Subcortical volumes differentiate Major Depressive Disorder, Bipolar Disorder, and remitted Major Depressive Disorder

The effects of psychotherapy for anhedonia on subcortical brain volumes measured with ultra-high field MRI

BACKGROUND

Anhedonia is a transdiagnostic symptom often resistant to treatment. The identification of biomarkers sensitive to anhedonia treatment will aid in the evaluation of novel anhedonia interventions.

METHODS

This is an exploratory analysis of changes in subcortical brain volumes accompanying psychotherapy in a transdiagnostic anhedonic sample using ultra-high field (7-Tesla) MRI. Outpatients with clinically impairing anhedonia (n = 116) received Behavioral Activation Treatment for Anhedonia, a novel psychotherapy, or Mindfulness-Based Cognitive Therapy (ClinicalTrials.gov Identifiers NCT02874534 and NCT04036136). Subcortical brain volumes were estimated via the MultisegPipeline, and regions of interest were the amygdala, caudate nucleus, hippocampus, pallidum, putamen, and thalamus. Bivariate mixed effects models estimated pre-treatment relations between anhedonia severity and subcortical brain volumes, change over time in subcortical brain volumes, and associations between changes in subcortical brain volumes and changes in anhedonia symptoms.

RESULTS

As reported previously (Cernasov et al., 2023), both forms of psychotherapy resulted in equivalent and significant reductions in anhedonia symptoms. Pre-treatment anhedonia severity and subcortical brain volumes were not related. No changes in subcortical brain volumes were observed over the course of treatment. Additionally, no relations were observed between changes in subcortical brain volumes and changes in anhedonia severity over the course of treatment.

LIMITATIONS

This trial included a modest sample size and did not have a waitlist-control condition or a non-anhedonic comparison group.

CONCLUSIONS

In this exploratory analysis, psychotherapy for anhedonia was not accompanied by changes in subcortical brain volumes, suggesting that subcortical brain volumes may not be a candidate biomarker sensitive to response to psychotherapy.

The pivotal role of the X-chromosome in the genetic architecture of the human brain

Genes on the X-chromosome are extensively expressed in the human brain. However, little is known for the X-chromosome's impact on the brain anatomy, microstructure, and functional network. We examined 1,045 complex brain imaging traits from 38,529 participants in the UK Biobank. We unveiled potential autosome-X-chromosome interactions, while proposing an atlas outlining dosage compensation (DC) for brain imaging traits. Through extensive association studies, we identified 72 genome-wide significant trait-locus pairs (including 29 new associations) that share genetic architectures with brain-related disorders, notably schizophrenia. Furthermore, we discovered unique sex-specific associations and assessed variations in genetic effects between sexes. Our research offers critical insights into the X-chromosome's role in the human brain, underscoring its contribution to the differences observed in brain structure and functionality between sexes.

Alterations in subcortical magnetic susceptibility and disease-specific relationship with brain volume in major depressive disorder and schizophrenia

Quantitative susceptibility mapping is a magnetic resonance imaging technique that measures brain tissues' magnetic susceptibility, including iron deposition and myelination. This study examines the relationship between subcortical volume and magnetic susceptibility and determines specific differences in these measures among patients with major depressive disorder (MDD), patients with schizophrenia, and healthy controls (HCs). This was a cross-sectional study. Sex- and age- matched patients with MDD (n = 49), patients with schizophrenia (n = 24), and HCs (n = 50) were included. Magnetic resonance imaging was conducted using quantitative susceptibility mapping and T1-weighted imaging to measure subcortical susceptibility and volume. The acquired brain measurements were compared among groups using analyses of variance and post hoc comparisons. Finally, a general linear model examined the susceptibility-volume relationship. Significant group-level differences were found in the magnetic susceptibility of the nucleus accumbens and amygdala (p = 0.045). Post-hoc analyses indicated that the magnetic susceptibility of the nucleus accumbens and amygdala for the MDD group was significantly higher than that for the HC group (p = 0.0054, p = 0.0065, respectively). However, no significant differences in subcortical volume were found between the groups. The general linear model indicated a significant interaction between group and volume for the nucleus accumbens in MDD group but not schizophrenia or HC groups. This study showed susceptibility alterations in the nucleus accumbens and amygdala in MDD patients. A significant relationship was observed between subcortical susceptibility and volume in the MDD group's nucleus accumbens, which indicated abnormalities in myelination and the dopaminergic system related to iron deposition.

Characterizing major depressive disorder and substance use disorder using heatmaps and variable interactions: The utility of operant behavior and brain structure relationships

BACKGROUND

Rates of depression and addiction have risen drastically over the past decade, but the lack of integrative techniques remains a barrier to accurate diagnoses of these mental illnesses. Changes in reward/aversion behavior and corresponding brain structures have been identified in those with major depressive disorder (MDD) and cocaine-dependence polysubstance abuse disorder (CD). Assessment of statistical interactions between computational behavior and brain structure may quantitatively segregate MDD and CD.

METHODS

Here, 111 participants [40 controls (CTRL), 25 MDD, 46 CD] underwent structural brain MRI and completed an operant keypress task to produce computational judgment metrics. Three analyses were performed: (1) linear regression to evaluate groupwise (CTRL v. MDD v. CD) differences in structure-behavior associations, (2) qualitative and quantitative heatmap assessment of structure-behavior association patterns, and (3) the k-nearest neighbor machine learning approach using brain structure and keypress variable inputs to discriminate groups.

RESULTS

This study yielded three primary findings. First, CTRL, MDD, and CD participants had distinct structure-behavior linear relationships, with only 7.8% of associations overlapping between any two groups. Second, the three groups had statistically distinct slopes and qualitatively distinct association patterns. Third, a machine learning approach could discriminate between CTRL and CD, but not MDD participants.

CONCLUSIONS

These findings demonstrate that variable interactions between computational behavior and brain structure, and the patterns of these interactions, segregate MDD and CD. This work raises the hypothesis that analysis of interactions between operant tasks and structural neuroimaging might aide in the objective classification of MDD, CD and other mental health conditions.

A structural equation modeling approach using behavioral and neuroimaging markers in major depressive disorder

Major depressive disorder (MDD) has consistently proven to be a multifactorial and highly comorbid disease. Despite recent depression-related research demonstrating causalities between MDD-related factors and a small number of variables, including brain structural changes, a high-statistical power analysis of the various factors is yet to be conducted. We retrospectively analyzed data from 155 participants (84 healthy controls and 71 patients with MDD). We used magnetic resonance imaging and diffusion tensor imaging data, scales assessing childhood trauma, depression severity, cognitive dysfunction, impulsivity, and suicidal ideation. To simultaneously evaluate the causalities between multivariable, we implemented two types of MDD-specified structural equation models (SEM), the behavioral and neurobehavioral models. Behavioral SEM showed significant results in the MDD group: Comparative Fit Index [CFI] = 1.000, Root Mean Square Error of Approximation [RMSEA]) = 0.000), with a strong correlation in the scales for childhood trauma, depression severity, suicidal ideation, impulsivity, and cognitive dysfunction. Based on behavioral SEM, we established neurobehavioral models showing the best-fit in MDD, especially including the right cingulate cortex, central to the posterior corpus callosum, right putamen, pallidum, whole brainstem, and ventral diencephalon, including the thalamus (CFI >0.96, RMSEA <0.05). Our MDD-specific model revealed that the limbic-associated regions are strongly connected with childhood trauma rather than depression severity, and that they independently affect suicidal ideation and cognitive dysfunction. Furthermore, cognitive dysfunction could affect impulsivity.

