summary : They proposed BrainGNN, which is a graph neural network framework to analyze fMRI and discover neurological biomarkers. BrainGNN contains novel ROI-aware graph convolutional (Ra-GConv) layers that leverage the topological and functional information of fMRI. They applied the BrainGNN framework on two independent fMRI datasets(ASD fMRI dataset and HCP 900 subject release).
summary : This paper uses multi-modal bio-signals such as EEG, Eye data (Pupil diameter, eye gaze coordinates), and Facial data (using a depth camera) to recognize an individual’s emotions in valence and arousal. This paper suggests the multi-branch convolutional neural network (MBCNN) which shows the best accuracy among the state-of-the-art models while using multi-modal data, especially depth data.
summary : They examine the link between brain-wide gene expression and morphometric changes in individuals with MDD. They observe that the expression of MDD-associated genes spatially correlates with MSN differences.
Summary: Suicidal attempt or ideation is well known associated with various environmental factors and psychopathology. In this study, they examined whether genetic susceptibility to major psychiatric disorders is associated with suicidal behaviors. Using polygenic risk scores and suicide risk measures from ABCD KSADS data, they found that MDD and ADHD are heavily associated with suicidal risks, internalizing and externalizing respectively.
Summary: The aim of study is to examine the association between dispositional mindfulness and PFC neural activity during working memory and identify the dispositional mindfulness from AAMS (Adult and Adolescent Mindfulness Scale) that would be associated with greater working memory performance. The result showed the decreased BOLD signal in the right vlPFC related to higher Attention and Awareness score and reduced FC between right vlPFC and dmPFC related to higher Nonreactivity.
Summary: in real-time neurofeedback experiments, there is not yet to be an empirical justification of the timing and data processing parameters. theses parameters and timing is important. so, they investigate how design parameters of decoded neurofeedback experiments affect accuracy and neurofeedback performance. and they demonstrate the usefulness of offline simulation to improve the success of real-time neurofeedback experiments.
Summary: Here, they conducted an EEG and fMRI experiment to investigate the neural basis of the impulse response function(IRF). They measured the IRF of each subject in the EEG session and then reconstructed an estimate of the EEG signal by convolving the IRF with the stimuli presented in the fMRI session. The envelope of reconstructed EEG signals in the theta, alpha, and beta bands was taken as regressors for the GLM. They found the envelope of the EEG alpha positively correlated with BOLD activity in V1 and V2, but not with activity in the retinotopically stimulated regions.
Summary: They investigated periodic and aperiodic EEG parameters associated with distinct resting state networks and used simultaneous EEG-fMRI recording (resting state). They found that increases in aperiodic power is associated with an auditory-salience-cerebellar network and decreases in aperiodic power is associated with prefrontal regions. Also, they found that global neural excitability may reflect stimulus processing or arousal attributable to the uniqueness of the resting-state MR-scanner environment.
Summary: In this study, they applied novel feature extraction and deep-learning methods to 4 public datasets including DEAP and MAHNOB-HCI for multimodal emotion classification. They proposed utilization of pre-trained VGG-net to compensate for data shortage in bio-sensing field. A wide range of modalities was used including EEG, HRV, GSR and face videos. They evaluate accuracy of single modality, combination of datasets in feature level and transfer learning. Result outperformed previous studies.
Summary: Current encoding models have ignored the temporal dimension in naturalistic stimuli. In this paper, the authors introduced temporal (i.e., 1 vs. 20 s) and multimodal (i.e., unimodal vs. audiovisual) features in the DNN-based encoding models that predicted whole-brain activities. They found the audiovisual and temporally more extended model improved encoding accuracies, especially within high-order sensory regions.