Optimized Combination of Multiple Graphs With Application to the Integration of Brain Imaging and (epi)Genomics Data

A comprehensive survey of complex brain network representation

Recent years have shown great merits in utilizing neuroimaging data to understand brain structural and functional changes, as well as its relationship to different neurodegenerative diseases and other clinical phenotypes. Brain networks, derived from different neuroimaging modalities, have attracted increasing attention due to their potential to gain system-level insights to characterize brain dynamics and abnormalities in neurological conditions. Traditional methods aim to pre-define multiple topological features of brain networks and relate these features to different clinical measures or demographical variables. With the enormous successes in deep learning techniques, graph learning methods have played significant roles in brain network analysis. In this survey, we first provide a brief overview of neuroimaging-derived brain networks. Then, we focus on presenting a comprehensive overview of both traditional methods and state-of-the-art deep-learning methods for brain network mining. Major models, and objectives of these methods are reviewed within this paper. Finally, we discuss several promising research directions in this field.

A systematic review of neuroimaging epigenetic research: calling for an increased focus on development

Epigenetic mechanisms, such as DNA methylation (DNAm), have gained increasing attention as potential biomarkers and mechanisms underlying risk for neurodevelopmental, psychiatric and other brain-based disorders. Yet, surprisingly little is known about the extent to which DNAm is linked to individual differences in the brain itself, and how these associations may unfold across development - a time of life when many of these disorders emerge. Here, we systematically review evidence from the nascent field of Neuroimaging Epigenetics, combining structural or functional neuroimaging measures with DNAm, and the extent to which the developmental period (birth to adolescence) is represented in these studies. We identified 111 articles published between 2011-2021, out of which only a minority (21%) included samples under 18 years of age. Most studies were cross-sectional (85%), employed a candidate-gene approach (67%), and examined DNAm-brain associations in the context of health and behavioral outcomes (75%). Nearly half incorporated genetic data, and a fourth investigated environmental influences. Overall, studies support a link between peripheral DNAm and brain imaging measures, but there is little consistency in specific findings and it remains unclear whether DNAm markers present a cause, correlate or consequence of brain alterations. Overall, there is large heterogeneity in sample characteristics, peripheral tissue and brain outcome examined as well as the methods used. Sample sizes were generally low to moderate (median nall = 98, ndevelopmental = 80), and attempts at replication or meta-analysis were rare. Based on the strengths and weaknesses of existing studies, we propose three recommendations on how advance the field of Neuroimaging Epigenetics. We advocate for: (1) a greater focus on developmentally oriented research (i.e. pre-birth to adolescence); (2) the analysis of large, prospective, pediatric cohorts with repeated measures of DNAm and imaging to assess directionality; and (3) collaborative, interdisciplinary science to identify robust signals, triangulate findings and enhance translational potential.

A Review of Fusion Methods for Omics and Imaging Data

The development of omics data and biomedical images has greatly advanced the progress of precision medicine in diagnosis, treatment, and prognosis. The fusion of omics and imaging data, i.e., omics-imaging fusion, offers a new strategy for understanding complex diseases. However, due to a variety of issues such as the limited number of samples, high dimensionality of features, and heterogeneity of different data types, efficiently learning complementary or associated discriminative fusion information from omics and imaging data remains a challenge. Recently, numerous machine learning methods have been proposed to alleviate these problems. In this review, from the perspective of fusion levels and fusion methods, we first provide an overview of preprocessing and feature extraction methods for omics and imaging data, and comprehensively analyze and summarize the basic forms and variations of commonly used and newly emerging fusion methods, along with their advantages, disadvantages and the applicable scope. We then describe public datasets and compare experimental results of various fusion methods on the ADNI and TCGA datasets. Finally, we discuss future prospects and highlight remaining challenges in the field.

