Using Convolutional Neural Networks to Automatically Detect Eye-Blink Artifacts in Magnetoencephalography Without Resorting to Electrooculography
- 9.1k Downloads
Magnetoencephelography (MEG) is a functional neuroimaging tool that records the magnetic fields induced by neuronal activity; however, signal from muscle activity often corrupts the data. Eye-blinks are one of the most common types of muscle artifact. They can be recorded by affixing eye proximal electrodes, as in electrooculography (EOG), however this complicates patient preparation and decreases comfort. Moreover, it can induce further muscular artifacts from facial twitching. We propose an EOG free, data driven approach. We begin with Independent Component Analysis (ICA), a well-known preprocessing approach that factors observed signal into statistically independent components. When applied to MEG, ICA can help separate neuronal components from non-neuronal ones, however, the components are randomly ordered. Thus, we develop a method to assign one of two labels, non-eye-blink or eye-blink, to each component.
Our contributions are two-fold. First, we develop a 10-layer Convolutional Neural Network (CNN), which directly labels eye-blink artifacts. Second, we visualize the learned spatial features using attention mapping, to reveal what it has learned and bolster confidence in the method’s ability to generalize to unseen data. We acquired 8-min, eyes open, resting state MEG from 44 subjects. We trained our method on the spatial maps from ICA of 14 subjects selected randomly with expertly labeled ground truth. We then tested on the remaining 30 subjects. Our approach achieves a test classification accuracy of 99.67%, sensitivity: 97.62%, specificity: 99.77%, and ROC AUC: 98.69%. We also show the learned spatial features correspond to those human experts typically use which corroborates our model’s validity. This work (1) facilitates creation of fully automated processing pipelines in MEG that need to remove motion artifacts related to eye blinks, and (2) potentially obviates the use of additional EOG electrodes for the recording of eye-blinks in MEG studies.
KeywordsMEG Eye-Blink Artifact EOG Automatic Deep learning CNN
The authors would like to thank Jillian Urban, Mireille Kelley, Derek Jones, and Joel Stitzel for their assistance in providing recruitment and study oversight. Support for this research was provided by NIH grant R01NS082453 (JAM, JDS), R03NS088125 (JAM), and R01NS091602 (CW, JAM, JDS).
- 2.Duan, F., Phothisonothai, M., Kikuchi, M., et al.: Boosting specificity of MEG artifact removal by weighted support vector machine. In: Conference proceedings: Annual International Conference of the IEEE EMBS. Annual Conference 2013, pp. 6039–6042 (2013)Google Scholar
- 5.Criswell, E.: Cram’s Introduction to Surface Electromyography (2011)Google Scholar
- 14.Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1–9 (2012)Google Scholar
- 15.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICRL), pp. 1–14 (2015)Google Scholar
- 17.Ioffe, S., Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Arxiv, pp. 1–11 (2015)Google Scholar
- 18.Kingma, D.P., Adam, B.J.: A Method for Stochastic Optimization. CoRR abs/1412.6980Google Scholar
- 19.Simonyan, K., Vedaldi, A., Zisserman, A.: Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. CoRR abs/1312.6034 (2013)Google Scholar
- 20.Selvaraju, R.R., Das, A., Vedantam, R., et al.: Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization(Nips), pp. 1–5 (2016)Google Scholar