Abnormal caudate nucleus activity in patients with depressive disorder: Meta-analysis of task-based functional magnetic resonance imaging studies with behavioral domain

During task-based functional magnetic resonance imaging (t-fMRI) patients with depressive disorder (DD) have shown abnormal caudate nucleus activation. There have been no meta-analyses that are conducted on the caudate nucleus using Activation Likelihood Estimation (ALE) in patients with DD, and the relationships between abnormal caudate activity and different behavior domains in patients with DD remain unclear. There were 24 previously published t-fMRI studies included in the study with the caudate nucleus as the region of interest. Meta-analyses were performed using the method of ALE. Included five ALE meta-analyses: (1) the hypoactivated caudate nucleus relative to healthy controls (HCs); (2) the hyper-activated caudate nucleus; (3) the abnormal activation in the caudate nucleus in the emotion domain; (4) the abnormal activation in cognition domain; (5) the abnormal activation in the affective cognition domain. Results revealed that the hypo-/hyper-activity in the caudate subregions is mainly located in the caudate body and head, while the relationships between abnormal caudate subregions and different behavior domains are complex. The hypoactivation of the caudate body and head plays a key role in the emotions which indicates there is a positive relationship between the decreased caudate activity and depressed emotional behaviors in patients with DD.

Neuroanatomical dimensions in medication-free individuals with major depressive disorder and treatment response to SSRI antidepressant medications or placebo

Major depressive disorder (MDD) is a heterogeneous clinical syndrome with widespread subtle neuroanatomical correlates. Our objective was to identify the neuroanatomical dimensions that characterize MDD and predict treatment response to selective serotonin reuptake inhibitor (SSRI) antidepressants or placebo. In the COORDINATE-MDD consortium, raw MRI data were shared from international samples (N = 1,384) of medication-free individuals with first-episode and recurrent MDD (N = 685) in a current depressive episode of at least moderate severity, but not treatment-resistant depression, as well as healthy controls (N = 699). Prospective longitudinal data on treatment response were available for a subset of MDD individuals (N = 359). Treatments were either SSRI antidepressant medication (escitalopram, citalopram, sertraline) or placebo. Multi-center MRI data were harmonized, and HYDRA, a semi-supervised machine-learning clustering algorithm, was utilized to identify patterns in regional brain volumes that are associated with disease. MDD was optimally characterized by two neuroanatomical dimensions that exhibited distinct treatment responses to placebo and SSRI antidepressant medications. Dimension 1 was characterized by preserved gray and white matter (N = 290 MDD), whereas Dimension 2 was characterized by widespread subtle reductions in gray and white matter (N = 395 MDD) relative to healthy controls. Although there were no significant differences in age of onset, years of illness, number of episodes, or duration of current episode between dimensions, there was a significant interaction effect between dimensions and treatment response. Dimension 1 showed a significant improvement in depressive symptoms following treatment with SSRI medication (51.1%) but limited changes following placebo (28.6%). By contrast, Dimension 2 showed comparable improvements to either SSRI (46.9%) or placebo (42.2%) (β = -18.3, 95% CI (-34.3 to -2.3), P = 0.03). Findings from this case-control study indicate that neuroimaging-based markers can help identify the disease-based dimensions that constitute MDD and predict treatment response.

Automatic Diagnosis of Major Depressive Disorder Using a High- and Low-Frequency Feature Fusion Framework

Major Depressive Disorder (MDD) is a common mental illness resulting in immune disorders and even thoughts of suicidal behavior. Neuroimaging techniques serve as a quantitative tool for the assessment of MDD diagnosis. In the domain of computer-aided magnetic resonance imaging diagnosis, current research predominantly focuses on isolated local or global information, often neglecting the synergistic integration of multiple data sources, thus potentially overlooking valuable details. To address this issue, we proposed a diagnostic model for MDD that integrates high-frequency and low-frequency information using data from diffusion tensor imaging (DTI), structural magnetic resonance imaging (sMRI), and functional magnetic resonance imaging (fMRI). First, we designed a meta-low-frequency encoder (MLFE) and a meta-high-frequency encoder (MHFE) to extract the low-frequency and high-frequency feature information from DTI and sMRI, respectively. Then, we utilized a multilayer perceptron (MLP) to extract features from fMRI data. Following the feature cross-fusion, we designed the ensemble learning threshold voting method to determine the ultimate diagnosis for MDD. The model achieved accuracy, precision, specificity, F1-score, MCC, and AUC values of 0.724, 0.750, 0.882, 0.600, 0.421, and 0.667, respectively. This approach provides new research ideas for the diagnosis of MDD.

An attention-based multi-modal MRI fusion model for major depressive disorder diagnosis

Objective.Major depressive disorder (MDD) is one of the biggest threats to human mental health. MDD is characterized by aberrant changes in both structure and function of the brain. Although recent studies have developed some deep learning models based on multi-modal magnetic resonance imaging (MRI) for MDD diagnosis, the latent associations between deep features derived from different modalities were largely unexplored by previous studies, which we hypothesized may have potential benefits in improving the diagnostic accuracy of MDD.Approach.In this study, we proposed a novel deep learning model that fused both structural MRI (sMRI) and resting-state MRI (rs-fMRI) data to enhance the diagnosis of MDD by capturing the interactions between deep features extracted from different modalities. Specifically, we first employed a brain function encoder (BFE) and a brain structure encoder (BSE) to extract the deep features from fMRI and sMRI, respectively. Then, we designed a function and structure co-attention fusion (FSCF) module that captured inter-modal interactions and adaptively fused multi-modal deep features for MDD diagnosis.Main results.This model was evaluated on a large cohort and achieved a high classification accuracy of 75.2% for MDD diagnosis. Moreover, the attention distribution of the FSCF module assigned higher attention weights to structural features than functional features for diagnosing MDD.Significance.The high classification accuracy highlights the effectiveness and potential clinical of the proposed model.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Reduced fractional anisotropy in bipolar disorder v. major depressive disorder independent of current symptoms

BACKGROUND

Patients with bipolar disorder (BD) show reduced fractional anisotropy (FA) compared to patients with major depressive disorder (MDD). Little is known about whether these differences are mood state-independent or influenced by acute symptom severity. Therefore, the aim of this study was (1) to replicate abnormalities in white matter microstructure in BD v. MDD and (2) to investigate whether these vary across depressed, euthymic, and manic mood.

METHODS

In this cross-sectional diffusion tensor imaging study, n = 136 patients with BD were compared to age- and sex-matched MDD patients and healthy controls (HC) (n = 136 each). Differences in FA were investigated using tract-based spatial statistics. Using interaction models, the influence of acute symptom severity and mood state on the differences between patient groups were tested.

RESULTS

Analyses revealed a main effect of diagnosis on FA across all three groups (ptfce-FWE = 0.003). BD patients showed reduced FA compared to both MDD (ptfce-FWE = 0.005) and HC (ptfce-FWE < 0.001) in large bilateral clusters. These consisted of several white matter tracts previously described in the literature, including commissural, association, and projection tracts. There were no significant interaction effects between diagnosis and symptom severity or mood state (all ptfce-FWE > 0.704).

CONCLUSIONS

Results indicated that the difference between BD and MDD was independent of depressive and manic symptom severity and mood state. Disruptions in white matter microstructure in BD might be a trait effect of the disorder. The potential of FA values to be used as a biomarker to differentiate BD from MDD should be further addressed in future studies using longitudinal designs.

Decreased dorsal attention network homogeneity as a potential neuroimaging biomarker for major depressive disorder

BACKGROUND

Gaining insight into abnormal functional brain network homogeneity (NH) has the potential to aid efforts to target or otherwise study major depressive disorder (MDD). The NH of the dorsal attention network (DAN) in first-episode treatment-naive MDD patients, however, has yet to be studied. As such, the present study was developed to explore the NH of the DAN in order to determine the ability of this parameter to differentiate between MDD patients and healthy control (HC) individuals.

