Ictal and Interictal Epileptiform Electroencephalogram Patterns

Yum, Alma; Shvarts, Vladimir

doi:10.1017/9781108754200.014

Cited by 2 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Continuous electroencephalography (cEEG) plays an important role in monitoring and diagnosis of epilepsy. Automatic detection of epileptiform discharges and distinguishing these activities from nonepileptiform abnormalities (Yum and Shvarts 2019;Shi et al 2020) and normal/benign EEG activities (Li et al 2020) are of great importance in the biomedical field, because that experts with various levels of diagnostic experience usually report discrepant opinions on the EEG records (Xiang et al 2015). In particular, patient-independent epileptiform detection aims at identifying seizures within an EEG recording without separate finetuning efforts on new data to establish a subject-specific de-tector.…”

Section: Introductionmentioning

confidence: 99%

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

et al. 2022

View full text Add to dashboard Cite

Patient-independent detection of epileptic activities based on visual spectral representation of continuous EEG (cEEG) has been widely used for diagnosing epilepsy. However, precise detection remains a considerable challenge due to subtle variabilities across subjects, channels and time points. Thus, capturing fine-grained, discriminative features of EEG patterns, which is associated with high-frequency textural information, is yet to be resolved. In this work, we propose Scattering Transformer (ScatterFormer), an invariant scattering transform-based hierarchical Transformer that specifically pays attention to subtle features. In particular, the disentangled frequency-aware attention (FAA) enables the Transformer to capture clinically informative high-frequency components, offering a novel clinical explainability based on visual encoding of multichannel EEG signals. Evaluations on two distinct tasks of epileptiform detection demonstrate the effectiveness our method. Our proposed model achieves median AUCROC and accuracy of 98.14%, 96.39% in patients with Rolandic epilepsy. On a neonatal seizure detection benchmark, it outperforms the state-of-the-art by 9% in terms of average AUCROC.

show abstract

Section: Introductionmentioning

confidence: 99%

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

et al. 2022

View full text Add to dashboard Cite

show abstract

“…It was also found that EEG can be normal in about 5 % of cases, which in turn does not exclude epileptogenicity [10]. In addition, it is known that about 10 % of patients without epilepsy have non-specific EEG abnormalities, and about 1 % can have interictal epileptiform abnormalities without seizures [22]. Another study [23] found that the absence of EEG disturbances did not exclude the occurrence of acute symptomatic seizures.…”

Section: Diagnosismentioning

confidence: 99%

1

Chemer¹,

Shevchenko²

2021

INJ

View full text Add to dashboard Cite

There is a tendency towards growing number of strokes in aging population. One of the most significant complications of stroke is post-stroke seizures (PSS), which cause nearly 11 % of all cases of epilepsy. The most important risk factors of seizures after stroke are severity of the stroke, involvement of the cortex and intracerebral hemorrhage. There are two mains forms of PSS — early- and late-onset seizures. The pathogenesis of early-onset seizures is mainly due to cytotoxic and metabolic changes in the ischemic focus in contrast to late-onset seizures, which mostly occur as a result of persistent changes in nervous system excitability. There are following types of seizures in adult patients with post-stroke complications: simple partial, generalized tonic-clonic and generalized seizures. Evaluation of electroencephalography and computed tomography results is an important diagnostic tool of the first line. At the same time, brain magnetic resonance imaging and magnetic resonance angiography are the more preferable methods of neuroimaging due to their more informative grade in detecting cortical malformations, small lesions and cavernomas. Pharmacological management of PSS is traditionally divided into two main categories: prophylactic and symptomatic treatment. Prophylactic antiepileptic treatment in stroke patients, including those with intracerebral haemorrhage to prevent an attack, is not recommended by the American Heart Association and European Stroke Organisation guidelines. Some authors indicate that diuretics, in particular thiazides and furosemide, may be protective, reducing the risk of seizures. Carbamazepine, sodium valproate, lamotrigine, oxcarbazepine or gabapentin are the most used symptomatic drugs recommended as a first-line treatment.

show abstract

Ictal and Interictal Epileptiform Electroencephalogram Patterns

Cited by 2 publications

References 39 publications

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

1

Contact Info

Product

Resources

About