Deep learning with convolutional neural networks for decoding and visualization of EEG pathology

Abstract

Abstract-We apply convolutional neural networks (ConvNets) to the task of distinguishing pathological from normal EEG recordings in the Temple University Hospital EEG Abnormal Corpus. We use two basic, shallow and deep ConvNet architectures recently shown to decode task-related information from EEG at least as well as established algorithms designed for this purpose. In decoding EEG pathology, both ConvNets reached substantially better accuracies (about 6% better, ≈85% vs. ≈79%) than the only published result for this dataset, and were still better when using only 1 minute of each recording for training and only six seconds of each recording for testing. We used automated methods to optimize architectural hyperparameters and found intriguingly different ConvNet architectures, e.g., with max pooling as the only nonlinearity. Visualizations of the ConvNet decoding behavior showed that they used spectral power changes in the delta (0-4 Hz) and theta (4-8 Hz) frequency range, possibly alongside other features, consistent with expectations derived from spectral analysis of the EEG data and from the textual medical reports. Analysis of the textual medical reports also highlighted the potential for accuracy increases by integrating contextual information, such as the age of subjects. In summary, the ConvNets and visualization techniques used in this study constitute a next step towards clinically useful automated EEG diagnosis and establish a new baseline for future work on this topic.I. I Electroencephalography (EEG) is widely used in clinical practice because of its low cost and its lack of side effects due to its noninvasive nature. It is important both as a screening method as well as for hypothesis-based diagnostics, e.g., in epilepsy or stroke. One of the main limitations of using EEG for diagnostics is the required time and specialized knowledge of experts that need to be well-trained on EEG diagnostics to reach reliable results. Therefore, a machine-learning approach that aids in the diagnostic process could make EEG diagnosis more widely accessible, reduce time and effort for clinicians and potentially make diagnoses more accurate.In recent years researchers have increasingly addressed the field of computer-aided EEG diagnosis. So far, the applications were mostly limited to specific diagnoses such as Alzheimer's disease regression, neural networks, and more. This large variety of used methods indicates that the search for the best decoding approach for diverse types of EEG diagnosis is still ongoing.To overcome the lack of large datasets representative of the variety of EEG-diagnosable diseases and the heterogeneity of clinical populations, the Temple University Hospital (TUH) has published an unprecedented public dataset of clinical EEG recordings [6]. From this dataset with over 16000 clinical recordings, the TUH Abnormal EEG Corpus with about 3000 recordings has been created specifically to foster the development of methods for distinguishing pathological from normal EEG. Due to its size and rich annotatio...

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

“…The overall performance level is remarkable when considering the simplicity of the model. Our results demonstrate that a Riemannian model can actually be used to perform end-to-end learning (Schirrmeister et al, 2017) involving nothing but signal filtering and covariance estimation and, importantly, without deep-learning (Roy et al, 2019). When using SSS, performance improves beyond the current benchmark set by the MNE model but probably not because of denoising but rather due to the addition of gradiometer information.…”

ChronoNet: A Deep Recurrent Neural Network for Abnormal EEG Identification

“…Results reported to date on this dataset are included for comparison. In [16], the author explored various machine-and deep learning algorithms and observed that best performance is obtained when frequency features extracted from the input time-series signal are fed into a convolutional neural - Table 2: Performance comparison of the four deep recurrent neural networks described in Section 3 and results reported in [16] (see CNN-MLP) and [19] (see DeepCNN).…”

“…Inspired by successess in time-domain signal classification, we explore recurrent neural network (RNN) architectures using the raw EEG time-series signal as input. This sets us apart from previous publications [15,16,19], in which the authors used both traditional machine learning algorithms such as k-nearest neighbour, random forests, and hidden markov models and modern deep learning techniques such as convolutional neural networks (CNN), however, did not use RNNs for this task.…”

Deep learning-based electroencephalography analysis: a systematic review

“…Nu ber of e)a ples 10 −2 10 −1 10 0 10 1 10 2 10 3 10 4 Ratio (e)a ples/ in) datasets with a much greater number of subjects: [132,160,188,149] all used datasets with at least 250 subjects, while [22] and [49] used datasets with 10,000 and 16,000 subjects, respectively. As explained in Section 3.7.4, the untapped potential of DL-EEG might reside in combining data coming from many different subjects and/or datasets to train a model that captures common underlying features and generalizes better.…”

“…Occlusion sensitivity techniques [92,26,175] use a similar idea, by which the decisions of the network when different parts of the input are occluded are analyzed. [135,211,86,34,87,200,182,122,170,228,164,109,204,85,25] Analysis of activations [212,194,87,83,208,167,154,109] Input-perturbation network-prediction correlation maps [149,191,67,16,150] Generating input to maximize activation [188,144,160,15] Occlusion of input [92,26,175] Several studies used backpropagation-based techniques to generate input maps that maximize activations of specific units [188,144,160,15]. These maps can then be used to infer the role of specific neurons, or the kind of input they are sensitive to.…”