METHODS

This study included 73 patients with first-episode treatment-naive MDD and 73 age-, gender-, and educational level-matched healthy controls. All participants completed the attentional network test (ANT), Hamilton Rating Scale for Depression (HRSD), and resting-state functional magnetic resonance imaging (rs-fMRI) analyses. A group independent component analysis (ICA) was used to identify the DAN and to compute the NH of the DAN in patients with MDD. Spearman's rank correlation analyses were used to explore relationships between significant NH abnormalities in MDD patients, clinical parameters, and executive control reaction time.

RESULTS

Relative to HCs, patients exhibited reduced NH in the left supramarginal gyrus (SMG). Support vector machine (SVM) analyses and receiver operating characteristic curves indicated that the NH of the left SMG could be used to differentiate between HCs and MDD patients with respective accuracy, specificity, sensitivity, and AUC values of 92.47 %, 91.78 %, 93.15 %, and 65.39 %. A significant positive correlation was observed between the left SMG NH values and HRSD scores among MDD patients.

CONCLUSIONS

These results suggest that NH changes in the DAN may offer value as a neuroimaging biomarker capable of differentiating between MDD patients and healthy individuals.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Unsupervised cross-domain functional MRI adaptation for automated major depressive disorder identification

Resting-state functional magnetic resonance imaging (rs-fMRI) data have been widely used for automated diagnosis of brain disorders such as major depressive disorder (MDD) to assist in timely intervention. Multi-site fMRI data have been increasingly employed to augment sample size and improve statistical power for investigating MDD. However, previous studies usually suffer from significant inter-site heterogeneity caused for instance by differences in scanners and/or scanning protocols. To address this issue, we develop a novel discrepancy-based unsupervised cross-domain fMRI adaptation framework (called UFA-Net) for automated MDD identification. The proposed UFA-Net is designed to model spatio-temporal fMRI patterns of labeled source and unlabeled target samples via an attention-guided graph convolution module, and also leverage a maximum mean discrepancy constrained module for unsupervised cross-site feature alignment between two domains. To the best of our knowledge, this is one of the first attempts to explore unsupervised rs-fMRI adaptation for cross-site MDD identification. Extensive evaluation on 681 subjects from two imaging sites shows that the proposed method outperforms several state-of-the-art methods. Our method helps localize disease-associated functional connectivity abnormalities and is therefore well interpretable and can facilitate fMRI-based analysis of MDD in clinical practice.

AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder: COORDINATE-MDD consortium design and rationale

BACKGROUND

Efforts to develop neuroimaging-based biomarkers in major depressive disorder (MDD), at the individual level, have been limited to date. As diagnostic criteria are currently symptom-based, MDD is conceptualized as a disorder rather than a disease with a known etiology; further, neural measures are often confounded by medication status and heterogeneous symptom states.

METHODS

We describe a consortium to quantify neuroanatomical and neurofunctional heterogeneity via the dimensions of novel multivariate coordinate system (COORDINATE-MDD). Utilizing imaging harmonization and machine learning methods in a large cohort of medication-free, deeply phenotyped MDD participants, patterns of brain alteration are defined in replicable and neurobiologically-based dimensions and offer the potential to predict treatment response at the individual level. International datasets are being shared from multi-ethnic community populations, first episode and recurrent MDD, which are medication-free, in a current depressive episode with prospective longitudinal treatment outcomes and in remission. Neuroimaging data consist of de-identified, individual, structural MRI and resting-state functional MRI with additional positron emission tomography (PET) data at specific sites. State-of-the-art analytic methods include automated image processing for extraction of anatomical and functional imaging variables, statistical harmonization of imaging variables to account for site and scanner variations, and semi-supervised machine learning methods that identify dominant patterns associated with MDD from neural structure and function in healthy participants.

RESULTS

We are applying an iterative process by defining the neural dimensions that characterise deeply phenotyped samples and then testing the dimensions in novel samples to assess specificity and reliability. Crucially, we aim to use machine learning methods to identify novel predictors of treatment response based on prospective longitudinal treatment outcome data, and we can externally validate the dimensions in fully independent sites.

CONCLUSION

We describe the consortium, imaging protocols and analytics using preliminary results. Our findings thus far demonstrate how datasets across many sites can be harmonized and constructively pooled to enable execution of this large-scale project.

A neural network approach to optimising treatments for depression using data from specialist and community psychiatric services in Australia, New Zealand and Japan

This study investigated the application of a recurrent neural network for optimising pharmacological treatment for depression. A clinical dataset of 458 participants from specialist and community psychiatric services in Australia, New Zealand and Japan were extracted from an existing custom-built, web-based tool called Psynary . This data, which included baseline and self-completed reviews, was used to train and refine a novel algorithm which was a fully connected network feature extractor and long short-term memory algorithm was firstly trained in isolation and then integrated and annealed using slow learning rates due to the low dimensionality of the data. The accuracy of predicting depression remission before processing patient review data was 49.8%. After processing only 2 reviews, the accuracy was 76.5%. When considering a change in medication, the precision of changing medications was 97.4% and the recall was 71.4% . The medications with predicted best results were antipsychotics (88%) and selective serotonin reuptake inhibitors (87.9%). This is the first study that has created an all-in-one algorithm for optimising treatments for all subtypes of depression. Reducing treatment optimisation time for patients suffering with depression may lead to earlier remission and hence reduce the high levels of disability associated with the condition. Furthermore, in a setting where mental health conditions are increasing strain on mental health services, the utilisation of web-based tools for remote monitoring and machine/deep learning algorithms may assist clinicians in both specialist and primary care in extending specialist mental healthcare to a larger patient community.

Distinguish bipolar and major depressive disorder in adolescents based on multimodal neuroimaging: Results from the Adolescent Brain Cognitive Development study®

Background

Major depressive disorder and bipolar disorder in adolescents are prevalent and are associated with cognitive impairment, executive dysfunction, and increased mortality. Early intervention in the initial stages of major depressive disorder and bipolar disorder can significantly improve personal health.

Methods

We collected 309 samples from the Adolescent Brain Cognitive Development study, including 116 adolescents with bipolar disorder, 64 adolescents with major depressive disorder, and 129 healthy adolescents, and employed a support vector machine to develop classification models for identification. We developed a multimodal model, which combined functional connectivity of resting-state functional magnetic resonance imaging and four anatomical measures of structural magnetic resonance imaging (cortical thickness, area, volume, and sulcal depth). We measured the performances of both multimodal and single modality classifiers.

Results

The multimodal classifiers showed outstanding performance compared with all five single modalities, and they are 100% for major depressive disorder versus healthy controls, 100% for bipolar disorder versus healthy control, 98.5% (95% CI: 95.4–100%) for major depressive disorder versus bipolar disorder, 100% for major depressive disorder versus depressed bipolar disorder and the leave-one-site-out analysis results are 77.4%, 63.3%, 79.4%, and 81.7%, separately.

Conclusions

The study shows that multimodal classifiers show high classification performances. Moreover, cuneus may be a potential biomarker to differentiate major depressive disorder, bipolar disorder, and healthy adolescents. Overall, this study can form multimodal diagnostic prediction workflows for clinically feasible to make more precise diagnose at the early stage and potentially reduce loss of personal pain and public society.

Altered voxel-mirrored homotopic connectivity in right temporal lobe epilepsy as measured using resting-state fMRI and support vector machine analyses

BACKGROUND

Prior reports revealed abnormalities in voxel-mirrored homotopic connectivity (VMHC) when analyzing neuroimaging data from patients with various psychiatric conditions, including temporal lobe epilepsy (TLE). Whether these VHMC changes can be leveraged to aid in the diagnosis of right TLE (rTLE), however, remains to be established. This study was thus developed to examine abnormal VMHC findings associated with rTLE to determine whether these changes can be used to guide rTLE diagnosis.

