scholarly journals Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy

2018 ◽  
Vol 15 (4) ◽  
pp. 046035 ◽  
Author(s):  
Yogatheesan Varatharajah ◽  
Brent Berry ◽  
Jan Cimbalnik ◽  
Vaclav Kremen ◽  
Jamie Van Gompel ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
Focal Epilepsy ◽  
Eeg Monitoring ◽  
Seizure Onset ◽  
Intracranial Eeg ◽  
Seizure Onset Zones

scholarly journals Stereotyped high-frequency oscillations discriminate seizure onset zones and critical functional cortex in focal epilepsy

Brain ◽  
2018 ◽  
Vol 141 (3) ◽  
pp. 713-730 ◽  
Author(s):  
Su Liu ◽  
Candan Gurses ◽  
Zhiyi Sha ◽  
Michael M Quach ◽  
Altay Sencer ◽  
...  
Keyword(s):  
High Frequency ◽  
Focal Epilepsy ◽  
Machine Learning Techniques ◽  
Seizure Onset ◽  
Functional Regions ◽  
Clinical Biomarkers ◽  
High Frequency Oscillations ◽  
Potential Association ◽  
Waveform Similarity ◽  
Seizure Onset Zones

Abstract High-frequency oscillations in local field potentials recorded with intracranial EEG are putative biomarkers of seizure onset zones in epileptic brain. However, localized 80–500 Hz oscillations can also be recorded from normal and non-epileptic cerebral structures. When defined only by rate or frequency, physiological high-frequency oscillations are indistinguishable from pathological ones, which limit their application in epilepsy presurgical planning. We hypothesized that pathological high-frequency oscillations occur in a repetitive fashion with a similar waveform morphology that specifically indicates seizure onset zones. We investigated the waveform patterns of automatically detected high-frequency oscillations in 13 epilepsy patients and five control subjects, with an average of 73 subdural and intracerebral electrodes recorded per patient. The repetitive oscillatory waveforms were identified by using a pipeline of unsupervised machine learning techniques and were then correlated with independently clinician-defined seizure onset zones. Consistently in all patients, the stereotypical high-frequency oscillations with the highest degree of waveform similarity were localized within the seizure onset zones only, whereas the channels generating high-frequency oscillations embedded in random waveforms were found in the functional regions independent from the epileptogenic locations. The repetitive waveform pattern was more evident in fast ripples compared to ripples, suggesting a potential association between waveform repetition and the underlying pathological network. Our findings provided a new tool for the interpretation of pathological high-frequency oscillations that can be efficiently applied to distinguish seizure onset zones from functionally important sites, which is a critical step towards the translation of these signature events into valid clinical biomarkers. 5721572971001 awx374media1 5721572971001

scholarly journals Contribution of ictal source imaging for localizing seizure onset zone in patients with focal epilepsy patients

Neurology ◽  
2020 ◽  
pp. 10.1212/WNL.0000000000011109
Author(s):  
Shuai Ye ◽  
Lin Yang ◽  
Yunfeng Lu ◽  
Michal T. Kucewicz ◽  
Benjamin Brinkmann ◽  
...  
Keyword(s):  
Surgical Resection ◽  
Focal Epilepsy ◽  
High Density ◽  
Concordance Rate ◽  
Added Value ◽  
Seizure Onset ◽  
Source Imaging ◽  
Intracranial Eeg ◽  
Seizure Onset Zone ◽  
Eeg Recordings

