The MCIC collection: a shared repository of multi-modal, multi-site brain image data from a clinical investigation of schizophrenia

Molecular and micro-architectural mapping of gray matter alterations in psychosis

The psychosis spectrum encompasses a heterogeneous range of clinical conditions associated with abnormal brain development. Detecting patterns of atypical neuroanatomical maturation across psychiatric disorders requires an interpretable metric standardized by age-, sex- and site-effect. The molecular and micro-architectural attributes that account for these deviations in brain structure from typical neurodevelopment are still unknown. Here, we aggregate structural magnetic resonance imaging data from 38,696 healthy controls (HC) and 1256 psychosis-related conditions, including first-degree relatives of schizophrenia (SCZ) and schizoaffective disorder (SAD) patients (n = 160), individuals who had psychotic experiences (n = 157), patients who experienced a first episode of psychosis (FEP, n = 352), and individuals with chronic SCZ or SAD (n = 587). Using a normative modeling approach, we generated centile scores for cortical gray matter (GM) phenotypes, identifying deviations in regional volumes below the expected trajectory for all conditions, with a greater impact on the clinically diagnosed ones, FEP and chronic. Additionally, we mapped 46 neurobiological features from healthy individuals (including neurotransmitters, cell types, layer thickness, microstructure, cortical expansion, and metabolism) to these abnormal centiles using a multivariate approach. Results revealed that neurobiological features were highly co-localized with centile deviations, where metabolism (e.g., cerebral metabolic rate of oxygen (CMRGlu) and cerebral blood flow (CBF)) and neurotransmitter concentrations (e.g., serotonin (5-HT) and acetylcholine (α4β2) receptors) showed the most consistent spatial overlap with abnormal GM trajectories. Taken together these findings shed light on the vulnerability factors that may underlie atypical brain maturation during different stages of psychosis.

Individualized Texture Similarity Network in Schizophrenia

BACKGROUND

Structural covariance network disruption has been considered an important pathophysiological indicator for schizophrenia. Here, we introduced a novel individualized structural covariance network measure, referred to as a texture similarity network (TSN), and hypothesized that the TSN could reliably reveal unique intersubject heterogeneity and complex dysconnectivity patterns in schizophrenia.

METHODS

The TSN was constructed by measuring the covariance of 180 three-dimensional voxelwise gray-level co-occurrence matrix feature maps between brain areas in each participant. We first tested the validity and reproducibility of the TSN in characterizing the intersubject variability in 2 longitudinal test-retest healthy cohorts. The TSN was further applied to elucidate intersubject variability and dysconnectivity patterns in 10 schizophrenia case-control datasets (609 schizophrenia cases vs. 579 controls) as well as in a first-episode depression dataset (69 patients with depression vs. 69 control participants).

RESULTS

The test-retest analysis demonstrated higher TSN intersubject than intrasubject variability. Moreover, the TSN reliably revealed higher intersubject variability in both chronic and first-episode schizophrenia, but not in depression. The TSN also reproducibly detected coexistent increased and decreased TSN strength in widespread brain areas, increased global small-worldness, and the coexistence of both structural hyposynchronization in the central networks and hypersynchronization in peripheral networks in patients with schizophrenia but not in patients with depression. Finally, aberrant intersubject variability and covariance strength patterns revealed by the TSN showed a missing or weak correlation with other individualized structural covariance network measures, functional connectivity, and regional volume changes.

CONCLUSIONS

These findings support the reliability of a TSN in revealing unique structural heterogeneity and complex dysconnectivity in patients with schizophrenia.

Neurostructural subgroup in 4291 individuals with schizophrenia identified using the subtype and stage inference algorithm

Machine learning can be used to define subtypes of psychiatric conditions based on shared biological foundations of mental disorders. Here we analyzed cross-sectional brain images from 4,222 individuals with schizophrenia and 7038 healthy subjects pooled across 41 international cohorts from the ENIGMA, non-ENIGMA cohorts and public datasets. Using the Subtype and Stage Inference (SuStaIn) algorithm, we identify two distinct neurostructural subgroups by mapping the spatial and temporal 'trajectory' of gray matter change in schizophrenia. Subgroup 1 was characterized by an early cortical-predominant loss with enlarged striatum, whereas subgroup 2 displayed an early subcortical-predominant loss in the hippocampus, striatum and other subcortical regions. We confirmed the reproducibility of the two neurostructural subtypes across various sample sites, including Europe, North America and East Asia. This imaging-based taxonomy holds the potential to identify individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.

Connectional-style-guided contextual representation learning for brain disease diagnosis

Structural magnetic resonance imaging (sMRI) has shown great clinical value and has been widely used in deep learning (DL) based computer-aided brain disease diagnosis. Previous DL-based approaches focused on local shapes and textures in brain sMRI that may be significant only within a particular domain. The learned representations are likely to contain spurious information and have poor generalization ability in other diseases and datasets. To facilitate capturing meaningful and robust features, it is necessary to first comprehensively understand the intrinsic pattern of the brain that is not restricted within a single data/task domain. Considering that the brain is a complex connectome of interlinked neurons, the connectional properties in the brain have strong biological significance, which is shared across multiple domains and covers most pathological information. In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis. Specifically, it has a vision transformer (ViT) encoder and leverages mask reconstruction as the proxy task and Gram matrices to guide the representation of connectional information. It facilitates the capture of global context and the aggregation of features with biological plausibility. The results indicate that CS-CRL achieves superior accuracy in multiple brain disease diagnosis tasks across six datasets and three diseases and outperforms state-of-the-art models. Furthermore, we demonstrate that CS-CRL captures more brain-network-like properties, and better aggregates features, is easier to optimize, and is more robust to noise, which explains its superiority in theory.

Verbal Learning and Memory Deficits across Neurological and Neuropsychiatric Disorders: Insights from an ENIGMA Mega Analysis

Deficits in memory performance have been linked to a wide range of neurological and neuropsychiatric conditions. While many studies have assessed the memory impacts of individual conditions, this study considers a broader perspective by evaluating how memory recall is differentially associated with nine common neuropsychiatric conditions using data drawn from 55 international studies, aggregating 15,883 unique participants aged 15-90. The effects of dementia, mild cognitive impairment, Parkinson's disease, traumatic brain injury, stroke, depression, attention-deficit/hyperactivity disorder (ADHD), schizophrenia, and bipolar disorder on immediate, short-, and long-delay verbal learning and memory (VLM) scores were estimated relative to matched healthy individuals. Random forest models identified age, years of education, and site as important VLM covariates. A Bayesian harmonization approach was used to isolate and remove site effects. Regression estimated the adjusted association of each clinical group with VLM scores. Memory deficits were strongly associated with dementia and schizophrenia (p < 0.001), while neither depression nor ADHD showed consistent associations with VLM scores (p > 0.05). Differences associated with clinical conditions were larger for longer delayed recall duration items. By comparing VLM across clinical conditions, this study provides a foundation for enhanced diagnostic precision and offers new insights into disease management of comorbid disorders.