METHODS

The resultant imaging data of resting-state functional MRI (rs-fMRI) analyses of 59 patients with rTLE and 60 normal control individuals were analyzed using VMHC and support vector machine (SVM) approaches.

RESULTS

Relative to normal controls, patients with rTLE were found to exhibit decreased VMHC values in the bilateral superior and the middle temporal pole (STP and MTP), the bilateral middle and inferior temporal gyri (MTG and ITG), and the bilateral orbital portion of the inferior frontal gyrus (OrbIFG). These patients further exhibited increases in VMHC values in the bilateral precentral gyrus (PreCG), the postcentral gyrus (PoCG), and the supplemental motor area (SMA). The ROC curve of MTG VMHC values showed a great diagnostic efficacy in the diagnosis of rTLE with AUCs, sensitivity, specificity, and optimum cutoff values of 0.819, 0.831, 0.717, and 0.465. These findings highlight the value of the right middle temporal gyrus (rMTG) when differentiating between rTLE and control individuals, with a corresponding SVM analysis yielding respective accuracy, sensitivity, and specificity values of 70.59% (84/119), 78.33% (47/60), and 69.49% (41/59).

CONCLUSION

In summary, patients with rTLE exhibit various forms of abnormal functional connectivity, and SVM analyses support the potential value of abnormal VMHC values as a neuroimaging biomarker that can aid in the diagnosis of this condition.

Sleep disturbance-related neuroimaging features as potential biomarkers for the diagnosis of major depressive disorder: A multicenter study based on machine learning

BACKGROUND

Objective biomarkers are crucial for overcoming the clinical dilemma in major depressive disorder (MDD), and the individualized diagnosis is essential to facilitate the precise medicine for MDD.

METHODS

Sleep disturbance-related magnetic resonance imaging (MRI) features was identified in the internal dataset (92 MDD patients) using the relevance vector regression algorithm, which was further verified in 460 MDD patients of an independent, multicenter dataset. Subsequently, using these MRI features, the eXtreme Gradient Boosting classification model was constructed in the current multicenter dataset (460 MDD patients and 470 normal controls). Meanwhile, the association between classification outputs and the severity of depressive symptoms was also investigated.

RESULTS

In MDD patients, the combination of gray matter density and fractional amplitude of low-frequency fluctuation can accurately predict individual sleep disturbance score that was calculated by the sum of item 4 score, item 5 score, and item 6 score of the 17-Item Hamilton Rating Scale for Depression (HAMD-17) (R² = 0.158 in the internal dataset; R² = 0.110 in multicenter dataset). Furthermore, the classification model based on these MRI features distinguished MDD patients from normal controls with 86.3% accuracy (area under the curve = 0.937). Importantly, the classification outputs significantly correlated with HAMD-17 scores in MDD patients.

LIMITATION

Lacking some specialized tools to assess the personal sleep quality, e.g. Pittsburgh Sleep Quality Index.

CONCLUSION

Neuroimaging features can reflect accurately individual sleep disturbance manifestation and serve as potential diagnostic biomarkers of MDD.

Potential structural trait markers of depression in the form of alterations in the structures of subcortical nuclei and structural covariance network properties

It has been proposed recently that major depressive disorder (MDD) could represent an adaptation to conserve energy after the perceived loss of an investment in a vital source, such as group identity, personal assets, or relationships. Energy conserving behaviors associated with MDD may form a persistent marker in brain regions and networks involved in cognition and emotion regulation. In this study, we examined whether subcortical regions and volume-based structural covariance networks (SCNs) have state-independent alterations (trait markers). First-episode drug-naïve currently depressed (cMDD) patients (N = 131), remitted MDD (RD) patients (N = 67), and healthy controls (HCs, N = 235) underwent structural magnetic resonance imaging (MRI). Subcortical gray matter volumes (GMVs) were calculated in FreeSurfer software, and group differences in GMVs and SCN were analyzed. Compared to HCs, major findings were decreased GMVs of left pallidum and pulvinar anterior of thalamus in the cMDD and RD groups, indicative of a trait marker. Relative to HCs, subcortical SCNs of both cMDD and RD patients were found to have reduced small-world-ness and path length, which together may represent a trait-like topological feature of depression. In sum, the left pallidum, left pulvinar anterior of thalamus volumetric alterations may represent trait marker and reduced small-world-ness, path length may represent trait-like topological feature of MDD.

Cortical thickness distinguishes between major depression and schizophrenia in adolescents

BACKGROUND

Early diagnosis of adolescent psychiatric disorder is crucial for early intervention. However, there is extensive comorbidity between affective and psychotic disorders, which increases the difficulty of precise diagnoses among adolescents.

METHODS

We obtained structural magnetic resonance imaging scans from 150 adolescents, including 67 and 47 patients with major depressive disorder (MDD) and schizophrenia (SCZ), as well as 34 healthy controls (HC) to explore whether psychiatric disorders could be identified using a machine learning technique. Specifically, we used the support vector machine and the leave-one-out cross-validation method to distinguish among adolescents with MDD and SCZ and healthy controls.

RESULTS

We found that cortical thickness was a classification feature of a) MDD and HC with 79.21% accuracy where the temporal pole had the highest weight; b) SCZ and HC with 69.88% accuracy where the left superior temporal sulcus had the highest weight. Notably, adolescents with MDD and SCZ could be classified with 62.93% accuracy where the right pars triangularis had the highest weight.

CONCLUSIONS

Our findings suggest that cortical thickness may be a critical biological feature in the diagnosis of adolescent psychiatric disorders. These findings might be helpful to establish an early prediction model for adolescents to better diagnose psychiatric disorders.

A Review of Publicly Available Automatic Brain Segmentation Methodologies, Machine Learning Models, Recent Advancements, and Their Comparison

BACKGROUND

The noninvasive study of the structure and functions of the brain using neuroimaging techniques is increasingly being used for its clinical and research perspective. The morphological and volumetric changes in several regions and structures of brains are associated with the prognosis of neurological disorders such as Alzheimer's disease, epilepsy, schizophrenia, etc. and the early identification of such changes can have huge clinical significance. The accurate segmentation of three-dimensional brain magnetic resonance images into tissue types (i.e., grey matter, white matter, cerebrospinal fluid) and brain structures, thus, has huge importance as they can act as early biomarkers. The manual segmentation though considered the "gold standard" is time-consuming, subjective, and not suitable for bigger neuroimaging studies. Several automatic segmentation tools and algorithms have been developed over the years; the machine learning models particularly those using deep convolutional neural network (CNN) architecture are increasingly being applied to improve the accuracy of automatic methods.

PURPOSE

The purpose of the study is to understand the current and emerging state of automatic segmentation tools, their comparison, machine learning models, their reliability, and shortcomings with an intent to focus on the development of improved methods and algorithms.

METHODS

The study focuses on the review of publicly available neuroimaging tools, their comparison, and emerging machine learning models particularly those based on CNN architecture developed and published during the last five years.

CONCLUSION

Several software tools developed by various research groups and made publicly available for automatic segmentation of the brain show variability in their results in several comparison studies and have not attained the level of reliability required for clinical studies. The machine learning models particularly three dimensional fully convolutional network models can provide a robust and efficient alternative with relation to publicly available tools but perform poorly on unseen datasets. The challenges related to training, computation cost, reproducibility, and validation across distinct scanning modalities for machine learning models need to be addressed.

