A novel scheme for the validation of an automated classification method for epileptic spikes by comparison with multiple observers

Sharma, Niraj; Pedreira, Carlos Eduardo; Centeno, María; Chaudhary, Umair J.; Wehner, Tim; França, Lucas Gabriel Souza; Yadee, Tinonkorn; Murta, Teresa; Leite, Marco; Vos, Sjoerd B.; Ourselin, Sébastien; Diehl, Beate; Lemieux, Louis

doi:10.1016/j.clinph.2017.04.016

Cited by 11 publications

(25 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(2017). This study validated an automated neuronal spike classification algorithm, Wave_clus (WC) (Quiroga et al., 2004; Pedreira et al., 2014) for the automated classification of icEEG IEDs (Sharma et al., 2017), by formally demonstrating that the WC results fall within the observed inter-rater variability for three expert EEG reviewers.…”

Section: Introductionmentioning

confidence: 59%

“…Two IED classification strategies were employed for subsequent BOLD mapping using general linear modelling (GLM): firstly, conventional visual IED classification (Vulliemoz et al., 2011); and secondly, automated IED classification using a version of WC (Quiroga et al., 2004) adapted specifically for epileptic discharges on icEEG (Sharma et al., 2017).…”

Section: Methodsmentioning

confidence: 99%

“…However as noted above, the high sensitivity of icEEG can result in much more abundant IEDs than in scalp recordings, and often more varied in their morphology and distribution than on scalp EEG (Spencer et al., 2007). Indeed, the detection and classification of IEDs on icEEG by clinical neurophysiologists can be time consuming and is unreliable (Dümpelmann and Elger, 1999; Barkmeier et al., 2012; Gaspard et al., 2014; Sharma et al., 2017). Furthermore, the incorrect and inconsistent markings of IEDs have been shown to result in an excess of false positive and false negative BOLD clusters (Flanagan et al., 2009).…”

Section: Introductionmentioning

confidence: 99%

“…Such methods are able to detect IEDs but do not exploit the relationship between the activity across channels. Given that IED field distribution is an important consideration in the way IEDs are typically classified visually, we favour automated schemes that incorporate the waveforms across several channels (Hufnagel et al., 2000; Bourien et al., 2005; Pedreira et al., 2014; Sharma et al., 2017). To our knowledge, the only such classification scheme evaluated by comparison with multiple observers was Sharma et al.…”

Section: Introductionmentioning

confidence: 99%

“…In the present work, our aim was to use this automated IED classification algorithm (WC) (Sharma et al., 2017) to determine whether the models of the IED-related BOLD changes obtained based on the resulting IED classification are comparable to those obtained using the traditional, visual approach. This follows our previous work on the evaluation of the value of the automated classification of IED on scalp EEG-fMRI based on their BOLD correlates (Pedreira et al., 2014); In essence we use the fMRI data as an additional, independent means of assessing the IED classifications’ biological value.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

BOLD mapping of human epileptic spikes recorded during simultaneous intracranial EEG-fMRI: The impact of automated spike classification

et al. 2019

Self Cite

View full text Add to dashboard Cite

ObjectivesSimultaneous intracranial EEG and functional MRI (icEEG-fMRI) can be used to map the haemodynamic (BOLD) changes associated with the generation of IEDs. Unlike scalp EEG-fMRI, in most patients who undergo icEEG-fMRI, IEDs recorded intracranially are numerous and show variability in terms of field amplitude and morphology. Therefore, visual marking can be highly subjective and time consuming. In this study, we applied an automated spike classification algorithm, Wave_clus (WC), to IEDs marked visually on icEEG data acquired during simultaneous fMRI acquisition. The motivation of this work is to determine whether using a potentially more consistent and unbiased automated approach can produce more biologically meaningful BOLD patterns compared to the BOLD patterns obtained based on the conventional, visual classification.MethodsWe analysed simultaneous icEEG-fMRI data from eight patients with severe drug resistant epilepsy, and who subsequently underwent resective surgery that resulted in a good outcome: confirmed epileptogenic zone (EZ). For each patient two fMRI analyses were performed: one based on the conventional visual IED classification and the other based on the automated classification. We used the concordance of the IED-related BOLD maps with the confirmed EZ as an indication of their biological meaning, which we compared for the automated and visual classifications for all IED originating in the EZ.ResultsAcross the group, the visual and automated classifications resulted in 32 and 24 EZ IED classes respectively, for which 75% vs 83% of the corresponding BOLD maps were concordant. At the single-subject level, the BOLD maps for the automated approach had greater concordance in four patients, and less concordance in one patient, compared to those obtained using the conventional visual classification, and equal concordance for three remaining patients. These differences did not reach statistical significance.ConclusionWe found automated IED classification on icEEG data recorded during fMRI to be feasible and to result in IED-related BOLD maps that may contain similar or greater biological meaning compared to the conventional approach in the majority of the cases studied. We anticipate that this approach will help to gain significant new insights into the brain networks associated with IEDs and in relation to postsurgical outcome.

show abstract

Section: Introductionmentioning

confidence: 59%