University of Twente Student Theses

Login

Clustering and source localisation of interictal epileptiform discharges in scalp EEG and design of an interface for the clinic.

Steenis, E.M. van (2021) Clustering and source localisation of interictal epileptiform discharges in scalp EEG and design of an interface for the clinic.

[img] PDF
21MB
Abstract:This work presents an algorithms that localises, clusters and determines the sources of Interictal Epileptiform Discharges (IEDs), based on the output of a deep learning model. The results are presented to the neurologists with an interface design. The resulting clusters of 31 patients were analysed by an expert. Dipole modelling determined the dipoles of the first peak of cluster averages and their Goodness of Fit (GoF) values. Semi-functional prototypes were used for usability testing, to gain insight into user preferences and interaction with the interface. The algorithm found correct clusters for all patients. IEDs from different brain areas were found for almost all multi-focal patients. The dipoles of Rolandic clusters were located in the centrotemporal area. Correct clusters showed higher GoF values (84.0% ± 17.4 (mean ± sd)) than incorrect clusters (64.7% ± 17.2). Usability testing with semi-functional prototypes confirmed that the images are familiar to the end users and the interaction is intuitive. The algorithm decreases EEG analysis time in the clinic. The interface design improves ease of use and clinical acceptance.
Item Type:Essay (Master)
Faculty:TNW: Science and Technology
Subject:42 biology, 44 medicine, 50 technical science in general
Programme:Biomedical Engineering MSc (66226)
Link to this item:http://purl.utwente.nl/essays/88434
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page