Detecting Epileptic Regions Based on Global Brain Connectivity Patterns

Andrew Sweet¹, Archana Venkataraman¹, Steven M. Stufflebeam², Hesheng Liu², Naoro Tanaka², Joseph Madsen³, and Polina Golland¹

¹MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, UK

²Athinoula A. Martinos Center for Biomedical Imaging, Boston, MA, UK

³Boston Children’s Hospital, Boston, MA, UK

Abstract. We present a method to detect epileptic regions based on functional connectivity differences between individual epilepsy patients and a healthy population. Our model assumes that the global functional characteristics of these differences are shared across patients, but it allows for the epileptic regions to vary between individuals. We evaluate the detection performance against intracranial EEG observations and compare our approach with two baseline methods that use standard statistics. The baseline techniques are sensitive to the choice of thresholds, whereas our algorithm automatically estimates the appropriate model parameters and compares favorably with the best baseline results. This suggests the promise of our approach for pre-surgical planning in epilepsy.

LNCS 8149, p. 98 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2013