You are hereEpilepsy: Automatic Seizure Detection and Focus Localization for Drug-Resistant Patients
Epilepsy: Automatic Seizure Detection and Focus Localization for Drug-Resistant Patients
Epilepsy affects 50 million people worldwide -, and 30% remain drug-resistant -. This has increased interest in both chronic and responsive neurostimulation -, which is most effective when administered at or near the foci and immediately prior to or at the seizure onset. Precise focus localization and automatic online seizure detection (AOSD) from intracranial EEG (iEEG) recordings are therefore critical for closed-loop intervention, but remain challenging problems. Automated localization schemes have primarily been developed using univariate and bivariate features but lack consistency and accuracy -. Several AOSD algorithms has been proposed thus far (- to name only a few) and though they are highly sensitive (large number of true positives), these algorithms generally have low specificity (large number of false positives), which limits their clinical use. The lack of specificity presumably occurs because (i) they compute statistics from a few channels at a time which may not capture network dynamics of the brain, (ii) the channels used may be too far from the focus, and/or (iii) the detection thresholds are not explicitly optimized to maximize AOSD performance.
This program proposes a novel computational framework for seizure foci localization and AOSD that involves (i) constructing multivariate statistics from all electrodes to localize foci and distinguish between non-ictal vs. ictal states; (ii) modeling the evolution of these statistics in each state and the state-transition probabilities; and, (iii) developing an optimal model-based strategy to detect transitions to ictal states from sequential neural measurements. This strategy is formulated as the Bayesian “Quickest Detection” (QD) of the seizure onset , is solved via control optimization tools , and explicitly minimizes both the distance between detected and unequivocal onset times and the probability of false positives. Our team of clinicians and engineers will combine state of the art tools from matrix theory, system identification, and control theory to construct this framework using iEEG recordings from epilepsy patients.
We hypothesize that (i) foci localization accuracy will improve using multivariate statistics computed from all channels at a time, and that (ii) the QD algorithm combined with multivariate statistics will detect seizure onsets with fewer false positives while maintaining high true positive rates and smaller delays than current algorithms. We will test our hypotheses through the following research aims.
Aim 1: To identify robust multivariate statistics for seizure focus localization. Multi-site iEEG signals will be processed into generalized non-square connectivity matrices that describe the time-varying spectral dependencies between all the channels over multiple frequency bands. The singular value decomposition (SVD), a tool from matrix theory that highlights dependencies within a matrix, will be used to extract multivariate statistics (e.g., leading singular vector) that capture the nodes of the brain network with the strongest connections across multiple frequency bands. These nodes are an estimation of the seizure foci and will be compared to those annotated by the clinicians.
Aim 2: To construct models describing the evolution of multivariate statistics. The network-based statistics from Aim 1 evolve over time because of subclinical changes of the brain activity that affect iEEG data in time and frequency. To estimate these changes, we will model the evolution of each SVD statistic through a Hidden Markov Model (HMM). The HMMs will be estimated from training data for each patient and will characterize (i) neural dynamics in non-ictal and ictal states, and (ii) the probability distribution of the actual transition (T) from any non-ictal to ictal state.
Aim 3: To implement, compare, and validate QD. We will implement, test, and validate a QD-based strategy for AOSD on a rich clinical data set. For each patient and statistic, the QD strategy (i) will use the HMM to recursively estimate the a posteriori probability of being in ictal state conditioned on current and past iEEG measurements; and (ii) will compare this probability to a time-varying, state-dependent, unsupervised threshold to decide whether a seizure is occurred or not. This threshold will be obtained by solving a QD problem which explicitly minimizes the probability of false positives as well as the expected distance between actual seizure onset (T) and detected transition time (T_QD). The QD strategy will be compared to state-of-the-art AOSD schemes and critical aspects of the QD (e.g., computational and memory requirements, safety, etc.) will be validated to prove whether or not our control-theoretical approach performs significantly better than existing approaches.
