Neuroimaging-based single subject prediction of brain disorders has gained increasing attention in recent years. Using a variety of neuroimaging modalities such as structural, functional and diffusion MRI, along with machine learning techniques, hundreds of studies have been carried out for accurate classification of patients with heterogeneous mental and neurodegenerative disorders such as schizophrenia and Alzheimer's disease. More than 500 studies have been published during the past quarter century on single subject prediction focused on a multiple brain disorders. In the first part of this study, we provide a survey of more than 200 reports in this field with a focus on schizophrenia, mild cognitive impairment (MCI), Alzheimer's disease (AD), depressive disorders, autism spectrum disease (ASD) and attention-deficit hyperactivity disorder (ADHD). Detailed information about those studies such as sample size, type and number of extracted features and reported accuracy are summarized and discussed. To our knowledge, this is by far the most comprehensive review of neuroimaging-based single subject prediction of brain disorders. In the second part, we present our opinion on major pitfalls of those studies from a machine learning point of view. Common biases are discussed and suggestions are provided. Moreover, emerging trends such as decentralized data sharing, multimodal brain imaging, differential diagnosis, disease subtype classification and deep learning are also discussed. Based on this survey, there are extensive evidences showing the great potential of neuroimaging data for single subject prediction of various disorders. However, the main bottleneck of this exciting field is still the limited sample size, which could be potentially addressed by modern data sharing models such as the ones discussed in this paper. Emerging big data technologies and advanced data-intensive machine learning methodologies such as deep learning have coincided with an increasing need for accurate, robust and generalizable single subject prediction of brain disorders during an exciting time. In this report, we survey the past and offer some opinions regarding the road ahead.

It is becoming increasingly clear that combining multi-modal brain imaging data is able to provide more information for individual subjects by exploiting the rich multimodal information that exists. However, the number of studies that do true multimodal fusion (i.e. capitalizing on joint information among modalities) is still remarkably small given the known benefits. In part, this is because multi-modal studies require broader expertise in collecting, analyzing, and interpreting the results than do unimodal studies. In this paper, we start by introducing the basic reasons why multimodal data fusion is important and what it can do, and importantly how it can help us avoid wrong conclusions and help compensate for imperfect brain imaging studies. We also discuss the challenges that need to be confronted for such approaches to be more widely applied by the community. We then provide a review of the diverse studies that have used multimodal data fusion (primarily focused on psychosis) as well as provide an introduction to some of the existing analytic approaches. Finally, we discuss some up-and-coming approaches to multi-modal fusion including deep learning and multimodal classification which show considerable promise. Our conclusion is that multimodal data fusion is rapidly growing, but it is still underutilized. The complexity of the human brain coupled with the incomplete measurement provided by existing imaging technology makes multimodal fusion essential in order to mitigate against misdirection and hopefully provide a key to finding the missing link(s) in complex mental illness.

The development of various neuroimaging techniques is rapidly improving the measurements of brain function/structure. However, despite improvements in individual modalities, it is becoming increasingly clear that the most effective research approaches will utilize multi-modal fusion, which takes advantage of the fact that each modality provides a limited view of the brain. The goal of multimodal fusion is to capitalize on the strength of each modality in a joint analysis, rather than a separate analysis of each. This is a more complicated endeavor that must be approached more carefully and efficient methods should be developed to draw generalized and valid conclusions from high dimensional data with a limited number of subjects. Numerous research efforts have been reported in the field based on various statistical approaches, e.g. independent component analysis (ICA), canonical correlation analysis (CCA) and partial least squares (PLS). In this review paper, we survey a number of multivariate methods appearing in previous reports, which are performed with or without prior information and may have utility for identifying potential brain illness biomarkers. We also discuss the possible strengths and limitations of each method, and review their applications to brain imaging data.

Hemispheric asymmetry is a cardinal feature of human brain organization. Altered brain asymmetry has also been linked to some cognitive and neuropsychiatric disorders. Here the ENIGMA consortium presents the largest ever analysis of cerebral cortical asymmetry and its variability across individuals. Cortical thickness and surface area were assessed in MRI scans of 17,141 healthy individuals from 99 datasets worldwide. Results revealed widespread asymmetries at both hemispheric and regional levels, with a generally thicker cortex but smaller surface area in the left hemisphere relative to the right. Regionally, asymmetries of cortical thickness and/or surface area were found in the inferior frontal gyrus, transverse temporal gyrus, parahippocampal gyrus, and entorhinal cortex. These regions are involved in lateralized functions, including language and visuospatial processing. In addition to population-level asymmetries, variability in brain asymmetry was related to sex, age, and brain size (indexed by intracranial volume). Interestingly, we did not find significant associations between asymmetries and handedness. Finally, with two independent pedigree datasets (N = 1,443 and 1,113, respectively), we found several asymmetries showing modest but highly reliable heritability. The structural asymmetries identified, and their variabilities and heritability provide a reference resource for future studies on the genetic basis of brain asymmetry and altered laterality in cognitive, neurological, and psychiatric disorders.Significance StatementLeft-right asymmetry is a key feature of the human brain's structure and function. It remains unclear which cortical regions are asymmetrical on average in the population, and how biological factors such as age, sex and genetic variation affect these asymmetries. Here we describe by far the largest ever study of cerebral cortical brain asymmetry, based on data from 17,141 participants. We found a global anterior-posterior 'torque' pattern in cortical thickness, together with various regional asymmetries at the population level, which have not been previously described, as well as effects of age, sex, and heritability estimates. From these data, we have created an on-line resource that will serve future studies of human brain anatomy in health and disease.

