Search

Resting-state functional network connectivity (rsFNC) has shown utility for identifying characteristic functional brain patterns in individuals with psychiatric and mood disorders, providing a promising avenue for biomarker development. However, several factors have precluded widespread clinical adoption of rsFNC diagnostics, namely a lack of standardized approaches for capturing comparable and reproducible imaging markers across individuals, as well as the disagreement on the amount of data required to robustly detect intrinsic connectivity networks (ICNs) and diagnostically relevant patterns of rsFNC at the individual subject level. Recently, spatially constrained independent component analysis (scICA) has been proposed as an automated method for extracting ICNs standardized to a chosen network template while still preserving individual variation. Leveraging the scICA methodology, which solves the former challenge of standardized neuroimaging markers, we investigate the latter challenge of identifying a minimally sufficient data length for clinical applications of resting-state fMRI (rsfMRI). Using a dataset containing rsfMRI scans of individuals with schizophrenia and controls (M = 310) as well as simulated rsfMRI, we evaluated the robustness of ICN and rsFNC estimates at both the subject- and group-level, as well as the performance of diagnostic classification, with respect to the length of the rsfMRI time course. We found individual estimates of ICNs and rsFNC from the full-length (5 min) reference time course were sufficiently approximated with just 3-3.5 min of data (r = 0.85, 0.88, respectively), and significant differences in group-average rsFNC could be sufficiently approximated with even less data, just 2 min (r = 0.86). These results from the shorter clinical data were largely consistent with the results from validation experiments using longer time series from both simulated (30 min) and real-world (14 min) datasets, in which estimates of subject-level FNC were reliably estimated with 3-5 min of data. Moreover, in the real-world data we found rsFNC and ICN estimates generated across the full range of data lengths (0.5-14 min) more reliably matched those generated from the first 5 min of scan time than those generated from the last 5 min, suggesting increased influence of "late scan" noise factors such as fatigue or drowsiness may limit the reliability of FNC from data collected after 10+ min of scan time, further supporting the notion of shorter scans. Lastly, a diagnostic classification model trained on just 2 min of data retained 97%-98% classification accuracy relative to that of the full-length reference model. Our results suggest that, when decomposed with scICA, rsfMRI scans of just 2-5 min show good clinical utility without significant loss of individual FNC information of longer scan lengths., (© 2023 The Authors. Human Brain Mapping published by Wiley Periodicals LLC.)

Background: Differentiating bipolar disorder (BD) from major depressive disorder (MDD) often poses a major clinical challenge, and optimal clinical care can be hindered by misdiagnoses. This study investigated the differences between BD and MDD in resting-state functional network connectivity (FNC) using a data-driven image analysis method., Methods: In this study, fMRI data were collected from unmedicated subjects including 13 BD, 40 MDD and 33 healthy controls (HC). The FNC was calculated between functional brain networks derived from fMRI using group independent component analysis (ICA). Group comparisons were performed on connectivity strengths and other graph measures of FNC matrices., Results: Statistical tests showed that, compared to MDD, the FNC in BD was characterized by more closely connected and more efficient topological structures as assessed by graph theory. The differences were found at both the whole-brain-level and the functional-network-level in prefrontal networks located in the dorsolateral/ventrolateral prefrontal cortex (DLPFC, VLPFC) and anterior cingulate cortex (ACC). Furthermore, interconnected structures in these networks in both patient groups were negatively associated with symptom severity on depression rating scales., Limitations: As patients were unmedicated, the sample sizes were relatively small, although they were comparable to those in previous fMRI studies comparing BD and MDD., Conclusions: Our results suggest that the differences in FNC of the PFC reflect distinct pathophysiological mechanisms in BD and MDD. Such findings ultimately may elucidate the neural pathways in which distinct functional changes can give rise to the clinical differences observed between these syndromes., (Copyright © 2015 Elsevier B.V. All rights reserved.)

Transcranial direct current stimulation (tDCS) modulates glutamatergic neurotransmission and can be utilized as a novel treatment intervention for a multitude of populations. However, the exact mechanism by which tDCS modulates the brain׳s neural architecture, from the micro to macro scales, have yet to be investigated. Using a within-subjects design, resting-state functional magnetic resonance imaging (rs-fMRI) and proton magnetic resonance spectroscopy ((1)H MRS) were performed immediately before and after the administration of anodal tDCS over right parietal cortex. Group independent component analysis (ICA) was used to decompose fMRI scans into 75 brain networks, from which 12 resting-state networks were identified that had significant voxel-wise functional connectivity to anatomical regions of interest. (1)H MRS was used to obtain estimates of combined glutamate and glutamine (Glx) concentrations from bilateral intraparietal sulcus. Paired sample t-tests showed significantly increased Glx under the anodal electrode, but not in homologous regions of the contralateral hemisphere. Increases of within-network connectivity were observed within the superior parietal, inferior parietal, left frontal-parietal, salience and cerebellar intrinsic networks, and decreases in connectivity were observed in the anterior cingulate and the basal ganglia (p<0.05, FDR-corrected). Individual differences in Glx concentrations predicted network connectivity in most of these networks. The observed relationships between glutamatergic neurotransmission and network connectivity may be used to guide future tDCS protocols that aim to target and alter neuroplastic mechanisms in healthy individuals as well as those with psychiatric and neurologic disorders., (Copyright © 2014 Elsevier B.V. All rights reserved.)

Multimodal learning has emerged as a powerful technique that leverages diverse data sources to enhance learning and decision-making processes. Adapting this approach to analyzing data collected from different biological domains is intuitive, especially for studying neuropsychiatric disorders. A complex neuropsychiatric disorder like schizophrenia (SZ) can affect multiple aspects of the brain and biologies. These biological sources each present distinct yet correlated expressions of subjects underlying physiological processes. Joint learning from these data sources can improve our understanding of the disorder. However, combining these biological sources is challenging for several reasons: (i) observations are domain specific, leading to data being represented in dissimilar subspaces, and (ii) fused data are often noisy and high-dimensional, making it challenging to identify relevant information. To address these challenges, we propose a multimodal artificial intelligence model with a novel fusion module inspired by a bottleneck attention module. We use deep neural networks to learn latent space representations of the input streams. Next, we introduce a two-dimensional (spatio-modality) attention module to regulate the intermediate fusion for SZ classification. We implement spatial attention via a dilated convolutional neural network that creates large receptive fields for extracting significant contextual patterns. The resulting joint learning framework maximizes complementarity allowing us to explore the correspondence among the modalities. We test our model on a multimodal imaging-genetic dataset and achieve an SZ prediction accuracy of 94.10% (p