A Deep Local Patch Matching Network for Cell Tracking in Microscopy Image Sequences Without Registration

Cell tracking is critical for the modeling of plant cell growth patterns. A local graph matching algorithm is proposed to track cells by exploiting the tight spatial topology of cells. However, the local graph matching approach lacks robustness in the unregistered images because the feature descriptors are handcrafted. In this paper, we propose a Deep Local Patch Matching Network (DLPM-Net) to track cells robustly, by exploiting local patches' deep similarity information and cells' spatial-temporal contextual information. Furthermore, to reduce the time consumption during the matching process and enhance tracking accuracy, we take two steps to realize the tracking of non-division cells and the detection of cell divisions. In the first step, the DLPM-Net is employed to match the non-division cells by exploiting the cell pair candidates' local patch contextual information, then the non-matched cells are recorded as the cell division candidates. In the second step, the DLPM-Net is used to detect cell divisions from these non-matched cells, by exploiting the local patch contextual similarity between the mother cell's local patch and daughter cells' local patch. Compared with the existing local graph matching method, the experimental results show that the proposed method gains 29.1% improvement in the tracking accuracy.

Multi-Modal Imaging Genetics Data Fusion via a Hypergraph-Based Manifold Regularization: Application to Schizophrenia Study

Recent studies show that multi-modal data fusion techniques combine information from diverse sources for comprehensive diagnosis and prognosis of complex brain disorder, often resulting in improved accuracy compared to single-modality approaches. However, many existing data fusion methods extract features from homogeneous networs, ignoring heterogeneous structural information among multiple modalities. To this end, we propose a Hypergraph-based Multi-modal data Fusion algorithm, namely HMF. Specifically, we first generate a hypergraph similarity matrix to represent the high-order relationships among subjects, and then enforce the regularization term based upon both the inter- and intra-modality relationships of the subjects. Finally, we apply HMF to integrate imaging and genetics datasets. Validation of the proposed method is performed on both synthetic data and real samples from schizophrenia study. Results show that our algorithm outperforms several competing methods, and reveals significant interactions among risk genes, environmental factors and abnormal brain regions.

The roots of paternal depression: Experienced and nonexperienced trauma or Folie a Deux?

The transition to fatherhood may be challenged with anxiety and trepidation. A high prevalence has been found for paternal depression and it is reactive to maternal depression. This review aims to address potential sources of paternal depression, which may have adverse consequences on child development. We describe through three hypotheses how fathers may be at risk of depression during the transition to fatherhood: (1) psychological (interacting with ecological systems); (2) brain functional∖structural changes; and (3) (epi)genomic. We propose that paternal stressful experiences during the transition to fatherhood may be the source for paternal depression through direct stressful paternal experiences or via (potential, currently debated) nonexperienced (by the father) epigenomic transgenerational transmission. On the other hand, we suggest that resilient fathers may undergo a transient dysphoric period affected by identifying with the newborn's vulnerability as well as with the mother's postpartum vulnerability resulting in "paternity blues." In accordance with recent views on paternal "heightened sensitivity" toward the infant, we propose that the identification of both parents with the vulnerability of the newborn creates a sensitive period of Folie a Deux (shared madness) which may be a healthy transient, albeit a quasi-pathological period, recruited by the orienting response of the newborn for survival.

Multiview Diffusion Map Improves Prediction of Fluid Intelligence With Two Paradigms of fMRI Analysis

OBJECTIVE

To understand the association between brain networks and behaviors of an individual, most studies build predictive models based on functional connectivity (FC) from a single dataset with linear analysis techniques. Such approaches may fail to capture the nonlinear structure of brain networks and neglect the complementary information contained in FC networks (FCNs) from multiple datasets. To address this challenging issue, we use multiview dimensionality reduction to extract a coherent low-dimensional representation of the FCNs from resting-state and emotion identification task-based functional magnetic resonance imaging (fMRI) datasets.

METHODS

We propose a scheme based on multiview diffusion map to extract intrinsic features while preserving the underlying geometric structure of high dimensional datasets. This method is robust to noise and small variations in the data.

RESULTS

After validation on the Philadelphia Neurodevelopmental Cohort data, the predictive model built from both resting-state and emotion identification task-based fMRI datasets outperforms the one using each individual fMRI dataset. In addition, the proposed model achieves better prediction performance than principal component analysis (PCA) and three other competing data fusion methods.

CONCLUSION

Our framework for combing multiple FCNs in one predictive model exhibits improved prediction performance.

SIGNIFICANCE

To our knowledge, we demonstrate a first application of multiview diffusion map to successfully fuse different types of fMRI data for predicting fluid intelligence (gF).