Detecting schizophrenia at the level of the individual: relative diagnostic value of whole-brain images, connectome-wide functional connectivity and graph-based metrics

Schizophrenia and Neurodevelopment: Insights From Connectome Perspective

BACKGROUND

Schizophrenia is conceptualized as a brain connectome disorder that can emerge as early as late childhood and adolescence. However, the underlying neurodevelopmental basis remains unclear. Recent interest has grown in children and adolescent patients who experience symptom onset during critical brain development periods. Inspired by advanced methodological theories and large patient cohorts, Chinese researchers have made significant original contributions to understanding altered brain connectome development in early-onset schizophrenia (EOS).

STUDY DESIGN

We conducted a search of PubMed and Web of Science for studies on brain connectomes in schizophrenia and neurodevelopment. In this selective review, we first address the latest theories of brain structural and functional development. Subsequently, we synthesize Chinese findings regarding mechanisms of brain structural and functional abnormalities in EOS. Finally, we highlight several pivotal challenges and issues in this field.

STUDY RESULTS

Typical neurodevelopment follows a trajectory characterized by gray matter volume pruning, enhanced structural and functional connectivity, improved structural connectome efficiency, and differentiated modules in the functional connectome during late childhood and adolescence. Conversely, EOS deviates with excessive gray matter volume decline, cortical thinning, reduced information processing efficiency in the structural brain network, and dysregulated maturation of the functional brain network. Additionally, common functional connectome disruptions of default mode regions were found in early- and adult-onset patients.

CONCLUSIONS

Chinese research on brain connectomes of EOS provides crucial evidence for understanding pathological mechanisms. Further studies, utilizing standardized analyses based on large-sample multicenter datasets, have the potential to offer objective markers for early intervention and disease treatment.

Neuroimage Analysis Methods and Artificial Intelligence Techniques for Reliable Biomarkers and Accurate Diagnosis of Schizophrenia: Achievements Made by Chinese Scholars Around the Past Decade

BACKGROUND AND HYPOTHESIS

Schizophrenia (SZ) is characterized by significant cognitive and behavioral disruptions. Neuroimaging techniques, particularly magnetic resonance imaging (MRI), have been widely utilized to investigate biomarkers of SZ, distinguish SZ from healthy conditions or other mental disorders, and explore biotypes within SZ or across SZ and other mental disorders, which aim to promote the accurate diagnosis of SZ. In China, research on SZ using MRI has grown considerably in recent years.

STUDY DESIGN

The article reviews advanced neuroimaging and artificial intelligence (AI) methods using single-modal or multimodal MRI to reveal the mechanism of SZ and promote accurate diagnosis of SZ, with a particular emphasis on the achievements made by Chinese scholars around the past decade.

STUDY RESULTS

Our article focuses on the methods for capturing subtle brain functional and structural properties from the high-dimensional MRI data, the multimodal fusion and feature selection methods for obtaining important and sparse neuroimaging features, the supervised statistical analysis and classification for distinguishing disorders, and the unsupervised clustering and semi-supervised learning methods for identifying neuroimage-based biotypes. Crucially, our article highlights the characteristics of each method and underscores the interconnections among various approaches regarding biomarker extraction and neuroimage-based diagnosis, which is beneficial not only for comprehending SZ but also for exploring other mental disorders.

CONCLUSIONS

We offer a valuable review of advanced neuroimage analysis and AI methods primarily focused on SZ research by Chinese scholars, aiming to promote the diagnosis, treatment, and prevention of SZ, as well as other mental disorders, both within China and internationally.

Causal relationship between schizophrenia and sex hormone binding globulin: A Mendelian randomization study

OBJECTIVE

The underlying etiology of schizophrenia is still not fully understood, and recent studies have pointed to a potential link between hormonal factors and the risk of developing this condition. Sex Hormone-Binding Globulin (SHBG) is a protein that regulates the bioavailability of sex hormones. However, the causal relationship between SHBG levels and schizophrenia remains unclear, this study aimed to investigate the causal relationship based on two-sample Mendelian randomization (MR) analysis.

METHODS

This study was based on the summary data of genome-wide association studies (GWAS) of schizophrenia and SHBG in European populations. Two-sample MR was applied, and genetic factors were used as instrumental variables, and the causal relationship between schizophrenia and SHBG was assessed.

RESULTS

We selected 79 single nucleotide polymorphisms with genome-wide significance from the schizophrenia GWAS as instrumental variables. The inverse variance weighting (IVW) method results showed that there is a causal relationship and a positive correlation between schizophrenia and female SHBG, with an odds ratio (OR) of 1.024 (95%CI: 1.007-1.042, P = 0.005), and this result was further confirmed by the Weighted median odds ratio (OR) of 1.032 (95%CI: 1.016-1.048, P = 5.58E-05) and the Weighted mode of 1.035 (95%CI: 1.004-1.067, P = 0.028). Schizophrenia and male SHBG also have a causal relationship and a positive correlation, with an odds ratio (OR) of 1.027 (95%CI: 1.007-1.047, P = 0.008).

CONCLUSION

This study found a positive correlation between schizophrenia and SHBG in both men and women through MR analysis, indicating that the level of SHBG may be elevated in patients with schizophrenia, regardless of gender.

Effects of PRRT2 mutation on brain gray matter networks in paroxysmal kinesigenic dyskinesia

Although proline-rich transmembrane protein 2 is the primary causative gene of paroxysmal kinesigenic dyskinesia, its effects on the brain structure of paroxysmal kinesigenic dyskinesia patients are not yet clear. Here, we explored the influence of proline-rich transmembrane protein 2 mutations on similarity-based gray matter morphological networks in individuals with paroxysmal kinesigenic dyskinesia. A total of 51 paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 mutations, 55 paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 non-mutation, and 80 healthy controls participated in the study. We analyzed the structural connectome characteristics across groups by graph theory approaches. Relative to paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 non-mutation and healthy controls, paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 mutations exhibited a notable increase in characteristic path length and a reduction in both global and local efficiency. Relative to healthy controls, both patient groups showed reduced nodal metrics in right postcentral gyrus, right angular, and bilateral thalamus; Relative to healthy controls and paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 non-mutation, paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 mutations showed almost all reduced nodal centralities and structural connections in cortico-basal ganglia-thalamo-cortical circuit including bilateral supplementary motor area, bilateral pallidum, and right caudate nucleus. Finally, we used support vector machine by gray matter network matrices to classify paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 mutations and paroxysmal kinesigenic dyskinesia patients possessing proline-rich transmembrane protein 2 non-mutation, achieving an accuracy of 73%. These results show that proline-rich transmembrane protein 2 related gray matter network deficits may contribute to paroxysmal kinesigenic dyskinesia, offering new insights into its pathophysiological mechanisms.

