Resting-state Features Research Articles

Prediction of individual performance and verbal intelligence scores from resting-state fMRI in children and adolescents.

The neuroimaging basis of intelligence remains elusive; however, there is a growing body of research employing connectome-based predictive modeling to estimate individual intelligence scores, aiming to identify the optimal set of neuroimaging features for accurately predicting an individual's cognitive abilities. Compared to adults, the disparities in cognitive performance among children and adolescents are more likely to captivate individuals' interest and attention. Limited research has been dedicated to exploring neuroimaging markers of intelligence specifically in the pediatric population. In this study, we utilized resting-state functional magnetic resonance imaging (fMRI) and intelligence quotient (IQ) scores of 170 healthy children and adolescents obtained from a public database to identify brain functional connectivity markers associated with individual intellectual behavior. Initially, we extracted and summarized relevant resting-state features from whole-brain or functional network connectivity that were most pertinent to IQ scores. Subsequently, these features were employed to establish prediction models for both performance and verbal IQ scores. Within a 10-fold cross-validation framework, our findings revealed that prediction models based on whole-brain functional connectivity effectively predicted performance IQ scores( ) but not verbal IQ scores( ). Results of prediction models based on brain functional network connectivity further demonstrated the exceptional predictive ability of the default mode network (DMN) and fronto-parietal task control network (FTPN) for performance IQ scores ( ). The above findings have also been validated using an independent dataset. Our findings suggest that the performance IQ of children and adolescents primarily relies on the connectivity of brain regions associated with DMN and FTPN. Moreover, variations in intellectual performance during childhood and adolescences are closely linked to alterations in brain functional network connectivity.

Predicting Task Activation Maps from Resting-State Functional Connectivity using Deep Learning.

Recent work has shown that deep learning is a powerful tool for predicting brain activation patterns evoked through various tasks using resting state features. We replicate and improve upon this recent work to introduce two models, BrainSERF and BrainSurfGCN, that perform at least as well as the state-of-the-art while greatly reducing memory and computational footprints. Our performance analysis observed that low predictability was associated with a possible lack of task engagement derived from behavioral performance. Furthermore, a deficiency in model performance was also observed for closely matched task contrasts, likely due to high individual variability confirmed by low test-retest reliability. Overall, we successfully replicate recently developed deep learning architecture and provide scalable models for further research.

Diagnostic identification of chronic insomnia using ALFF and FC features of resting-state functional MRI and logistic regression approach

This study investigated whether the amplitude of low-frequency fluctuation (ALFF) and functional connectivity (FC) features could be used as potentially neurological markers to identify chronic insomnia (CI) using resting-state functional MRI and machine learning method logistic regression (LR). This study included 49 CI patients and 47 healthy controls (HC). Voxel-wise features, including the amplitude of low-frequency fluctuations (ALFF) and functional connectivity (FC), were extracted from resting-state functional magnetic resonance brain images. Then, we divided the data into two independent cohorts for training (44 CI patients and 42 HC patients), and independent validation (5 CI patients and 5 HC patients) by using logistic regression. The model was evaluated using 20 rounds of fivefold cross‑validation for training. In particular, a two-sample t-test (GRF corrected, p-voxel < 0.001, p-cluster < 0.05) was used for feature selection during the model training. Finally, single‑shot testing of the final model was performed on the independent validation cohort. A correlation analysis (Bonferroni correction, p < 0.05/4) was also conducted to determine whether the features contributing to the prediction were correlated with clinical characteristics, including the Insomnia Severity Index (ISI), Pittsburgh sleep quality index (PSQI), self-rating anxiety scale (SAS), and self-rating depression scale (SDS). Results showed that resting-state features had a discrimination accuracy of 86.40%, with a sensitivity of 93.00% and specificity of 79.80%. The area under the curve (AUC) was 0.89 (all {P}_{mathrm{permutation}}< 0.001). The ALFF and FC features showed significant differences between the CI patients and HC. The regions contributing to the prediction mainly included the anterior cingulate, prefrontal cortex, orbital part of the frontal lobe, angular gyrus, cingulate gyrus, praecuneus, parietal lobe, temporal gyrus, superior temporal gyrus, and middle temporal gyrus. Furthermore, some specific functional connectivity among related regions was positively correlated with the ISI, and also negatively related to the SDS in correlation analysis. Our current study suggested that ALFF and FC in the regions contributing to diagnostic identification might serve as potential neuromarkers for CI.