Diagnosing schizophrenia using deep learning: Novel interpretation approaches and multi-site validation

Schizophrenia is a profound and enduring mental disorder that imposes significant negative impacts on individuals, their families, and society at large. The development of more accurate and objective diagnostic tools for schizophrenia can be expedited through the employment of deep learning (DL), that excels at deciphering complex hierarchical non-linear patterns. However, the limited interpretability of deep learning has eroded confidence in the model and restricted its clinical utility. At the same time, if the data source is only derived from a single center, the model's generalizability is difficult to test. To enhance the model's reliability and applicability, leave-one-center-out validation with a large and diverse sample from multiple centers is crucial. In this study, we utilized Nine different global centers to train and test the 3D Resnet model's generalizability, resulting in an 82% classification performance (area under the curve) on all datasets sourced from different countries, employing a leave-one-center-out-validation approach. Per our approximation of the feature significance of each region on the atlas, we identified marked differences in the thalamus, pallidum, and inferior frontal gyrus between individuals with schizophrenia and healthy controls, lending credence to prior research findings. At the same time, in order to translate the model's output into clinically applicable insights, the SHapley Additive exPlanations (SHAP) permutation explainer method with an anatomical atlas have been refined, thereby offering precise neuroanatomical and functional interpretations of different brain regions.

Using a deep generation network reveals neuroanatomical specificity in hemispheres

Asymmetry is an important property of brain organization, but its nature is still poorly understood. Capturing the neuroanatomical components specific to each hemisphere facilitates the understanding of the establishment of brain asymmetry. Since deep generative networks (DGNs) have powerful inference and recovery capabilities, we use one hemisphere to predict the opposite hemisphere by training the DGNs, which automatically fit the built-in dependencies between the left and right hemispheres. After training, the reconstructed images approximate the homologous components in the hemisphere. We use the difference between the actual and reconstructed hemispheres to measure hemisphere-specific components due to asymmetric expression of environmental and genetic factors. The results show that our model is biologically plausible and that our proposed metric of hemispheric specialization is reliable, representing a wide range of individual variation. Together, this work provides promising tools for exploring brain asymmetry and new insights into self-supervised DGNs for representing the brain.

Decentralized Mixed Effects Modeling in COINSTAC

Performing group analysis on magnetic resonance imaging (MRI) data with linear mixed-effects (LME) models is challenging due to its large dimensionality and inherent multi-level covariance structure. In addition, as large-scale collaborative projects become commonplace in neuroimaging, data must increasingly be stored and analyzed from different locations. In such settings, substantial overhead can occur in terms of data transfer and coordination between participating research groups. In some cases, data cannot be pooled together due to privacy or regulatory concerns. In this work, we propose a decentralized LME model to perform a large-scale analysis of data from different collaborations without data pooling. This method is efficient as it overcomes the hurdles of data sharing and has lower bandwidth and memory requirements for analysis than the centralized modeling approach. We evaluate our model using features extracted from structural magnetic resonance imaging (sMRI) data. Results highlight gray matter reductions in the temporal lobe/insula and medial frontal regions in schizophrenia, consistent with prior studies. Our analysis also demonstrates that decentralized LME models achieve similar performance compared to the models trained with all the data in one location. We also implement the decentralized LME approach in COINSTAC, an open source, decentralized platform for federating neuroimaging analysis, providing an easy to use tool for dissemination to the neuroimaging community.

Thalamic nuclei volume differences in schizophrenia patients and healthy controls using probabilistic mapping: A comparative analysis

AIM

We aimed to investigate potential discrepancies in the volume of thalamic nuclei between individuals with schizophrenia and healthy controls.

METHODS

The imaging data for this study were obtained from the MCICShare data repository within SchizConnect. We employed probabilistic mapping technique developed by Iglesias et al. (2018). The analytical component entailed volumetric segmentation of the thalamus using the FreeSurfer image analysis suite. Our analysis focused on evaluating the differences in the volumes of various thalamic nuclei groups within the thalami, specifically the anterior, intralaminar, medial, posterior, lateral, and ventral groups in both the right and left thalami, between schizophrenia patients and healthy controls. We employed MANCOVA to analyse these dependent variables (volumes of 12 distinct thalamic nuclei groups), with diagnosis (SCZ vs. HCs) as the main explanatory variable, while controlling for covariates such as eTIV and age.

RESULTS

The assumptions of MANCOVA, including the homogeneity of covariance matrices, were met. Specific univariate tests for the right thalamus revealed significant differences in the medial (F[1, 200] = 26.360, p < 0.001), and the ventral groups (F[1, 200] = 4.793, p = 0.030). For the left thalamus, the medial (F[1, 200] = 22.527, p < 0.001); posterior (F[1, 200] = 8.227, p = 0.005), lateral (F[1, 200] = 7.004, p = 0.009), and ventral groups (F[1, 200] = 9.309, p = 0.003) showed significant differences.

CONCLUSION

These findings suggest that particular thalamic nuclei groups in both the right and left thalami may be most affected in schizophrenia, with more pronounced differences observed in the left thalamic nuclei.

FUNDINGS

The authors received no financial support for the research.

Structural variability of the cerebral cortex in schizophrenia and its association with clinical symptoms

BACKGROUND

Substantial evidence indicates structural abnormalities in the cerebral cortex of patients with schizophrenia (SCZ), although their clinical implications remain unclear. Previous case-control studies have investigated group-level differences in structural abnormalities, although the study design cannot account for interindividual differences. Recent research has focused on the association between the heterogeneity of the cerebral cortex morphometric features and clinical heterogeneity.

METHODS

We used neuroimaging data from 420 healthy controls and 695 patients with SCZ from seven studies. Four cerebral cortex measures were obtained: surface area, gray matter volume, thickness, and local gyrification index. We calculated the coefficient of variation (CV) and person-based similarity index (PBSI) scores and performed group comparisons. Associations between the PBSI scores and cognitive functions were evaluated using Spearman's rho test and normative modeling.

RESULTS

Patients with SCZ had a greater CV of surface area and cortical thickness than those of healthy controls. All PBSI scores across cortical measures were lower in patients with SCZ than in HCs. In the patient group, the PBSI scores for gray matter volume and all cortical measures taken together positively correlated with the full-scale IQ scores. Patients with deviant PBSI scores for gray matter volume and all cortical measures taken together had lower full-scale IQ scores than those of other patients.

CONCLUSIONS

The cerebral cortex in patients with SCZ showed greater regional and global structural variability than that in healthy controls. Patients with deviant similarity of cortical structural profiles exhibited a lower general intelligence than those exhibited by the other patients.

Two neurostructural subtypes: results of machine learning on brain images from 4,291 individuals with schizophrenia

Machine learning can be used to define subtypes of psychiatric conditions based on shared clinical and biological foundations, presenting a crucial step toward establishing biologically based subtypes of mental disorders. With the goal of identifying subtypes of disease progression in schizophrenia, here we analyzed cross-sectional brain structural magnetic resonance imaging (MRI) data from 4,291 individuals with schizophrenia (1,709 females, age=32.5 years±11.9) and 7,078 healthy controls (3,461 females, age=33.0 years±12.7) pooled across 41 international cohorts from the ENIGMA Schizophrenia Working Group, non-ENIGMA cohorts and public datasets. Using a machine learning approach known as Subtype and Stage Inference (SuStaIn), we implemented a brain imaging-driven classification that identifies two distinct neurostructural subgroups by mapping the spatial and temporal trajectory of gray matter (GM) loss in schizophrenia. Subgroup 1 (n=2,622) was characterized by an early cortical-predominant loss (ECL) with enlarged striatum, whereas subgroup 2 (n=1,600) displayed an early subcortical-predominant loss (ESL) in the hippocampus, amygdala, thalamus, brain stem and striatum. These reconstructed trajectories suggest that the GM volume reduction originates in the Broca's area/adjacent fronto-insular cortex for ECL and in the hippocampus/adjacent medial temporal structures for ESL. With longer disease duration, the ECL subtype exhibited a gradual worsening of negative symptoms and depression/anxiety, and less of a decline in positive symptoms. We confirmed the reproducibility of these imaging-based subtypes across various sample sites, independent of macroeconomic and ethnic factors that differed across these geographic locations, which include Europe, North America and East Asia. These findings underscore the presence of distinct pathobiological foundations underlying schizophrenia. This new imaging-based taxonomy holds the potential to identify a more homogeneous sub-population of individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.

