Expert-Level Intracranial Electroencephalogram Ictal Pattern Detection by a Deep Learning Neural Network

Abstract

Background: Decision-making in epilepsy surgery is strongly connected to the interpretation of the intracranial EEG (iEEG). Although deep learning approaches have demonstrated efficiency in processing extracranial EEG, few studies have addressed iEEG seizure detection, in part due to the small number of seizures per patient typically available from intracranial investigations. This study aims to evaluate the efficiency of deep learning methodology in detecting iEEG seizures using a large dataset of ictal patterns collected from epilepsy patients implanted with a responsive neurostimulation system (RNS).Methods: Five thousand two hundred and twenty-six ictal events were collected from 22 patients implanted with RNS. A convolutional neural network (CNN) architecture was created to provide personalized seizure annotations for each patient. Accuracy of seizure identification was tested in two scenarios: patients with seizures occurring following a period of chronic recording (scenario 1) and patients with seizures occurring immediately following implantation (scenario 2). The accuracy of the CNN in identifying RNS-recorded iEEG ictal patterns was evaluated against human neurophysiology expertise. Statistical performance was assessed via the area-under-precision-recall curve (AUPRC).Results: In scenario 1, the CNN achieved a maximum mean binary classification AUPRC of 0.84 ± 0.19 (95%CI, 0.72–0.93) and mean regression accuracy of 6.3 ± 1.0 s (95%CI, 4.3–8.5 s) at 30 seed samples. In scenario 2, maximum mean AUPRC was 0.80 ± 0.19 (95%CI, 0.68–0.91) and mean regression accuracy was 6.3 ± 0.9 s (95%CI, 4.8–8.3 s) at 20 seed samples. We obtained near-maximum accuracies at seed size of 10 in both scenarios. CNN classification failures can be explained by ictal electro-decrements, brief seizures, single-channel ictal patterns, highly concentrated interictal activity, changes in the sleep-wake cycle, and progressive modulation of electrographic ictal features.Conclusions: We developed a deep learning neural network that performs personalized detection of RNS-derived ictal patterns with expert-level accuracy. These results suggest the potential for automated techniques to significantly improve the management of closed-loop brain stimulation, including during the initial period of recording when the device is otherwise naïve to a given patient's seizures.

A Data-Efficient Framework for the Identification of Vaginitis Based on Deep Learning

“…For medical image diagnostic assistance, deep learning methods can outperform many traditional image processing and machine learning methods due to their efficiency in feature extraction from original data [ 12 , 13 ]. The performance of deep learning techniques heavily relies on the size and quality of training data, and typically a tremendous amount of labeled data is needed for a high-performance model.…”

Sleep increases firing rate modulation during interictal epileptic activities in mesial temporal structures

“…Many algorithms have been proposed for IED detection over the last decades (Wilson and Emerson, 2002; Halford, 2009; Halford et al, 2013; da Silva Lourenço et al, 2021), with recent implementations showing good, or better, performance than human experts (Brown et al, 2007; Nonclercq et al, 2012; Scheuer et al, 2017; Reus et al, 2022). Recent examples include the use of adaptive morphological filters (Krishnan et al, 2014), signal envelope distribution modeling (Janca et al, 2015; Peter-Derex et al, 2020), convolutional neural networks (CNN) and deep learning (Lourenço et al, 2020; Constantino et al, 2021; Fukumori et al, 2019; Tjepkema-Cloostermans et al, 2018; Fürbass et al, 2020; Antoniades et al, 2017), long short-term memory (LSTM) neural networks (Medvedev et al, 2019) and generative adversarial networks (GANs) (Geng et al, 2021; Tanaka and Aranha, 2019). Two-step methods have been proposed to reduce the need to manually optimize parameters per different datasets (Liu et al, 2013; Bagheri et al, 2019).…”

Responsive Neurostimulation for Seizure Control: Current Status and Future Directions

“…In addition to using interictal ECoG data from RNS to predict seizure frequency, groups such as Constantino et al explored whether machine learning algorithms could detect RNS-derived ictal patterns with an accuracy comparable to that of epileptologists ( Table 3 ) [ 59 ]. Specifically, Constantino et al trained a convolutional neural network (CNN) model to distinguish ictal activity from non-ictal activity [ 59 ]. A CNN model is a specific type of deep learning model; it is considered the model of choice when working with multiple array data, such as EEG data [ 59 ].…”

“…Specifically, Constantino et al trained a convolutional neural network (CNN) model to distinguish ictal activity from non-ictal activity [ 59 ]. A CNN model is a specific type of deep learning model; it is considered the model of choice when working with multiple array data, such as EEG data [ 59 ]. Constantino et al’s group was able to show that with a large training set of RNS-derived ECoG data, a CNN model could detect seizures with an accuracy that was similar to that of expert epileptologists [ 59 ].…”