Multimodal MRI assessment for first episode psychosis: A major change in the thalamus and an efficient stratification of a subgroup

Multi‐institutional brain imaging studies have emerged to resolve conflicting results among individual studies. However, adjusting multiple variables at the technical and cohort levels is challenging. Therefore, it is important to explore approaches that provide meaningful results from relatively small samples at institutional levels. We studied 87 first episode psychosis (FEP) patients and 62 healthy subjects by combining supervised integrated factor analysis (SIFA) with a novel pipeline for automated structure‐based analysis, an efficient and comprehensive method for dimensional data reduction that our group recently established. We integrated multiple MRI features (volume, DTI indices, resting state fMRI—rsfMRI) in the whole brain of each participant in an unbiased manner. The automated structure‐based analysis showed widespread DTI abnormalities in FEP and rs‐fMRI differences between FEP and healthy subjects mostly centered in thalamus. The combination of multiple modalities with SIFA was more efficient than the use of single modalities to stratify a subgroup of FEP (individuals with schizophrenia or schizoaffective disorder) that had more robust deficits from the overall FEP group. The information from multiple MRI modalities and analytical methods highlighted the thalamus as significantly abnormal in FEP. This study serves as a proof‐of‐concept for the potential of this methodology to reveal disease underpins and to stratify populations into more homogeneous sub‐groups.

Voxel-based morphometry in patients with mood disorder bipolar I mania in comparison to normal controls

Background

Neuroimaging is used to study brain structural alterations in neuropsychiatric diseases including bipolar disorder (BD). Voxel-based morphometry (VBM) quantifies structural changes detected in magnetic resonance imaging (MRI). The aim of this study was to identify brain structural changes in patients with mood disorder bipolar I mania, compared to healthy controls; and detect any correlations between volumetric findings and different clinical aspects of the disease. VBM was used to identify structural changes in 24 patients with bipolar I mania compared to 16 controls. Young Mania Rating Scale (YMRS) was used to evaluate clinical severity of BD. t test was used to compare differences in volumetric data and Spearman’s rank correlation coefficient was used to detect potential correlations between volumetric data and clinical parameters of BD.

Results

Compared to controls, BD patients had significantly larger right globus pallidus and right lateral ventricle. There was significant correlation between volumetric data of different brain structures and clinical criteria of BD including age of onset, illness duration, YMRS, number of manic attacks, and duration of the last attack.

Conclusions

VBM could address specific structural findings in bipolar I mania that may contribute to pathophysiology of the disease and show significant correlation with different clinical aspects of the disease.

Trial registration

This clinical trial was registered at ClinicalTrials.gov under registration number NCT03181698, registered 11 June 2017.

Automated classification of depression from structural brain measures across two independent community-based cohorts

Major depressive disorder (MDD) has been the subject of many neuroimaging case-control classification studies. Although some studies report accuracies ≥80%, most have investigated relatively small samples of clinically-ascertained, currently symptomatic cases, and did not attempt replication in larger samples. We here first aimed to replicate previously reported classification accuracies in a small, well-phenotyped community-based group of current MDD cases with clinical interview-based diagnoses (from STratifying Resilience and Depression Longitudinally cohort, 'STRADL'). We performed a set of exploratory predictive classification analyses with measures related to brain morphometry and white matter integrity. We applied three classifier types-SVM, penalised logistic regression or decision tree-either with or without optimisation, and with or without feature selection. We then determined whether similar accuracies could be replicated in a larger independent population-based sample with self-reported current depression (UK Biobank cohort). Additional analyses extended to lifetime MDD diagnoses-remitted MDD in STRADL, and lifetime-experienced MDD in UK Biobank. The highest cross-validation accuracy (75%) was achieved in the initial current MDD sample with a decision tree classifier and cortical surface area features. The most frequently selected decision tree split variables included surface areas of bilateral caudal anterior cingulate, left lingual gyrus, left superior frontal, right precentral and paracentral regions. High accuracy was not achieved in the larger samples with self-reported current depression (53.73%), with remitted MDD (57.48%), or with lifetime-experienced MDD (52.68-60.29%). Our results indicate that high predictive classification accuracies may not immediately translate to larger samples with broader criteria for depression, and may not be robust across different classification approaches.

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.

Support Vector Machines and Affective Science

Support vector machines (SVMs) are being used increasingly in affective science as a data-driven classification method and feature reduction technique. Whereas traditional statistical methods typically compare group averages on selected variables, SVMs use a predictive algorithm to learn multivariate patterns that optimally discriminate between groups. In this review, we provide a framework for understanding the methods of SVM-based analyses and summarize the findings of seminal studies that use SVMs for classification or data reduction in the behavioral and neural study of emotion and affective disorders. We conclude by discussing promising directions and potential applications of SVMs in future research in affective science.

Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions

OBJECTIVES

The existence of anatomofunctional brain abnormalities in bipolar disorder (BD) is now well established by magnetic resonance imaging (MRI) studies. To create diagnostic and prognostic tools, as well as identifying biologically valid subtypes of BD, research has recently turned towards the use of machine learning (ML) techniques. We assessed both supervised ML and unsupervised ML studies in BD to evaluate their robustness, reproducibility and the potential need for improvement.

METHOD

We systematically searched for studies using ML algorithms based on MRI data of patients with BD until February 2019.

RESULT

We identified 47 studies, 45 using supervised ML techniques and 2 including unsupervised ML analyses. Among supervised studies, 43 focused on diagnostic classification. The reported accuracies for classification of BD ranged between (a) 57% and 100%, for BD vs healthy controls; (b) 49.5% and 93.1% for BD vs patients with major depressive disorder; and (c) 50% and 96.2% for BD vs patients with schizophrenia. Reported accuracies for discriminating subjects genetically at risk for BD (either from control or from patients with BD) ranged between 64.3% and 88.93%.

CONCLUSIONS

Although there are strong methodological limitations in previous studies and an important need for replication in large multicentric samples, the conclusions of our review bring hope of future computer-aided diagnosis of BD and pave the way for other applications, such as treatment response prediction. To reinforce the reliability of future results we provide methodological suggestions for good practice in conducting and reporting MRI-based ML studies in BD.

Predicting differential diagnosis between bipolar and unipolar depression with multiple kernel learning on multimodal structural neuroimaging

One of the greatest challenges in providing early effective treatment in mood disorders is the early differential diagnosis between major depression (MDD) and bipolar disorder (BD). A remarkable need exists to identify reliable biomarkers for these disorders. We integrate structural neuroimaging techniques (i.e. Tract-based Spatial Statistics, TBSS, and Voxel-based morphometry) in a multiple kernel learning procedure in order to define a predictive function of BD against MDD diagnosis in a sample of 148 patients. We achieved a balanced accuracy of 73.65% with a sensitivity for BD of 74.32% and specificity for MDD of 72.97%. Mass-univariates analyses showed reduced grey matter volume in right hippocampus, amygdala, parahippocampal, fusiform gyrus, insula, rolandic and frontal operculum and cerebellum, in BD compared to MDD. Volumes in these regions and in anterior cingulate cortex were also reduced in BD compared to healthy controls (n = 74). TBSS analyses revealed widespread significant effects of diagnosis on fractional anisotropy, axial, radial, and mean diffusivity in several white matter tracts, suggesting disruption of white matter microstructure in depressed patients compared to healthy controls, with worse pattern for MDD. To best of our knowledge, this is the first study combining grey matter and diffusion tensor imaging in predicting BD and MDD diagnosis. Our results prompt brain quantitative biomarkers and multiple kernel learning as promising tool for personalized treatment in mood disorders.