CHIASM-Net: Artificial Intelligence-Based Direct Identification of Chiasmal Abnormalities in Albinism

Purpose

Albinism is a congenital disorder affecting pigmentation levels, structure, and function of the visual system. The identification of anatomical changes typical for people with albinism (PWA), such as optic chiasm malformations, could become an important component of diagnostics. Here, we tested an application of convolutional neural networks (CNNs) for this purpose.

Methods

We established and evaluated a CNN, referred to as CHIASM-Net, for the detection of chiasmal malformations from anatomic magnetic resonance (MR) images of the brain. CHIASM-Net, composed of encoding and classification modules, was developed using MR images of controls (n = 1708) and PWA (n = 32). Evaluation involved 8-fold cross validation involving accuracy, precision, recall, and F1-score metrics and was performed on a subset of controls and PWA samples excluded from the training. In addition to quantitative metrics, we used Explainable AI (XAI) methods that granted insights into factors driving the predictions of CHIASM-Net.

Results

The results for the scenario indicated an accuracy of 85 ± 14%, precision of 90 ± 14% and recall of 81 ± 18%. XAI methods revealed that the predictions of CHIASM-Net are driven by optic-chiasm white matter and by the optic tracts.

Conclusions

CHIASM-Net was demonstrated to use relevant regions of the optic chiasm for albinism detection from magnetic resonance imaging (MRI) brain anatomies. This indicates the strong potential of CNN-based approaches for visual pathway analysis and ultimately diagnostics.

Brain Growth Charts for Quantitative Analysis of Pediatric Clinical Brain MRI Scans with Limited Imaging Pathology

Background Clinically acquired brain MRI scans represent a valuable but underused resource for investigating neurodevelopment due to their technical heterogeneity and lack of appropriate controls. These barriers have curtailed retrospective studies of clinical brain MRI scans compared with more costly prospectively acquired research-quality brain MRI scans. Purpose To provide a benchmark for neuroanatomic variability in clinically acquired brain MRI scans with limited imaging pathology (SLIPs) and to evaluate if growth charts from curated clinical MRI scans differed from research-quality MRI scans or were influenced by clinical indication for the scan. Materials and Methods In this secondary analysis of preexisting data, clinical brain MRI SLIPs from an urban pediatric health care system (individuals aged ≤22 years) were scanned across nine 3.0-T MRI scanners. The curation process included manual review of signed radiology reports and automated and manual quality review of images without gross pathology. Global and regional volumetric imaging phenotypes were measured using two image segmentation pipelines, and clinical brain growth charts were quantitatively compared with charts derived from a large set of research controls in the same age range by means of Pearson correlation and age at peak volume. Results The curated clinical data set included 532 patients (277 male; median age, 10 years [IQR, 5-14 years]; age range, 28 days after birth to 22 years) scanned between 2005 and 2020. Clinical brain growth charts were highly correlated with growth charts derived from research data sets (22 studies, 8346 individuals [4947 male]; age range, 152 days after birth to 22 years) in terms of normative developmental trajectories predicted by the models (median r = 0.979). Conclusion The clinical indication of the scans did not significantly bias the output of clinical brain charts. Brain growth charts derived from clinical controls with limited imaging pathology were highly correlated with brain charts from research controls, suggesting the potential of curated clinical MRI scans to supplement research data sets. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Ertl-Wagner and Pai in this issue.

An overview of artificial intelligence in medical physics and radiation oncology

Artificial intelligence (AI) is developing rapidly and has found widespread applications in medicine, especially radiotherapy. This paper provides a brief overview of AI applications in radiotherapy, and highlights the research directions of AI that can potentially make significant impacts and relevant ongoing research works in these directions. Challenging issues related to the clinical applications of AI, such as robustness and interpretability of AI models, are also discussed. The future research directions of AI in the field of medical physics and radiotherapy are highlighted.

Enhancing collaborative neuroimaging research: introducing COINSTAC Vaults for federated analysis and reproducibility

Collaborative neuroimaging research is often hindered by technological, policy, administrative, and methodological barriers, despite the abundance of available data. COINSTAC (The Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation) is a platform that successfully tackles these challenges through federated analysis, allowing researchers to analyze datasets without publicly sharing their data. This paper presents a significant enhancement to the COINSTAC platform: COINSTAC Vaults (CVs). CVs are designed to further reduce barriers by hosting standardized, persistent, and highly-available datasets, while seamlessly integrating with COINSTAC's federated analysis capabilities. CVs offer a user-friendly interface for self-service analysis, streamlining collaboration, and eliminating the need for manual coordination with data owners. Importantly, CVs can also be used in conjunction with open data as well, by simply creating a CV hosting the open data one would like to include in the analysis, thus filling an important gap in the data sharing ecosystem. We demonstrate the impact of CVs through several functional and structural neuroimaging studies utilizing federated analysis showcasing their potential to improve the reproducibility of research and increase sample sizes in neuroimaging studies.

Enhancing Collaborative Neuroimaging Research: Introducing COINSTAC Vaults for Federated Analysis and Reproducibility

Collaborative neuroimaging research is often hindered by technological, policy, administrative, and methodological barriers, despite the abundance of available data. COINSTAC is a platform that successfully tackles these challenges through federated analysis, allowing researchers to analyze datasets without publicly sharing their data. This paper presents a significant enhancement to the COINSTAC platform: COINSTAC Vaults (CVs). CVs are designed to further reduce barriers by hosting standardized, persistent, and highly-available datasets, while seamlessly integrating with COINSTAC's federated analysis capabilities. CVs offer a user-friendly interface for self-service analysis, streamlining collaboration and eliminating the need for manual coordination with data owners. Importantly, CVs can also be used in conjunction with open data as well, by simply creating a CV hosting the open data one would like to include in the analysis, thus filling an important gap in the data sharing ecosystem. We demonstrate the impact of CVs through several functional and structural neuroimaging studies utilizing federated analysis showcasing their potential to improve the reproducibility of research and increase sample sizes in neuroimaging studies.

SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining

Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) difficultly generalise to unseen domains. When segmenting brain scans, CNNs are highly sensitive to changes in resolution and contrast: even within the same MRI modality, performance can decrease across datasets. Here we introduce SynthSeg, the first segmentation CNN robust against changes in contrast and resolution. SynthSeg is trained with synthetic data sampled from a generative model conditioned on segmentations. Crucially, we adopt a domain randomisation strategy where we fully randomise the contrast and resolution of the synthetic training data. Consequently, SynthSeg can segment real scans from a wide range of target domains without retraining or fine-tuning, which enables straightforward analysis of huge amounts of heterogeneous clinical data. Because SynthSeg only requires segmentations to be trained (no images), it can learn from labels obtained by automated methods on diverse populations (e.g., ageing and diseased), thus achieving robustness to a wide range of morphological variability. We demonstrate SynthSeg on 5,000 scans of six modalities (including CT) and ten resolutions, where it exhibits unparallelled generalisation compared with supervised CNNs, state-of-the-art domain adaptation, and Bayesian segmentation. Finally, we demonstrate the generalisability of SynthSeg by applying it to cardiac MRI and CT scans.

