Context with Transformers for Clinically Viable EEG Seizure Detection](https://mlsanity.com/paper/2601.06016/) (2026)
- [NeuroCanvas: VLLM-Powered Robust Seizure Detection by Reformulating Multichannel EEG as Image](https://mlsanity.com/paper/2602.04769/) (2026)
- [From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks](https://mlsanity.com/paper/2606.22258/) (2026)

## Abstract (arXiv)

A deep learning classifier for detecting seizures in neonates is proposed. This architecture is designed to detect seizure events from raw electroencephalogram (EEG) signals as opposed to the state-of-the-art hand engineered feature-based representation employed in traditional machine learning based solutions. The seizure detection system utilises only convolutional layers in order to process the multichannel time domain signal and is designed to exploit the large amount of weakly labelled data in the training stage. The system performance is assessed on a large database of continuous EEG recordings of 834h in duration; this is further validated on a held-out publicly available dataset and compared with two baseline SVM based systems. The developed system achieves a 56% relative improvement with respect to a feature-based state-of-the art baseline, reaching an AUC of 98.5%; this also compares favourably both in terms of performance and run-time. The effect of varying architectural parameters is thoroughly studied. The performance improvement is achieved through novel architecture design which allows more efficient usage of available training data and end-to-end optimisation from the front-end feature extraction to the back-end classification. The proposed architecture opens new avenues for the application of deep learning to neonatal EEG, where the performance becomes a function of the amount of training data with less dependency on the availability of precise clinical labels.