MULTI-FEATURE FUSION EMOTION RECOGNITION BASED ON RESTING EEG

An important task of brain–computer interface (BCI) research is to read or decode mental content from a large number of electroencephalographic (EEG) signals, which is an exciting, attractive, and challenging goal. In this paper, resting EEG data are collected from spontaneous EEG, and 16 random features such as correlation coefficient, covariance, and brainpower spectrum are extracted as reference vectors. In the subsequent emotion recognition experiment, the same feature information is extracted and separated from the EEG signal, and the translation and normalization processing are carried out based on the resting-state features. Finally, with the machine learning methods such as [Formula: see text]-means clustering and multi-feature fusion, the positive, negative, and neutral emotional characteristic parameters were correctly separated. In a group of 12 subjects, the correct recognition rate of visual evoked positive, negative, and neutral emotions reached 83.9%, which was better than the literature mentioned in this paper. Another highlight of this method is that it can quickly, accurately, and efficiently select the number of features with the best matching and the least resource consumption from multiple features and multiple potential acquisition points. Further analysis and comparison of EEG characteristics can find the relationship between specific stimuli and corresponding EEG characteristic signals.

Combining Multiple Resting-State fMRI Features during Classification: Optimized Frameworks and Their Application to Nicotine Addiction

Machine learning techniques have been applied to resting-state fMRI data to predict neurological or neuropsychiatric disease states. Existing studies have used either a single type of resting-state feature or a few feature types (<4) in the prediction model. However, resting-state data can be processed in many different ways, yielding different feature types containing complementary and/or novel information, leaving uncertain the most informative features to provide to the classifier. In this study, multiple resting-state features were calculated from two main analytical categories: local measures and network measures. Feature selection was adopted using an optimized grid-search approach selecting top ranked features from statistical tests. We then tested three optimized frameworks: feature combination, kernel combination, and classifier combination, all using the support vector machine as an elementary classifier, to combine these resting-state feature types. When applied to nicotine addiction, with a cohort size of 100 smokers and 100 non-smokers, via a 10-fold cross-validation procedure, the feature combination and the classifier combination achieved an accuracy of 75.5%, while the kernel combination achieved a 73.0% accuracy; all three combination frameworks improved classification performance compared to the single feature type based results (best accuracy 70.5%). This study not only reveals the discriminative power of resting-state data, but also demonstrates the efficiency of combining multiple features from one data phenotype to improve classification performance.

Differential lateralization of hippocampal connectivity reflects features of recent context and ongoing demands: An examination of immediate post‐task activity

Neuroimaging studies have shown that task demands affect connectivity patterns in the human brain not only during task performance but also during subsequent rest periods. Our goal was to determine whether ongoing connectivity patterns during rest contain information about both the current rest state, as well as the recently terminated task. Our experimental design consisted of two types of active tasks that were followed by two types of low-demand rest states. Using this design, we examined whether hippocampal functional connectivity during wakeful rest reflects both features of a recently terminated task and those of the current resting-state condition. We identified four types of networks: (i) one whose connectivity with the hippocampus was determined only by features of a recently terminated task, (ii) one whose connectivity was determined only by features of the current resting-state, (iii) one whose connectivity reflected aspects of both the recently terminated task and ongoing resting-state features, and (iv) one whose connectivity with the hippocampus was strong, but not affected by any external factor. The left and right hippocampi played distinct roles in these networks. These findings suggest that ongoing hippocampal connectivity networks mediate information integration across multiple temporal scales, with hippocampal laterality moderating these connectivity patterns.

Dissociative part-dependent resting-state activity in dissociative identity disorder: a controlled FMRI perfusion study.

BackgroundIn accordance with the Theory of Structural Dissociation of the Personality (TSDP), studies of dissociative identity disorder (DID) have documented that two prototypical dissociative subsystems of the personality, the “Emotional Part” (EP) and the “Apparently Normal Part” (ANP), have different biopsychosocial reactions to supraliminal and subliminal trauma-related cues and that these reactions cannot be mimicked by fantasy prone healthy controls nor by actors.MethodsArterial spin labeling perfusion MRI was used to test the hypotheses that ANP and EP in DID have different perfusion patterns in response to rest instructions, and that perfusion is different in actors who were instructed to simulate ANP and EP. In a follow-up study, regional cerebral blood flow of DID patients was compared with the activation pattern of healthy non-simulating controls.ResultsCompared to EP, ANP showed elevated perfusion in bilateral thalamus. Compared to ANP, EP had increased perfusion in the dorsomedial prefrontal cortex, primary somatosensory cortex, and motor-related areas. Perfusion patterns for simulated ANP and EP were different. Fitting their reported role-play strategies, the actors activated brain structures involved in visual mental imagery and empathizing feelings. The follow-up study demonstrated elevated perfusion in the left temporal lobe in DID patients, whereas non-simulating healthy controls had increased activity in areas which mediate the mental construction of past and future episodic events.ConclusionDID involves dissociative part-dependent resting-state differences. Compared to ANP, EP activated brain structures involved in self-referencing and sensorimotor actions more. Actors had different perfusion patterns compared to genuine ANP and EP. Comparisons of neural activity for individuals with DID and non-DID simulating controls suggest that the resting-state features of ANP and EP in DID are not due to imagination. The findings are consistent with TSDP and inconsistent with the idea that DID is caused by suggestion, fantasy proneness, and role-playing.