Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) approaches for brain imaging data analysis. However, their conclusions are often based on ...pre-engineered features depriving DL of its main advantage - representation learning. We conduct a large-scale systematic comparison profiled in multiple classification and regression tasks on structural MRI images and show the importance of representation learning for DL. Results show that if trained following prevalent DL practices, DL methods have the potential to scale particularly well and substantially improve compared to SML methods, while also presenting a lower asymptotic complexity in relative computational time, despite being more complex. We also demonstrate that DL embeddings span comprehensible task-specific projection spectra and that DL consistently localizes task-discriminative brain biomarkers. Our findings highlight the presence of nonlinearities in neuroimaging data that DL can exploit to generate superior task-discriminative representations for characterizing the human brain.
Brain functional imaging data, especially functional magnetic resonance imaging (fMRI) data, have been employed to reflect functional integration of the brain. Alteration in brain functional ...connectivity (FC) is expected to provide potential biomarkers for classifying or predicting brain disorders. In this paper, we present a comprehensive review in order to provide guidance about the available brain FC measures and typical classification strategies. We survey the state-of-the-art FC analysis methods including widely used static functional connectivity (SFC) and more recently proposed dynamic functional connectivity (DFC). Temporal correlations among regions of interest (ROIs), data-driven spatial network and functional network connectivity (FNC) are often computed to reflect SFC from different angles. SFC can be extended to DFC using a sliding-window framework, and intrinsic connectivity states along the time-varying connectivity patterns are typically extracted using clustering or decomposition approaches. We also briefly summarize window-less DFC approaches. Subsequently, we highlight various strategies for feature selection including the filter, wrapper and embedded methods. In terms of model building, we include traditional classifiers as well as more recently applied deep learning methods. Moreover, we review representative applications with remarkable classification accuracy for psychosis and mood disorders, neurodevelopmental disorder, and neurological disorders using fMRI data. Schizophrenia, bipolar disorder, autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), Alzheimer's disease and mild cognitive impairment (MCI) are discussed. Finally, challenges in the field are pointed out with respect to the inaccurate diagnosis labeling, the abundant number of possible features and the difficulty in validation. Some suggestions for future work are also provided.
Thalamocortical dysrhythmia is a key pathology of chronic neuropathic pain, but few studies have investigated thalamocortical networks in chronic low back pain (cLBP) given its non-specific etiology ...and complexity. Using fMRI, we propose an analytical pipeline to identify abnormal thalamocortical network dynamics in cLBP patients and validate the findings in two independent cohorts. We first identify two reoccurring dynamic connectivity states and their associations with chronic and temporary pain. Further analyses show that cLBP patients have abnormal connectivity between the ventral lateral/posterolateral nucleus (VL/VPL) and postcentral gyrus (PoCG) and between the dorsal/ventral medial nucleus and insula in the less frequent connectivity state, and temporary pain exacerbation alters connectivity between the VL/VPL and PoCG and the default mode network in the more frequent connectivity state. These results extend current findings on thalamocortical dysfunction and dysrhythmia in chronic pain and demonstrate that cLBP pathophysiology and clinical pain intensity are associated with distinct thalamocortical network dynamics.
•Our deep learning model can reveal disorder-dependent network connectivity.•Sensorimotor and default-mode connectivity is key for classifying dementia and gender.•Schizophrenia exhibits ...dysconnectivity in visual and sensorimotor networks.•Connectivity among brain regions is dynamic and directed.•A few sparse time points turn out amply predictive in downstream classification.
Brain network interactions are commonly assessed via functional (network) connectivity, captured as an undirected matrix of Pearson correlation coefficients. Functional connectivity can represent static and dynamic relations, but often these are modeled using a fixed choice for the data window Alternatively, deep learning models may flexibly learn various representations from the same data based on the model architecture and the training task. However, the representations produced by deep learning models are often difficult to interpret and require additional posthoc methods, e.g., saliency maps. In this work, we integrate the strengths of deep learning and functional connectivity methods while also mitigating their weaknesses. With interpretability in mind, we present a deep learning architecture that exposes a directed graph layer that represents what the model has learned about relevant brain connectivity. A surprising benefit of this architectural interpretability is significantly improved accuracy in discriminating controls and patients with schizophrenia, autism, and dementia, as well as age and gender prediction from functional MRI data. We also resolve the window size selection problem for dynamic directed connectivity estimation as we estimate windowing functions from the data, capturing what is needed to estimate the graph at each time-point. We demonstrate efficacy of our method in comparison with multiple existing models that focus on classification accuracy, unlike our interpretability-focused architecture. Using the same data but training different models on their own discriminative tasks we are able to estimate task-specific directed connectivity matrices for each subject. Results show that the proposed approach is also more robust to confounding factors compared to standard dynamic functional connectivity models. The dynamic patterns captured by our model are naturally interpretable since they highlight the intervals in the signal that are most important for the prediction. The proposed approach reveals that differences in connectivity among sensorimotor networks relative to default-mode networks are an important indicator of dementia and gender. Dysconnectivity between networks, specially sensorimotor and visual, is linked with schizophrenic patients, however schizophrenic patients show increased intra-network default-mode connectivity compared to healthy controls. Sensorimotor connectivity was important for both dementia and schizophrenia prediction, but schizophrenia is more related to dysconnectivity between networks whereas, dementia bio-markers were mostly intra-network connectivity.
