Abstract
K-Means is one of the most popular clustering algorithms that partitions observations into nonoverlapping subgroups based on a predefined similarity metric. Its drawbacks include a sensitivity to noisy features and a dependency of its resulting clusters upon the initial selection of cluster centroids resulting in the algorithm converging to local optima. Minkowski weighted K-Means (MWK-Means) addresses the issue of sensitivity to noisy features, but is sensitive to the initialization of clusters, and so the algorithm may similarly converge to local optima. Particle Swarm Optimization (PSO) uses a globalized search method to solve this issue. We present a hybrid Particle Swarm Optimization (PSO) + MWK-Means clustering algorithm to address all the above problems in a single framework, while maintaining benefits of PSO and MWK Means methods. This study investigated the utility of this approach in lateralizing the epileptogenic hemisphere for temporal lobe epilepsy (TLE) cases using magnetoencephalography (MEG) coherence source imaging (CSI) and diffusion tensor imaging (DTI). Using MEG-CSI, we analyzed preoperative resting state MEG data from 17 adults TLE patients with Engel class I outcomes to determine coherence at 54 anatomical sites and compared the results with 17 age- and gender-matched controls. Fiber-tracking was performed through the same anatomical sites using DTI data. Indices of both MEG coherence and DTI nodal degree were calculated. A PSO + MWK-Means clustering algorithm was applied to identify the side of temporal lobe epileptogenicity and distinguish between normal and TLE cases. The PSO module was aimed at identifying initial cluster centroids and assigning initial feature weights to cluster centroids and, hence, transferring to the MWK-Means module for the final optimal clustering solution. We demonstrated improvements with the use of the PSO + MWK-Means clustering algorithm compared to that of K-Means and MWK-Means independently. PSO + MWK-Means was able to successfully distinguish between normal and TLE in 97.2% and 82.3% of cases for DTI and MEG data, respectively. It also lateralized left and right TLE in 82.3% and 93.6% of cases for DTI and MEG data, respectively. The proposed optimization and clustering methodology for MEG and DTI features, as they relate to focal epileptogenicity, would enhance the identification of the TLE laterality in cases of unilateral epileptogenicity.
Similar content being viewed by others
References
Adcock J et al (2003) Quantitative fMRI assessment of the differences in lateralization of language-related brain activation in patients with temporal lobe epilepsy. Neuroimage 18(2):423–438
Aghakhani Y et al (2014) Epilepsy surgery in patients with bilateral temporal lobe seizures: a systematic review. Epilepsia 55(12):1892–1901
Barkley GL, Baumgartner C (2003) MEG and EEG in epilepsy. J Clin Neurophysiol 20:163–178
Bonilha L et al (2005) Voxel-based morphometry of the thalamus in patients with refractory medial temporal lobe epilepsy. Neuroimage 25(3):1016–1021
Bonilha L et al (2007) Extrahippocampal gray matter atrophy and memory impairment in patients with medial temporal lobe epilepsy. Hum Brain Mapp 28(12):1376–1390
Breaban, M.E. and H. Luchian (2011). PSO aided k-means clustering: introducing connectivity in k-means. in Proceedings of the 13th annual conference on Genetic and evolutionary computation. ACM.
Bulacio JC et al (2012) Long-term seizure outcome after resective surgery in patients evaluated with intracranial electrodes. Epilepsia 53(10):1722–1730
Cao, X., et al. (2014) Altered intrinsic connectivity networks in frontal lobe epilepsy: a resting-state fMRI study. Computational and mathematical methods in medicine, 2014.
Chen, C.-Y. and F. Ye (2012). Particle swarm optimization algorithm and its application to clustering analysis. in 2012 Proceedings of 17th Conference on Electrical Power Distribution. IEEE.