ObjectiveTo determine whether seizure onset zone can be accurately localized prior to surgical planning in focal epilepsy patients, we performed non-invasive EEG recordings and source localization analyses on 39 patients.MethodsIn a total of 39 focal epilepsy patients, we recorded and extracted 138 seizures and 1,325 interictal epileptic discharges using high-density EEG. We have investigated a novel approach for directly imaging sources of seizures and interictal spikes from high density EEG recordings, and rigorously validated it for noninvasive localization of seizure onset zone (SOZ) determined from intracranial EEG findings and surgical resection volume. Conventional source imaging analyses were also performed for comparison.ResultsIctal source imaging showed a concordance rate of 95% when compared to intracranial EEG or resection results. The average distance from estimation to seizure onset (intracranial) electrodes is 1.35 cm in patients with concordant results, and 0.74 cm to surgical resection boundary in patients with successful surgery. About 41% of the patients were found to have multiple types of interictal activities; coincidentally, a lower concordance rate and a significantly worse performance in localizing SOZ were observed in these patients.ConclusionNoninvasive ictal source imaging with high-density EEG recording can provide highly concordant results with clinical decisions obtained by invasive monitoring or confirmed by resective surgery. By means of direct seizure imaging using high-density scalp EEG recordings, the added value of ictal source imaging is particularly high in patients with complex interictal activity patterns, who may represent the most challenging cases with poor prognosis.

scholarly journals Dynamic Training of a Novelty Classifier Algorithm for Real-Time Early Seizure Onset Detection

2021 ◽  
Author(s):  
Daniel Ehrens ◽  
Mackenzie C. Cervenka ◽  
Gregory K. Bergey ◽  
Christophe C. Jouny
Keyword(s):  
Real Time ◽  
High Performance ◽  
Epileptiform Activity ◽  
Support Vector ◽  
List Type ◽  
Onset Detection ◽  
Seizure Onset ◽  
Intracranial Eeg ◽  
Early Seizure ◽  
Epilepsy Monitoring

AbstractThe objective of this study was to develop an adaptive framework for seizure detection in real-time that is practical to use in the Epilepsy Monitoring Unit (EMU) as a warning signal, and whose output helps characterize epileptiform activity. Our framework uses a one-class Support Vector Machine (SVM) that is being trained dynamically according to past activity in all available channels. This is done to evaluate the novelty of the current instance according to previous activity. Our algorithm was tested on intracranial EEG from human epilepsy patients that are admitted to the EMU for presurgical evaluation. In this study, we compared multiple configurations for using a one-class SVM to assess if there is significance over specific neural features or electrode locations. Our results show our algorithm is capable of running in real-time and achieving a high performance for early seizure-onset detection with a low false-positive rate and robustness to different types of seizure-onset patterns as well as to the number of channels used. This algorithm offers a solution to warning systems in the EMU as well as a tool for seizure characterization during post-hoc analysis of intracranial EEG data for surgical resection of the epileptogenic network.HighlightsThis study proposes a dynamic training algorithm that efficiently detects sudden novel changes in intracranial electroencephalographic activity, creating a reliable seizure onset detection algorithm that does not need prior training.The algorithm described has the capability to be implemented in real-time, independently of the number of channels that are being analyzed.The presented detector shows high performance and reliability to be easily implemented in the Epilepsy Monitoring Unit to quickly alert clinical staff of seizure events.

Neurophysiological seizure-onset predictors of epilepsy surgery outcome: a multivariable analysis

2020 ◽  
Vol 133 (6) ◽  
pp. 1863-1872 ◽  
Author(s):  
Hideaki Tanaka ◽  
Jean Gotman ◽  
Hui Ming Khoo ◽  
André Olivier ◽  
Jeffery Hall ◽  
...  
Keyword(s):  
Surgical Outcome ◽  
Focal Epilepsy ◽  
Univariate Analysis ◽  
Multivariable Analysis ◽  
Postoperative Outcome ◽  
Seizure Onset ◽  
Resective Surgery ◽  
Scalp Eeg ◽  
Surgery Outcome ◽  
Intracerebral Eeg