- de Boer HM, Mula M, Sander JW (2008) The global burden and stigma of epilepsy. Epilepsy Behav. 12:540-546.
- Leonardi M, Ustun TB (2002) The global burden of epilepsy. Epilepsia 43:S21-S25.
- Sander JW (2003) The epidemiology of epilepsy revisited. Curr Opin Neurol. 16:165-170.
- Theodore WH, Spencer SS, Wiebe S, et al. (2006) Epilepsy in North America: a report prepared under the auspices of the global campaign against epilepsy, the International Bureau for Epilepsy, the International League Against Epilepsy, and the World Health Organization. Epilepsia 47:1700-1722.
- Elger CE, Schmidt D (2008) Modern management of epilepsy: a practical approach. Epilepsy Behav. 12:501-539.
- Perucca E, Kwan P (2005) Overtreatment in epilepsy. How it occurs and how it can be avoided. CNS Drugs 19:897-908.
- Schmidt D (2009) Drug treatment of epilepsy: options and limitations. Epilepsy Behav. 15:56-65.
- Jiruska P, Powell AD, Deans JK, Jefferys JG (2010) Effects of direct brain stimulation depend on seizure dynamics. Epilepsia 51:S93-S97.
- Jobst BC, Darcey TM, Thadani VM, Roberts DW (2010) Brain stimulation for the treatment of epilepsy. Epilepsia 51:S88-S92.
- Morrell M. (2006) Brain stimulation for epilepsy: Can scheduled or responsive neurostimulation stop seizures? Curr Opin Neurol. 19:164-168.
- Anderson WS, Kossoff EH, Bergey GK, Jallo GI (2008) Implantation of a responsive neurostimulator device in patients with refractory epilepsy. Neurosurg Focus. 25:E12.
- Fountas KN, Smith JR, Murro AM, Politsky J, et al. (2005) Implantation of a closed-loop stimulation in the management of medically refractory focal epilepsy: a technical note. Stereotact Funct Neurosurg. 83:153-158.
- Morrell M, Hirsch L, Bergey G, Barkley G, et al. (2008) Long-term safety and efficacy of the RNSTM system in adults with medically intractable partial onset seizures. Proc. American Epilepsy Society Annual Meeting. Abstract No. 8536. www.aesnet.org.
- Morrell MJ (2011): On behalf of the RNS System in Epilepsy Study Group. Responsive cortical stimulation for the treatment of medically intractable partial epilepsy. Neurology; 77:1295-1304.
- Fisher RS, van Emde Boas S, Blume W, Elger C, et al. (2005) Epileptic seizures and epilepsy: definitions proposed by the international league against epilepsy (ILAE) and the international bureau for epilepsy (IBE). Epilepsia 46:470-472.
- Ben-Jacob E, Boccaletti S, Pomyalov A, Procaccia I., Towle V L (2007) Detecting and localizing the foci in human epileptic seizures. Chaos 17:043113.
- Ben-Jacob E, Doron I, Gazit T, Rephaeli E, Sagher O, Towle V L (2007b) Mapping and assessment of epileptogenic foci using frequency-entropy templates. Phys. Rev. E 76:051903.
- Bettus G, Wendling F, Guye M, Valton L, Regis J, Chauvel P, Bartolomei F (2008) Enhanced EEG functional connectivity in mesial temporal lobe epilepsy. Epilepsy Res. 81:58-68.
- Franaszczuk P J, Bergey G K, Kamifiski M J (1994) Analysis of mesial temporal seizure onset and propagation using the directed transfer function method. Electroenceph. Clin. Neurophysiol. 91:413-427.
- Franaszczuk P J, Bergey G K (1998) Application of the directed transfer function method to mesial and lateral onset temporal lobe seizures. Brain Topogr. 11(1):13-21.
- Gotman J (1983) Measurements of small time differences between EEG channels: method and application to epileptic seizure propagation. Electroenceph. clin. Neurophysiol., 56:501-514.
- Luders H O, Awad I (1992) Conceptual considerations. In Epilepsy Surgery. Raven Press, New York pgs 51-62.
