Alireza Fallahi1, Mohammad Pooyan1, Nastaran Lotfi2, Fatemeh Baniasad3,4, Leili Tapak5,6, Neda Mohammadi-Mobarakeh3,4, Seyed Sohrab Hashemi-Fesharaki7, Jafar Mehvari-Habibabadi8, Mohammad Reza Ay3,4, Mohammad-Reza Nazem-Zadeh9,10. 1. Biomedical Engineering Department, Engineering Faculty, Shahed University, Tehran, Iran. 2. Departamento de Fsica, Universidade Federal de Pernambuco, Recife, PE 50670-901, Brazil. 3. Research Center for Molecular and Cellular Imaging, Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medical Sciences, Tehran, Iran. 4. Medical Physics and Biomedical Engineering Department, Tehran University of Medical Sciences (TUMS), Tehran, Iran. 5. Department of Biostatistics, School of Public Health, Hamadan University of Medical Science, Hamadan, Iran. 6. Modeling of Noncommunicable Diseases Research Center, Hamadan University of Medical Science, Hamadan, Iran. 7. Pars Advanced and Minimally Invasive Medical Manners Research Center, Pars Hospital, Iran University of Medical Sciences, Tehran, Iran. 8. Isfahan Neuroscience Research Center, Isfahan University of Medical Sciences, Isfahan, Iran. 9. Research Center for Molecular and Cellular Imaging, Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medical Sciences, Tehran, Iran. mnazemzadeh@tums.ac.ir. 10. Medical Physics and Biomedical Engineering Department, Tehran University of Medical Sciences (TUMS), Tehran, Iran. mnazemzadeh@tums.ac.ir.
Abstract
PURPOSE: Functional magnetic resonance imaging (fMRI) in resting state can be used to evaluate the functional organization of the human brain in the absence of any task or stimulus. The functional connectivity (FC) has non-stationary nature and consented to be varying over time. By considering the dynamic characteristics of the FC and using graph theoretical analysis and a machine learning approach, we aim to identify the laterality in cases of temporal lobe epilepsy (TLE). METHODS: Six global graph measures are extracted from static and dynamic functional connectivity matrices using fMRI data of 35 unilateral TLE subjects. Alterations in the time trend of the graph measures are quantified. The random forest (RF) method is used for the determination of feature importance and selection of dynamic graph features including mean, variance, skewness, kurtosis, and Shannon entropy. The selected features are used in the support vector machine (SVM) classifier to identify the left and right epileptogenic sides in patients with TLE. RESULTS: Our results for the performance of SVM demonstrate that the utility of dynamic features improves the classification outcome in terms of accuracy (88.5% for dynamic features compared with 82% for static features). Selecting the best dynamic features also elevates the accuracy to 91.5%. CONCLUSION: Accounting for the non-stationary characteristics of functional connectivity, dynamic connectivity analysis of graph measures along with machine learning approach can identify the temporal trend of some specific network features. These network features may be used as potential imaging markers in determining the epileptogenic hemisphere in patients with TLE.
PURPOSE: Functional magnetic resonance imaging (fMRI) in resting state can be used to evaluate the functional organization of the human brain in the absence of any task or stimulus. The functional connectivity (FC) has non-stationary nature and consented to be varying over time. By considering the dynamic characteristics of the FC and using graph theoretical analysis and a machine learning approach, we aim to identify the laterality in cases of temporal lobe epilepsy (TLE). METHODS: Six global graph measures are extracted from static and dynamic functional connectivity matrices using fMRI data of 35 unilateral TLE subjects. Alterations in the time trend of the graph measures are quantified. The random forest (RF) method is used for the determination of feature importance and selection of dynamic graph features including mean, variance, skewness, kurtosis, and Shannon entropy. The selected features are used in the support vector machine (SVM) classifier to identify the left and right epileptogenic sides in patients with TLE. RESULTS: Our results for the performance of SVM demonstrate that the utility of dynamic features improves the classification outcome in terms of accuracy (88.5% for dynamic features compared with 82% for static features). Selecting the best dynamic features also elevates the accuracy to 91.5%. CONCLUSION: Accounting for the non-stationary characteristics of functional connectivity, dynamic connectivity analysis of graph measures along with machine learning approach can identify the temporal trend of some specific network features. These network features may be used as potential imaging markers in determining the epileptogenic hemisphere in patients with TLE.
Authors: S Dupont; Y Samson; P-F Van de Moortele; S Samson; J-B Poline; D Hasboun; D Le Bihan; M Baulac Journal: J Neurol Neurosurg Psychiatry Date: 2002-11 Impact factor: 10.154
Authors: Anne T Berg; Barbara G Vickrey; John T Langfitt; Michael R Sperling; Thaddeus S Walczak; Shlomo Shinnar; Carl W Bazil; Steven V Pacia; Susan S Spencer Journal: Epilepsia Date: 2003-11 Impact factor: 5.864
Authors: M C G Vlooswijk; J F A Jansen; H J M Majoie; P A M Hofman; M C T F M de Krom; A P Aldenkamp; W H Backes Journal: Neurology Date: 2010-08-03 Impact factor: 9.910
Authors: Taha Gholipour; Xiaozhen You; Steven M Stufflebeam; Murray Loew; Mohamad Z Koubeissi; Victoria L Morgan; William D Gaillard Journal: Epilepsia Date: 2022-01-04 Impact factor: 6.740