Joint Sparse Collaborative Regression on Imaging Genetics Study of Schizophrenia

The imaging genetics approach generates large amount of high dimensional and multi-modal data, providing complementary information for comprehensive study of Schizophrenia, a complex mental disease. However, at the same time, the variety of these data in structures, resolutions, and formats makes their integrative study a forbidding task. In this paper, we propose a novel model called Joint Sparse Collaborative Regression (JSCoReg), which can extract class-specific features from different health conditions/disease classes. We first evaluate the performance of feature selection in terms of Receiver operating characteristic curve and the area under the ROC curve in the simulation experiment. We demonstrate that the JSCoReg model can achieve higher accuracy compared with similar models including Joint Sparse Canonical Correlation Analysis and Sparse Collaborative Regression. We then applied the JSCoReg model to the analysis of schizophrenia dataset collected from the Mind Clinical Imaging Consortium. The JSCoReg enables us to better identify biomarkers associated with schizophrenia, which are verified to be both biologically and statistically significant.

Gray matter volume drives the brain age gap in schizophrenia: a SHAP study

Neuroimaging-based brain age is a biomarker that is generated by machine learning (ML) predictions. The brain age gap (BAG) is typically defined as the difference between the predicted brain age and chronological age. Studies have consistently reported a positive BAG in individuals with schizophrenia (SCZ). However, there is little understanding of which specific factors drive the ML-based brain age predictions, leading to limited biological interpretations of the BAG. We gathered data from three publicly available databases - COBRE, MCIC, and UCLA - and an additional dataset (TOPSY) of early-stage schizophrenia (82.5% untreated first-episode sample) and calculated brain age with pre-trained gradient-boosted trees. Then, we applied SHapley Additive Explanations (SHAP) to identify which brain features influence brain age predictions. We investigated the interaction between the SHAP score for each feature and group as a function of the BAG. These analyses identified total gray matter volume (group × SHAP interaction term β = 1.71 [0.53; 3.23]; p_corr < 0.03) as the feature that influences the BAG observed in SCZ among the brain features that are most predictive of brain age. Other brain features also presented differences in SHAP values between SCZ and HC, but they were not significantly associated with the BAG. We compared the findings with a non-psychotic depression dataset (CAN-BIND), where the interaction was not significant. This study has important implications for the understanding of brain age prediction models and the BAG in SCZ and, potentially, in other psychiatric disorders.

A review of deep learning-based deformable medical image registration

The alignment of images through deformable image registration is vital to clinical applications (e.g., atlas creation, image fusion, and tumor targeting in image-guided navigation systems) and is still a challenging problem. Recent progress in the field of deep learning has significantly advanced the performance of medical image registration. In this review, we present a comprehensive survey on deep learning-based deformable medical image registration methods. These methods are classified into five categories: Deep Iterative Methods, Supervised Methods, Unsupervised Methods, Weakly Supervised Methods, and Latest Methods. A detailed review of each category is provided with discussions about contributions, tasks, and inadequacies. We also provide statistical analysis for the selected papers from the point of view of image modality, the region of interest (ROI), evaluation metrics, and method categories. In addition, we summarize 33 publicly available datasets that are used for benchmarking the registration algorithms. Finally, the remaining challenges, future directions, and potential trends are discussed in our review.

The UT health Psychological Autopsy Interview Schedule (UTH- PAIS) - Description and reliability of diagnoses and transdiagnostic personality measures

Few studies have used psychological autopsies to evaluate large and diverse populations on transdiagnostically relevant variables such as personality, temperament, and trauma exposure; rather, they tend to focus on specific psychiatric disorders or manner of death. We therefore developed the UT Health Psychological Autopsy Interview Schedule (UTH-PAIS). The measure is described, and our results show that the PAIS diagnoses and dimensions can be reliably assessed. Furthermore, we were able to show that our sample of donated brains overall matches the demographic characteristics of a larger pool of individuals receiving a medical autopsy. In the Discussion we review the strengths and potential limitations of the study and outline in which context the PAIS will prove to be useful.

Clinical and cortical similarities identified between bipolar disorder I and schizophrenia: A multivariate approach

BACKGROUND

Structural neuroimaging studies have identified similarities in the brains of individuals diagnosed with schizophrenia (SZ) and bipolar I disorder (BP), with overlap in regions of gray matter (GM) deficits between the two disorders. Recent studies have also shown that the symptom phenotypes associated with SZ and BP may allow for a more precise categorization than the current diagnostic criteria. In this study, we sought to identify GM alterations that were unique to each disorder and whether those alterations were also related to unique symptom profiles.

MATERIALS AND METHODS

We analyzed the GM patterns and clinical symptom presentations using independent component analysis (ICA), hierarchical clustering, and n-way biclustering in a large (N ∼ 3,000), merged dataset of neuroimaging data from healthy volunteers (HV), and individuals with either SZ or BP.

RESULTS

Component A showed a SZ and BP < HV GM pattern in the bilateral insula and cingulate gyrus. Component B showed a SZ and BP < HV GM pattern in the cerebellum and vermis. There were no significant differences between diagnostic groups in these components. Component C showed a SZ < HV and BP GM pattern bilaterally in the temporal poles. Hierarchical clustering of the PANSS scores and the ICA components did not yield new subgroups. N-way biclustering identified three unique subgroups of individuals within the sample that mapped onto different combinations of ICA components and symptom profiles categorized by the PANSS but no distinct diagnostic group differences.

CONCLUSION

These multivariate results show that diagnostic boundaries are not clearly related to structural differences or distinct symptom profiles. Our findings add support that (1) BP tend to have less severe symptom profiles when compared to SZ on the PANSS without a clear distinction, and (2) all the gray matter alterations follow the pattern of SZ < BP < HV without a clear distinction between SZ and BP.

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.

A morphological study of schizophrenia with magnetic resonance imaging, advanced analytics, and machine learning

We have performed a morphological analysis of patients with schizophrenia and compared them with healthy controls. Our analysis includes the use of publicly available automated extraction tools to assess regional cortical thickness (inclusive of within region cortical thickness variability) from structural magnetic resonance imaging (MRI), to characterize group-wise abnormalities associated with schizophrenia based on a publicly available dataset. We have also performed a correlation analysis between the automatically extracted biomarkers and a variety of patient clinical variables available. Finally, we also present the results of a machine learning analysis. Results demonstrate regional cortical thickness abnormalities in schizophrenia. We observed a correlation (rho = 0.474) between patients’ depression and the average cortical thickness of the right medial orbitofrontal cortex. Our leading machine learning technology evaluated was the support vector machine with stepwise feature selection, yielding a sensitivity of 92% and a specificity of 74%, based on regional brain measurements, including from the insula, superior frontal, caudate, calcarine sulcus, gyrus rectus, and rostral middle frontal regions. These results imply that advanced analytic techniques combining MRI with automated biomarker extraction can be helpful in characterizing patients with schizophrenia.

Morphometric Integrated Classification Index: A Multisite Model-Based, Interpretable, Shareable and Evolvable Biomarker for Schizophrenia

BACKGROUND AND HYPOTHESIS

Multisite massive schizophrenia neuroimaging data sharing is becoming critical in understanding the pathophysiological mechanism and making an objective diagnosis of schizophrenia; it remains challenging to obtain a generalizable and interpretable, shareable, and evolvable neuroimaging biomarker for schizophrenia diagnosis.

STUDY DESIGN

A Morphometric Integrated Classification Index (MICI) was proposed as a potential biomarker for schizophrenia diagnosis based on structural magnetic resonance imaging data of 1270 subjects from 10 sites (588 schizophrenia patients and 682 normal controls). An optimal XGBoost classifier plus sample-weighted SHapley Additive explanation algorithms were used to construct the MICI measure.

