Search for: All records

Applications of multimodal neuroimaging techniques, including electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have gained prominence in recent years, and they are widely practiced in brain–computer interface (BCI) and neuro-pathological diagnosis applications. Most existing approaches assume observations are independent and identically distributed (i.i.d.), as shown in the top section of the right figure, yet ignore the difference among subjects. It has been challenging to model subject groups to maintain topological information (e.g., patient graphs) while fusing BCI signals for discriminant feature learning. In this article, we introduce a topology-aware graph-based multimodal fusion (TaGMF) framework to classify amyotrophic lateral sclerosis (ALS) and healthy subjects, illustrated in the lower section of the right image. Our framework is built on graph neural networks (GNNs) but with two unique contributions. First, a novel topology-aware graph (TaG) is proposed to model subject groups by considering: 1) intersubject; 2) intrasubject; and 3) intergroup relations. Second, the learned representation of EEG and fNIRS signals of each subject allows for explorations of different fusion strategies along with the TaGMF optimizations. Our analysis demonstrates the effectiveness of our graph-based fusion approach in multimodal classification by achieving a 22.6% performance improvement over classical approaches. 

The prospect of electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) in the presence of topological information of participants is often left unexplored in most of the brain-computer interface (BCI) systems. Additionally, the usage of these modalities together in the field of multimodality analysis to support multiple brain signals toward improving BCI performance is not fully examined. This study first presents a multimodal data fusion framework to exploit and decode the complementary synergistic properties in multimodal neural signals. Moreover, the relations among different subjects and their observations also play critical roles in classifying unknown subjects. We developed a context-aware graph neural network (GNN) model utilizing the pairwise relationship among participants to investigate the performance on an auditory task classification. We explored standard and deviant auditory EEG and fNIRS data where each subject was asked to perform an auditory oddball task and has multiple trials regarded as context-aware nodes in our graph construction. In experiments, our multimodal data fusion strategy showed an improvement up to 8.40% via SVM and 2.02% via GNN, compared to the single-modal EEG or fNIRS. In addition, our context-aware GNN achieved 5.3%, 4.07% and 4.53% higher accuracy for EEG, fNIRS and multimodal data based experiments, compared to the baseline models. 

Neural networks (NN) has been adopted by brain-computer interfaces (BCI) to encode brain signals acquired using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS). However, it has been found that NN models are vulnerable to adversarial examples, i.e., corrupted samples with imperceptible noise. Once attacked, it could impact medical diagnosis and patients’ quality of life. While early work focuses on interference using external devices at the time of signal acquisition, recent research shifts to collected signals, features, and learning models under various attack modes (e.g., white-, grey-, and black-box). However, existing work only considers single-modality attacks and ignores the topological relationships among different observations, e.g., samples having strong similarities. Different from previous approaches, we introduce graph neural networks (GNN) to multimodal BCI-based classification and explore its performance and robustness against adversarial attacks. This study will evaluate the robustness of NN models with and without graph knowledge on both single and multimodal data. 

Multimodal data fusion is one of the current primary neuroimaging research directions to overcome the fundamental limitations of individual modalities by exploiting complementary information from different modalities. Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) are especially compelling modalities due to their potentially complementary features reflecting the electro-hemodynamic characteristics of neural responses. However, the current multimodal studies lack a comprehensive systematic approach to properly merge the complementary features from their multimodal data. Identifying a systematic approach to properly fuse EEG-fNIRS data and exploit their complementary potential is crucial in improving performance. This paper proposes a framework for classifying fused EEG-fNIRS data at the feature level, relying on a mutual information-based feature selection approach with respect to the complementarity between features. The goal is to optimize the complementarity, redundancy and relevance between multimodal features with respect to the class labels as belonging to a pathological condition or healthy control. Nine amyotrophic lateral sclerosis (ALS) patients and nine controls underwent multimodal data recording during a visuo-mental task. Multiple spectral and temporal features were extracted and fed to a feature selection algorithm followed by a classifier, which selected the optimized subset of features through a cross-validation process. The results demonstrated considerably improved hybrid classification performance compared to the individual modalities and compared to conventional classification without feature selection, suggesting a potential efficacy of our proposed framework for wider neuro-clinical applications. 

Recent evidence increasingly associates network disruption in brain organization with multiple neurodegenerative diseases, including amyotrophic lateral sclerosis (ALS), a rare terminal disease. However, the comparability of brain network characteristics across different studies remains a challenge for conventional graph theoretical methods. One suggested method to address this issue is minimum spanning tree (MST) analysis, which provides a less biased comparison. Here, we assessed the novel application of MST network analysis to hemodynamic responses recorded by functional near-infrared spectroscopy (fNIRS) neuroimaging modality, during an activity-based paradigm to investigate hypothetical disruptions in frontal functional brain network topology as a marker of the executive dysfunction, one of the most prevalent cognitive deficit reported across ALS studies. We analyzed data recorded from nine participants with ALS and ten age-matched healthy controls by first estimating functional connectivity, using phase-locking value (PLV) analysis, and then constructing the corresponding individual and group MSTs. Our results showed significant between-group differences in several MST topological properties, including leaf fraction, maximum degree, diameter, eccentricity, and degree divergence. We further observed a global shift toward more centralized frontal network organizations in the ALS group, interpreted as a more random or dysregulated network in this cohort. Moreover, the similarity analysis demonstrated marginally significantly increased overlap in the individual MSTs from the control group, implying a reference network with lower topological variation in the healthy cohort. Our nodal analysis characterized the main local hubs in healthy controls as distributed more evenly over the frontal cortex, with slightly higher occurrence in the left prefrontal cortex (PFC), while in the ALS group, the most frequent hubs were asymmetrical, observed primarily in the right prefrontal cortex. Furthermore, it was demonstrated that the global PLV (gPLV) synchronization metric is associated with disease progression, and a few topological properties, including leaf fraction and tree hierarchy, are linked to disease duration. These results suggest that dysregulation, centralization, and asymmetry of the hemodynamic-based frontal functional network during activity are potential neuro-topological markers of ALS pathogenesis. Our findings can possibly support new bedside assessments of the functional status of ALS’ brain network and could hypothetically extend to applications in other neurodegenerative diseases.