Graph neural network and machine learning analysis of functional neuroimaging for understanding schizophrenia

BACKGROUND

Graph representational learning can detect topological patterns by leveraging both the network structure as well as nodal features. The basis of our exploration involves the application of graph neural network architectures and machine learning to resting-state functional Magnetic Resonance Imaging (rs-fMRI) data for the purpose of detecting schizophrenia. Our study uses single-site data to avoid the shortcomings in generalizability of neuroimaging data obtained from multiple sites.

RESULTS

The performance of our graph neural network models is on par with that of our machine learning models, each of which is trained using 69 graph-theoretical measures computed from functional correlations between various regions of interest (ROI) in a brain graph. Our deep graph convolutional neural network (DGCNN) demonstrates a promising average accuracy score of 0.82 and a sensitivity score of 0.84.

CONCLUSIONS

This study provides insights into the role of advanced graph theoretical methods and machine learning on fMRI data to detect schizophrenia by harnessing changes in brain functional connectivity. The results of this study demonstrate the capabilities of using both traditional ML techniques as well as graph neural network-based methods to detect schizophrenia using features extracted from fMRI data. The study also proposes two methods to obtain potential biomarkers for the disease, many of which are corroborated by research in this area and can further help in the understanding of schizophrenia as a mental disorder.

Discriminative analysis of schizophrenia patients using an integrated model combining 3D CNN with 2D CNN: A multimodal MR image and connectomics analysis

OBJECTIVE

Few studies have applied deep learning to the discriminative analysis of schizophrenia (SZ) patients using the fusional features of multimodal MRI data. Here, we proposed an integrated model combining a 3D convolutional neural network (CNN) with a 2D CNN to classify SZ patients.

METHOD

Structural MRI (sMRI) and resting-state functional MRI (rs-fMRI) data were acquired for 140 SZ patients and 205 normal controls. We computed structural connectivity (SC) from the sMRI data as well as functional connectivity (FC), amplitude of low-frequency fluctuation (ALFF), and regional homogeneity (ReHo) from the rs-fMRI data. The 3D images of T1, ReHo, and ALFF were used as the inputs for the 3D CNN model, while the SC and FC matrices were used as the inputs for the 2D CNN model. Moreover, we added squeeze and excitation blocks (SE-blocks) to each layer of the integrated model and used a support vector machine (SVM) to replace the softmax classifier.

RESULTS

The integrated model proposed in this study, using the fusional features of the T1 images, and the matrices of FC, showed the best performance. The use of the SE-blocks and SVM classifiers significantly improved the performance of the integrated model, in which the accuracy, sensitivity, specificity, area under the curve, and F1-score were 89.86%, 86.21%, 92.50%, 89.35%, and 87.72%, respectively.

CONCLUSIONS

Our findings indicated that an integrated model combining 3D CNN with 2D CNN is a promising method to improve the classification performance of SZ patients and has potential for the clinical diagnosis of psychiatric diseases.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

Brain morphometric features predict medication response in youth with bipolar disorder: a prospective randomized clinical trial

BACKGROUND

Identification of treatment-specific predictors of drug therapies for bipolar disorder (BD) is important because only about half of individuals respond to any specific medication. However, medication response in pediatric BD is variable and not well predicted by clinical characteristics.

METHODS

A total of 121 youth with early course BD (acute manic/mixed episode) were prospectively recruited and randomized to 6 weeks of double-blind treatment with quetiapine (n = 71) or lithium (n = 50). Participants completed structural magnetic resonance imaging (MRI) at baseline before treatment and 1 week after treatment initiation, and brain morphometric features were extracted for each individual based on MRI scans. Positive antimanic treatment response at week 6 was defined as an over 50% reduction of Young Mania Rating Scale scores from baseline. Two-stage deep learning prediction model was established to distinguish responders and non-responders based on different feature sets.

RESULTS

Pre-treatment morphometry and morphometric changes occurring during the first week can both independently predict treatment outcome of quetiapine and lithium with balanced accuracy over 75% (all p < 0.05). Combining brain morphometry at baseline and week 1 allows prediction with the highest balanced accuracy (quetiapine: 83.2% and lithium: 83.5%). Predictions in the quetiapine and lithium group were found to be driven by different morphometric patterns.

CONCLUSIONS

These findings demonstrate that pre-treatment morphometric measures and acute brain morphometric changes can serve as medication response predictors in pediatric BD. Brain morphometric features may provide promising biomarkers for developing biologically-informed treatment outcome prediction and patient stratification tools for BD treatment development.

Metastability as a candidate neuromechanistic biomarker of schizophrenia pathology

The disconnection hypothesis of schizophrenia proposes that symptoms of the disorder arise as a result of aberrant functional integration between segregated areas of the brain. The concept of metastability characterizes the coexistence of competing tendencies for functional integration and functional segregation in the brain, and is therefore well suited for the study of schizophrenia. In this study, we investigate metastability as a candidate neuromechanistic biomarker of schizophrenia pathology, including a demonstration of reliability and face validity. Group-level discrimination, individual-level classification, pathophysiological relevance, and explanatory power were assessed using two independent case-control studies of schizophrenia, the Human Connectome Project Early Psychosis (HCPEP) study (controls n = 53, non-affective psychosis n = 82) and the Cobre study (controls n = 71, cases n = 59). In this work we extend Leading Eigenvector Dynamic Analysis (LEiDA) to capture specific features of dynamic functional connectivity and then implement a novel approach to estimate metastability. We used non-parametric testing to evaluate group-level differences and a naïve Bayes classifier to discriminate cases from controls. Our results show that our new approach is capable of discriminating cases from controls with elevated effect sizes relative to published literature, reflected in an up to 76% area under the curve (AUC) in out-of-sample classification analyses. Additionally, our new metric showed explanatory power of between 81-92% for measures of integration and segregation. Furthermore, our analyses demonstrated that patients with early psychosis exhibit intermittent disconnectivity of subcortical regions with frontal cortex and cerebellar regions, introducing new insights about the mechanistic bases of these conditions. Overall, these findings demonstrate reliability and face validity of metastability as a candidate neuromechanistic biomarker of schizophrenia pathology.

Statistical power in network neuroscience

Network neuroscience has emerged as a leading method to study brain connectivity. The success of these investigations is dependent not only on approaches to accurately map connectivity but also on the ability to detect real effects in the data - that is, statistical power. We review the state of statistical power in the field and discuss sample size, effect size, measurement error, and network topology as key factors that influence the power of brain connectivity investigations. We use the term 'differential power' to describe how power can vary between nodes, edges, and graph metrics, leaving traces in both positive and negative connectome findings. We conclude with strategies for working with, rather than around, power in connectivity studies.

Static and dynamic topological organization of brain functional connectome in acute mild traumatic brain injury

BACKGROUND

Prior studies have detected topological changes of brain functional networks in patients with acute mild traumatic brain injury (mTBI). However, the alterations of dynamic topological characteristics in mTBI have been scarcely elucidated.

PURPOSE

To evaluate static and dynamic functional connectivity topological networks in patients with acute mTBI using resting-state functional magnetic resonance imaging (fMRI).

