An official website of the United States government
We propose a joint dictionary learning framework that couples imaging and genetics data in a low dimensional subspace as guided by clinical diagnosis. We use a graph regularization penalty to simultaneously capture inter-regional brain interactions and identify the representative set anatomical basis vectors that span the low dimensional space. We further employ group sparsity to find the representative set of genetic basis vectors that span the same latent space. Finally, the latent projection is used to classify patients versus controls. We have evaluated our model on two task fMRI paradigms and single nucleotide polymorphism (SNP) data from schizophrenic patients and matched neurotypical controls. We employ a ten fold cross validation technique to show the predictive power of our model. We compare our model with canonical correlation analysis of imaging and genetics data and random forest classification. Our approach shows better prediction accuracy on both task datasets. Moreover, the implicated brain regions and genetic variants underlie the well documented deficits in schizophrenia.
more »
« less
A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease
We propose a novel end-to-end framework for whole-brain and whole-genome imaging-genetics. Our genetics network uses hierarchical graph convolution and pooling operations to embed subject-level data onto a low-dimensional latent space. The hierarchical network implicitly tracks the convergence of genetic risk across well-established biological pathways, while an attention mechanism automatically identifies the salient edges of this network at the subject level. In parallel, our imaging network projects multimodal data onto a set of latent embeddings. For interpretability, we implement a Bayesian feature selection strategy to extract the discriminative imaging biomarkers; these feature weights are optimized alongside the other model parameters. We couple the imaging and genetic embeddings with a predictor network, to ensure that the learned representations are linked to phenotype. We evaluate our framework on a schizophrenia dataset that includes two functional MRI paradigms and gene scores derived from Single Nucleotide Polymorphism data. Using repeated 10-fold cross-validation, we show that our imaging-genetics fusion achieves the better classification performance than state-of-the-art baselines. In an exploratory analysis, we further show that the biomarkers identified by our model are reproducible and closely associated with deficits in schizophrenia.
more »
« less
- Award ID(s):
- 1822575
- PAR ID:
- 10379197
- Date Published:
- Journal Name:
- International Conference on Learning Representations
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Schizophrenia is a severe brain disorder with serious symptoms including delusions, disorganized speech, and hallucinations that can have a long-term detrimental impact on different aspects of a patient's life. It is still unclear what the main cause of schizophrenia is, but a combination of altered brain connectivity and structure may play a role. Neuroimaging data has been useful in characterizing schizophrenia, but there has been very little work focused on voxel-wise changes in multiple brain networks over time, despite evidence that functional networks exhibit complex spatiotemporal changes over time within individual subjects. Recent studies have primarily focused on static (average) features of functional data or on temporal variations between fixed networks; however, such approaches are not able to capture multiple overlapping networks which change at the voxel level. In this work, we employ a deep residual convolutional neural network (CNN) model to extract 53 different spatiotemporal networks each of which captures dynamism within various domains including subcortical, cerebellar, visual, sensori-motor, auditory, cognitive control, and default mode. We apply this approach to study spatiotemporal brain dynamism at the voxel level within multiple functional networks extracted from a large functional magnetic resonance imaging (fMRI) dataset of individuals with schizophrenia (N= 708) and controls (N= 510). Our analysis reveals widespread group level differences across multiple networks and spatiotemporal features including voxel-wise variability, magnitude, and temporal functional network connectivity in widespread regions expected to be impacted by the disorder. We compare with typical average spatial amplitude and show highly structured and neuroanatomically relevant results are missed if one does not consider the voxel-wise spatial dynamics. Importantly, our approach can summarize static, temporal dynamic, spatial dynamic, and spatiotemporal dynamics features, thus proving a powerful approach to unify and compare these various perspectives. In sum, we show the proposed approach highlights the importance of accounting for both temporal and spatial dynamism in whole brain neuroimaging data generally, shows a high-level of sensitivity to schizophrenia highlighting global but spatially unique dynamics showing group differences, and may be especially important in studies focused on the development of brain-based biomarkers.more » « less
-