STUDY RESULTS

The MICI measure achieved comparable performance with the sample-weighted ensembling model and merged model based on raw data (Delong test, P > 0.82) while outperformed the single-site models (Delong test, P < 0.05) in either the independent-sample testing datasets from the 9 sites or the independent-site dataset (generalizable). Besides, when new sites were embedded in, the performance of this measure was gradually increasing (evolvable). Finally, MICI was strongly associated with the severity of schizophrenia brain structural abnormality, with the patients' positive and negative symptoms, and with the brain expression profiles of schizophrenia risk genes (interpretable).

CONCLUSIONS

In summary, the proposed MICI biomarker may provide a simple and explainable way to support clinicians for objectively diagnosing schizophrenia. Finally, we developed an online model share platform to promote biomarker generalization and provide free individual prediction services (http://micc.tmu.edu.cn/mici/index.html).

Detecting abnormal connectivity in schizophrenia via a joint directed acyclic graph estimation model

Functional connectivity (FC) between brain region has been widely studied and linked with cognition and behavior of an individual. FC is usually defined as the correlation or partial correlation of fMRI blood oxygen level-dependent (BOLD) signals between two brain regions. Although FC has been effective to understand brain organization, it cannot reveal the direction of interactions. Many directed acyclic graph (DAG) based methods have been applied to study the directed interactions but their performance was limited by the small sample size while high dimensionality of the available data. By enforcing group regularization and utilizing samples from both case and control groups, we propose a joint DAG model to estimate the directed FC. We first demonstrate that the proposed model is efficient and accurate through a series of simulation studies. We then apply it to the case-control study of schizophrenia (SZ) with data collected from the MIND Clinical Imaging Consortium (MCIC). We have successfully identified decreased functional integration, disrupted hub structures and characteristic edges (CtEs) in SZ patients. Those findings have been confirmed by previous studies with some identified to be potential markers for SZ patients. A comparison of the results between the directed FC and undirected FC showed substantial differences in the selected features. In addition, we used the identified features based on directed FC for the classification of SZ patients and achieved better accuracy than using undirected FC or raw features, demonstrating the advantage of using directed FC for brain network analysis.

TopoFit: Rapid Reconstruction of Topologically-Correct Cortical Surfaces

Mesh-based reconstruction of the cerebral cortex is a fundamental component in brain image analysis. Classical, iterative pipelines for cortical modeling are robust but often time-consuming, mostly due to expensive procedures that involve topology correction and spherical mapping. Recent attempts to address reconstruction with machine learning methods have accelerated some components in these pipelines, but these methods still require slow processing steps to enforce topological constraints that comply with known anatomical structure. In this work, we introduce a novel learning-based strategy, TopoFit, which rapidly fits a topologically-correct surface to the white-matter tissue boundary. We design a joint network, employing image and graph convolutions and an efficient symmetric distance loss, to learn to predict accurate deformations that map a template mesh to subject-specific anatomy. This technique encompasses the work of current mesh correction, fine-tuning, and inflation processes and, as a result, offers a 150× faster solution to cortical surface reconstruction compared to traditional approaches. We demonstrate that TopoFit is 1.8× more accurate than the current state-of-the-art deep-learning strategy, and it is robust to common failure modes, such as white-matter tissue hypointensities.

Tracing Evolving Networks Using Tensor Factorizations vs. ICA-Based Approaches

Analysis of time-evolving data is crucial to understand the functioning of dynamic systems such as the brain. For instance, analysis of functional magnetic resonance imaging (fMRI) data collected during a task may reveal spatial regions of interest, and how they evolve during the task. However, capturing underlying spatial patterns as well as their change in time is challenging. The traditional approach in fMRI data analysis is to assume that underlying spatial regions of interest are static. In this article, using fractional amplitude of low-frequency fluctuations (fALFF) as an effective way to summarize the variability in fMRI data collected during a task, we arrange time-evolving fMRI data as a subjects by voxels by time windows tensor, and analyze the tensor using a tensor factorization-based approach called a PARAFAC2 model to reveal spatial dynamics. The PARAFAC2 model jointly analyzes data from multiple time windows revealing subject-mode patterns, evolving spatial regions (also referred to as networks) and temporal patterns. We compare the PARAFAC2 model with matrix factorization-based approaches relying on independent components, namely, joint independent component analysis (ICA) and independent vector analysis (IVA), commonly used in neuroimaging data analysis. We assess the performance of the methods in terms of capturing evolving networks through extensive numerical experiments demonstrating their modeling assumptions. In particular, we show that (i) PARAFAC2 provides a compact representation in all modes, i.e., subjects, time, and voxels, revealing temporal patterns as well as evolving spatial networks, (ii) joint ICA is as effective as PARAFAC2 in terms of revealing evolving networks but does not reveal temporal patterns, (iii) IVA's performance depends on sample size, data distribution and covariance structure of underlying networks. When these assumptions are satisfied, IVA is as accurate as the other methods, (iv) when subject-mode patterns differ from one time window to another, IVA is the most accurate. Furthermore, we analyze real fMRI data collected during a sensory motor task, and demonstrate that a component indicating statistically significant group difference between patients with schizophrenia and healthy controls is captured, which includes primary and secondary motor regions, cerebellum, and temporal lobe, revealing a meaningful spatial map and its temporal change.

Learning the Effect of Registration Hyperparameters with HyperMorph

We introduce HyperMorph, a framework that facilitates efficient hyperparameter tuning in learning-based deformable image registration. Classical registration algorithms perform an iterative pair-wise optimization to compute a deformation field that aligns two images. Recent learning-based approaches leverage large image datasets to learn a function that rapidly estimates a deformation for a given image pair. In both strategies, the accuracy of the resulting spatial correspondences is strongly influenced by the choice of certain hyperparameter values. However, an effective hyperparameter search consumes substantial time and human effort as it often involves training multiple models for different fixed hyperparameter values and may lead to suboptimal registration. We propose an amortized hyperparameter learning strategy to alleviate this burden by learning the impact of hyperparameters on deformation fields. We design a meta network, or hypernetwork, that predicts the parameters of a registration network for input hyperparameters, thereby comprising a single model that generates the optimal deformation field corresponding to given hyperparameter values. This strategy enables fast, high-resolution hyperparameter search at test-time, reducing the inefficiency of traditional approaches while increasing flexibility. We also demonstrate additional benefits of HyperMorph, including enhanced robustness to model initialization and the ability to rapidly identify optimal hyperparameter values specific to a dataset, image contrast, task, or even anatomical region, all without the need to retrain models. We make our code publicly available at http://hypermorph.voxelmorph.net.

Scan Once, Analyse Many: Using Large Open-Access Neuroimaging Datasets to Understand the Brain

We are now in a time of readily available brain imaging data. Not only are researchers now sharing data more than ever before, but additionally large-scale data collecting initiatives are underway with the vision that many future researchers will use the data for secondary analyses. Here I provide an overview of available datasets and some example use cases. Example use cases include examining individual differences, more robust findings, reproducibility-both in public input data and availability as a replication sample, and methods development. I further discuss a variety of considerations associated with using existing data and the opportunities associated with large datasets. Suggestions for further readings on general neuroimaging and topic-specific discussions are also provided.