MATERIAL AND METHODS

A total of 55 patients with acute mTBI and 55 age-, sex-, and education-matched healthy controls (HCs) were enrolled in this study. All participants underwent resting-state fMRI scans, and data were analyzed using graph-theory methods and a sliding window approach. Post-traumatic cognitive performance and resting-state fMRI data were collected within one week after injury. Static and dynamic functional connectivity patterns were determined by independent component analysis. Spearman's correlation analysis was further performed between fMRI changes and Montreal cognitive assessment (MoCA) scores.

RESULTS

Global efficiency was lower (P = 0.02), and local efficiency (P < 0.001) and mean Cp (P < 0.001) were higher in patients with acute mTBI than in HCs. Local efficiency was correlated with visuospatial/executive performance (r = -0.421; P = 0.002) in patients with acute mTBI. Significant differences in nodal efficiency and node degree centrality (P < 0.01) were found between the mTBI and HC groups. For dynamic properties, patients with mTBI showed higher variance (P = 0.016) in global efficiency than HCs.

CONCLUSIONS

The present study shows that patients with mTBI have abnormal brain functional connectome topology, especially the dynamic graph theory characteristics, which provide new insights into the role of topological network properties in patients with acute mTBI.

Acquired Pedophilia: international Delphi-method-based consensus guidelines

Idiopathic and acquired pedophilia are two different disorders with two different etiologies. However, the differential diagnosis is still very difficult, as the behavioral indicators used to discriminate the two forms of pedophilia are underexplored, and clinicians are still devoid of clear guidelines describing the clinical and neuroscientific investigations suggested to help them with this difficult task. Furthermore, the consequences of misdiagnosis are not known, and a consensus regarding the legal consequences for the two kinds of offenders is still lacking. The present study used the Delphi method to reach a global consensus on the following six topics: behavioral indicators/red flags helpful for differential diagnosis; neurological conditions potentially leading to acquired pedophilia; neuroscientific investigations important for a correct understanding of the case; consequences of misdiagnosis; legal consequences; and issues and future perspectives. An international and multidisciplinary board of scientists and clinicians took part in the consensus statements as Delphi members. The Delphi panel comprised 52 raters with interdisciplinary competencies, including neurologists, psychiatrists, neuropsychologists, forensic psychologists, expert in ethics, etc. The final recommendations consisted of 63 statements covering the six different topics. The current study is the first expert consensus on a delicate topic such as pedophilia. Important exploitable consensual recommendations that can ultimately be of immediate use by clinicians to help with differential diagnosis and plan and guide therapeutic interventions are described, as well as future perspectives for researchers.

Classification and prediction of cognitive performance differences in older age based on brain network patterns using a machine learning approach

Age-related cognitive decline varies greatly in healthy older adults, which may partly be explained by differences in the functional architecture of brain networks. Resting-state functional connectivity (RSFC) derived network parameters as widely used markers describing this architecture have even been successfully used to support diagnosis of neurodegenerative diseases. The current study aimed at examining whether these parameters may also be useful in classifying and predicting cognitive performance differences in the normally aging brain by using machine learning (ML). Classifiability and predictability of global and domain-specific cognitive performance differences from nodal and network-level RSFC strength measures were examined in healthy older adults from the 1000BRAINS study (age range: 55-85 years). ML performance was systematically evaluated across different analytic choices in a robust cross-validation scheme. Across these analyses, classification performance did not exceed 60% accuracy for global and domain-specific cognition. Prediction performance was equally low with high mean absolute errors (MAEs ≥ 0.75) and low to none explained variance (R2 ≤ 0.07) for different cognitive targets, feature sets, and pipeline configurations. Current results highlight limited potential of functional network parameters to serve as sole biomarker for cognitive aging and emphasize that predicting cognition from functional network patterns may be challenging.

The topology, stability, and instability of learning-induced brain network repertoires in schizophrenia

There is a paucity of graph theoretic methods applied to task-based data in schizophrenia (SCZ). Tasks are useful for modulating brain network dynamics, and topology. Understanding how changes in task conditions impact inter-group differences in topology can elucidate unstable network characteristics in SCZ. Here, in a group of patients and healthy controls (n = 59 total, 32 SCZ), we used an associative learning task with four distinct conditions (Memory Formation, Post-Encoding Consolidation, Memory Retrieval, and Post-Retrieval Consolidation) to induce network dynamics. From the acquired fMRI time series data, betweenness centrality (BC), a metric of a node's integrative value was used to summarize network topology in each condition. Patients showed (a) differences in BC across multiple nodes and conditions; (b) decreased BC in more integrative nodes, but increased BC in less integrative nodes; (c) discordant node ranks in each of the conditions; and (d) complex patterns of stability and instability of node ranks across conditions. These analyses reveal that task conditions induce highly variegated patterns of network dys-organization in SCZ. We suggest that the dys-connection syndrome that is schizophrenia, is a contextually evoked process, and that the tools of network neuroscience should be oriented toward elucidating the limits of this dys-connection.

Topological disruption of high-order functional networks in cognitively preserved Parkinson's disease

AIMS

This study aimed to characterize the topological alterations and classification performance of high-order functional connectivity (HOFC) networks in cognitively preserved patients with Parkinson's disease (PD), relative to low-order FC (LOFC) networks.

METHODS

The topological metrics of the constructed networks (LOFC and HOFC) obtained from fifty-one cognitively normal patients with PD and 60 matched healthy control subjects were analyzed. The discriminative abilities were evaluated using machine learning approach.

RESULTS

The HOFC networks in the PD group showed decreased segregation and integration. The normalized clustering coefficient and small-worldness in the HOFC networks were correlated to motor performance. The altered nodal centralities (distributed in the precuneus, putamen, lingual gyrus, supramarginal gyrus, motor area, postcentral gyrus and inferior occipital gyrus) and intermodular FC (frontoparietal and visual networks, sensorimotor and subcortical networks) were specific to HOFC networks. Several highly connected nodes (thalamus, paracentral lobule, calcarine fissure and precuneus) and improved classification performance were found based on HOFC profiles.

CONCLUSION

This study identified disrupted topology of functional interactions at a high level with extensive alterations in topological properties and improved differentiation ability in patients with PD prior to clinical symptoms of cognitive impairment, providing complementary insights into complex neurodegeneration in PD.

The implication of a diversity of non-neuronal cells in disorders affecting brain networks

In the central nervous system (CNS) neurons are classically considered the functional unit of the brain. Analysis of the physical connections and co-activation of neurons, referred to as structural and functional connectivity, respectively, is a metric used to understand their interplay at a higher level. A myriad of glial cell types throughout the brain composed of microglia, astrocytes and oligodendrocytes are key players in the maintenance and regulation of neuronal network dynamics. Microglia are the central immune cells of the CNS, able to affect neuronal populations in number and connectivity, allowing for maturation and plasticity of the CNS. Microglia and astrocytes are part of the neurovascular unit, and together they are essential to protect and supply nutrients to the CNS. Oligodendrocytes are known for their canonical role in axonal myelination, but also contribute, with microglia and astrocytes, to CNS energy metabolism. Glial cells can achieve this variety of roles because of their heterogeneous populations comprised of different states. The neuroglial relationship can be compromised in various manners in case of pathologies affecting development and plasticity of the CNS, but also consciousness and mood. This review covers structural and functional connectivity alterations in schizophrenia, major depressive disorder, and disorder of consciousness, as well as their correlation with vascular connectivity. These networks are further explored at the cellular scale by integrating the role of glial cell diversity across the CNS to explain how these networks are affected in pathology.