Coito A et al (2016) Altered directed functional connectivity in temporal lobe epilepsy in the absence of interictal spikes: a high density EEG study. Epilepsia 57(3):402–411
De Amorim RC, Mirkin B (2012) Minkowski metric, feature weighting and anomalous cluster initializing in K-Means clustering. Pattern Recogn 45(3):1061–1075
DeSalvo MN et al (2014) Altered Structural Connectome in Temporal Lobe Epilepsy. Radiology 270(3):842–848
Devinsky O et al (1993) Anterior temporal language areas in patients with early onset of temporal lobe epilepsy. Ann Neurol 34(5):727–732
Dubey AK, Gupta U, Jain S (2016) Analysis of k-means clustering approach on the breast cancer Wisconsin dataset. Int J Comput Assist Radiol Surg 11(11):2033–2047
Dupont, S et al. (2015) Lateralizing value of semiology in medial temporal lobe epilepsy. Acta Neurologica Scandinavica.
Ebersole JS, Hawes-Ebersole SH (2007) Clinical application of dipole models in the localization of epileptiform activity. J Clin Neurophysiol 24(2):120–129
Elisevich K et al (2011) An assessment of MEG coherence imaging in the study of temporal lobe epilepsy. Epilepsia 52(6):1110–1119
Engel J Jr (1996) Surgery for seizures. N Engl J Med 334(10):647–653
Englot, D.J. et al. (2015) Epileptogenic zone localization using magnetoencephalography predicts seizure freedom in epilepsy surgery. Epilepsia.
Hirsch LJ et al (1991) Temporal lobectomy in patients with bitemporal epilepsy defined by depth electroencephalography. Ann Neurol 30(3):347–356
Hsiao F-J et al (2017) Altered insula–default mode network connectivity in fibromyalgia: a resting-state magnetoencephalographic study. J Headache Pain 18(1):89
Huang JZ et al (2005) Automated variable weighting in k-means type clustering. IEEE Trans Pattern Anal Mach Intell 5:657–668
Huang, J.Z., et al. (2008) Weighting method for feature selection in k-means. Computational Methods of feature selection, p. 193–209.
Isnard J et al (2000) The role of the insular cortex in temporal lobe epilepsy. Ann Neurol 48(4):614–623
Hufnagel A et al (1994) Prognostic significance of ictal and interictal epileptiform activity in temporal lobe epilepsy. Epilepsia 35(6):1146–1153
Jenkinson M et al (2002) Improved optimization for the robust and accurate linear registration and motion correction of brain images. Neuroimage 17(2):825–841
Kaoungku N et al. (2018) The Silhouette Width Criterion for Clustering and Association Mining to Select Image Features. International Journal of Machine Learning and Computing8(1).
Knowlton RC (2008) Can magnetoencephalography aid epilepsy surgery? Epilepsy Curr 8(1):1–5
Kraskov, A. (2004) Applications of synchronization and interdependence measures in particular to EEG of epilepsy patients, in John Von Neumann Institute for Computing, NIC
Kuzniecky R et al (1997) Multimodality MRI in mesial temporal sclerosis: relative sensitivity and specificity. Neurology 49(3):774–778
Moran N et al (2001) Extrahippocampal temporal lobe atrophy in temporal lobe epilepsy and mesial temporal sclerosis. Brain 124(1):167–175
Moran J, Bowyer S, Tepley N (2005) Multi-resolution FOCUSS: a source imaging technique applied to MEG data. Brain Topogr 18(1):1–17
Moran JE, Drake CL, Tepley N (2004) ICA methods for MEG imaging. Neurol Clin Neurophysiol 2004:72
Moran, J., Manoharan, A., SM Bowyer, KM Mason, N Tepley, M. Morrell, D. Greene, BJ Smith, and GL Barkley. (2006) MEG coherence imaging compared to electrocortical recordings from neuropace implants to determine the location of ictal onset in epilepsy patients,. in 15th International Conference on Biomagnetism.. Vancouver, BC Canada: Elsiver.