A proof of concept machine learning analysis using multimodal neuroimaging and neurocognitive measures as predictive biomarker in bipolar disorder

BACKGROUND

Concomitant use of complementary, multimodal imaging measures and neurocognitive measures is reported to have higher accuracy as a biomarker in Alzheimer's dementia. However, such an approach has not been examined to differentiate healthy individuals from Bipolar disorder. In this study, we examined the utility of support vector machine (SVM) technique to differentiate bipolar disorder patients and healthy using structural, functional and diffusion tensor images of brain and neurocognitive measures.

METHODS

30 patients with Bipolar disorder-I and 30 age, sex matched individuals participated in the study. Structural MRI, resting state functional MRI and diffusion tensor images were obtained using a 1.5 T scanner. All participants were administered neuropsychological tests to measure executive functions. SVM, a supervised machine learning technique was applied to differentiate patients and healthy individuals with k-fold cross validation over 10 trials.

RESULTS

The composite marker consisting of both neuroimaging and neuropsychological measures, had an accuracy of 87.60 %, sensitivity of 82.3 % and specificity of 92.7 %. The performance of composite marker was better compared to that of individual markers on classificatory.

CONCLUSIONS

We were able to achieve a high accuracy for machine learning technique in distinguishing BD from HV using a combination of multimodal neuroimaging and neurocognitive measures. Findings of this proof of concept study, if replicated in larger samples, could have potential clinical applications.

Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group

Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47-67.00, ROC-AUC = 71.49%, 95% CI = 69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70-60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen's Kappa = 0.83, 95% CI = 0.829-0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.

Linking personality types to depressive symptoms: A prospective typology based on neuroticism, extraversion and conscientiousness

From a traditional variable-centered perspective, the personality traits specifically linked to depressive symptoms are neuroticism, extraversion, and conscientiousness (NEC). Few studies have considered the interactive effects of personality traits within individuals from the taxonomic perspective. We explored novel NEC personality subtypes in general and subthreshold depressive subjects by using graph-based classification algorithms and multiple external validators. Personality and depressive symptoms were assessed in 1055 healthy subjects (150 with subthreshold depression) using the NEO-PI-R and BDI at baseline. NEC personality data were used to identify subtypes in healthy and subthreshold depressive samples, and external validators, including current and longitudinal depressive symptoms and seven subcortical gray matter volumes, were examined. Four novel NEC personality types in the general sample showed superior current and longitudinal behavioral validation of depressive symptoms as well as some discrimination in biological indicators (putamen, nucleus accumbens, and amygdala). Four profiles defined in subthreshold depression selectively exhibited meaningful differences in longitudinal depressive symptoms. In both samples, some types adhere to the principles previously described NEC three-way interaction. The resulting typology, especially the four types in the general population, linked depressive symptoms provided a superior description of within-person organization of neuroticism, extraversion, and conscientiousness.

State-independent and -dependent structural alterations in limbic-cortical regions in patients with current and remitted depression

BACKGROUND

The high recurrence of major depressive disorder (MDD) may derive from underlying state-independent structural alterations.

METHODS

First-episode drug-naïve currently depressed (cMDD) patients (N = 97), remitted depressed (RD) patients (N = 72), and healthy controls (HCs, N = 100) underwent structural magnetic resonance imaging (MRI). Group differences in cortical thickness (CT), surface area (SA), and local gyrification index (lGI) were analyzed in FreeSurfer.

RESULTS

Both groups of depressed patients had significantly decreased CT, relative to HCs, in the left precentral gyrus and significantly increased lGI values in the left superior frontal gyrus (SFG) indicative of state-independent alterations. Relative to HCs, the cMDD group had decreased CT of the SFG, caudal middle frontal gyrus (MFG), posterior cingulate cortex (PCC), and lateral occipital regions as well as increased SA or lGI of the superior temporal gyrus, precuneus, and pericalcarine, whereas the RD group had increased SA or lGI of the SFG, caudal MFG, and supramarginal gyrus; these alterations appeared to be state-dependent. SA or lGI values of the fusiform gyrus, inferior temporal gyrus, and superior parietal lobule differed between the cMDD and RD groups, consistent with state-dependent alterations. Beck depression inventory scores correlated with CT or lGI values of the caudal MFG, lateral occipital cortex in depressed patients.

LIMITATIONS

The structural features of several subcortical limbic regions were not analyzed.

CONCLUSIONS

Left precentral gyrus CT and left SFG gyrification alterations may represent state-independent alterations in MDD.

Quantifying deep grey matter atrophy using automated segmentation approaches: A systematic review of structural MRI studies

The deep grey matter (DGM) nuclei of the brain play a crucial role in learning, behaviour, cognition, movement and memory. Although automated segmentation strategies can provide insight into the impact of multiple neurological conditions affecting these structures, such as Multiple Sclerosis (MS), Huntington's disease (HD), Alzheimer's disease (AD), Parkinson's disease (PD) and Cerebral Palsy (CP), there are a number of technical challenges limiting an accurate automated segmentation of the DGM. Namely, the insufficient contrast of T1 sequences to completely identify the boundaries of these structures, as well as the presence of iso-intense white matter lesions or extensive tissue loss caused by brain injury. Therefore in this systematic review, 269 eligible studies were analysed and compared to determine the optimal approaches for addressing these technical challenges. The automated approaches used among the reviewed studies fall into three broad categories, atlas-based approaches focusing on the accurate alignment of atlas priors, algorithmic approaches which utilise intensity information to a greater extent, and learning-based approaches that require an annotated training set. Studies that utilise freely available software packages such as FIRST, FreeSurfer and LesionTOADS were also eligible, and their performance compared. Overall, deep learning approaches achieved the best overall performance, however these strategies are currently hampered by the lack of large-scale annotated data. Improving model generalisability to new datasets could be achieved in future studies with data augmentation and transfer learning. Multi-atlas approaches provided the second-best performance overall, and may be utilised to construct a "silver standard" annotated training set for deep learning. To address the technical challenges, providing robustness to injury can be improved by using multiple channels, highly elastic diffeomorphic transformations such as LDDMM, and by following atlas-based approaches with an intensity driven refinement of the segmentation, which has been done with the Expectation Maximisation (EM) and level sets methods. Accounting for potential lesions should be achieved with a separate lesion segmentation approach, as in LesionTOADS. Finally, to address the issue of limited contrast, R2*, T2* and QSM sequences could be used to better highlight the DGM due to its higher iron content. Future studies could look to additionally acquire these sequences by retaining the phase information from standard structural scans, or alternatively acquiring these sequences for only a training set, allowing models to learn the "improved" segmentation from T1-sequences alone.

Aberrant brain network topology in fronto-limbic circuitry differentiates euthymic bipolar disorder from recurrent major depressive disorder

INTRODUCTION

Previous studies have established graph theoretical analysis of functional network connectivity (FNC) as a potential tool to detect neurobiological underpinnings of psychiatric disorders. Despite the promising outcomes in studies that examined FNC aberrancies in bipolar disorder (BD) and major depressive disorder (MDD), there is still a lack of research comparing both mood disorders, especially in a nondepressed state. In this study, we used graph theoretical network analysis to compare brain network properties of euthymic BD, euthymic MDD and healthy controls (HC) to evaluate whether these groups showed distinct features in FNC.

METHODS

We collected resting-state functional magnetic resonance imaging (fMRI) data from 20 BD patients, 15 patients with recurrent MDD as well as 30 age- and gender-matched HC. Graph theoretical analyses were then applied to investigate functional brain networks on a global and regional network level.

RESULTS

Global network analysis revealed a significantly higher mean global clustering coefficient in BD compared to HC. We further detected frontal, temporal and subcortical nodes in emotion regulation areas such as the limbic system and associated regions exhibiting significant differences in network integration and segregation in BD compared to MDD patients and HC. Participants with MDD and HC only differed in frontal and insular network centrality.