OBJECTIVEThe authors sought to determine which neurophysiological seizure-onset features seen during scalp electroencephalography (EEG) and intracerebral EEG (iEEG) monitoring are predictors of postoperative outcome in a large series of patients with drug-resistant focal epilepsy who underwent resective surgery.METHODSThe authors retrospectively analyzed the records of 75 consecutive patients with focal epilepsy, who first underwent scalp EEG and then iEEG (stereo-EEG) for presurgical assessment and who went on to undergo resective surgery between 2004 and 2015. To determine the independent prognostic factors from the neurophysiological scalp EEG and iEEG seizure-onset information, univariate and standard multivariable logistic regression analyses were used. Since scalp EEG and iEEG data were recorded at different times, the authors matched scalp seizures with intracerebral seizures for each patient using strict criteria.RESULTSA total of 3057 seizures were assessed. Forty-eight percent (36/75) of patients had a favorable outcome (Engel class I–II) after a minimum follow-up of at least 1 year. According to univariate analysis, a localized scalp EEG seizure onset (p < 0.001), a multilobar intracerebral seizure-onset zone (SOZ) (p < 0.001), and an extended SOZ (p = 0.001) were significantly associated with surgical outcome. According to multivariable analysis, the following two independent factors were found: 1) the ability of scalp EEG to localize the seizure onset was a predictor of a favorable postoperative outcome (OR 6.073, 95% CI 2.011–18.339, p = 0.001), and 2) a multilobar SOZ was a predictor of an unfavorable outcome (OR 0.076, 95% CI 0.009–0.663, p = 0.020).CONCLUSIONSThe study findings show that localization at scalp seizure onset and a multilobar SOZ were strong predictors of surgical outcome. These predictors can help to select the better candidates for resective surgery.

scholarly journals BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13849-13850
Author(s):  
Donghyeon Lee ◽  
Man-Je Kim ◽  
Chang Wook Ahn
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Real Time ◽  
Large Scale ◽  
Outcome Predictor ◽  
Short Term ◽  
Rts Game

In a real-time strategy (RTS) game, StarCraft II, players need to know the consequences before making a decision in combat. We propose a combat outcome predictor which utilizes terrain information as well as squad information. For training the model, we generated a StarCraft II combat dataset by simulating diverse and large-scale combat situations. The overall accuracy of our model was 89.7%. Our predictor can be integrated into the artificial intelligence agent for RTS games as a short-term decision-making module.

scholarly journals Design of a dynamic and self-adapting system, supported with artificial intelligence, machine learning and real-time intelligence for predictive cyber risk analytics in extreme environments – cyber risk in the colonisation of Mars

2021 ◽  
Author(s):  
Petar Radanliev ◽  
David De Roure ◽  
Kevin Page ◽  
Max Van Kleek ◽  
Omar Santos ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Real Time ◽  
Cyber Security ◽  
Extreme Environments ◽  
Learning Technologies ◽  
Cyber Attacks ◽  
Edge Computing ◽  
Mathematical Formulas ◽  
Cyber Risk

AbstractMultiple governmental agencies and private organisations have made commitments for the colonisation of Mars. Such colonisation requires complex systems and infrastructure that could be very costly to repair or replace in cases of cyber-attacks. This paper surveys deep learning algorithms, IoT cyber security and risk models, and established mathematical formulas to identify the best approach for developing a dynamic and self-adapting system for predictive cyber risk analytics supported with Artificial Intelligence and Machine Learning and real-time intelligence in edge computing. The paper presents a new mathematical approach for integrating concepts for cognition engine design, edge computing and Artificial Intelligence and Machine Learning to automate anomaly detection. This engine instigates a step change by applying Artificial Intelligence and Machine Learning embedded at the edge of IoT networks, to deliver safe and functional real-time intelligence for predictive cyber risk analytics. This will enhance capacities for risk analytics and assists in the creation of a comprehensive and systematic understanding of the opportunities and threats that arise when edge computing nodes are deployed, and when Artificial Intelligence and Machine Learning technologies are migrated to the periphery of the internet and into local IoT networks.

Sign in / Sign up

Export Citation Format

Share Document