Data sharing and privacy issues in neuroimaging research: Opportunities, obstacles, challenges, and monsters under the bed

Collaborative networks and data sharing initiatives are broadening the opportunities for the advancement of science. These initiatives offer greater transparency in science, with the opportunity for external research groups to reproduce, replicate, and extend research findings. Further, larger datasets offer the opportunity to identify homogeneous patterns within subgroups of individuals, where these patterns may be obscured by the heterogeneity of the neurobiological measure in smaller samples. However, data sharing and data pooling initiatives are not without their challenges, especially with new laws that may at first glance appear quite restrictive for open science initiatives. Interestingly, what is key to some of these new laws (i.e, the European Union's general data protection regulation) is that they provide greater control of data to those who "give" their data for research purposes. Thus, the most important element in data sharing is allowing the participants to make informed decisions about how they want their data to be used, and, within the law of the specific country, to follow the participants' wishes. This framework encompasses obtaining thorough informed consent and allowing the participant to determine the extent that they want their data shared, many of the ethical and legal obstacles are reduced to just monsters under the bed. In this manuscript we discuss the many options and obstacles for data sharing, from fully open, to federated learning, to fully closed. Importantly, we highlight the intersection of data sharing, privacy, and data ownership and highlight specific examples that we believe are informative to the neuroimaging community.

White matter impairments in patients with schizophrenia: A multisite diffusion MRI study

There is a lack of convincing and replicative findings regarding white matter abnormalities in schizophrenia. Several multisite diffusion magnetic resonance imaging (dMRI) studies have been conducted to increase statistical power and reveal subtle white matter changes. Data pooling methods are crucial in joint analysis to compensate for the use of different scanners and image acquisition parameters. A harmonization method using raw dMRI data was developed to overcome the limited generalizability of previous data pooling methods. We obtained dMRI data of 242 healthy controls and 190 patients with schizophrenia from four different study sites. After applying the harmonization method to the raw dMRI data, a two-tensor whole-brain tractography was performed, and diffusion measures were compared between the two groups. The correlation of fractional anisotropy (FA) with the positive and negative symptoms was evaluated, and the interaction effect of diagnosis-by-age, age-squared, and sex was examined. The following white matter tracts showed significant group differences in the FA: the right superior longitudinal fascicle (SLF), the left-to-right lateral orbitofrontal commissural tract, pars orbitalis (pOr-pOr) commissural tract, and pars triangularis (pTr-pTr) commissural tract. The FA of the right SLF and pTr-pTr commissural tract were significantly associated with the Positive and Negative Syndrome Scale (PANSS) positive and negative scores. No significant interaction effect was observed. These findings add to the evidence on structural brain abnormalities in schizophrenia and can aid in obtaining a better understanding of the biological foundations of schizophrenia.

Resolving heterogeneity in schizophrenia through a novel systems approach to brain structure: individualized structural covariance network analysis

Reliable mapping of system-level individual differences is a critical first step toward precision medicine for complex disorders such as schizophrenia. Disrupted structural covariance indicates a system-level brain maturational disruption in schizophrenia. However, most studies examine structural covariance at the group level. This prevents subject-level inferences. Here, we introduce a Network Template Perturbation approach to construct individual differential structural covariance network (IDSCN) using regional gray-matter volume. IDSCN quantifies how structural covariance between two nodes in a patient deviates from the normative covariance in healthy subjects. We analyzed T1 images from 1287 subjects, including 107 first-episode (drug-naive) patients and 71 controls in the discovery datasets and established robustness in 213 first-episode (drug-naive), 294 chronic, 99 clinical high-risk patients, and 494 controls from the replication datasets. Patients with schizophrenia were highly variable in their altered structural covariance edges; the number of altered edges was related to severity of hallucinations. Despite this variability, a subset of covariance edges, including the left hippocampus-bilateral putamen/globus pallidus edges, clustered patients into two distinct subgroups with opposing changes in covariance compared to controls, and significant differences in their anxiety and depression scores. These subgroup differences were stable across all seven datasets with meaningful genetic associations and functional annotation for the affected edges. We conclude that the underlying physiology of affective symptoms in schizophrenia involves the hippocampus and putamen/pallidum, predates disease onset, and is sufficiently consistent to resolve morphological heterogeneity throughout the illness course. The two schizophrenia subgroups identified thus have implications for the nosology and clinical treatment.

Multivariate alterations in insula - Medial prefrontal cortex linked to genetics in 12q24 in schizophrenia

The direct effect of genetic variations on clinical phenotypes within schizophrenia (SZ) remains elusive. We examined the previously identified association of reduced gray matter concentration in the insula - medial prefrontal cortex and a quantitative trait locus located in 12q24 in a SZ dataset. The main analysis was performed on 1461 SNPs and 830 participants. The highest contributing SNPs were localized in five genes including TMEM119, which encodes a microglial marker, that is associated with neuroinflammation and Alzheimer's disease. The gene set in 12q4 may partially explain brain alterations in SZ, but they may also relate to other psychiatric and developmental disorders.

A review of deep learning-based three-dimensional medical image registration methods

Medical image registration is a vital component of many medical procedures, such as image-guided radiotherapy (IGRT), as it allows for more accurate dose-delivery and better management of side effects. Recently, the successful implementation of deep learning (DL) in various fields has prompted many research groups to apply DL to three-dimensional (3D) medical image registration. Several of these efforts have led to promising results. This review summarized the progress made in DL-based 3D image registration over the past 5 years and identify existing challenges and potential avenues for further research. The collected studies were statistically analyzed based on the region of interest (ROI), image modality, supervision method, and registration evaluation metrics. The studies were classified into three categories: deep iterative registration, supervised registration, and unsupervised registration. The studies are thoroughly reviewed and their unique contributions are highlighted. A summary is presented following a review of each category of study, discussing its advantages, challenges, and trends. Finally, the common challenges for all categories are discussed, and potential future research topics are identified.

The psychosis human connectome project: An overview

Investigations within the Human Connectome Project have expanded to include studies focusing on brain disorders. This paper describes one of the investigations focused on psychotic psychopathology: The psychosis Human Connectome Project (P-HCP). The data collected as part of this project were multimodal and derived from clinical assessments of psychopathology, cognitive assessments, instrument-based motor assessments, blood specimens, and magnetic resonance imaging (MRI) data. The dataset will be made publicly available through the NIMH Data Archive. In this report we provide specific information on how the sample of participants was obtained and characterized and describe the experimental tasks and procedures used to probe neural functions involved in psychotic disorders that may also mark genetic liability for psychotic psychopathology. Our goal in this paper is to outline the data acquisition process so that researchers intending to use these publicly available data can plan their analyses. MRI data described in this paper are limited to data acquired at 3 Tesla. A companion paper describes the study's 7 Tesla image acquisition protocol in detail, which is focused on visual perceptual functions in psychotic psychopathology.

White matter microstructural associates of apathy-avolition in schizophrenia

Apathy is present at the onset in nearly half the patients with schizophrenia. Current therapies lack the efficiency to improve apathy in patients. The presence of apathy is also associated with poorer outcomes. Despite its clinical importance, the underlying mechanism of apathy in schizophrenia is unclear, but it seems frontostriatal connections play a role. In this study, we investigated whole-brain white matter microstructural properties associated with the severity of apathy-avolition in schizophrenia. We included 80 schizophrenia patients (60 Male, 20 Female) from the Mind Clinical Imaging Consortium database and associated Apathy-Avolition score of "Scale for Assessment of Negative Symptoms" with fiber integrity measures derived from diffusion-weighted imaging using Tract-Based Spatial Statistics (TBSS). We also did tractography on eight tracts, including bilateral superior longitudinal fasciculus, uncinate fasciculus, cingulum, genu and splenium of the corpus callosum. Age, gender, years of education, chlorpromazine equivalent cumulative dose, and acquisition site were inserted as covariates. We showed a widespread association between lower fiber integrity (by measures of increased mean diffusivity and decreased fractional anisotropy) and increased apathy-avolition in TBSS, which we also validated in tractography. Moreover, mean diffusivity, and not fractional anisotropy, was associated with apathy independent of disease severity. In conclusion, we propose diffuse white-matter pathology, within the corpus callosum, limbic system, and the frontostriatal circuit is involved in apathy-avolition in schizophrenia. Also, we suggest that diffuse neuroinflammatory processes may play a part in apathy-avolition, independent of disease severity.

