Multi-label learning deals with the problem where each training example is represented by a single instance while associated with a set of class labels. For an unseen example, existing approaches choose to determine the membership of each possible class label to it based on identical feature set, i.e. the very instance representation of the unseen example is employed in the discrimination processes of all labels. However, this commonly-used strategy might be suboptimal as different class labels usually carry specific characteristics of their own, and it could be beneficial to exploit different feature sets for the discrimination of different labels. Based on the above reflection, we propose a new strategy to multi-label learning by leveraging labelspecific features, where a simple yet effective algorithm named LIFT is presented. Briefly, LIFT constructs features specific to each label by conducting clustering analysis on its positive and negative instances, and then performs training and testing by querying the clustering results. Extensive experiments across sixteen diversified data sets clearly validate the superiority of LIFT against other wellestablished multi-label learning algorithms.
The human brain operates by dynamically modulating different neural populations to enable goal directed behavior. The synchrony or lack thereof between different brain regions is thought to correspond to observed functional connectivity dynamics in resting state brain imaging data. In a large sample of healthy human adult subjects and utilizing a sliding windowed correlation method on functional imaging data, earlier we demonstrated the presence of seven distinct functional connectivity states/patterns between different brain networks that reliably occur across time and subjects. Whether these connectivity states correspond to meaningful electrophysiological signatures was not clear. In this study, using a dataset with concurrent EEG and resting state functional imaging data acquired during eyes open and eyes closed states, we demonstrate the replicability of previous findings in an independent sample, and identify EEG spectral signatures associated with these functional network connectivity changes. Eyes open and eyes closed conditions show common and different connectivity patterns that are associated with distinct EEG spectral signatures. Certain connectivity states are more prevalent in the eyes open case and some occur only in eyes closed state. Both conditions exhibit a state of increased thalamocortical anticorrelation associated with reduced EEG spectral alpha power and increased delta and theta power possibly reflecting drowsiness. This state occurs more frequently in the eyes closed state. In summary, we find a link between dynamic connectivity in fMRI data and concurrently collected EEG data, including a large effect of vigilance on functional connectivity. As demonstrated with EEG and fMRI, the stationarity of connectivity cannot be assumed, even for relatively short periods.
Default mode network (DMN) has been reported altered in schizophrenia (SZ) using static connectivity analysis. However, the studies on dynamic characteristics of DMN in SZ are still limited. In this work, we compare dynamic connectivity within DMN between 82 healthy controls (HC) and 82 SZ patients using resting-state fMRI. Firstly, dynamic DMN was computed using a sliding time window method for each subject. Then, the overall connectivity strengths were compared between two groups. Furthermore, we estimated functional connectivity states using K-means clustering, and then investigated group differences with respect to the connectivity strengths in states, the dwell time in each state, and the transition times between states. Finally, graph metrics of time-varying connectivity patterns and connectivity states were assessed. Results suggest that measured by the overall connectivity, HC showed stronger inter-subsystem interaction than patients. Compared to HC, patients spent less time in the states with nodes tightly connected. For each state, SZ patients presented relatively weaker connectivity strengths mainly in inter-subsystem. Patients also exhibited lower values in averaged node strength, clustering coefficient, global efficiency, and local efficiency than HC. In summary, our findings indicate that SZ showed impaired interaction among DMN subsystems, with a reduced central role for posterior cingulate cortex (PCC) and anterior medial prefrontal cortex (aMPFC) hubs as well as weaker interaction between dorsal medial prefrontal cortex (dMPFC) subsystem and medial temporal lobe (MTL) subsystem. For SZ, decreased integration of DMN may be associated with impaired ability in making self-other distinctions and coordinating present mental states with episodic decisions about future.