Although both resting and task-induced functional connectivity (FC) have been used to characterize the human brain and cognitive abilities, the potential of task-induced FCs in individualized ...prediction for out-of-scanner cognitive traits remains largely unexplored. A recent study Greene et al. (2018) predicted the fluid intelligence scores using FCs derived from rest and multiple task conditions, suggesting that task-induced brain state manipulation improved prediction of individual traits. Here, using a large dataset incorporating fMRI data from rest and 7 distinct task conditions, we replicated the original study by employing a different machine learning approach, and applying the method to predict two reading comprehension-related cognitive measures. Consistent with their findings, we found that task-based machine learning models often outperformed rest-based models. We also observed that combining multi-task fMRI improved prediction performance, yet, integrating the more fMRI conditions can not necessarily ensure better predictions. Compared with rest, the predictive FCs derived from language and working memory tasks were highlighted with more predictive power in predominantly default mode and frontoparietal networks. Moreover, prediction models demonstrated high stability to be generalizable across distinct cognitive states. Together, this replication study highlights the benefit of using task-based FCs to reveal brain-behavior relationships, which may confer more predictive power and promote the detection of individual differences of connectivity patterns underlying relevant cognitive traits, providing strong evidence for the validity and robustness of the original findings.
•Functional connectivity can be used to predict reading comprehension abilities.•Task based models outperformed rest-based models in cognition prediction.•Combining connectomes from multiple fMRI states improved prediction performance.•Prediction models can be generalized across distinct cognitive states.
Abstract
Scores on intelligence tests are strongly predictive of various important life outcomes. However, the gender discrepancy on intelligence quotient (IQ) prediction using brain imaging ...variables has not been studied. To this aim, we predicted individual IQ scores for males and females separately using whole-brain functional connectivity (FC). Robust predictions of intellectual capabilities were achieved across three independent data sets (680 subjects) and two intelligence measurements (IQ and fluid intelligence) using the same model within each gender. Interestingly, we found that intelligence of males and females were underpinned by different neurobiological correlates, which are consistent with their respective superiority in cognitive domains (visuospatial vs verbal ability). In addition, the identified FC patterns are uniquely predictive on IQ and its sub-domain scores only within the same gender but neither for the opposite gender nor on the IQ-irrelevant measures such as temperament traits. Moreover, females exhibit significantly higher IQ predictability than males in the discovery cohort. This findings facilitate our understanding of the biological basis of intelligence by demonstrating that intelligence is underpinned by a variety of complex neural mechanisms that engage an interacting network of regions—particularly prefrontal–parietal and basal ganglia—whereas the network pattern differs between genders.
The human brain is a dynamic system that incorporates the evolution of local activities and the reconfiguration of brain interactions. Reoccurring brain patterns, regarded as “brain states”, have ...revealed new insights into the pathophysiology of brain disorders, particularly schizophrenia. However, previous studies only focus on the dynamics of either brain activity or connectivity, ignoring the temporal co-evolution between them. In this work, we propose to capture dynamic brain states with covarying activity-connectivity and probe schizophrenia-related brain abnormalities. We find that the state-based activity and connectivity show high correspondence, where strong and antagonistic connectivity is accompanied with strong low-frequency fluctuations across the whole brain while weak and sparse connectivity co-occurs with weak low-frequency fluctuations. In addition, graphical analysis shows that connectivity network efficiency is associated with the fluctuation of brain activities and such associations are different across brain states. Compared with healthy controls, schizophrenia patients spend more time in weakly-connected and -activated brain states but less time in strongly-connected and -activated brain states. schizophrenia patients also show lower efficiency in thalamic regions within the “strong” states. Interestingly, the atypical fractional occupancy of one brain state is correlated with individual attention performance. Our findings are replicated in another independent dataset and validated using different brain parcellation schemes. These converging results suggest that the brain spontaneously reconfigures with covarying activity and connectivity and such co-evolutionary property might provide meaningful information on the mechanism of brain disorders which cannot be observed by investigating either of them alone.