Hold-out validation for the assessment of stability and reliability of multivariable regression demonstrated with magnetic resonance imaging of patients with schizophrenia

Neuroscience studies are very often tasked with identifying measurable differences between two groups of subjects, typically one group with a pathological condition and one group representing control subjects. It is often expected that the measurements acquired for comparing groups are also affected by a variety of additional patient characteristics such as sex, age, and comorbidities. Multivariable regression (MVR) is a statistical analysis technique commonly employed in neuroscience studies to "control for" or "adjust for" secondary effects (such as sex, age, and comorbidities) in order to ensure that the main study findings are focused on actual differences between the groups of interest associated with the condition under investigation. It is common practice in the neuroscience literature to utilize MVR to control for secondary effects; however, at present, it is not typically possible to assess whether the MVR adjustments correct for more error than they introduce. In common neuroscience practice, MVR models are not validated and no attempt to characterize deficiencies in the MVR model is made. In this article, we demonstrate how standard hold-out validation techniques (commonly used in machine learning analyses) that involve repeatedly randomly dividing datasets into training and testing samples can be adapted to the assessment of stability and reliability of MVR models with a publicly available neurological magnetic resonance imaging (MRI) dataset of patients with schizophrenia. Results demonstrate that MVR can introduce measurement error up to 30.06% and, on average across all considered measurements, introduce 9.84% error on this dataset. When hold-out validated MVR does not agree with the results of the standard use of MVR, the use of MVR in the given application is unstable. Thus, this paper helps evaluate the extent to which the simplistic use of MVR introduces study error in neuroscientific analyses with an analysis of patients with schizophrenia.

A Latent Gaussian Copula Model for Mixed Data Analysis in Brain Imaging Genetics

Recent advances in imaging genetics make it possible to combine different types of data including medical images like functional magnetic resonance imaging (fMRI) and genetic data like single nucleotide polymorphisms (SNPs) for comprehensive diagnosis of mental disorders. Understanding complex interactions among these heterogeneous data may give rise to a new perspective, while at the same time demand statistical models for their integration. Various graphical models have been proposed for the study of interaction or association networks with continuous, binary, and count data as well as the mixture of them. However, limited efforts have been made for the multinomial case, for instance, SNP data. Our goal is therefore to fill the void by developing a graphical model for the integration of fMRI image and SNP data, which can provide deeper understanding of the unknown neurogenetic mechanism. In this article, we propose a latent Gaussian copula model for mixed data containing multinomial components. We assume that the discrete variable is obtained by discretizing a latent (unobserved) continuous variable and then create a semi-rank based estimator of the graph structure. The simulation results demonstrate that the proposed latent correlation has more steady and accurate performance than several existing methods in detecting graph structure. When applying to a real schizophrenia data consisting of SNP array and fMRI image collected by the Mind Clinical Imaging Consortium (MCIC), the proposed method reveals a set of distinct SNP-brain associations, which are verified to be biologically significant. The proposed model is statistically promising in handling mixed types of data including multinomial components, which can find widespread applications. To promote reproducible research, the R code is available at https://github.com/Aiying0512/LGCM.

Disjoint subspaces for common and distinct component analysis: Application to the fusion of multi-task FMRI data

BACKGROUND

Data-driven methods such as independent component analysis (ICA) makes very few assumptions on the data and the relationships of multiple datasets, and hence, are attractive for the fusion of medical imaging data. Two important extensions of ICA for multiset fusion are the joint ICA (jICA) and the multiset canonical correlation analysis and joint ICA (MCCA-jICA) techniques. Both approaches assume identical mixing matrices, emphasizing components that are common across the multiple datasets. However, in general, one would expect to have components that are both common across the datasets and distinct to each dataset.

NEW METHOD

We propose a general framework, disjoint subspace analysis using ICA (DS-ICA), which identifies and extracts not only the common but also the distinct components across multiple datasets. A key component of the method is the identification of these subspaces and their separation before subsequent analyses, which helps establish better model match and provides flexibility in algorithm and order choice.

COMPARISON

We compare DS-ICA with jICA and MCCA-jICA through both simulations and application to multiset functional magnetic resonance imaging (fMRI) task data collected from healthy controls as well as patients with schizophrenia.

RESULTS

The results show DS-ICA estimates more components discriminative between healthy controls and patients than jICA and MCCA-jICA, and with higher discriminatory power showing activation differences in meaningful regions. When applied to a classification framework, components estimated by DS-ICA results in higher classification performance for different dataset combinations than the other two methods.

CONCLUSION

These results demonstrate that DS-ICA is an effective method for fusion of multiple datasets.

Structural Connectivity-Based Parcellation of the Dopaminergic Midbrain in Healthy Subjects and Schizophrenic Patients

Background and objectives: Functional deregulation of dopaminergic midbrain regions is a core feature of schizophrenia pathophysiology. Anatomical research on primates suggests that these regions may be subdivided into distinct, topographically organized functional territories according to their connectivity to the striatum. The aim of the present work was the reconstruction of dopaminergic midbrain subregions in healthy subjects and schizophrenic patients and the evaluation of their structural connectivity profiles. Materials and Methods: A hypothesis-driven connectivity-based parcellation derived from diffusion tractography was applied on 24 healthy subjects and 30 schizophrenic patients to identify distinct territories within the human dopaminergic midbrain in vivo and non-invasively. Results: We identified a tripartite subdivision of dopaminergic midbrain, including limbic, prefrontal and sensorimotor territories. No significant differences in structural features or connectivity were found between subjects and patients. Conclusions: The parcellation scheme proposed herein may help to achieve detailed characterization of structural and functional anomalies of the dopaminergic midbrain in schizophrenic patients.

Genes associated with gray matter volume alterations in schizophrenia

Although both schizophrenia and gray matter volume (GMV) show high heritability, however, genes accounting for GMV alterations in schizophrenia remain largely unknown. Based on risk genes identified in schizophrenia by the genome-wide association study of the Schizophrenia Working Group of the Psychiatric Genomics Consortium, we used transcription-neuroimaging association analysis to test that which of these genes are associated with GMV changes in schizophrenia. For each brain tissue sample, the expression profiles of 196 schizophrenia risk genes were extracted from six donated normal brains of the Allen Human Brain Atlas, and GMV differences between patients with schizophrenia and healthy controls were calculated based on five independent case-control structural MRI datasets (276 patients and 284 controls). Genes associated with GMV changes in schizophrenia were identified by performing cross-sample spatial correlations between expression levels of each gene and case-control GMV difference derived from the five MRI datasets integrated by harmonization and meta-analysis. We found that expression levels of 98 genes consistently showed significant cross-sample spatial correlations with GMV changes in schizophrenia. These genes were functionally enriched for chemical synaptic transmission, central nervous system development, and cell projection. Overall, this study provides a set of genes possibly associated with GMV changes in schizophrenia, which could be used as candidate genes to explore biological mechanisms underlying the structural impairments in schizophrenia.