CONCLUSION

In conclusion, our findings indicate that a significantly altered brain network topology in the limbic system might be a trait marker specific to BD. Brain network analysis in these regions may therefore be used to differentiate euthymic BD not only from HC but also from patients with MDD.

Altered resting-state cerebral blood flow and functional connectivity of striatum in bipolar disorder and major depressive disorder

BACKGROUND

Clinically distinguishing bipolar disorder (BD) from major depressive disorder (MDD) during depressive states is difficult. Neuroimaging findings suggested that patients with BD and those with MDD differed with respect to the gray matter volumes of their subcortical structures, especially in their striatum. However, whether these disorders have different effects on functionally striatal neuronal activity and connectivity is unclear.

METHODS

Arterial spin labeling and resting-state functional MRI was performed on 25 currently depressive patients with BD, 25 depressive patients with MDD, and 34 healthy controls (HCs). The functional properties of striatal neuronal activity (cerebral blood flow, CBF) and its functional connectivity (FC) were analyzed, and the results from the three groups were compared. The result of the multiple comparisons was corrected on the basis of the Gaussian Random Field theory.

RESULTS

The patients with BD and those with MDD both had higher CBF values than the HCs in the right caudate and right putamen. The hyper-metabolism of right striatum in BD patients was associated with increased average duration per depressive episode. The two disorders showed commonly increased FC between the striatum and dorsolateral prefrontal cortex, whereas the altered FC of the striatum with precuneus/cuneus was observed only in patients with BD.

CONCLUSIONS

Patients with BD and those with MDD had a common deficit in their prefrontal-limbic-striatal circuits. The altered striato-precuneus FC can be considered as a marker for the differentiation of patients with BD from those with MDD.

Lifetime major depression and grey-matter volume

BACKGROUND

There is evidence of structural brain alterations in major depressive disorder (MDD), but little is known about how these alterations might be affected by age at onset or genetic vulnerability. This study examines whether lifetime episodes of MDD are associated with specific alterations in grey-matter volume, and whether those alterations vary according to sex or serotonin transporter-linked promoter region (5-HTTLPR) genotype (LL, SL or SS).

METHODS

We used structural MRI to acquire anatomic scans from 610 community-dwelling participants. We derived quantitative regional estimates of grey-matter volume in 16 subregions using FreeSurfer software. We diagnosed MDD according to DSM-IV criteria. We adjusted analyses for age, sex, total brain volume, education level, head injury and comorbidities.

RESULTS

Lifetime MDD was associated with a smaller insula, thalamus, ventral diencephalon, pallidum and nucleus accumbens and with a larger pericalcarine region in both men and women. These associations remained after adjustment for false discovery rate. Lifetime MDD was also associated with a smaller caudate nucleus and amygdala in men and with a larger rostral anterior cingulate cortex in women. Late-onset first episodes of MDD (after age 50 years) were associated with a larger rostral anterior cingulate cortex and lingual and pericalcarine regions; early-onset MDD was associated with a smaller ventral diencephalon and nucleus accumbens. Some associations differed according to 5-HTTLPR genotype: the thalamus was smaller in participants with MDD and the LL genotype; pericalcarine and lingual volumes were higher in those with the SL genotype.

LIMITATIONS

This study was limited by its cross-sectional design.

CONCLUSION

Major depressive disorder was associated with persistent volume reductions in the deep nuclei and insula and with enlargements in visual cortex subregions; alterations varied according to age of onset and genotype.

Differentiation of Transformed Bipolar Disorder From Unipolar Depression by Resting-State Functional Connectivity Within Reward Circuit

Previous studies have found that neural functional abnormalities detected by functional magnetic resonance imaging (fMRI) in brain regions implicated in reward processing during reward tasks show promise to distinguish bipolar from unipolar depression (UD), but little is known regarding resting-state functional connectivity (rsFC) within the reward circuit. In this study, we investigated neurobiomarkers for early recognition of bipolar disorder (BD) by retrospectively comparing rsFC within the reward circuit between UD and depressed BD. Sixty-six depressed patients were enrolled, none of whom had ever experienced any manic/hypomanic episodes before baseline. Simultaneously, 40 matched healthy controls (HC) were also recruited. Neuroimaging data of each participant were obtained from resting-state fMRI scans. Some patients began to manifest bipolar disorder (tBD) during the follow-up period. All patients were retrospectively divided into two groups (33 tBD and 33 UD) according to the presence or absence of mania/hypomania in the follow-up. rsFC between key regions of the reward circuit was calculated and compared among groups. Results showed decreased rsFC between the left ventral tegmental area (VTA) and left ventral striatum (VS) in the tBD group compared with the UD group, which showed good accuracy in predicting diagnosis (tBD vs. UD) according to receiver operating characteristic (ROC) analysis. No significant different rsFC was found within the reward circuit between any patient group and HC. Our preliminary findings indicated that bipolar disorder, in early depressive stages before onset of mania/hypomania attacks, already differs from UD in the reward circuit of VTA-VS functional synchronicity at the resting state.

Machine learning in major depression: From classification to treatment outcome prediction

AIMS

Major depression disorder (MDD) is the single greatest cause of disability and morbidity, and affects about 10% of the population worldwide. Currently, there are no clinically useful diagnostic biomarkers that are able to confirm a diagnosis of MDD from bipolar disorder (BD) in the early depressive episode. Therefore, exploring translational biomarkers of mood disorders based on machine learning is in pressing need, though it is challenging, but with great potential to improve our understanding of these disorders.

DISCUSSIONS

In this study, we review popular machine-learning methods used for brain imaging classification and predictions, and provide an overview of studies, specifically for MDD, that have used magnetic resonance imaging data to either (a) classify MDDs from controls or other mood disorders or (b) investigate treatment outcome predictors for individual patients. Finally, challenges, future directions, and potential limitations related to MDD biomarker identification are also discussed, with a goal of offering a comprehensive overview that may help readers to better understand the applications of neuroimaging data mining in depression.

CONCLUSIONS

We hope such efforts may highlight the need for an urgently needed paradigm shift in treatment, to guide personalized optimal clinical care.

Pattern recognition of magnetic resonance imaging-based gray matter volume measurements classifies bipolar disorder and major depressive disorder

BACKGROUND

Bipolar Disorder (BD) cannot be reliably distinguished from Major Depressive Disorder (MDD) until the first manic or hypomanic episode. Consequently, many patients with BD are treated with antidepressants without mood stabilizers, a strategy that is often ineffective and carries a risk of inducing a manic episode. We previously reported reduced cortical thickness in right precuneus, right caudal middle-frontal cortex and left inferior parietal cortex in BD compared with MDD.

METHODS

This study extends our previous work by performing individual level classification of BD or MDD in an expanded, currently unmedicated, cohort using gray matter volume (GMV) based on Magnetic Resonance Imaging and a Support Vector Machine. All patients were in a Major Depressive Episode and a leave-two-out analysis was performed.

RESULTS

Nineteen out of 26 BD subjects and 20 out of 26 MDD subjects were correctly identified, for a combined accuracy of 75%. The three brain regions contributing to the classification were higher GMV in bilateral supramarginal gyrus and occipital cortex indicating MDD, and higher GMV in right dorsolateral prefrontal cortex indicating BD.

LIMITATIONS

This analysis included scans performed with two different headcoils and scan sequences, which limited the interpretability of results in an independent cohort analysis.

CONCLUSIONS

Our results add to previously published data which suggest that regional gray matter volume should be investigated further as a clinical diagnostic tool to predict BD before the appearance of a manic or hypomanic episode.

