Investigating the Impact of CNN Depth on Neonatal Seizure Detection Performance

2018/06/08 by O'Shea, Alison, Lightbody, Gordon, Boylan, Geraldine +1
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1806.03044

Abstract

This study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep convolutional networks are compared with a shallow SVM-based neonatal seizure detector, which relies on the extraction of hand-crafted features. On a large clinical dataset, of over 800 hours of multichannel unedited EEG, containing 1389 seizure events, the deep 11-layer architecture significantly outperforms the shallower architectures, improving the AUC90 from 82.6% to 86.8%. Combining the end-to-end deep architecture with the feature-based shallow SVM further improves the AUC90 to 87.6%. The fusion of classifiers of different depths gives greatly improved performance and reduced variability, making the combined classifier more clinically reliable.

Related

• Neonatal Seizure Detection using Convolutional Neural Networks
• Scaling convolutional neural networks achieves expert-level seizure detection in neonatal EEG
• Using Explainable AI for EEG-based Reduced Montage Neonatal Seizure Detection
• Scalable Machine Learning Architecture for Neonatal Seizure Detection on Ultra-Edge Devices
• Validating an SVM-based neonatal seizure detection algorithm for generalizability, non-inferiority and clinical efficacy