Detect and correct bias in multi-site neuroimaging datasets

The desire to train complex machine learning algorithms and to increase the statistical power in association studies drives neuroimaging research to use ever-larger datasets. The most obvious way to increase sample size is by pooling scans from independent studies. However, simple pooling is often ill-advised as selection, measurement, and confounding biases may creep in and yield spurious correlations. In this work, we combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging. In the first experiment, Name That Dataset, we provide empirical evidence for the presence of bias by showing that scans can be correctly assigned to their respective dataset with 71.5% accuracy. Given such evidence, we take a closer look at confounding bias, which is often viewed as the main shortcoming in observational studies. In practice, we neither know all potential confounders nor do we have data on them. Hence, we model confounders as unknown, latent variables. Kolmogorov complexity is then used to decide whether the confounded or the causal model provides the simplest factorization of the graphical model. Finally, we present methods for dataset harmonization and study their ability to remove bias in imaging features. In particular, we propose an extension of the recently introduced ComBat algorithm to control for global variation across image features, inspired by adjusting for unknown population stratification in genetics. Our results demonstrate that harmonization can reduce dataset-specific information in image features. Further, confounding bias can be reduced and even turned into a causal relationship. However, harmonization also requires caution as it can easily remove relevant subject-specific information. Code is available at https://github.com/ai-med/Dataset-Bias.

Neuroharmony: A new tool for harmonizing volumetric MRI data from unseen scanners

•We present Neuroharmony, a harmonization tool for images from unseen scanners. •We developed Neuroharmony using a total of 15,026 sMRI images. •The tool was able to reduce scanner-related bias from unseen scans. •Neuroharmony represents a significant step towards imaging-based clinical tools. •Neuroharmony is available at https://github.com/garciadias/Neuroharmony .

Multi-dimensional predictions of psychotic symptoms via machine learning

The diagnostic criteria for schizophrenia comprise a diverse range of heterogeneous symptoms. As a result, individuals each present a distinct set of symptoms despite having the same overall diagnosis. Whilst previous machine learning studies have primarily focused on dichotomous patient-control classification, we predict the severity of each individual symptom on a continuum. We applied machine learning regression within a multi-modal fusion framework to fMRI and behavioural data acquired during an auditory oddball task in 80 schizophrenia patients. Brain activity was highly predictive of some, but not all symptoms, namely hallucinations, avolition, anhedonia and attention. Critically, each of these symptoms was associated with specific functional alterations across different brain regions. We also found that modelling symptoms as an ensemble of subscales was more accurate, specific and informative than models which predict compound scores directly. In principle, this approach is transferrable to any psychiatric condition or multi-dimensional diagnosis.

White Matter Microstructural Properties Associated with Impaired Attention in Chronic Schizophrenia: A Multi-Center Study

Attention as a key cognitive function is impaired in schizophrenia, interfering with the normal daily life of the patients. Previous studies on the microstructural correlates of attention in schizophrenia were limited to single fibers, did not include a control group, or did not adjust for drug dosage. In the current study, we investigated the association between microstructural properties of the white matter fibers and attention tests in 81 patients and 79 healthy controls from the Mind Clinical Imaging Consortium database. Integrity measures of superior longitudinal fasciculus, cingulum, genu, and splenium were extracted after tractography. Using an interaction model between diagnosis and microstructural properties, and adjusting for age, gender, acquisition site, education, and cumulative drug usage dose, and after correcting for family-wise error, we showed decreased integrity in the patients and a significant negative association between fractional anisotropy of the tracts and trail making test part A with a greater expected decrease in the attention per unit of decrease of integrity in the patients compared to the healthy controls. Our findings suggest that decreased integrity of the bilateral cingulum, and splenium, are independent of the cumulative drug dosage, age, gender, and site, and may underlie the impaired attention in the schizophrenia.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

Sparse representation and dictionary learning model incorporating group sparsity and incoherence to extract abnormal brain regions associated with schizophrenia

Schizophrenia is a complex mental illness, the mechanism of which is currently unclear. Using sparse representation and dictionary learning (SDL) model to analyze functional magnetic resonance imaging (fMRI) dataset of schizophrenia is currently a popular method for exploring the mechanism of the disease. The SDL method decomposed the fMRI data into a sparse coding matrix X and a dictionary matrix D. However, these traditional methods overlooked group structure information in X and the coherence between the atoms in D. To address this problem, we propose a new SDL model incorporating group sparsity and incoherence, namely GS2ISDL to detect abnormal brain regions. Specifically, GS2ISDL uses the group structure information that defined by AAL anatomical template from fMRI dataset as priori to achieve inter-group sparsity in X. At the same time, L ₁ - norm is enforced on X to achieve intra-group sparsity. In addition, our algorithm also imposes incoherent constraint on the dictionary matrix D to reduce the coherence between the atoms in D, which can ensure the uniqueness of X and the discriminability of the atoms. To validate our proposed model GS2ISDL, we compared it with both IK-SVD and SDL algorithm for analyzing fMRI dataset collected by Mind Clinical Imaging Consortium (MCIC). The results show that the accuracy, sensitivity, recall and MCC values of GS2ISDL are 93.75%, 95.23%, 80.50% and 88.19%, respectively, which outperforms both IK-SVD and SDL. The ROIs extracted by GS2ISDL model (such as Precentral gyrus, Hippocampus and Caudate nucleus, etc.) are further verified by the literature review on schizophrenia studies, which have significant biological significance.

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

With the rapid development of high-throughput technologies, a growing amount of multi-omics data are collected, giving rise to a great demand for combining such data for biomedical discovery. Due to the cost and time to label the data manually, the number of labelled samples is limited. This motivated the need for semi-supervised learning algorithms. In this work, we applied a graph-based semi-supervised learning (GSSL) to classify a severe chronic mental disorder, schizophrenia (SZ). An advantage of GSSL is that it can simultaneously analyse more than two types of data, while many existing models focus on pairwise data analysis. In particular, we applied GSSL to the analysis of single nucleotide polymorphism (SNP), functional magnetic resonance imaging (fMRI) and DNA methylation data, which accounts for genetics, brain imaging (endophenotypes), and environmental factors (epigenomics) respectively. While parameter selection has been an open challenge for most models, another key contribution of this work is that we explored the parameter space to interpret their meaning and established practical guidelines. Based on the practical significance of each hyper-parameter, a relatively small range of candidate values can be determined in a data-driven way to both optimize and speed up the parameter tuning process. We validated the model through both synthetic data and a real SZ dataset of 184 subjects from the Mental Illness and Neuroscience Discovery (MIND) Clinical Imaging Consortium. In comparison to several existing approaches, our algorithm achieved better performance in terms of classification accuracy. We also confirmed the significance of several brain regions associated with SZ.

Brain Imaging Genomics: Integrated Analysis and Machine Learning

Brain imaging genomics is an emerging data science field, where integrated analysis of brain imaging and genomics data, often combined with other biomarker, clinical and environmental data, is performed to gain new insights into the phenotypic, genetic and molecular characteristics of the brain as well as their impact on normal and disordered brain function and behavior. It has enormous potential to contribute significantly to biomedical discoveries in brain science. Given the increasingly important role of statistical and machine learning in biomedicine and rapidly growing literature in brain imaging genomics, we provide an up-to-date and comprehensive review of statistical and machine learning methods for brain imaging genomics, as well as a practical discussion on method selection for various biomedical applications.