Dynamic functional connectivity in temporal lobe epilepsy: a graph theoretical and machine learning approach
- PDF / 1,449,468 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 88 Downloads / 206 Views
ORIGINAL ARTICLE
Dynamic functional connectivity in temporal lobe epilepsy: a graph theoretical and machine learning approach Alireza Fallahi 1 & Mohammad Pooyan 1 & Nastaran Lotfi 2 & Fatemeh Baniasad 3,6 & Leili Tapak 4,5 & Neda Mohammadi-Mobarakeh 3,6 & Seyed Sohrab Hashemi-Fesharaki 7 & Jafar Mehvari-Habibabadi 8 & Mohammad Reza Ay 3,6 & Mohammad-Reza Nazem-Zadeh 3,6 Received: 11 July 2020 / Accepted: 23 September 2020 # Fondazione Società Italiana di Neurologia 2020
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. Keywords Dynamic functional connectivity . Temporal lobe epilepsy . Graph theory . Lateralization . Machine learning
Introduction Temporal lobe epilepsy (TLE) is the most frequent type of pharmacoresistant focal epilepsy in adults accountable for surgical treatment. However, due to a lack of clear localizing the
* Mohammad-Reza Nazem-Zadeh [email protected] Alireza Fallahi [email protected] Mohammad Pooyan [email protected] Fatemeh Baniasad [email protected] Leili Tapak [email protected]
seizer source, surgery cannot be performed in about 30% of TLE patients [1]. In standard presurgical evaluation protocols, videoEEG and high-resolution MRI play a critical role [2]. Functional connectivity based on functional MRI (fMRI) may provide additional useful information for the purpose of lateralization.
Neda Mohammadi-Mobarakeh [email protected]
Data Loading...