Individuals at clinical high-risk (CHR) for psychosis are characterized by attenuated psychotic symptoms. Only a minority of CHR individuals convert to full-blown psychosis. Therefore, there is a ...strong interest in identifying neurobiological abnormalities underlying the psychosis risk syndrome. Dynamic functional connectivity (DFC) captures time-varying connectivity over short time scales, and has the potential to reveal complex brain functional organization. Based on resting-state functional magnetic resonance imaging (fMRI) data from 70 healthy controls (HCs), 53 CHR individuals, and 58 early illness schizophrenia (ESZ) patients, we applied a novel group information guided ICA (GIG-ICA) to estimate inherent connectivity states from DFC, and then investigated group differences. We found that ESZ patients showed more aberrant connectivities and greater alterations than CHR individuals. Results also suggested that disease-related connectivity states occurred in CHR and ESZ groups. Regarding the dominant state with the highest contribution to dynamic connectivity, ESZ patients exhibited greater impairments than CHR individuals primarily in the cerebellum, frontal cortex, thalamus and temporal cortex, while CHR and ESZ populations shared common aberrances mainly in the supplementary motor area, parahippocampal gyrus and postcentral cortex. CHR-specific changes were also found in the connections between the superior frontal gyrus and calcarine cortex in the dominant state. Our findings suggest that CHR individuals generally show an intermediate functional connectivity pattern between HCs and SZ patients but also have unique connectivity alterations.
Display omitted
•Propose a new pipeline to link brain changes among different datasets, studies, and disorders.•Identify reproducible biomarkers in schizophrenia using independent data.•Find both ...common and unique brain impairments in schizophrenia and autism.•Reveal gradual changes from healthy controls to mild cognitive impairment to Alzheimer’s disease.•Obtain high classification accuracy (~90%) between bipolar disorder and major depressive disorder.
Many mental illnesses share overlapping or similar clinical symptoms, confounding the diagnosis. It is important to systematically characterize the degree to which unique and similar changing patterns are reflective of brain disorders. Increasing sharing initiatives on neuroimaging data have provided unprecedented opportunities to study brain disorders. However, it is still an open question on replicating and translating findings across studies. Standardized approaches for capturing reproducible and comparable imaging markers are greatly needed. Here, we propose a pipeline based on the priori-driven independent component analysis, NeuroMark, which is capable of estimating brain functional network measures from functional magnetic resonance imaging (fMRI) data that can be used to link brain network abnormalities among different datasets, studies, and disorders. NeuroMark automatically estimates features adaptable to each individual subject and comparable across datasets/studies/disorders by taking advantage of the reliable brain network templates extracted from 1828 healthy controls as guidance. Four studies including 2442 subjects were conducted spanning six brain disorders (schizophrenia, autism spectrum disorder, mild cognitive impairment, Alzheimer’s disease, bipolar disorder, and major depressive disorder) to evaluate validity of the proposed pipeline from different perspectives (replication of brain abnormalities, cross-study comparison, identification of subtle brain changes, and multi-disorder classification using identified biomarkers). Our results highlight that NeuroMark effectively identified replicated brain network abnormalities of schizophrenia across different datasets; revealed interesting neural clues on the overlap and specificity between autism and schizophrenia; demonstrated brain functional impairments present to varying degrees in mild cognitive impairments and Alzheimer's disease; and captured biomarkers that achieved good performance in classifying bipolar disorder and major depressive disorder.
Temperament consists of multi-dimensional traits that affect various domains of human life. Evidence has shown functional connectome-based predictive models are powerful predictors of cognitive ...abilities. Putatively, individuals' innate temperament traits may be predictable by unique patterns of brain functional connectivity (FC) as well. However, quantitative prediction for multiple temperament traits at the individual level has not yet been studied. Therefore, we were motivated to realize the individualized prediction of four temperament traits (novelty seeking NS, harm avoidance HA, reward dependence RD and persistence PS) using whole-brain FC. Specifically, a multivariate prediction framework integrating feature selection and sparse regression was applied to resting-state fMRI data from 360 college students, resulting in 4 connectome-based predictive models that enabled prediction of temperament scores for unseen subjects in cross-validation. More importantly, predictive models for HA and NS could be successfully generalized to two relevant personality traits for unseen individuals, i.e., neuroticism and extraversion, in an independent dataset. In four temperament trait predictions, brain connectivities that show top contributing power commonly concentrated on the hippocampus, prefrontal cortex, basal ganglia, amygdala, and cingulate gyrus. Finally, across independent datasets and multiple traits, we show person's temperament traits can be reliably predicted using functional connectivity strength within frontal-subcortical circuits, indicating that human social and behavioral performance can be characterized by specific brain connectivity profile.
•Development of connectome-based predictive models for four temperament metrics.•Temperaments can be characterized by functional connections within the frontal-subcortical circuits.•Prediction of harm avoidance can be generalized to neuroticism in new independent dataset.•Prediction of novelty seeking can be generalized to extraversion in new independent dataset.