Automatic Diagnosis of Temporal Lobe Epilepsy and Its Lateralization Using EEG-Based Directed

Automatic Diagnosis of Temporal Lobe Epilepsy and its Lateralization using EEG-based Directed Functional Connectivity

T. Verhoeven1*, A. Coito2, P. van Mierlo1, M. Seeck3, C. M. Michel2, G. Plomp4, J. Dambre1, S. Vulliemoz3

1Department of Electronics and Information Systems, Ghent University, Belgium;2Functional Brain Mapping Lab, University of Geneva, Geneva, Switzerland 3 Epilepsy Unit, University Hospital of Geneva, Geneva, Switzerland4 Perceptual Networks Group, Department of Psychology, University of Fribourg, Switzerland.

*Sint-Pietersnieuwstr. 41, 9000 Gent, Belgium. E-mail:

Introduction:

Temporal lobe epilepsy (TLE) is the most common type of pharmaco-resistant epilepsy in adults.During pre-surgical evaluation, EEG is recorded to identify pathological activity such as interictal spikes that can help to identify the epileptogenic zone. However, sometimes no spikes are recorded in the scalp EEG. The characterization of brain network dysfunction in the absence of visible scalp epileptic activity could be very important to improve diagnostic accuracy and treat these patients. Here, we aimed to build a classification system that uses EEG-based directed functional connectivity patterns to assign a patient to one of three classes: left TLE (LTLE), right TLE (RTLE) or healthy control.

Methods:

Sixty subjects underwent a resting-state high-density EEG recording: 20 LTLE, 20 RTLE and 20 healthy controls. For each subject sixty 1-sec epochs free of artifacts or interictal spikes were selected. The cortical source activity was obtained for 82 regions of interest (ROIs) using an individual head model and distributed linear inverse solution. The whole-brain directed functional connectivity was estimated in the theta, alpha and beta frequency bands using Granger-causal modeling (weighted Partial Directed Coherence[1-3]) applied to the source signal of all ROIs. The summed outflow from each ROI was computed for each frequency band (total of 246 connectivity values per subject). Details of this analysis can be found in [4]. Here, we used logistic regression classifiers which take a linear combination of these connectivity values and compare it with a threshold in order to assign the subject to one of the three given classes. A leave-one-out procedure was used to compute the mean classification accuracy on subjects that are not used as example to build the classifier system. Due to the low amount of recorded subjectscompared to the number of connectivity values, a subsetwas selected for classification purpose. We selected a maximum of six connectivity values making use of a greedy forward selection algorithm: gradually adding connectivity values to improve the classification accuracy. Finally, three classifiers were built: ‘Control vs. LTLE’, ‘Control vs. RTLE’ and ‘LTLE vs. RTLE’. In the final classification system, a new subject is assigned to the class that was most voted for by these three individual classifiers. Subjects for which every class is voted once were classified as undefined.

Results:

The selected brain regions and corresponding frequency bands for the three classifiers are depicted in Figure 1. The ‘Control vs. RTLE’ classifier achieved an accuracy of 92.5% (sensitivity: 95.0%, specificity 90.0%), the ‘Control vs. LTLE’ classifier an accuracy of 87.5% (sensitivity 90.0%, specificity 85.0%) and the ‘LTLE vs. RTLE’ classifier an accuracy of 80.0% (sensitivity 85.0%, specificity 75.0%). Combining these individual classifiers in one system resulted in the confusion matrix shown in Figure 2.

Figure1Connectivity values selected for building the three individual classifiers.

Figure2Confusion matrix showing how the subjects from the three classes are classified by the system.

Conclusion:

We had previously found significant differences in the summed outflow from regions included in the Default-Mode Network and also known to be important in TLE in patients vs healthy controls using these EEG periods without interictal spikes[4]. Here, the high accuracy achieved in classifying a subject as LTLE, RTLE or healthy control in periods of EEG without visible interictal pathological events further demonstrates the potential of resting-state EEG-based directed functional connectivity for the diagnosis and lateralization of TLE. This could thus constitute a new important clinical biomarker in surgical candidates or even earlier in the course of the disease, especially to lateralize the epilepsy.

References

[1]L. A. Baccala, and K. Sameshima (Jun, 2001), 'Partial directed coherence: a new concept in neural structure determination',Biol Cybern,vol. 84, no. 6, pp. 463-74.

[2]L. Astolfi, F. Cincotti, D. Mattia, M. G. Marciani, L. A. Baccala, F. de Vico Fallani, S. Salinari, M. Ursino, M. Zavaglia, and F. Babiloni (Sep, 2006), 'Assessing cortical functional connectivity by partial directed coherence: simulations and application to real data',IEEE Trans Biomed Eng,vol. 53, no. 9, pp. 1802-12.

[3]G. Plomp, C. Quairiaux, C. M. Michel, and L. Astolfi (Aug, 2014), 'The physiological plausibility of time-varying Granger-causal modeling: normalization and weighting by spectral power',Neuroimage,vol. 97, pp. 206-16.

[4]A. Coito, M. Genetti, D. Pittman, G. R. Iannotti, A. Thomschewski, Y. Höller, E. Trinka, R. Wiest, M. Seeck, C. M. Michel, G. Plomp, and S. Vulliemoz (2016), 'Altered directed connectivity in temporal lobe epilepsy in the absence of interictal spikes: a high density EEG study',Epilepsia,vol. in press.