| Title:
|
Multimodal Brain Mapping Using EEG and fMRI in Autism Spectrum Disorder
|
| Author(s):
|
1
|
| Subject:
|
Artificial Intelligence and Brain Mapping
|
|
|
|
Presenter Author:
|
|
| Name:
|
Elina Lovineh
|
|
|
|
Author:
|
|
| Name 1:
|
Elina Lovineh - Corresponding - Presenter
|
| Affiliation 1:
|
Student Research Committee, Abadan University of Medical Sciences, Abadan, Iran
|
|
|
| Name 2:
|
|
| Affiliation 2:
|
|
|
|
| Name 3:
|
|
| Affiliation 3:
|
|
|
|
| Name 4:
|
|
| Affiliation 4:
|
|
|
|
| Name 5:
|
|
| Affiliation 5:
|
|
|
|
| Name 6:
|
|
| Affiliation 6:
|
|
|
|
| Name 7:
|
|
| Affiliation 7:
|
|
|
|
| Name 8:
|
|
| Affiliation 8:
|
|
|
|
| Name 9:
|
|
| Affiliation 9:
|
|
|
|
| Name 10:
|
|
| Affiliation 10:
|
|
|
|
Abstract
|
Original Research
|
|
introduction :
|
Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by deficits in social communication and repetitive behaviors. Single-modality imaging, such as EEG or fMRI, provides valuable but limited insights. Integrating both modalities offers complementary spatiotemporal information that may enhance understanding of ASD-related brain alterations. This study investigates the feasibility of simultaneous EEG–fMRI recordings to identify multimodal biomarkers for ASD. Results indicate that combined EEG–fMRI features improve classification and provide a richer description of neural dysfunction, supporting multimodal mapping as a promising tool for early ASD detection
|
|
Methods:
|
Participants included children and adolescents diagnosed with ASD and age-matched typically developing controls. Resting-state EEG and fMRI data were collected simultaneously to capture high temporal resolution electrical activity and high spatial resolution hemodynamic responses [4]. Preprocessing included artifact removal, EEG–MR pulse correction, and fMRI realignment and normalization. EEG features (spectral power, temporal dynamics) and fMRI features (functional connectivity, BOLD correlations) were extracted. Multimodal integration was performed using feature fusion and dimensionality reduction, followed by classification using Support Vector Machines (SVM) and deep learning models Performance was evaluated via accuracy, sensitivity, and specificity.
|
|
Results:
|
Multimodal EEG–fMRI features outperformed unimodal analyses in distinguishing ASD from controls. Combined features achieved higher classification accuracy, particularly in networks related to social cognition, default mode, and attentional control [1,3]. EEG revealed altered spectral patterns in ASD participants, while fMRI showed disrupted long-range connectivity and atypical network topology. Multimodal classifiers achieved robust performance, indicating that EEG temporal dynamics enhanced the discriminative power of fMRI connectivity features
|
|
Conclusion:
|
Integrating EEG and fMRI provides a more comprehensive characterization of neural alterations in ASD than single modalities. EEG captures rapid neural dynamics, while fMRI maps spatial connectivity. Combined, these modalities allow detection of subtle neurobiological signatures, improving diagnostic accuracy. Multimodal machine learning classifiers further enhance prediction of ASD, offering a promising approach for early and objective detection. Future research should focus on optimizing integration methods, addressing artifacts, and validating findings across larger, diverse cohorts to support clinical translation of multimodal biomarkers
|
| Attachment:
|
|
| Keywords:
|
EEG. Brain Mapping . Spectrum
|
| Key message:
|
|
| Do you want your abstract to be indexed, if this is selected as one of the top 100
articles?
|
