An official website of the United States government
Abstract We present a new clustering-enabled regression approach to investigate how functional connectivity (FC) of the entire brain changes from childhood to old age. By applying this method to resting-state functional magnetic resonance imaging data aggregated from three Human Connectome Project studies, we cluster brain regions that undergo identical age-related changes in FC and reveal diverse patterns of these changes for different region clusters. While most brain connections between pairs of regions show minimal yet statistically significant FC changes with age, only a tiny proportion of connections exhibit practically significant age-related changes in FC. Among these connections, FC between region clusters from the same functional network tends to decrease over time, whereas FC between region clusters from different networks demonstrates various patterns of age-related changes. Moreover, our research uncovers sex-specific trends in FC changes. Females show much higher FC mainly within the default mode network, whereas males display higher FC across several more brain networks. These findings underscore the complexity and heterogeneity of FC changes in the brain throughout the lifespan.
more »
« less
Conditional Variational Autoencoder for Functional Connectivity Analysis of Autism Spectrum Disorder Functional Magnetic Resonance Imaging Data: A Comparative Study
Generative models, such as Variational Autoencoders (VAEs), are increasingly employed for atypical pattern detection in brain imaging. During training, these models learn to capture the underlying patterns within “normal” brain images and generate new samples from those patterns. Neurodivergent states can be observed by measuring the dissimilarity between the generated/reconstructed images and the input images. This paper leverages VAEs to conduct Functional Connectivity (FC) analysis from functional Magnetic Resonance Imaging (fMRI) scans of individuals with Autism Spectrum Disorder (ASD), aiming to uncover atypical interconnectivity between brain regions. In the first part of our study, we compare multiple VAE architectures—Conditional VAE, Recurrent VAE, and a hybrid of CNN parallel with RNN VAE—aiming to establish the effectiveness of VAEs in application FC analysis. Given the nature of the disorder, ASD exhibits a higher prevalence among males than females. Therefore, in the second part of this paper, we investigate if introducing phenotypic data could improve the performance of VAEs and, consequently, FC analysis. We compare our results with the findings from previous studies in the literature. The results showed that CNN-based VAE architecture is more effective for this application than the other models.
more »
« less
- Award ID(s):
- 1846658
- PAR ID:
- 10494052
- Publisher / Repository:
- Bioengineering
- Date Published:
- Journal Name:
- Bioengineering
- Volume:
- 10
- Issue:
- 10
- ISSN:
- 2306-5354
- Page Range / eLocation ID:
- 1209
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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
-
IntroductionEarly and accurate diagnosis of autism spectrum disorder (ASD) is crucial for effective intervention, yet it remains a significant challenge due to its complexity and variability. Micro-expressions are rapid, involuntary facial movements indicative of underlying emotional states. It is unknown whether micro-expression can serve as a valid bio-marker for ASD diagnosis. MethodsThis study introduces a novel machine-learning (ML) framework that advances ASD diagnostics by focusing on facial micro-expressions. We applied cutting-edge algorithms to detect and analyze these micro-expressions from video data, aiming to identify distinctive patterns that could differentiate individuals with ASD from typically developing peers. Our computational approach included three key components: (1) micro-expression spotting using Shallow Optical Flow Three-stream CNN (SOFTNet), (2) feature extraction via Micron-BERT, and (3) classification with majority voting of three competing models (MLP, SVM, and ResNet). ResultsDespite the sophisticated methodology, the ML framework's ability to reliably identify ASD-specific patterns was limited by the quality of video data. This limitation raised concerns about the efficacy of using micro-expressions for ASD diagnostics and pointed to the necessity for enhanced video data quality. DiscussionOur research has provided a cautious evaluation of micro-expression diagnostic value, underscoring the need for advancements in behavioral imaging and multimodal AI technology to leverage the full capabilities of ML in an ASD-specific clinical context.more » « less
-
Abstract The study of human brain connectivity, including structural connectivity (SC) and functional connectivity (FC), provides insights into the neurophysiological mechanism of brain function and its relationship to human behavior and cognition. Both types of connectivity measurements provide crucial yet complementary information. However, integrating these two modalities into a single framework remains a challenge, because of the differences in their quantitative interdependencies as well as their anatomical representations due to distinctive imaging mechanisms. In this study, we introduced a new method, joint connectivity matrix independent component analysis (cmICA), which provides a data‐driven parcellation and automated‐linking of SC and FC information simultaneously using a joint analysis of functional magnetic resonance imaging (MRI) and diffusion‐weighted MRI data. We showed that these two connectivity modalities produce common cortical segregation, though with various degrees of (dis)similarity. Moreover, we show conjoint FC networks and structural white matter tracts that directly link these cortical parcellations/sources, within one analysis. Overall, data‐driven joint cmICA provides a new approach for integrating or fusing structural connectivity and FC systematically and conveniently, and provides an effective tool for connectivity‐based multimodal data fusion in brain.more » « less
-
Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent effort in using visual attention maps as a means for visual explanations. A key problem, however, is these methods are designed for classification and categorization tasks, and their extension to explaining generative models, e.g., variational autoencoders (VAE) is not trivial. In this work, we take a step towards bridging this crucial gap, proposing the first technique to visually explain VAEs by means of gradient-based attention. We present methods to generate visual attention from the learned latent space, and also demonstrate such attention explanations serve more than just explaining VAE predictions. We show how these attention maps can be used to localize anomalies in images, demonstrating state-of-the-art performance on the MVTec-AD dataset. We also show how they can be infused into model training, helping bootstrap the VAE into learning improved latent space disentanglement, demonstrated on the Dsprites dataset.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.3390/bioengineering10101209
