Loading...

Ensemble multi-modal brain source localization using theory of evidence

Oliaiee, A ; Sharif University of Technology | 2021

434 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.bspc.2021.102668
  3. Publisher: Elsevier Ltd , 2021
  4. Abstract:
  5. The primary aim in pre-surgical evaluations in patients with neurological disorders such as epilepsy is determining the precise location of the cortical region responsible for the malfunctions which is called source localization. Different modalities unravel different views of brain activity. Combining these complementary aspects of the brain yields more accurate source localization. In this paper, a method is proposed for combining localization methods in different modalities based on the theory of evidence, the result of some localization methods in modalities are integrated using weights in accordance to their relative performance and are combined using Dempster's rule of combination and is used for the case of EEG and MEG combinatory source localization. The proposed method is evaluated on simulated realistic MEG and EEG data and in different noise and artifact levels and finds the zone of interest in a more accurate way. The AUC criterion is used as a metric for the evaluation. The proposed method results in better localization accuracy in terms of AUC showing the combination of modalities could lead to superior performance. Combining two modalities needs an exact knowledge of the phenomena happening in each modality, making the combination difficult. Here rather of combining EEG and MEG information at the initial phase, the results of some source localization techniques on both modalities are combined. In spite of the simplicity of use, the experimental results of combination showed improvement in epileptic source localization accuracy even in cases that one method shows poor performance. Using the proposed method any number of modalities can be combined without complex consideration and a better brain source localization could be obtained. © 2021
  6. Keywords:
  7. Brain ; Inverse problems ; Neurology ; Brain source localization ; Dempster-Shafer theory ; Inverse problem ; Localization accuracy ; Localization method ; MEG ; Multi-modal ; Source localization ; Surgical evaluations ; Theory of evidence ; Electroencephalography ; area under the curve ; Bayesian learning ; Brain ; Dempster Shafer theory ; Diagnostic accuracy ; Distributed model ; Electroencephalogram ; Epifocus method ; Epilepsy ; Equivalent current dipole ; Human ; Laura method ; Low resolution brain electromagnetic tomography ; Magnetoencephalography ; mne method ; Network analysis ; Parametric test ; Signal noise ratio ; Simulation ; Statistical analysis ; wmne method
  8. Source: Biomedical Signal Processing and Control ; Volume 69 , 2021 ; 17468094 (ISSN)
  9. URL: https://www.sciencedirect.com/science/article/abs/pii/S1746809421002652