Combined brain network topological metrics with machine learning algorithms to identify essential tremor

BACKGROUND AND OBJECTIVE

Essential tremor (ET) is a common movement syndrome, and the pathogenesis mechanisms, especially the brain network topological changes in ET are still unclear. The combination of graph theory (GT) analysis with machine learning (ML) algorithms provides a promising way to identify ET from healthy controls (HCs) at the individual level, and further help to reveal the topological pathogenesis in ET.

METHODS

Resting-state functional magnetic resonance imaging (fMRI) data were obtained from 101 ET and 105 HCs. The topological properties were analyzed by using GT analysis, and the topological metrics under every single threshold and the area under the curve (AUC) of all thresholds were used as features. Then a Mann-Whitney U-test and least absolute shrinkage and selection operator (LASSO) were conducted to feature dimensionality reduction. Four ML algorithms were adopted to identify ET from HCs. The mean accuracy, mean balanced accuracy, mean sensitivity, mean specificity, and mean AUC were used to evaluate the classification performance. In addition, correlation analysis was carried out between selected topological features and clinical tremor characteristics.

RESULTS

All classifiers achieved good classification performance. The mean accuracy of Support vector machine (SVM), logistic regression (LR), random forest (RF), and naïve bayes (NB) was 84.65, 85.03, 84.85, and 76.31%, respectively. LR classifier achieved the best classification performance with 85.03% mean accuracy, 83.97% sensitivity, and an AUC of 0.924. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with tremor severity.

CONCLUSION

These results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET from HCs but also help us to reveal the potential topological pathogenesis of ET.

Deep multimodal predictome for studying mental disorders

Characterizing neuropsychiatric disorders is challenging due to heterogeneity in the population. We propose combining structural and functional neuroimaging and genomic data in a multimodal classification framework to leverage their complementary information. Our objectives are two-fold (i) to improve the classification of disorders and (ii) to introspect the concepts learned to explore underlying neural and biological mechanisms linked to mental disorders. Previous multimodal studies have focused on naïve neural networks, mostly perceptron, to learn modality-wise features and often assume equal contribution from each modality. Our focus is on the development of neural networks for feature learning and implementing an adaptive control unit for the fusion phase. Our mid fusion with attention model includes a multilayer feed-forward network, an autoencoder, a bi-directional long short-term memory unit with attention as the features extractor, and a linear attention module for controlling modality-specific influence. The proposed model acquired 92% (p < .0001) accuracy in schizophrenia prediction, outperforming several other state-of-the-art models applied to unimodal or multimodal data. Post hoc feature analyses uncovered critical neural features and genes/biological pathways associated with schizophrenia. The proposed model effectively combines multimodal neuroimaging and genomics data for predicting mental disorders. Interpreting salient features identified by the model may advance our understanding of their underlying etiological mechanisms.

Going deep into schizophrenia with artificial intelligence

Despite years of research, the mechanisms governing the onset, relapse, symptomatology, and treatment of schizophrenia (SZ) remain elusive. The lack of appropriate analytic tools to deal with the heterogeneity and complexity of SZ may be one of the reasons behind this situation. Deep learning, a subfield of artificial intelligence (AI) inspired by the nervous system, has recently provided an accessible way of modeling and analyzing complex, high-dimensional, nonlinear systems. The unprecedented accuracy of deep learning algorithms in classification and prediction tasks has revolutionized a wide range of scientific fields and is rapidly permeating SZ research. Deep learning has the potential of becoming a valuable aid for clinicians in the prediction, diagnosis, and treatment of SZ, especially in combination with principles from Bayesian statistics. Furthermore, deep learning could become a powerful tool for uncovering the mechanisms underlying SZ thanks to a growing number of techniques designed for improving model interpretability and causal reasoning. The purpose of this article is to introduce SZ researchers to the field of deep learning and review its latest applications in SZ research. In general, existing studies have yielded impressive results in classification and outcome prediction tasks. However, methodological concerns related to the assessment of model performance in several studies, the widespread use of small training datasets, and the little clinical value of some models suggest that some of these results should be taken with caution.

Graph Convolutional Networks Reveal Network-Level Functional Dysconnectivity in Schizophrenia

BACKGROUND AND HYPOTHESIS

Schizophrenia is increasingly understood as a disorder of brain dysconnectivity. Recently, graph-based approaches such as graph convolutional network (GCN) have been leveraged to explore complex pairwise similarities in imaging features among brain regions, which can reveal abstract and complex relationships within brain networks.

STUDY DESIGN

We used GCN to investigate topological abnormalities of functional brain networks in schizophrenia. Resting-state functional magnetic resonance imaging data were acquired from 505 individuals with schizophrenia and 907 controls across 6 sites. Whole-brain functional connectivity matrix was extracted for each individual. We examined the performance of GCN relative to support vector machine (SVM), extracted the most salient regions contributing to both classification models, investigated the topological profiles of identified salient regions, and explored correlation between nodal topological properties of each salient region and severity of symptom.

STUDY RESULTS

GCN enabled nominally higher classification accuracy (85.8%) compared with SVM (80.9%). Based on the saliency map, the most discriminative brain regions were located in a distributed network including striatal areas (ie, putamen, pallidum, and caudate) and the amygdala. Significant differences in the nodal efficiency of bilateral putamen and pallidum between patients and controls and its correlations with negative symptoms were detected in post hoc analysis.

CONCLUSIONS

The present study demonstrates that GCN allows classification of schizophrenia at the individual level with high accuracy, indicating a promising direction for detection of individual patients with schizophrenia. Functional topological deficits of striatal areas may represent a focal neural deficit of negative symptomatology in schizophrenia.

