Implementation and evaluation of an interictal spike detector

Horak, Peter C.; Meisenhelter, Stephen; Testorf, Markus E.; Connolly, Andrew C.; Davis, Kathryn A.; Jobst, Barbara C.

doi:10.1117/12.2189248

Cited by 14 publications

(25 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human annotations of IEDs in intracranial EEG exhibit significant interrater variability . To avoid potential inconsistencies in human review while marking a large amount of data, we chose to use an automated IED detector after validating it relative to multiple clinicians . Figure B shows an example IED detection.…”

Section: Methodsmentioning

confidence: 99%

“…Recently, template‐matching spike detection has been used more routinely for research . The original algorithm was modified based on observations from a dataset of hippocampal recordings and then validated on two independent datasets, each annotated by three neurophysiologists . Furthermore, the detector performed with a receiver operating characteristic (ROC) curve similar to that of another published detector .…”

Section: Methodsmentioning

confidence: 99%

“…22,23 To avoid potential inconsistencies in human review while marking a large amount of data, we chose to use an automated IED detector after validating it relative to multiple clinicians. 24 Figure 1B shows an example IED detection. Intracranial recordings eliminate some of the issues and artifacts that can make automated detection difficult for scalp EEG.…”

Section: Spike Detectionmentioning

confidence: 99%

“…25 The original algorithm was modified based on observations from a dataset of hippocampal recordings and then validated on two independent datasets, each annotated by three neurophysiologists. 24 Furthermore, the detector performed with a receiver operating characteristic (ROC) curve similar to that of another published detector. 23 In the present dataset, we excluded 10 electrodes across five subjects in which the detector mistakenly marked sharp time-locked signals.…”

Section: Spike Detectionmentioning

confidence: 99%

See 3 more Smart Citations

Interictal epileptiform discharges impair word recall in multiple brain areas

et al. 2016

Self Cite

View full text Add to dashboard Cite

Summary Objectives Interictal epileptiform discharges (IEDs) have been linked to memory impairment, but the spatial and temporal dynamics of this relationship remain elusive. In the present study, we aim to systematically characterize the brain areas and times at which IEDs affect memory. Methods Eighty epilepsy patients participated in a delayed free recall task while undergoing intracranial EEG monitoring. We analyzed the locations and timing of IEDs relative to the behavioral data in order to measure their effects on memory. Results Overall IED rates did not correlate with task performance across subjects (r = 0.03, p = 0.8). However, at a finer temporal scale, within-subject memory was negatively affected by IEDs during the encoding and recall periods of the task but not during the rest and distractor periods (p < 0.01, p < 0.001, p = 0.3, and p = 0.8 respectively). The effects of IEDs during encoding and recall were stronger in the left hemisphere than in the right (p < 0.05). Out of six brain areas analyzed, IEDs in the inferior temporal, medial temporal, and parietal areas significantly affected memory (false discovery rate < 0.05). Significance These findings reveal a network of brain areas sensitive to IEDs with key nodes in temporal as well as parietal lobes. They also demonstrate the time-dependent effects of IEDs in this network on memory.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Spike Detectionmentioning

confidence: 99%

Section: Spike Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Interictal epileptiform discharges impair word recall in multiple brain areas

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…We utilized a template‐based IED detector that was validated and performed comparably to clinicians at Dartmouth‐Hitchcock (DH) and other published detectors 2,18–20 . In terms of inter‐reviewer variability, this template‐matching detector showed similar performance (average agreement with neurophysiologists = 0.54, range = 0.43–0.66) to three neurophysiologists (average agreement between neurophysiologists = 0.43, range = 0.27–0.70) and higher performance than another published detector (average agreement with neurophysiologists = 0.27, range = 0.17–0.40) 18 . Thus, we elected to use our automated detector due to the time‐intensive nature of human annotations of IEDs and the notable inter‐rater variability between human reviewers 21 .…”

Section: Methodsmentioning

confidence: 71%

40‐Hz auditory stimulation for intracranial interictal activity: A pilot study

et al. 2021

Self Cite

View full text Add to dashboard Cite

Objectives To study the effects of auditory stimuli on interictal epileptiform discharge (IED) rates evident with intracranial monitoring. Materials and methods Eight subjects undergoing intracranial EEG monitoring for refractory epilepsy participated in this study. Auditory stimuli consisted of a 40‐Hz tone, a 440‐Hz tone modulated by a 40‐Hz sinusoid, Mozart's Sonata for Two Pianos in D Major (K448), and K448 modulated by a 40‐Hz sinusoid (modK448). Subjects were stratified into high‐ and low‐IED rate groups defined by baseline IED rates. Subject‐level analyses identified individual responses to auditory stimuli, discerned specific brain regions with significant reductions in IED rates, and examined the influence auditory stimuli had on whole‐brain sigma power (12–16 Hz). Results All subjects in the high baseline IED group had a significant 35.25% average reduction in IEDs during the 40‐Hz tone; subject‐level reductions localized to mesial and lateral temporal regions. Exposure to Mozart K448 showed significant yet less homogeneous responses. A post hoc analysis demonstrated two of the four subjects with positive IED responses had increased whole‐brain power at the sigma frequency band during 40‐Hz stimulation. Conclusions Our study is the first to evaluate the relationship between 40‐Hz auditory stimulation and IED rates in refractory epilepsy. We reveal that 40‐Hz auditory stimuli may be a noninvasive adjunctive intervention to reduce IED burden. Our pilot study supports the future examination of 40‐Hz auditory stimuli in a larger population of subjects with high baseline IED rates.

show abstract

Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning

Jaoude

Jin

Sun

et al. 2020

Clinical Neurophysiology

View full text Add to dashboard Cite

Objective: Develop a high-performing algorithm to detect mesial temporal lobe (mTL) epileptiform discharges on intracranial electrode recordings.Methods: An epileptologist annotated 13,959 epileptiform discharges from a dataset of intracranial EEG recordings from 46 epilepsy patients. Using this dataset, we trained a convolutional neural network (CNN) to recognize mTL epileptiform discharges from a single intracranial bipolar channel. The CNN outputs from multiple bipolar channel inputs were averaged to generate the final detector output. Algorithm performance was estimated using a nested 5-fold cross-validation Results: On the receiver-operating characteristic curve, our algorithm achieved an area under the curve (AUC) of 0.996 and a partial AUC (for specificity > 0.9) of 0.981. AUC on a precisionrecall curve was 0.807. A sensitivity of 84% was attained at a false positive rate of 1 per minute. 35.9% of the false positive detections corresponded to epileptiform discharges that were missed during expert annotation. Conclusions:Using deep learning, we developed a high-performing, patient non-specific algorithm for detection of mTL epileptiform discharges on intracranial electrodes.Significance: Our algorithm has many potential applications for understanding the impact of mTL epileptiform discharges in epilepsy and on cognition, and for developing therapies to specifically reduce mTL epileptiform activity.

show abstract

Implementation and evaluation of an interictal spike detector

Cited by 14 publications

References 15 publications

Interictal epileptiform discharges impair word recall in multiple brain areas

Interictal epileptiform discharges impair word recall in multiple brain areas

40‐Hz auditory stimulation for intracranial interictal activity: A pilot study

Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning

Contact Info

Product

Resources

About