Putamen Volume Differences Among Older Adults: Depression Status, Melancholia, and Age

BACKGROUND

Individuals with major depressive disorder (MDD) may exhibit smaller striatal volumes reflecting deficits in the reward circuit. Deficits may change with age and be more pronounced among the melancholic subtype. Limited research has investigated striatal volume differences in older adults and by depression subtypes.

METHOD

We used baseline data from the Neurocognitive Outcomes of Depression in the Elderly study. We examined volumetric differences in the putamen and caudate nucleus among older adults (60 years and older), comparing healthy control participants (n = 134) to depressed participants (n = 226), and comparing nonmelancholic depressed participants (n = 93) to melancholic depressed participants (n = 133). Group-by-age interactions were examined.

RESULTS

There were no significant group differences for the caudate nucleus. For the left putamen, investigation of the significant group-by-age interaction revealed that volume size was greater for the healthy controls compared to the depressed participants but only at younger ages (60-65 years); group differences diminished with increasing age. Examining volume by depression subtype revealed that the melancholic depressed participants had a smaller left putamen compared to the nonmelancholic depressed participants. Anhedonia symptoms were related to both smaller left and right putamen.

CONCLUSION

Structural abnormalities in reward regions may underlie the anhedonic phenotype. Volume loss associated with MDD may attenuate in older age.

Detecting Neuroimaging Biomarkers for Depression: A Meta-analysis of Multivariate Pattern Recognition Studies

BACKGROUND

Multiple studies have examined functional and structural brain alteration in patients diagnosed with major depressive disorder (MDD). The introduction of multivariate statistical methods allows investigators to utilize data concerning these brain alterations to generate diagnostic models that accurately differentiate patients with MDD from healthy control subjects (HCs). However, there is substantial heterogeneity in the reported results, the methodological approaches, and the clinical characteristics of participants in these studies.

METHODS

We conducted a meta-analysis of all studies using neuroimaging (volumetric measures derived from T1-weighted images, task-based functional magnetic resonance imaging [MRI], resting-state MRI, or diffusion tensor imaging) in combination with multivariate statistical methods to differentiate patients diagnosed with MDD from HCs.

RESULTS

Thirty-three (k = 33) samples including 912 patients with MDD and 894 HCs were included in the meta-analysis. Across all studies, patients with MDD were separated from HCs with 77% sensitivity and 78% specificity. Classification based on resting-state MRI (85% sensitivity, 83% specificity) and on diffusion tensor imaging data (88% sensitivity, 92% specificity) outperformed classifications based on structural MRI (70% sensitivity, 71% specificity) and task-based functional MRI (74% sensitivity, 77% specificity).

CONCLUSIONS

Our results demonstrate the high representational capacity of multivariate statistical methods to identify neuroimaging-based biomarkers of depression. Future studies are needed to elucidate whether multivariate neuroimaging analysis has the potential to generate clinically useful tools for the differential diagnosis of affective disorders and the prediction of both treatment response and functional outcome.

The impact of machine learning techniques in the study of bipolar disorder: A systematic review

Machine learning techniques provide new methods to predict diagnosis and clinical outcomes at an individual level. We aim to review the existing literature on the use of machine learning techniques in the assessment of subjects with bipolar disorder. We systematically searched PubMed, Embase and Web of Science for articles published in any language up to January 2017. We found 757 abstracts and included 51 studies in our review. Most of the included studies used multiple levels of biological data to distinguish the diagnosis of bipolar disorder from other psychiatric disorders or healthy controls. We also found studies that assessed the prediction of clinical outcomes and studies using unsupervised machine learning to build more consistent clinical phenotypes of bipolar disorder. We concluded that given the clinical heterogeneity of samples of patients with BD, machine learning techniques may provide clinicians and researchers with important insights in fields such as diagnosis, personalized treatment and prognosis orientation.

Subcortical volume and white matter integrity abnormalities in major depressive disorder: findings from UK Biobank imaging data

Previous reports of altered grey and white matter structure in Major Depressive Disorder (MDD) have been inconsistent. Recent meta-analyses have, however, reported reduced hippocampal grey matter volume in MDD and reduced white matter integrity in several brain regions. The use of different diagnostic criteria, scanners and imaging sequences may, however, obscure further anatomical differences. In this study, we tested for differences in subcortical grey matter volume (n = 1157) and white matter integrity (n = 1089) between depressed individuals and controls in the subset of 8590 UK Biobank Imaging study participants who had undergone depression assessments. Whilst we found no significant differences in subcortical volumes, significant reductions were found in depressed individuals versus controls in global white matter integrity, as measured by fractional anisotropy (FA) (β = −0.182, p = 0.005). We also found reductions in FA in association/commissural fibres (β = −0.184, p_corrected = 0.010) and thalamic radiations (β = −0.159, p_corrected = 0.020). Tract-specific FA reductions were also found in the left superior longitudinal fasciculus (β = −0.194, p_corrected = 0.025), superior thalamic radiation (β = −0.224, p_corrected = 0.009) and forceps major (β = −0.193, p_corrected = 0.025) in depression (all betas standardised). Our findings provide further evidence for disrupted white matter integrity in MDD.

Microstructural Abnormalities of Basal Ganglia and Thalamus in Bipolar and Unipolar Disorders: A Diffusion Kurtosis and Perfusion Imaging Study

OBJECTIVE

Bipolar disorder (BD) is often misdiagnosed as unipolar depression (UD), leading to mistreatment and poor clinical outcomes. However, little is known about the similarities and differences in subcorticalgray matter regions between BD and UD.

METHODS

Thirty-five BD patients, 30 UD patients and 40 healthy controls underwent diffusional kurtosis imaging (DKI) and three dimensional arterial spin labeling (3D ASL). The parameters including mean kurtosis (MK), axial kurtosis (Ka), radial kurtosis (Kr), fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (Da), radial diffusivity (Dr) and cerebral blood flow (CBF) were measured by using regions-of-interest analysis in the caudate, putamen and thalamus of the subcortical gray matter regions.

RESULTS

UD exhibited differences from controls for DKI measures and CBF in the left putamen and caudate. BD showed differences from controls for DKI measures in the left caudate. Additionally, BD showed lower Ka in right putamen, higher MD in right caudate compared with UD. Receiver operating characteristic analysis revealed the Kr of left caudate had the highest predictive power for distinguishing UD from controls.

CONCLUSION

The two disorders may have overlaps in microstructural abnormality in basal ganglia. The change of caudate may serve as a potential biomarker for UD.

Comparison of accuracy between FSL's FIRST and Freesurfer for caudate nucleus and putamen segmentation

Although several methods have been developed to automatically delineate subcortical gray matter structures from MR images, the accuracy of these algorithms has not been comprehensively examined. Most of earlier studies focused primarily on the hippocampus. Here, we assessed the accuracy of two widely used non-commercial programs (FSL-FIRST and Freesurfer) for segmenting the caudate and putamen. T1-weighted 1 mm³ isotropic resolution MR images were acquired for thirty healthy subjects (15 females). Caudate nucleus and putamen were segmented manually by two independent observers and automatically by FIRST and Freesurfer (v4.5 and v5.3). Utilizing manual labels as reference standard the following measures were studied: Dice coefficient (D), percentage volume difference (PVD), absolute volume difference as well as intraclass correlation coefficient (ICC) for consistency and absolute agreement. For putamen segmentation, FIRST achieved higher D, lower PVD and higher ICC for absolute agreement with manual tracing than either version of Freesurfer. Freesurfer overestimated the putamen, while FIRST was not statistically different from manual tracing. The ICC for consistency with manual tracing was similar between the two methods. For caudate segmentation, FIRST and Freesurfer performed more similarly. In conclusion, Freesurfer and FIRST are not equivalent when comparing to manual tracing. FIRST was superior for putaminal segmentation.