Mori S, van Zijl PC (2002) Fiber tracking: principles and strategies - a technical review. NMR Biomed 15(7–8):468–480
Nazem-Zadeh MR et al (2012) Radiation therapy effects on white matter fiber tracts of the limbic circuit. Med Phys 39(9):5603–5613
Nazem-Zadeh M-R et al (2014a) Lateralization of temporal lobe epilepsy by multimodal multinomial hippocampal response-driven models. J Neurol Sci 347(1):107–118
Nazem-Zadeh, M.-R., et al. (2014b) A Bayesian averaged response-driven multinomial model for lateralization of temporal lobe epilepsy. in Biomedical Imaging (ISBI), IEEE 11th International Symposium on. 2014. IEEE.
Nazem-Zadeh M-R et al (2014c) Lateralization of temporal lobe epilepsy using a novel uncertainty analysis of MR diffusion in hippocampus, cingulum, and fornix, and hippocampal volume and FLAIR intensity. J Neurol Sci 342(1–2):152–161
Nazem-Zadeh, M.-R., et al., (2015) DTI-based Response-Driven Modeling of mTLE Laterality NeuroImage Clinical
Nazem-Zadeh M-R et al (2016a) MEG coherence and DTI connectivity in mTLE. Brain Topogr 29(4):598–622
Nazem-Zadeh, M.-R., et al. (2016b) DTI-based response-driven modeling of mTLE laterality. NeuroImage: Clinical, 11: p. 694–706.
Pierpaoli C et al (2001) Water diffusion changes in Wallerian degeneration and their dependence on white matter architecture. Neuroimage 13(6):1174–1185
Powell H et al (2007) Abnormalities of language networks in temporal lobe epilepsy. Neuroimage 36(1):209–221
Řehulka P et al (2014) Ictal and postictal semiology in patients with bilateral temporal lobe epilepsy. Epilepsy Behav 41:40–46
Riederer F et al (2008) Network atrophy in temporal lobe epilepsy: a voxel-based morphometry study. Neurology 71(6):419–425
Rugg-Gunn FJ (2007) Diffusion imaging in epilepsy. Expert Rev Neurother 7(8):1043–1054
Saini G, Kaur H (2014) A novel approach towards K-mean clustering algorithm with PSO. Int J Comput Sci Inf Technol 5:5978–5986
Schevon CA et al (2007) Cortical abnormalities in epilepsy revealed by local EEG synchrony. Neuroimage 35(1):140–148
Shattuck DW et al (2008) Construction of a 3D probabilistic atlas of human cortical structures. Neuroimage 39(3):1064–1080
Sperling M et al (1992) A noninvasive protocol for anterior temporal lobectomy. Neurology 42(2):416–416
Stieltjes B et al (2001) Diffusion tensor imaging and axonal tracking in the human brainstem. NeuroImage 14:723–735
Sutherling WW et al (2008) Influence of magnetic source imaging for planning intracranial EEG in epilepsy. Neurology 71(13):990–996
Vora P, Oza B (2013) A survey on k-mean clustering and particle swarm optimization. Int J Sci Modern Eng 1(3):24–26
Towle VL et al (1999) Electrocorticographic coherence patterns. J Clin Neurophysiol 16(6):528–547
Yogarajah M, Duncan JS (2007) Diffusion-based magnetic resonance imaging and tractography in epilepsy. Epilepsia
Zhang J et al (2014) Identifying the affected hemisphere with a multimodal approach in MRI-positive or negative, unilateral or bilateral temporal lobe epilepsy. Neuropsychiat Dis Treat 10:71
Author information
Authors and Affiliations
Corresponding author
Additional information
Handling Edtor: Christoph M. Michel.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jamali-Dinan, SS., Soltanian-Zadeh, H., Bowyer, S.M. et al. A Combination of Particle Swarm Optimization and Minkowski Weighted K-Means Clustering: Application in Lateralization of Temporal Lobe Epilepsy. Brain Topogr 33, 519–532 (2020). https://doi.org/10.1007/s10548-020-00770-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10548-020-00770-9