Exploring Brain Structural and Functional Biomarkers in Schizophrenia via Brain-Network-Constrained Multi-View SCCA

Recent studies have proved that dynamic regional measures extracted from the resting-state functional magnetic resonance imaging, such as the dynamic fractional amplitude of low-frequency fluctuation (d-fALFF), could provide a great insight into brain dynamic characteristics of the schizophrenia. However, the unimodal feature is limited for delineating the complex patterns of brain deficits. Thus, functional and structural imaging data are usually analyzed together for uncovering the neural mechanism of schizophrenia. Investigation of neural function-structure coupling enables to find the potential biomarkers and further helps to understand the biological basis of schizophrenia. Here, a brain-network-constrained multi-view sparse canonical correlation analysis (BN-MSCCA) was proposed to explore the intrinsic associations between brain structure and dynamic brain function. Specifically, the d-fALFF was first acquired based on the sliding window method, whereas the gray matter map was computed based on voxel-based morphometry analysis. Then, the region-of-interest (ROI)-based features were extracted and further selected by performing the multi-view sparse canonical correlation analysis jointly with the diagnosis information. Moreover, the brain-network-based structural constraint was introduced to prompt the detected biomarkers more interpretable. The experiments were conducted on 191 patients with schizophrenia and 191 matched healthy controls. Results showed that the BN-MSCCA could identify the critical ROIs with more sparse canonical weight patterns, which are corresponding to the specific brain networks. These are biologically meaningful findings and could be treated as the potential biomarkers. The proposed method also obtained a higher canonical correlation coefficient for the testing data, which is more consistent with the results on training data, demonstrating its promising capability for the association identification. To demonstrate the effectiveness of the potential clinical applications, the detected biomarkers were further analyzed on a schizophrenia-control classification task and a correlation analysis task. The experimental results showed that our method had a superior performance with a 5-8% increment in accuracy and 6-10% improvement in area under the curve. Furthermore, two of the top-ranked biomarkers were significantly negatively correlated with the positive symptom score of Positive and Negative Syndrome Scale (PANSS). Overall, the proposed method could find the association between brain structure and dynamic brain function, and also help to identify the biological meaningful biomarkers of schizophrenia. The findings enable our further understanding of this disease.

Deep learning model using retinal vascular images for classifying schizophrenia

Contemporary psychiatric diagnosis still relies on the subjective symptom report of the patient during a clinical interview by a psychiatrist. Given the significant variability in personal reporting and differences in the skill set of psychiatrists, it is desirable to have objective diagnostic markers that could help clinicians differentiate patients from healthy individuals. A few recent studies have reported retinal vascular abnormalities in patients with schizophrenia (SCZ) using retinal fundus images. The goal of this study was to use a trained convolution neural network (CNN) deep learning algorithm to detect SCZ using retinal fundus images. A total of 327 subjects [139 patients with Schizophrenia (SCZ) and 188 Healthy volunteers (HV)] were recruited, and retinal images were acquired using a fundus camera. The images were preprocessed and fed to a convolution neural network for the classification. The model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The CNN achieved an accuracy of 95% for classifying SCZ and HV with an AUC of 0.98. Findings from the current study suggest the potential utility of deep learning to classify patients with SCZ and assist clinicians in clinical settings. Future studies need to examine the utility of the deep learning model with retinal vascular images as biomarkers in schizophrenia with larger sample sizes.

Evaluating the Performance of Machine Learning Models for Automatic Diagnosis of Patients with Schizophrenia Based on a Single Site Dataset of 440 Participants

Background

Methods

Results

Conclusions

Searching for Imaging Biomarkers of Psychotic Dysconnectivity

BACKGROUND

Progress in precision psychiatry is predicated on identifying reliable individual-level diagnostic biomarkers. For psychosis, measures of structural and functional connectivity could be promising biomarkers given consistent reports of dysconnectivity across psychotic disorders using magnetic resonance imaging.

METHODS

We leveraged data from four independent cohorts of patients with psychosis and control subjects with observations from approximately 800 individuals. We used group-level analyses and two supervised machine learning algorithms (support vector machines and ridge regression) to test within-, between-, and across-sample classification performance of white matter and resting-state connectivity metrics.

RESULTS

Although we replicated group-level differences in brain connectivity, individual-level classification was suboptimal. Classification performance within samples was variable across folds (highest area under the curve [AUC] range = 0.30) and across datasets (average support vector machine AUC range = 0.50; average ridge regression AUC range = 0.18). Classification performance between samples was similarly variable or resulted in AUC values of approximately 0.65, indicating a lack of model generalizability. Furthermore, collapsing across samples (resting-state functional magnetic resonance imaging, N = 888; diffusion tensor imaging, N = 860) did not improve model performance (maximal AUC = 0.67). Ridge regression models generally outperformed support vector machine models, although classification performance was still suboptimal in terms of clinical relevance. Adjusting for demographic covariates did not greatly affect results.

CONCLUSIONS

Connectivity measures were not suitable as diagnostic biomarkers for psychosis as assessed in this study. Our results do not negate that other approaches may be more successful, although it is clear that a systematic approach to individual-level classification with large independent validation samples is necessary to properly vet neuroimaging features as diagnostic biomarkers.

Multi-modal deep learning of functional and structural neuroimaging and genomic data to predict mental illness

Neuropsychiatric disorders such as schizophrenia are very heterogeneous in nature and typically diagnosed using self-reported symptoms. This makes it difficult to pose a confident prediction on the cases and does not provide insight into the underlying neural and biological mechanisms of these disorders. Combining neuroimaging and genomic data with a multi-modal 'predictome' paves the way for biologically informed markers and may improve prediction reliability. With that, we develop a multi-modal deep learning framework by fusing data from different modalities to capture the interaction between the latent features and evaluate their complementary information in characterizing schizophrenia. Our deep model uses structural MRI, functional MRI, and genome-wide polymorphism data to perform the classification task. It includes a multi-layer feed-forward network, an encoder, and a long short-term memory (LSTM) unit with attention to learn the latent features and adopt a joint training scheme capturing synergies between the modalities. The hybrid network also uses different regularizers for addressing the inherent overfitting and modality-specific bias in the multi-modal setup. Next, we run the network through a saliency model to analyze the learned features. Integrating modalities enhances the performance of the classifier, and our framework acquired 88% (P < 0.0001) accuracy on a dataset of 437 subjects. The trimodal accuracy is comparable to the state-of-the-art performance on a data collection of this size and outperforms the unimodal and bimodal baselines we compared. Model introspection was used to expose the salient neural features and genes/biological pathways associated with schizophrenia. To our best knowledge, this is the first approach that fuses genomic information with structural and functional MRI biomarkers for predicting schizophrenia. We believe this type of modality blending can better explain the disorder's dynamics by adding cross-modal prospects.Clinical Relevance- This study combinedly learns imaging and genomic features for the classification of schizophrenia. The data fusion scheme extracts modality interactions, and the saliency experiments report multiple functional and structural networks closely connected to the disorder.

Using deep learning to classify pediatric posttraumatic stress disorder at the individual level

BACKGROUND

Children exposed to natural disasters are vulnerable to developing posttraumatic stress disorder (PTSD). Previous studies using resting-state functional neuroimaging have revealed alterations in graph-based brain topological network metrics in pediatric PTSD patients relative to healthy controls (HC). Here we aimed to apply deep learning (DL) models to neuroimaging markers of classification which may be of assistance in diagnosis of pediatric PTSD.

METHODS

We studied 33 pediatric PTSD and 53 matched HC. Functional connectivity between 90 brain regions from the automated anatomical labeling atlas was established using partial correlation coefficients, and the whole-brain functional connectome was constructed by applying a threshold to the resultant 90 * 90 partial correlation matrix. Graph theory analysis was used to examine the topological properties of the functional connectome. A DL algorithm then used this measure to classify pediatric PTSD vs HC.

