Synthesising Interictal Epileptiform Discharges With Generative Adversarial Network
Nhu, D.; Janmohamed, M.; Kwan, P.; Obrien, T.; Gilligan, A.; Perucca, P.; Tan, C. W.; Kuhlmann, L.
Show abstract
Interictal epileptiform discharges (IEDs) are reliable biomarkers in electroencephalograms for epilepsy. To automate IED detection, deep learning (DL) has been applied to treat EEG signals as time-series data. However, collecting sufficient IEDs for training DL models is expensive; public and private datasets are often overwhelmed with background activities. To address this issue, generative adversarial networks (GANs) have been used to synthesise IEDs. Previous works using GANs achieved some improvements, but the quality metrics of synthetic samples were not contextualised, resulting in suboptimal model tuning. In this work, we proposed to use density and coverage to evaluate synthetic data and to tune a GAN model. We also utilised soft dynamic time warping (soft-DTW), a differentiable version of DTW, as the reconstruction loss to learn temporal alignments of the IEDs waveforms and improve the diversity of synthetic samples. Our proposed approach achieved a 10% improvement in the AUPRC score on the Temple University Events (TUEV) dataset by combining synthetic and real data, demonstrating the potential of this method to enhance the accuracy of IED detection.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- HeartNet: Self Multi-Head Attention Mechanism via Convolutional Network with Adversarial Data Synthesis for ECG-based Arrhythmia Classification 93%
- SleepSatelightFTC: A Lightweight and Interpretable Deep Learning Model for Single-Channel EEG-Based Sleep Stage Classification 93%
- Self-Supervised Electrocardiograph De-noising 92%
Similar papers in this journal
- Multiple Instance Learning Framework can Facilitate Explainability in Murmur Detection 95%
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 95%
- Enhancing Fairness in Disease Prediction by Optimizing Multiple Domain Adversarial Networks 93%
Similar papers in this journal
- PyHFO: Lightweight Deep Learning-poweredEnd-to-End High-Frequency Oscillations AnalysisApplication 96%
- Speech decoding from a small set of spatially segregated minimally invasive intracranial EEG electrodes with a compact and interpretable neural network 95%
- Firing-rate-modulated spike detection and neural decoding co-design 95%
Similar papers in this journal
- Assessing the robustness of deep learning based brain age prediction models across multiple EEG datasets 96%
- Maximum Classifier Discrepancy Generative Adversarial Network for Jointly Harmonizing Scanner Effects and Improving Reproducibility of Downstream Tasks 95%
- GLAPAL-H: Global, Local, And Parts Aware Learner for Hydrocephalus Infection Diagnosis in Low-Field MRI 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.