Correcting for physiological ripples improves epileptic focus identification and outcome prediction

Zweiphenning, Willemiek; Ellenrieder, Nicolás von; Dubeau, François; Martineau, Laurence; Minotti, Lorella; Hall, Jeffery A.; Chabardès, Stéphan; Dudley, Roy; Kahane, Philippe; Gotman, Jean; Frauscher, Birgit

doi:10.1111/epi.17145

Cited by 27 publications

(30 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…40,41 Fast ripples (250-500 Hz) might more specifically localize epileptogenic zones than ripples do (80-250 Hz), but their detection rate is much lower than ripples. 13 Correcting the HFO detection rate with region-specific normative values seems a reasonable approach, 32,[42][43][44] but this does not determine each HFO event as either pathological or physiological.…”

Section: Discussionmentioning

confidence: 99%

Characterizing physiological high-frequency oscillations using deep learning

Zhang

Chung

Ngo

et al. 2022

Preprint

View full text Add to dashboard Cite

Objective: Intracranially-recorded interictal high-frequency oscillations (HFOs) have been proposed as a promising spatial biomarker of the epileptogenic zone. However, HFOs can also be recorded in the healthy brain regions, which complicates the interpretation of HFOs. The present study aimed to characterize salient features of physiological HFOs using deep learning (DL). Methods: We studied children with neocortical epilepsy who underwent intracranial strip/grid evaluation. Time-series EEG data were transformed into DL training inputs. The eloquent cortex (EC) was defined by functional cortical mapping and used as a DL label. Morphological characteristics of HFOs obtained from EC (ecHFOs) were distilled and interpreted through a novel weakly supervised DL model. Results: A total of 63,379 interictal intracranially-recorded HFOs from 18 children were analyzed. The ecHFOs had lower amplitude throughout the 80-500 Hz frequency band around the HFO onset and also had a lower signal amplitude in the low frequency band throughout a one-second time window than non-ecHFOs, resembling a bell-shaped template in the time-frequency map. A minority of ecHFOs were HFOs with spikes (22.9%). Such morphological characteristics were confirmed to influence DL model prediction via perturbation analyses. Using the resection ratio (removed HFOs/detected HFOs) of non-ecHFOs, the prediction of postoperative seizure outcomes improved compared to using uncorrected HFOs (area under the ROC curve of 0.82, increased from 0.76). Interpretation: We characterized salient features of physiological HFOs using a DL algorithm. Our results suggested that this DL-based HFO classification, once trained, might help separate physiological from pathological HFOs, and efficiently guide surgical resection using HFOs.

show abstract

Section: Discussionmentioning

confidence: 99%

Characterizing physiological high-frequency oscillations using deep learning

Zhang

Chung

Ngo

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…While in some other brain cases, for instance, cognitive task, vision, movement, epilepsy, etc., high frequency true ripples are used as a biomarker [ 42 , 43 , 44 , 45 ]. Therefore, in these cases, removing spikes and sharp artifacts, which cause false ripples, is required [ 46 , 47 ]. In fact, initially detecting true ripples using any algorithm required a band-pass filter; therefore, any sharp signal passing through this filter would be presented as a false ripple which is due to the ringing effect of this filter.…”

Section: Study Backgroundmentioning

confidence: 99%

Implementation of a Morphological Filter for Removing Spikes from the Epileptic Brain Signals to Improve Identification Ripples

Al-Bakri

Martínek

Pelc

et al. 2022

Sensors

View full text Add to dashboard Cite

Epilepsy is a very common disease affecting at least 1% of the population, comprising a number of over 50 million people. As many patients suffer from the drug-resistant version, the number of potential treatment methods is very small. However, since not only the treatment of epilepsy, but also its proper diagnosis or observation of brain signals from recordings are important research areas, in this paper, we address this very problem by developing a reliable technique for removing spikes and sharp transients from the baseline of the brain signal using a morphological filter. This allows much more precise identification of the so-called epileptic zone, which can then be resected, which is one of the methods of epilepsy treatment. We used eight patients with 5 KHz data set and depended upon the Staba 2002 algorithm as a reference to detect the ripples. We found that the average sensitivity and false detection rate of our technique are significant, and they are ∼94% and ∼14%, respectively.

show abstract

“…These algorithms have varying aims, primarily to improve SOZ localization [ 72 ], reduce functional deficits, and reduce the time needed for interpretation and presurgical investigations [ 76 ]. There is much work being done on reliably predicting the probability of seizure freedom [ 70 , 71 , 77 , 78 ] and postoperative satisfaction [ 79 ] following a planned resection in advance – a crucial step in providing the patient with as much accurate information as possible when making an informed decision on whether to proceed with epilepsy surgery or not.…”

Section: Expert Opinionmentioning

confidence: 99%

Previous, current, and future stereotactic EEG techniques for localising epileptic foci

Dasgupta

Miserocchi

McEvoy

et al. 2022

Expert Review of Medical Devices

View full text Add to dashboard Cite

Introduction Drug-resistant focal epilepsy presents a significant morbidity burden globally, and epilepsy surgery has been shown to be an effective treatment modality. Therefore, accurate identification of the epileptogenic zone for surgery is crucial, and in those with unclear noninvasive data, stereoencephalography is required. Areas covered This review covers the history and current practices in the field of intracranial EEG, particularly analyzing how stereotactic image-guidance, robot-assisted navigation, and improved imaging techniques have increased the accuracy, scope, and use of SEEG globally. Expert Opinion We provide a perspective on the future directions in the field, reviewing improvements in predicting electrode bending, image acquisition, machine learning and artificial intelligence, advances in surgical planning and visualization software and hardware. We also see the development of EEG analysis tools based on machine learning algorithms that are likely to work synergistically with neurophysiology experts and improve the efficiency of EEG and SEEG analysis and 3D visualization. Improving computer-assisted planning to minimize manual input from the surgeon, and seamless integration into an ergonomic and adaptive operating theater, incorporating hybrid microscopes, virtual and augmented reality is likely to be a significant area of improvement in the near future.

show abstract

Correcting for physiological ripples improves epileptic focus identification and outcome prediction

Cited by 27 publications

References 49 publications

Characterizing physiological high-frequency oscillations using deep learning

Characterizing physiological high-frequency oscillations using deep learning

Implementation of a Morphological Filter for Removing Spikes from the Epileptic Brain Signals to Improve Identification Ripples

Previous, current, and future stereotactic EEG techniques for localising epileptic foci

Contact Info

Product

Resources

About