RESULTS

Graphic topological measures using DL provide a potentially clinically useful classifier for differentiating pediatric PTSD and HC (overall accuracy 71.2%). Frontoparietal areas (central executive network), cingulate cortex, and amygdala contributed the most to the DL model's performance.

CONCLUSIONS

Graphic topological measures based on fMRI data could contribute to imaging models of clinical utility in distinguishing pediatric PTSD from HC. DL model may be a useful tool in the identification of brain mechanisms PTSD participants.

Topologically convergent and divergent morphological gray matter networks in early-stage Parkinson's disease with and without mild cognitive impairment

Patients with Parkinson's disease with mild cognitive impairment (PD-M) progress to dementia more frequently than those with normal cognition (PD-N), but the underlying neurobiology remains unclear. This study aimed to define the specific morphological brain network alterations in PD-M, and explore their potential diagnostic value. Twenty-four PD-M patients, 17 PD-N patients, and 29 healthy controls (HC) underwent a structural MRI scan. Similarity between interregional gray matter volume distributions was used to construct individual morphological brain networks. These were analyzed using graph theory and network-based statistics (NBS), and their relationship to neuropsychological tests was assessed. Support vector machine (SVM) was used to perform individual classification. Globally, compared with HC, PD-M showed increased local efficiency (p = .001) in their morphological networks, while PD-N showed decreased normalized path length (p = .008). Locally, similar nodal deficits were found in the rectus and lingual gyrus, and cerebellum of both PD groups relative to HC; additionally in PD-M nodal deficits involved several frontal and parietal regions, correlated with cognitive scores. NBS found that similar connections were involved in the default mode and cerebellar networks of both PD groups (to a greater extent in PD-M), while PD-M, but not PD-N, showed altered connections involving the frontoparietal network. Using connections identified by NBS, SVM allowed discrimination with high accuracy between PD-N and HC (90%), PD-M and HC (85%), and between the two PD groups (65%). These results suggest that default mode and cerebellar disruption characterizes PD, more so in PD-M, whereas frontoparietal disruption has diagnostic potential.

Disruption of the white matter structural network and its correlation with baseline progression rate in patients with sporadic amyotrophic lateral sclerosis

OBJECTIVE

There is increasing evidence that amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease impacting large-scale brain networks. However, it is still unclear which structural networks are associated with the disease and whether the network connectomics are associated with disease progression. This study was aimed to characterize the network abnormalities in ALS and to identify the network-based biomarkers that predict the ALS baseline progression rate.

METHODS

Magnetic resonance imaging was performed on 73 patients with sporadic ALS and 100 healthy participants to acquire diffusion-weighted magnetic resonance images and construct white matter (WM) networks using tractography methods. The global and regional network properties were compared between ALS and healthy subjects. The single-subject WM network matrices of patients were used to predict the ALS baseline progression rate using machine learning algorithms.

RESULTS

Compared with the healthy participants, the patients with ALS showed significantly decreased clustering coefficient Cp (P = 0.0034, t = 2.98), normalized clustering coefficient γ (P = 0.039, t = 2.08), and small-worldness σ (P = 0.038, t = 2.10) at the global network level. The patients also showed decreased regional centralities in motor and non-motor systems including the frontal, temporal and subcortical regions. Using the single-subject structural connection matrix, our classification model could distinguish patients with fast versus slow progression rate with an average accuracy of 85%.

CONCLUSION

Disruption of the WM structural networks in ALS is indicated by weaker small-worldness and disturbances in regions outside of the motor systems, extending the classical pathophysiological understanding of ALS as a motor disorder. The individual WM structural network matrices of ALS patients are potential neuroimaging biomarkers for the baseline disease progression in clinical practice.

Emotion-Related Network Reorganization Following Fish Oil Supplementation in Depressed Bipolar Offspring: An fMRI Graph-Based Connectome Analysis

INTRODUCTION

Mood disorders are associated with fronto-limbic structural and functional abnormalities and deficits in omega-3 polyunsaturated fatty acids including eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA). Emerging evidence also suggests that n-3 PUFA, which are enriched in fish oil, promote cortical plasticity and connectivity. The present study performed a graph-based connectome analysis to investigate the role of n-3 PUFA in emotion-related network organization in medication-free depressed adolescent bipolar offspring.

METHODS

At baseline patients (n = 53) were compared with healthy controls (n = 53), and patients were then randomized to 12-week double-blind treatment with placebo or fish oil. At baseline and endpoint, erythrocyte EPA+DHA levels were measured and fMRI scans (4 Tesla) were obtained while performing a continuous performance task with emotional and neutral distractors (CPT-END). Graph-based analysis was used to characterize topological properties of large-scale brain network organization.

RESULTS

Compared with healthy controls, patients exhibited lower erythrocyte EPA+DHA levels (p = 0.0001), lower network clustering coefficients (p = 0.029), global efficiency (p = 0.042), and lower node centrality and connectivity strengths in frontal-limbic regions (p<0.05). Compared with placebo, 12-week fish oil supplementation increased erythrocyte EPA+DHA levels (p<0.001), network clustering coefficient (p = 0.005), global (p = 0.047) and local (p = 0.023) efficiency, and node centralities mainly in temporal regions (p<0.05).

LIMITATIONS

The duration of fish oil supplementation was relatively short and the sample size was relatively small.

CONCLUSIONS

These findings provide preliminary evidence that abnormalities in emotion-related network organization observed in depressed high-risk youth may be amenable to modification through fish oil supplementation.

Disrupted brain gray matter networks in drug-naïve participants with essential tremor

PURPOSE

To use structural magnetic resonance imaging and graph theory approaches to investigate the topological organization of the brain morphological network based on gray matter in essential tremor, and its potential relation to disease severity.

METHODS

In this prospective study conducted from November 2018 to November 2019, 36 participants with essential tremor and 37 matched healthy controls underwent magnetic resonance imaging. Brain networks based on the morphological similarity of gray matter across regions were analyzed using graph theory. Nonparametric permutation testing was used to assess group differences in topological metrics. Support vector machine was applied to the gray matter morphological matrices to classify participants with essential tremor vs. healthy controls.

RESULTS

Compared with healthy controls, participants with essential tremor showed increased global efficiency (p < 0.01) and decreased path length (p < 0.01); abnormal nodal properties in frontal, parietal, and cerebellar lobes; and disconnectivity in cerebello-thalamo-cortical network. The abnormal brain nodal centralities (left superior cerebellum gyrus; right caudate nucleus) correlated with clinical measures, both motor (Fahn-Tolosa-Marìn tremor rating, p = 0.017, r = - 0.41) and nonmotor (Hamilton depression scale, p = 0.040, r = - 0.36; Hamilton anxiety scale, p = 0.008, r = - 0.436). Gray matter morphological matrices classified individuals with high accuracy of 80.0%.