Graphical abstract

Diverse structural and functional brain alterations have been identified in both schizophrenia and bipolar disorder, but with variable replicability, significant overlap and often in limited number of subjects. In this paper, we aimed to clarify differences between bipolar disorder and schizophrenia by combining fMRI (collected during an auditory oddball task) and diffusion tensor imaging (DTI) data. We proposed a fusion method, “multimodal CCA+ joint ICA’, which increases flexibility in statistical assumptions beyond existing approaches and can achieve higher estimation accuracy. The data collected from 164 participants (62 healthy controls, 54 schizophrenia and 48 bipolar) were extracted into “features” (contrast maps for fMRI and fractional anisotropy (FA) for DTI) and analyzed in multiple facets to investigate the group differences for each pair-wised groups and each modality. Specifically, both patient groups shared significant dysfunction in dorsolateral prefrontal cortex and thalamus, as well as reduced white matter (WM) integrity in anterior thalamic radiation and uncinate fasciculus. Schizophrenia and bipolar subjects were separated by functional differences in medial frontal and visual cortex, as well as WM tracts associated with occipital and frontal lobes. Both patients and controls showed similar spatial distributions in motor and parietal regions, but exhibited significant variations in temporal lobe. Furthermore, there were different group trends for age effects on loading parameters in motor cortex and multiple WM regions, suggesting brain dysfunction and WM disruptions occurred in identified regions for both disorders. Most importantly, we can visualize an underlying function-structure network by evaluating the joint components with strong links between DTI and fMRI. Our findings suggest that although the two patient groups showed several distinct brain patterns from each other and healthy controls, they also shared common abnormalities in prefrontal thalamic WM integrity and in frontal brain mechanisms.

Graph theory-based analysis has been widely employed in brain imaging studies, and altered topological properties of brain connectivity have emerged as important features of mental diseases such as schizophrenia. However, most previous studies have focused on graph metrics of stationary brain graphs, ignoring that brain connectivity exhibits fluctuations over time. Here we develop a new framework for accessing dynamic graph properties of time-varying functional brain connectivity in resting state fMRI data and apply it to healthy controls (HCs) and patients with schizophrenia (SZs). Specifically, nodes of brain graphs are defined by intrinsic connectivity networks (ICNs) identified by group independent component analysis (ICA). Dynamic graph metrics of the time-varying brain connectivity estimated by the correlation of sliding time-windowed ICA time courses of ICNs are calculated. First- and second-level connectivity states are detected based on the correlation of nodal connectivity strength between time-varying brain graphs. Our results indicate that SZs show decreased variance in the dynamic graph metrics. Consistent with prior stationary functional brain connectivity works, graph measures of identified first-level connectivity states show lower values in SZs. In addition, more first-level connectivity states are disassociated with the second-level connectivity state which resembles the stationary connectivity pattern computed by the entire scan. Collectively, the findings provide new evidence about altered dynamic brain graphs in schizophrenia which may underscore the abnormal brain performance in this mental illness.

Intrinsic functional brain networks (INs) are regions showing temporal coherence with one another. These INs are present in the context of a task (as opposed to an undirected task such as rest), albeit modulated to a degree both spatially and temporally. Prominent networks include the default mode, attentional fronto-parietal, executive control, bilateral temporal lobe, and motor networks. The characterization of INs has recently gained considerable momentum, however; most previous studies evaluate only a small subset of the INs (e.g., default mode). In this paper we use independent component analysis to study INs decomposed from functional magnetic resonance imaging data collected in a large group of schizophrenia patients, healthy controls, and individuals with bipolar disorder, while performing an auditory oddball task. Schizophrenia and bipolar disorder share significant overlap in clinical symptoms, brain characteristics, and risk genes which motivates our goal of identifying whether functional imaging data can differentiate the two disorders. We tested for group differences in properties of all identified INs including spatial maps, spectra, and functional network connectivity. A small set of default mode, temporal lobe, and frontal networks with default mode regions appearing to play a key role in all comparisons. Bipolar subjects showed more prominent changes in ventromedial and prefrontal default mode regions whereas schizophrenia patients showed changes in posterior default mode regions. Anti-correlations between left parietal areas and dorsolateral prefrontal cortical areas were different in bipolar and schizophrenia patients and amplitude was significantly different from healthy controls in both patient groups. Patients exhibited similar frequency behavior across multiple networks with decreased low frequency power. In summary, a comprehensive analysis of INs reveals a key role for the default mode in both schizophrenia and bipolar disorder.