Abstract BackgroundIn Alzheimer’s Diseases (AD) research, multimodal imaging analysis can unveil complementary information from multiple imaging modalities and further our understanding of the disease. One application is to discover disease subtypes using unsupervised clustering. However, existing clustering methods are often applied to input features directly, and could suffer from the curse of dimensionality with high-dimensional multimodal data. The purpose of our study is to identify multimodal imaging-driven subtypes in Mild Cognitive Impairment (MCI) participants using a multiview learning framework based on Deep Generalized Canonical Correlation Analysis (DGCCA), to learn shared latent representation with low dimensions from 3 neuroimaging modalities. ResultsDGCCA applies non-linear transformation to input views using neural networks and is able to learn correlated embeddings with low dimensions that capture more variance than its linear counterpart, generalized CCA (GCCA). We designed experiments to compare DGCCA embeddings with single modality features and GCCA embeddings by generating 2 subtypes from each feature set using unsupervised clustering. In our validation studies, we found that amyloid PET imaging has the most discriminative features compared with structural MRI and FDG PET which DGCCA learns from but not GCCA. DGCCA subtypes show differential measures in 5 cognitive assessments, 6 brain volume measures, and conversion to AD patterns. In addition, DGCCA MCI subtypes confirmed AD genetic markers with strong signals that existing late MCI group did not identify. ConclusionOverall, DGCCA is able to learn effective low dimensional embeddings from multimodal data by learning non-linear projections. MCI subtypes generated from DGCCA embeddings are different from existing early and late MCI groups and show most similarity with those identified by amyloid PET features. In our validation studies, DGCCA subtypes show distinct patterns in cognitive measures, brain volumes, and are able to identify AD genetic markers. These findings indicate the promise of the imaging-driven subtypes and their power in revealing disease structures beyond early and late stage MCI.more » « less
-
Large‐scale analysis of functional connectivity within intrinsic brain networks using functional magnetic resonance imaging (fMRI) data has been widely used for identifying biomarkers in various psychiatric disorders. While the emerging access to large neuroimaging datasets provides unprecedented opportunities for exploring brain functions, they also pose significant computational complexity challenges due to the large amount of inherent variability across individuals and the complexity of brain activity patterns. To address these challenges, this paper introduces two novel constrained ICA methods, arc‐EBM and minc‐EBM, designed to overcome the computational complexity issue by incorporating prior information into the analysis framework. The proposed methods preserve the subject variability by adaptively selecting the constrained parameters for different functional networks and individuals, while also allowing estimation flexibility for activities not covered by the prior information through the concept of free components. Our methods are shown to enhance the precision of functional network estimation and improve the capture of subject variability across different cohorts. We evaluate the proposed methods using both synthetic and real fMRI data. By applying the proposed methods to a resting‐state fMRI dataset including 179 subjects, both algorithms successfully reveal significant group differences in functional network connectivity between healthy controls and schizophrenia patients. The observed group differences, particularly the abnormal connectivity alterations in networks involving the thalamus, subthalamus/hypothalamus, and superior temporal gyrus, align with findings from previous clinical studies. Furthermore, our results demonstrate that the constraint parameters adaptively selected by arc‐EBM reveal more diverse resting‐state network structures in individuals with schizophrenia compared with healthy controls. This finding is consistent with prior studies and suggests that the selected constraint parameters could serve as potential biomarkers for mental disorder diagnosis.more » « less
-
IntroductionBrain imaging genetics aims to explore the genetic architecture underlying brain structure and functions. Recent studies showed that the incorporation of prior knowledge, such as subject diagnosis information and brain regional correlation, can help identify significantly stronger imaging genetic associations. However, sometimes such information may be incomplete or even unavailable. MethodsIn this study, we explore a new data-driven prior knowledge that captures the subject-level similarity by fusing multi-modal similarity networks. It was incorporated into the sparse canonical correlation analysis (SCCA) model, which is aimed to identify a small set of brain imaging and genetic markers that explain the similarity matrix supported by both modalities. It was applied to amyloid and tau imaging data of the ADNI cohort, respectively. ResultsFused similarity matrix across imaging and genetic data was found to improve the association performance better or similarly well as diagnosis information, and therefore would be a potential substitute prior when the diagnosis information is not available (i.e., studies focused on healthy controls). DiscussionOur result confirmed the value of all types of prior knowledge in improving association identification. In addition, the fused network representing the subject relationship supported by multi-modal data showed consistently the best or equally best performance compared to the diagnosis network and the co-expression network.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