CONCLUSION

Participants with essential tremor showed randomization in global properties and dysconnectivity in the cerebello-thalamo-cortical network. Participants with essential tremor could be distinguished from healthy controls by gray matter morphological matrices.

Thalamus Radiomics-Based Disease Identification and Prediction of Early Treatment Response for Schizophrenia

Background

Emerging evidence suggests structural and functional disruptions of the thalamus in schizophrenia, but whether thalamus abnormalities are able to be used for disease identification and prediction of early treatment response in schizophrenia remains to be determined. This study aims at developing and validating a method of disease identification and prediction of treatment response by multi-dimensional thalamic features derived from magnetic resonance imaging in schizophrenia patients using radiomics approaches.

Methods

A total of 390 subjects, including patients with schizophrenia and healthy controls, participated in this study, among which 109 out of 191 patients had clinical characteristics of early outcome (61 responders and 48 non-responders). Thalamus-based radiomics features were extracted and selected. The diagnostic and predictive capacity of multi-dimensional thalamic features was evaluated using radiomics approach.

Results

Using radiomics features, the classifier accurately discriminated patients from healthy controls, with an accuracy of 68%. The features were further confirmed in prediction and random forest of treatment response, with an accuracy of 75%.

Conclusion

Our study demonstrates a radiomics approach by multiple thalamic features to identify schizophrenia and predict early treatment response. Thalamus-based classification could be promising to apply in schizophrenia definition and treatment selection.

Changes in the brain structural connectome after a prospective randomized clinical trial of lithium and quetiapine treatment in youth with bipolar disorder

The goals of the current study were to determine whether topological organization of brain structural networks is altered in youth with bipolar disorder, whether such alterations predict treatment outcomes, and whether they are normalized by treatment. Youth with bipolar disorder were randomized to double-blind treatment with quetiapine or lithium and assessed weekly. High-resolution MRI images were collected from children and adolescents with bipolar disorder who were experiencing a mixed or manic episode (n = 100) and healthy youth (n = 63). Brain networks were constructed based on the similarity of morphological features across regions and analyzed using graph theory approaches. We tested for pretreatment anatomical differences between bipolar and healthy youth and for changes in neuroanatomic network metrics following treatment in the youth with bipolar disorder. Youth with bipolar disorder showed significantly increased clustering coefficient (Cp) (p = 0.009) and characteristic path length (Lp) (p = 0.04) at baseline, and altered nodal centralities in insula, inferior frontal gyrus, and supplementary motor area. Cp, Lp, and nodal centrality of the insula exhibited normalization in patients following treatment. Changes in these neuroanatomic parameters were correlated with improvement in manic symptoms but did not differ between the two drug therapies. Baseline structural network matrices significantly differentiated medication responders and non-responders with 80% accuracy. These findings demonstrate that both global and nodal structural network features are altered in early course bipolar disorder, and that pretreatment alterations in neuroanatomic features predicted treatment outcome and were reduced by treatment. Similar connectome normalization with lithium and quetiapine suggests that the connectome changes are a downstream effect of both therapies that is related to their clinical efficacy.

Disrupted morphological grey matter networks in early-stage Parkinson's disease

While previous structural-covariance studies have an advanced understanding of brain alterations in Parkinson's disease (PD), brain–behavior relationships have not been examined at the individual level. This study investigated the topological organization of grey matter (GM) networks, their relation to disease severity, and their potential imaging diagnostic value in PD. Fifty-four early-stage PD patients and 54 healthy controls (HC) underwent structural T1-weighted magnetic resonance imaging. GM networks were constructed by estimating interregional similarity in the distributions of regional GM volume using the Kullback–Leibler divergence measure. Results were analyzed using graph theory and network-based statistics (NBS), and the relationship to disease severity was assessed. Exploratory support vector machine analyses were conducted to discriminate PD patients from HC and different motor subtypes. Compared with HC, GM networks in PD showed a higher clustering coefficient (P = 0.014) and local efficiency (P = 0.014). Locally, nodal centralities in PD were lower in postcentral gyrus and temporal-occipital regions, and higher in right superior frontal gyrus and left putamen. NBS analysis revealed decreased morphological connections in the sensorimotor and default mode networks and increased connections in the salience and frontoparietal networks in PD. Connection matrices and graph-based metrics allowed single-subject classification of PD and HC with significant accuracy of 73.1 and 72.7%, respectively, while graph-based metrics allowed single-subject classification of tremor-dominant and akinetic–rigid motor subtypes with significant accuracy of 67.0%. The topological organization of GM networks was disrupted in early-stage PD in a way that suggests greater segregation of information processing. There is potential for application to early imaging diagnosis.

Hippocampal subfield alterations in pediatric patients with post-traumatic stress disorder

The hippocampus, a key structure with distinct subfield functions, is strongly implicated in the pathophysiology of post-traumatic stress disorder (PTSD); however, few studies of hippocampus subfields in PTSD have focused on pediatric patients. We therefore investigated the hippocampal subfield volume using an automated segmentation method and explored the subfield-centered functional connectivity aberrations related to the anatomical changes, in a homogenous population of traumatized children with and without PTSD. To investigate the potential diagnostic value in individual patients, we used a machine learning approach to identify features with significant discriminative power for diagnosis of PTSD using random forest classifiers. Compared to controls, we found significant mean volume reductions of 8.4% and 9.7% in the right presubiculum and hippocampal tail in patients, respectively. These two subfields' volumes were the most significant contributors to group discrimination, with a mean classification accuracy of 69% and a specificity of 81%. These anatomical alterations, along with the altered functional connectivity between (pre)subiculum and inferior frontal gyrus, may underlie deficits in fear circuitry leading to dysfunction of fear extinction and episodic memory, causally important in post-traumatic symptoms such as hypervigilance and re-experience. For the first time, we suggest that hippocampal subfield volumes might be useful in discriminating traumatized children with and without PTSD.

Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis

Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n = 22), schizophrenia (SZ; n = 22) and attention-deficit/hyperactivity disorder (ADHD; n = 9). Thirty-two of the thirty-five studies that directly compared DL to SML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and SML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. Our results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. However, it is not yet used to its full potential: most studies use pre-engineered features, whereas one of the main advantages of DL is its ability to learn representations of minimally processed data. Our current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets. To truly uncover the added value of DL, we need carefully designed comparisons of SML and DL models which are yet rarely performed.

Translational Application of a Neuro-Scientific Multi-Modal Approach Into Forensic Psychiatric Evaluation: Why and How?

