Abstract
PurposeScalp EEG remains the standard clinical procedure for the diagnosis of epilepsy. Manual detection of inter-ictal epileptiform discharges (IEDs) is slow and cumbersome, and few automated methods are used to assist in practice. This is mostly due to low sensitivities, high false positive rates, or a lack of trust in the automated method. In this study we aim to find a solution that will make computer assisted detection more efficient than conventional methods, while preserving the detection certainty of a manual search.MethodsOur solution consists of two phases. First, a detection phase finds all events similar to epileptiform activity by using a large database of template waveforms. Individual template detections are combined to form “IED nominations”, each with a corresponding certainty value based on the reliability of their contributing templates. The second phase uses the ten nominations with highest certainty and presents them to the reviewer one by one for confirmation. Confirmations are used to update certainty values of the remaining nominations, and another iteration is performed where ten nominations with the highest certainty are presented. This continues until the reviewer is satisfied with what has been seen. Reviewer feedback is also used to update template accuracies globally and improve future detections.Key FindingsUsing the described method and fifteen evaluation EEGs (241 IEDs), one third of all inter-ictal events were shown after one iteration, half after two iterations, and 74%, 90%, and 95% after 5, 10 and 15 iterations respectively. Reviewing fifteen iterations for the 20–30 min recordings 1took approximately 5 min.SignificanceThe proposed method shows a practical approach for combining automated detection with visual searching for inter-ictal epileptiform activity. Further evaluation is needed to verify its clinical feasibility and measure the added value it presents.
Highlights
Regardless of all the technological advances in recent years, routine scalp EEG is still used as the standard clinical procedure for diagnosing epilepsy
By using a wide range of ictal epileptiform discharges (IEDs) samples extracted from EEG training data and using the principle of voting and reliability to prioritize detections, the system is able to scale to any recording given that the IEDs it contains are similar in morphology than the templates in the database
Given that no thresholds were used to discard events with low certainties, the system would have a very high false positive rate if all nominations had to be shown to a reviewer
Summary
Regardless of all the technological advances in recent years, routine scalp EEG is still used as the standard clinical procedure for diagnosing epilepsy. The standard diagnostic strategy in a first-time seizure patient is to perform a routine 20–30 min scalp EEG recording and determine if any inter-ictal epileptiform discharges (IEDs) are present. IEDs appear in the raw signal in the form of spikes, sharp waves, polyspikes, or spike and slow-wave discharges. Given that these patterns are correlated with a high likelihood of a recurrent seizure, their presence play an important role in the diagnosis of epilepsy. Longer recordings and sleep-deprived EEGs have shown to improve the chances of finding inter-ictal activity and thereby yield higher diagnostic efficiency [3,4,5,6], but given the visual burden already with shorter recordings, this is difficult to implement on a routine basis. Beyond the diagnosis of epilepsy, there is a need to accurately mark epileptiform activity and investigate properties such as the potential seizure focus and epilepsy type
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
