An official website of the United States government
One of the most significant health issues the world is now ex- periencing is mental health. Since it is challenging to mea- sure, it fails to motivate behavioral change or other inter- ventions targeted at improving it. The lack of such mea- surements discourages learning and behavior modification, which are critical for enhancing healthy habits. Neuroimag- ing promises to provide a window into mental health. The use of resting fMRI (rs-fMRI) models capable of categorizing mental health at the individual level has the potential to pro- vide insights into how it impacts the brain. Here, we applied a deep learning approach to classify a mental health score using static functional network connectivity (FNC) derived from rs-fMRI data. Comparisons were made against traditional machine learning approaches to evaluate the model’s perfor- mance. The discriminative features present in each mental health category were analyzed for interpreting the deep learn- ing model. The experiments resulted in a classification ac- curacy of 91%, 91%, 100%, and 100% for excellent, good, fair, and poor mental health classes. Results also highlighted the most salient brain network in the sFNC matrix for each mental health score classification.
more »
« less
A deep learning approach for mental health quality prediction using functional network connectivity and assessment data
While one can characterize mental health using questionnaires, such tools do not provide direct insight into the underlying biology. By linking approaches that visualize brain activity to questionnaires in the context of individualized prediction, we can gain new insights into the biology and behavioral aspects of brain health. Resting-state fMRI (rs-fMRI) can be used to identify biomarkers of these conditions and study patterns of abnormal connectivity. In this work, we estimate mental health quality for individual participants using static functional network connectivity (sFNC) data from rs-fMRI. The deep learning model uses the sFNC data as input to predict four categories of mental health quality and visualize the neural patterns indicative of each group. We used guided gradient class activation maps (guided Grad-CAM) to identify the most discriminative sFNC patterns. The effectiveness of this model was validated using the UK Biobank dataset, in which we showed that our approach outperformed four alternative models by 4-18% accuracy. The proposed model’s performance evaluation yielded a classification accuracy of 76%, 78%, 88%, and 98% for the excellent, good, fair, and poor mental health categories, with poor mental health accuracy being the highest. The findings show distinct sFNC patterns across each group. The patterns associated with excellent mental health consist of the cerebellar-subcortical regions, whereas the most prominent areas in the poor mental health category are in the sensorimotor and visual domains. Thus the combination of rs-fMRI and deep learning opens a promising path for developing a comprehensive framework to evaluate and measure mental health. Moreover, this approach had the potential to guide the development of personalized interventions and enable the monitoring of treatment response. Overall this highlights the crucial role of advanced imaging modalities and deep learning algorithms in advancing our understanding and management of mental health.
more »
« less
- Award ID(s):
- 2112455
- PAR ID:
- 10569560
- Publisher / Repository:
- Springer
- Date Published:
- Journal Name:
- Brain Imaging and Behavior
- Volume:
- 18
- Issue:
- 3
- ISSN:
- 1931-7565
- Page Range / eLocation ID:
- 630 to 645
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Resting-state functional magnetic resonance imaging (rs-fMRI) is a noninvasive technique pivotal for understanding human neural mechanisms of intricate cognitive processes. Most rs-fMRI studies compute a single static functional connectivity matrix across brain regions of interest, or dynamic functional connectivity matrices with a sliding window approach. These approaches are at risk of oversimplifying brain dynamics and lack proper consideration of the goal at hand. While deep learning has gained substantial popularity for modeling complex relational data, its application to uncovering the spatiotemporal dynamics of the brain is still limited. In this study we propose a novel interpretable deep learning framework that learns goal-specific functional connectivity matrix directly from time series and employs a specialized graph neural network for the final classification. Our model, DSAM, leverages temporal causal convolutional networks to capture the temporal dynamics in both low- and high-level feature representations, a temporal attention unit to identify important time points, a self-attention unit to construct the goal-specific connectivity matrix, and a novel variant of graph neural network to capture the spatial dynamics for downstream classification. To validate our approach, we conducted experiments on the Human Connectome Project dataset with 1075 samples to build and interpret the model for the classification of sex group, and the Adolescent Brain Cognitive Development Dataset with 8520 samples for independent testing. Compared our proposed framework with other state-of-art models, results suggested this novel approach goes beyond the assumption of a fixed connectivity matrix, and provides evidence of goal-specific brain connectivity patterns, which opens up potential to gain deeper insights into how the human brain adapts its functional connectivity specific to the task at hand.more » « less