A prominent body of literature indicates that insanity evaluations, which are intended to provide influential expert reports for judges to reach a decision "beyond any reasonable doubt," suffer from a low inter-rater reliability. This paper reviews the limitations of the classical approach to insanity evaluation and the criticisms to the introduction of neuro-scientific approach in court. Here, we explain why in our opinion these criticisms, that seriously hamper the translational implementation of neuroscience into the forensic setting, do not survive scientific scrutiny. Moreover, we discuss how the neuro-scientific multimodal approach may improve the inter-rater reliability in insanity evaluation. Critically, neuroscience does not aim to introduce a brain-based concept of insanity. Indeed, criteria for responsibility and insanity are and should remain clinical. Rather, following the falsificationist approach and the convergence of evidence principle, the neuro-scientific multimodal approach is being proposed as a way to improve reliability of insanity evaluation and to mitigate the influence of cognitive biases on the formulation of insanity opinions, with the final aim to reduce errors and controversies.

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.

Individualized Prediction of PTSD Symptom Severity in Trauma Survivors From Whole-Brain Resting-State Functional Connectivity

Previous studies have demonstrated relations between spontaneous neural activity evaluated by resting-state functional magnetic resonance imaging (fMRI) and symptom severity in post-traumatic stress disorder. However, few studies have used brain-based measures to identify imaging associations with illness severity at the level of individual patients. This study applied connectome-based predictive modeling (CPM), a recently developed data-driven and subject-level method, to identify brain function features that are related to symptom severity of trauma survivors. Resting-state fMRI scans and clinical ratings were obtained 10-15 months after the earthquake from 122 earthquake survivors. Symptom severity of post-traumatic stress disorder features for each survivor was evaluated using the Clinician Administered Post-traumatic Stress Disorder Scale (CAPS-IV). A functionally pre-defined atlas was applied to divide the human brain into 268 regions. Each individual's functional connectivity 268 × 268 matrix was created to reflect correlations of functional time series data across each pair of nodes. The relationship between CAPS-IV scores and brain functional connectivity was explored in a CPM linear model. Using a leave-one-out cross-validation (LOOCV) procedure, findings showed that the positive network model predicted the left-out individual's CAPS-IV scores from resting-state functional connectivity. CPM predicted CAPS-IV scores, as indicated by a significant correspondence between predicted and actual values (r = 0.30, P = 0.001) utilizing primarily functional connectivity between visual cortex, subcortical-cerebellum, limbic, and motor systems. The current study provides data-driven evidence regarding the functional brain features that predict symptom severity based on the organization of intrinsic brain networks and highlights its potential application in making clinical evaluation of symptom severity at the individual level.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Functional Magnetic Resonance Imaging Connectivity Accurately Distinguishes Cases With Psychotic Disorders From Healthy Controls, Based on Cortical Features Associated With Brain Network Development

BACKGROUND

Machine learning (ML) can distinguish cases with psychotic disorder from healthy controls based on magnetic resonance imaging (MRI) data, but it is not yet clear which MRI metrics are the most informative for case-control ML, or how ML algorithms relate to the underlying biology.

METHODS

We analyzed multimodal MRI data from 2 independent case-control studies of psychotic disorders (cases, n = 65, 28; controls, n = 59, 80) and compared ML accuracy across 5 selected MRI metrics from 3 modalities. Cortical thickness, mean diffusivity, and fractional anisotropy were estimated at each of 308 cortical regions, as well as functional and structural connectivity between each pair of regions. Functional connectivity data were also used to classify nonpsychotic siblings of cases (n = 64) and to distinguish cases from controls in a third independent study (cases, n = 67; controls, n = 81).

RESULTS

In both principal studies, the most informative metric was functional MRI connectivity: The areas under the receiver operating characteristic curve were 88% and 76%, respectively. The cortical map of diagnostic connectivity features (ML weights) was replicable between studies (r = .27, p < .001); correlated with replicable case-control differences in functional MRI degree centrality and with a prior cortical map of adolescent development of functional connectivity; predicted intermediate probabilities of psychosis in siblings; and was replicated in the third case-control study.

CONCLUSIONS

ML most accurately distinguished cases from controls by a replicable pattern of functional MRI connectivity features, highlighting abnormal hubness of cortical nodes in an anatomical pattern consistent with the concept of psychosis as a disorder of network development.

Translating research findings into clinical practice: a systematic and critical review of neuroimaging-based clinical tools for brain disorders

A pivotal aim of psychiatric and neurological research is to promote the translation of the findings into clinical practice to improve diagnostic and prognostic assessment of individual patients. Structural neuroimaging holds much promise, with neuroanatomical measures accounting for up to 40% of the variance in clinical outcome. Building on these findings, a number of imaging-based clinical tools have been developed to make diagnostic and prognostic inferences about individual patients from their structural Magnetic Resonance Imaging scans. This systematic review describes and compares the technical characteristics of the available tools, with the aim to assess their translational potential into real-world clinical settings. The results reveal that a total of eight tools. All of these were specifically developed for neurological disorders, and as such are not suitable for application to psychiatric disorders. Furthermore, most of the tools were trained and validated in a single dataset, which can result in poor generalizability, or using a small number of individuals, which can cause overoptimistic results. In addition, all of the tools rely on two strategies to detect brain abnormalities in single individuals, one based on univariate comparison, and the other based on multivariate machine-learning algorithms. We discuss current barriers to the adoption of these tools in clinical practice and propose a checklist of pivotal characteristics that should be included in an "ideal" neuroimaging-based clinical tool for brain disorders.

Psychoradiological Biomarkers for Psychopharmaceutical Effects

The application of personalized medicine to psychiatry is challenging. Psychoradiology could provide biomarkers based on objective tests in support of the diagnostic classifications and treatment planning. We review potential psychoradiological biomarkers for psychopharmaceutical effects. Although none of the biomarkers reviewed are yet of sufficient clinical utility to inform the selection of a specific pharmacologic compound for an individual patient, there is strong consensus that advanced multimodal approaches will contribute to discovery of novel treatment predictors in psychiatric disorders. Progress has been sufficient to warrant enthusiasm, in which application of neuroimaging-based biomarkers would represent a paradigm shift and modernization of psychiatric practice.

The Neurodevelopment of Autism from Infancy Through Toddlerhood

Autism spectrum disorder (ASD) emerges during early childhood and is marked by a relatively narrow window in which infants transition from exhibiting normative behavioral profiles to displaying the defining features of the ASD phenotype in toddlerhood. Prospective brain imaging studies in infants at high familial risk for autism have revealed important insights into the neurobiology and developmental unfolding of ASD. In this article, we review neuroimaging studies of brain development in ASD from birth through toddlerhood, relate these findings to candidate neurobiological mechanisms, and discuss implications for future research and translation to clinical practice.

Neuroimaging in Schizophrenia

Schizophrenia is a chronic psychotic disorder with a lifetime prevalence of about 1%. Onset is typically in adolescence or early adulthood; characteristic symptoms include positive symptoms, negative symptoms, and impairments in cognition. Neuroimaging studies have shown substantive evidence of brain structural, functional, and neurochemical alterations that are more pronounced in the association cortex and subcortical regions. These abnormalities are not sufficiently specific to be of diagnostic value, but there may be a role for imaging techniques to provide predictions of outcome. Incorporating multimodal imaging datasets using machine learning approaches may offer better diagnostic and predictive value in schizophrenia.