Independent component analysis (ICA) has been widely applied to identify intrinsic brain networks from fMRI data. Group ICA computes group-level components from all data and subsequently estimates individual-level components to recapture inter-subject variability. However, the best approach to handle artifacts, which may vary widely among subjects, is not yet clear. In this work, we study and compare two ICA approaches for artifacts removal. One approach, recommended in recent work by the Human Connectome Project, first performs ICA on individual subject data to remove artifacts, and then applies a group ICA on the cleaned data from all subjects. We refer to this approach as Individual ICA based artifacts Removal Plus Group ICA (IRPG). A second proposed approach, called Group Information Guided ICA (GIG-ICA), performs ICA on group data, then removes the group-level artifact components, and finally performs subject-specific ICAs using the group-level non-artifact components as spatial references. We used simulations to evaluate the two approaches with respect to the effects of data quality, data quantity, variable number of sources among subjects, and spatially unique artifacts. Resting-state test-retest datasets were also employed to investigate the reliability of functional networks. Results from simulations demonstrate GIG-ICA has greater performance compared to IRPG, even in the case when single-subject artifacts removal is perfect and when individual subjects have spatially unique artifacts. Experiments using test-retest data suggest that GIG-ICA provides more reliable functional networks. Based on high estimation accuracy, ease of implementation, and high reliability of functional networks, we find GIG-ICA to be a promising approach.
Concurrent EEG-fMRI studies have provided increasing details of the dynamics of intrinsic brain activity during the resting state. Here, we investigate a prominent effect in EEG during relaxed resting, i.e. the increase of the alpha power when the eyes are closed compared to when the eyes are open. This phenomenon is related to changes in thalamo-cortical and cortico-cortical synchronization. In order to investigate possible changes to EEG-fMRI coupling and fMRI functional connectivity during the two states we adopted a data-driven approach that fuses the multimodal data on the basis of parallel ICA decompositions of the fMRI data in the spatial domain and of the EEG data in the spectral domain. The power variation of a posterior alpha component was used as a reference function to deconvolve the hemodynamic responses from occipital, frontal, temporal, and subcortical fMRI components. Additionally, we computed the functional connectivity between these components. The results showed widespread alpha hemodynamic responses and high functional connectivity during eyes-closed (EC) rest, while eyes open (EO) resting abolished many of the hemodynamic responses and markedly decreased functional connectivity. These data suggest that generation of local hemodynamic responses is highly sensitive to state changes that do not involve changes of mental effort or awareness. They also indicate the localized power differences in posterior alpha between EO and EC in resting state data are accompanied by spatially widespread amplitude changes in hemodynamic responses and inter-regional functional connectivity, i.e. low frequency hemodynamic signals display an equivalent of alpha reactivity.
No abstract
Mapping brain connectivity based on neuroimaging data is a promising new tool for understanding brain structure and function. In this methods paper, we demonstrate that group independent component analysis (GICA) can be used to perform a dual parcellation of the brain based on its connectivity matrix (cmICA). This dual parcellation consists of a set of spatially independent source maps, and a corresponding set of paired dual maps that define the connectivity of each source map to the brain. These dual maps are called the connectivity profiles of the source maps. Traditional analysis of connectivity matrices has been used previously for brain parcellation, but the present method provides additional information on the connectivity of these segmented regions. In this paper the whole brain structural connectivity matrices were calculated on a 5mm3 voxel scale from diffusion imaging data based on the probabilistic tractography method. The effect of the choice of the number of components (30 and 100) and their stability were examined. This method generated a set of spatially independent components that are consistent with the canonical brain tracts provided by previous anatomic descriptions, with the high order model yielding finer segmentations. The corpus-callosum example shows how this method leads to a robust parcellation of a brain structure based on its connectivity properties. We applied cmICA to study structural connectivity differences between a group of schizophrenia subjects and healthy controls. The connectivity profiles at both model orders showed similar regions with reduced connectivity in schizophrenia patients. These regions included forceps major, right inferior fronto-occipital fasciculus, uncinate fasciculus, thalamic radiation and corticospinal tract. This paper provides a novel unsupervised data-driven framework that summarizes the information in a large global connectivity matrix and tests for brain connectivity differences. It has the potential for capturing important brain changes related to disease in connectivity-based disorders.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.