- Lai Y-C, Harrison M, Frei M, Osorio I (2004) Controlled test for predictive power of Lyapunov exponents: Their inability to predict epileptic seizures. Chaos, 14(3):630-642.
- Osterhage H, Mormann F, Wagner T, Lehnertz K (2008) Detecting directional coupling in the human epileptic brain: Limitations and potential pitfalls. Phys Rev. E, 77:011914.
- Sabesan S, Good L B, Tsaklis K S, Spanias A, Treiman D M, Iasemidis L D (2009) Information flow and application to epileptogenic focus localization from intracranial EEG. IEEE Trans. Neural Sys. Rehab. Eng. 17(3):244-253.
- Schevon C A, Cappell J, Emerson R, Isler J, Grieve P, Goodman R, Mckhann G, Weiner H, Doyle W, Kuzniecky R, Devinsky O, Gilliam F (2007) Cortical abnormalities in epilepsy revealed by local EEG synchrony. NeuroImage 35:140:148.
- Staniek M, Lehnertz K (2008) Symbolic transfer entropy. Phys Rev. Let. 100:158101.
- Warren C P, Hu S, Stead M, Brinkmann B H, Bower M R, Worrell G A (2010) Synchrony in normal and focal epileptic brain: the seizure onset zone is functionally disconnected. J. Neurophysiol. 104:3530-3539.
- Zaveri H P, Pincus S M, Goncharva I I, Duckrow R B, Spencer D D, Spencer S S (2009) Localization-related epilepsy exhibits significant connectivity away from the seizure-onset area. NeuroReport, 20:891-895.
- Andrzejak R G, Chicharro D, Lehnertz K, Mormann F (2011) Using bivariate signal analysis to characterize the epileptic focus: The benefit of surrogates. Phys. Rev. E 83:046203.
- Alarcon G, Garcia Seoane J J, Binnie C D, Martin Miguel M C, Juler J, Polkey C E, Elwes R D C, Ortiz Blasco J M (1997) Origin and propagation of interictal discharges in the acute electrocorticogram Implications for pathophysiology and surgical treatment of temporal lobe epilepsy. Brain 120:2259-2282.
- Osorio I, Frei MG. (2009) Real-time detection, quantification, warning, and control of epileptic seizures: the foundations for a scientific epileptology. Epilepsy Behav. 16:391-396.
- Esteller R, Echauz J, D'Alessandro M, Worrell G, et al. (2005) Continuous energy variation during the seizure cycle: towards an on-line accumulated energy. Clin Neurophysiol. 116:517-526.
- Gardner AB, Worrell GA, Marsh E, Dlugos D, Litt B. (2007) Human and automated detection of high-frequency oscillations in clinical intracranial EEG recordings. Clin Neurophysiol. 118:1134-1143.
- Temko A, Thomas E, Marnane W, Lightbody G, Boylan G. (2011) EEG-based neonatal seizure detection with Support Vector Machines. Clin Neurophysiol. 122:464-473.
- Guo L, Rivero D, Dorado J, Rabuñal JR, Pazos A. (2010) Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks. J. Neurosci. Methods 191:101-109.
- Shoeb A, Pang T, Guttag J, Schachter S (2009) Non-invasive computerized system for automatically initiating vagus nerve stimulation following patient-specific detection of seizures or epileptiform discharges. Int J Neural Syst. 19:157-172.
- Lee HC, van Drongelen W, McGee AB, Frim DM, Kohrman MH. (2007) Comparison of seizure detection algorithms in continuously monitored pediatric patients. J Clin Neurophysiol 24:137-146.
- Shiryayev AN. (1963) On optimum methods in quickest detection problems. Theory Probab Appl. 8: 22-46.
- Poor HV, Hadjiliadis O. (2008) Quickest Detection. Cambridge, UK: Cambridge Univ. Press.
- Bertsekas DP. (2005) Dynamic Programming and Optimal Control. Belmont, MA: Athena Scientific.