# Bayesian uncertainty-aware deep learning with noisy labels: Tackling annotation ambiguity in EEG seizure detection

arXiv: https://arxiv.org/abs/2410.19815 · HTML: https://mlsanity.com/paper/2410.19815/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 80 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels](https://mlsanity.com/paper/1905.05040/) (2019)
- [Self-Adaptive Training: beyond Empirical Risk Minimization](https://mlsanity.com/paper/2002.10319/) (2020)
- [The Temple University Hospital Seizure Detection Corpus](https://mlsanity.com/paper/1801.08085/) (2018)
- [Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization](https://mlsanity.com/paper/2102.02414/) (2021)
- [Improved Regularization and Robustness for Fine-tuning in Neural Networks](https://mlsanity.com/paper/2111.04578/) (2021)
- [Mitigating Memorization of Noisy Labels by Clipping the Model Prediction](https://mlsanity.com/paper/2212.04055/) (2022)
- [Machine-Learning-Based Diagnostics of EEG Pathology](https://mlsanity.com/paper/2002.05115/) (2020)
- [Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification](https://mlsanity.com/paper/1901.07759/) (2019)
- [Label Noise Types and Their Effects on Deep Learning](https://mlsanity.com/paper/2003.10471/) (2020)
- [Temporal Graph Convolutional Networks for Automatic Seizure Detection](https://mlsanity.com/paper/1905.01375/) (2019)
- [Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels](https://mlsanity.com/paper/2305.19518/) (2023)
- [Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy](https://mlsanity.com/paper/2311.01002/) (2023)
- [EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network](https://mlsanity.com/paper/2011.12107/) (2020)
- [On the Robustness of Monte Carlo Dropout Trained with Noisy Labels](https://mlsanity.com/paper/2103.12002/) (2021)
- [Dynamics-Aware Loss for Learning with Label Noise](https://mlsanity.com/paper/2303.11562/) (2023)
- [Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review](https://mlsanity.com/paper/2312.09454/) (2023)
- [A Novel Method for Epileptic Seizure Detection Using Coupled Hidden Markov Models](https://mlsanity.com/paper/1808.03630/) (2018)
- [Ensemble learning using individual neonatal data for seizure detection](https://mlsanity.com/paper/2204.07043/) (2022)
- [Controlling seizure propagation in large-scale brain networks](https://mlsanity.com/paper/1804.03588/) (2018)

## Abstract (arXiv)

Deep learning is advancing EEG processing for automated epileptic seizure detection and onset zone localization, yet its performance relies heavily on high-quality annotated training data. However, scalp EEG is susceptible to high noise levels, which in turn leads to imprecise annotations of the seizure timing and characteristics. This "label noise" presents a significant challenge in model training and generalization. In this paper, we introduce Bayesian UncertaiNty-aware Deep Learning (BUNDL), a novel algorithm that informs a deep learning model of label ambiguities, thereby enhancing the robustness of seizure detection systems. By integrating domain knowledge into an underlying Bayesian framework, we derive a novel KL-divergence-based loss function that capitalizes on uncertainty to better learn seizure characteristics from scalp EEG. Thus, BUNDL offers a straightforward and model-agnostic method for training deep neural networks with noisy training labels that does not add any parameters to existing architectures. Additionally, we explore the impact of improved detection system on the task of automated onset zone localization. We validate BUNDL using a comprehensive simulated EEG dataset and two publicly available datasets collected by Temple University Hospital (TUH) and Boston Children's Hospital (CHB-MIT). Results show that BUNDL consistently identifies noisy labels and improves the robustness of three base models under various label noise conditions. We also evaluate cross-site generalizability and quantify computational cost of all methods. Ultimately, BUNDL presents as a reliable method that can be seamlessly integrated with existing deep models used in clinical practice, enabling the training of trustworthy models for epilepsy evaluation.