-
The investigation of brain health development is paramount, as a healthy brain underpins cognitive and physical well-being, and mitigates cognitive decline, neurodegenerative diseases, and mental health disorders. This study leverages the UK Biobank dataset containing static functional network connectivity (sFNC) data derived from resting-state functional magnetic resonance imaging (rs-fMRI) and assessment data. We introduce a novel approach to forecasting a brain health index (BHI) by deploying three distinct models, each capitalizing on different modalities for training and testing. The first model exclusively employs psychological assessment measures, while the second model harnesses both neuroimaging and assessment data for training but relies solely on assessment data during testing. The third model encompasses a holistic strategy, utilizing neuroimaging and assessment data for the training and testing phases. The proposed models employ a two-step approach for calculating the BHI. In the first step, the input data is subjected to dimensionality reduction using principal component analysis (PCA) to identify critical patterns and extract relevant features. The resultant concatenated feature vector is then utilized as input to variational autoencoders (VAE). This network generates a low-dimensional representation of the input data used for calculating BHI in new subjects without requiring imaging data. The results suggest that incorporating neuroimaging data into the BHI model, even when predicting from assessments alone, enhances its ability to accurately evaluate brain health. The VAE model exemplifies this improvement by reconstructing the sFNC matrix more accurately than the assessment data. Moreover, these BHI models also enable us to identify distinct behavioral and neural patterns. Hence, this approach lays the foundation for larger-scale efforts to monitor and enhance brain health, aiming to build resilient brain systems.more » « less
-
Brain network models (BNMs) have become a promising theoretical framework for simulating signals that are representative of whole-brain activity such as resting-state fMRI. However, it has been difficult to compare the complex brain activity obtained from simulations to empirical data. Previous studies have used simple metrics to characterize coordination between regions such as functional connectivity. We extend this by applying various different dynamic analysis tools that are currently used to understand empirical resting-state fMRI (rs-fMRI) to the simulated data. We show that certain properties correspond to the structural connectivity input that is shared between the models, and certain dynamic properties relate more to the mathematical description of the brain network model. We conclude that the dynamic properties that explicitly examine patterns of signal as a function of time rather than spatial coordination between different brain regions in the rs-fMRI signal seem to provide the largest contrasts between different BNMs and the unknown empirical dynamical system. Our results will be useful in constraining and developing more realistic simulations of whole-brain activity.more » « less
-
Despite extensive efforts to identify interhemispheric functional connectivity (FC) with resting-state (rs-) fMRI, correlated low-frequency rs-fMRI signal fluctuation across homotopic cortices originates from multiple sources. It remains challenging to differentiate circuit-specific FC from global regulation. Here, we developed a bilateral line-scanning fMRI method to detect laminar-specific rs-fMRI signals from homologous forepaw somatosensory cortices with high spatial and temporal resolution in rat brains. Based on spectral coherence analysis, two distinct bilateral fluctuation spectral features were identified: ultra-slow fluctuation (<0.04 Hz) across all cortical laminae versus Layer (L) 2/3-specific evoked BOLD at 0.05 Hz based on 4 s on/16 s off block design and resting-state fluctuations at 0.08–0.1 Hz. Based on the measurements of evoked BOLD signal at corpus callosum (CC), this L2/3-specific 0.05 Hz signal is likely associated with neuronal circuit-specific activity driven by the callosal projection, which dampened ultra-slow oscillation less than 0.04 Hz. Also, the rs-fMRI power variability clustering analysis showed that the appearance of L2/3-specific 0.08–0.1 Hz signal fluctuation is independent of the ultra-slow oscillation across different trials. Thus, distinct laminar-specific bilateral FC patterns at different frequency ranges can be identified by the bilateral line-scanning fMRI method.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s11682-024-00857-y
