Intrinsic Functional Brain Connectivity Predicts Onset of Major Depression Disorder in Adolescence: A Pilot Study

Familial risk for depression moderates neural circuitry in healthy preadolescents to predict adolescent depression symptoms in the Adolescent Brain Cognitive Development (ABCD) Study

BACKGROUND

There is an imminent need to identify neural markers during preadolescence that are linked to developing depression during adolescence, especially among youth at elevated familial risk. However, longitudinal studies remain scarce and exhibit mixed findings. Here we aimed to elucidate functional connectivity (FC) patterns among preadolescents that interact with familial depression risk to predict depression two years later.

METHODS

9-10 year-olds in the Adolescent Brain Cognitive Development (ABCD) Study were classified as healthy (i.e., no lifetime psychiatric diagnoses) at high familial risk for depression (HR; n=559) or at low familial risk for psychopathology (LR; n=1203). Whole-brain seed-to-voxel resting-state FC patterns with the amygdala, putamen, nucleus accumbens, and caudate were calculated. Multi-level, mixed-effects regression analyses were conducted to test whether FC at ages 9-10 interacted with familial risk to predict depression symptoms at ages 11-12.

RESULTS

HR youth demonstrated stronger associations between preadolescent FC and adolescent depression symptoms (ps<0.001) as compared to LR youth (ps>0.001), primarily among amygdala/striatal FC with visual and sensory/somatomotor networks.

CONCLUSIONS

Preadolescent amygdala and striatal FC may be useful biomarkers of adolescent-onset depression, particularly for youth with family histories of depression. This research may point to neurobiologically-informed approaches to prevention and intervention for depression in adolescents.

Predicting depression risk in early adolescence via multimodal brain imaging

Depression is an incapacitating psychiatric disorder with increased risk through adolescence. Among other factors, children with family history of depression have significantly higher risk of developing depression. Early identification of pre-adolescent children who are at risk of depression is crucial for early intervention and prevention. In this study, we used a large longitudinal sample from the Adolescent Brain Cognitive Development (ABCD) Study (2658 participants after imaging quality control, between 9-10 years at baseline), we applied advanced machine learning methods to predict depression risk at the two-year follow-up from the baseline assessment, using a set of comprehensive multimodal neuroimaging features derived from structural MRI, diffusion tensor imaging, and task and rest functional MRI. Prediction performance underwent a rigorous cross-validation method of leave-one-site-out. Our results demonstrate that all brain features had prediction scores significantly better than expected by chance, with brain features from rest-fMRI showing the best classification performance in the high-risk group of participants with parental history of depression (N = 625). Specifically, rest-fMRI features, which came from functional connectomes, showed significantly better classification performance than other brain features. This finding highlights the key role of the interacting elements of the connectome in capturing more individual variability in psychopathology compared to measures of single brain regions. Our study contributes to the effort of identifying biological risks of depression in early adolescence in population-based samples.

Neural Circuit Markers of Familial Risk for Depression Among Healthy Youths in the Adolescent Brain Cognitive Development Study

BACKGROUND

Family history of depression is a robust predictor of early-onset depression, which may confer risk through alterations in neural circuits that have been implicated in reward and emotional processing. These alterations may be evident in youths who are at familial risk for depression but who do not currently have depression. However, the identification of robust and replicable findings has been hindered by few studies and small sample sizes. In the current study, we sought to identify functional connectivity (FC) patterns associated with familial risk for depression.

METHODS

Participants included healthy (i.e., no lifetime psychiatric diagnoses) youths at high familial risk for depression (HR) (n = 754; at least one parent with a history of depression) and healthy youths at low familial risk for psychiatric problems (LR) (n = 1745; no parental history of psychopathology) who were 9 to 10 years of age and from the Adolescent Brain Cognitive Development (ABCD) Study sample. We conducted whole-brain seed-to-voxel analyses to examine group differences in resting-state FC with the amygdala, caudate, nucleus accumbens, and putamen. We hypothesized that HR youths would exhibit global amygdala hyperconnectivity and striatal hypoconnectivity patterns primarily driven by maternal risk.

RESULTS

HR youths exhibited weaker caudate-angular gyrus FC than LR youths (α = 0.04, Cohen's d = 0.17). HR youths with a history of maternal depression specifically exhibited weaker caudate-angular gyrus FC (α = 0.03, Cohen's d = 0.19) as well as weaker caudate-dorsolateral prefrontal cortex FC (α = 0.04, Cohen's d = 0.21) than LR youths.

CONCLUSIONS

Weaker striatal connectivity may be related to heightened familial risk for depression, primarily driven by maternal history. Identifying brain-based markers of depression risk in youths can inform approaches to improving early detection, diagnosis, and treatment.

Conceptualizing psychological resilience through resting-state functional MRI in a mentally healthy population: a systematic review

Conceptualizations and operational definitions of psychological resilience vary across resilience neuroimaging studies. Data on the neural features of resilience among healthy individuals has been scarce. Furthermore, findings from resting-state functional magnetic resonance imaging (fMRI) studies were inconsistent across studies. This systematic review summarized resting-state fMRI findings in different modalities from various operationally defined resilience in a mentally healthy population. The PubMed and MEDLINE databases were searched. Articles that focused on resting-state fMRI in relation to resilience, and published before 2022, were targeted. Orbitofrontal cortex, anterior cingulate cortex, insula and amygdala, were reported the most from the 19 included studies. Regions in emotional network was reported the most from the included studies. The involvement of regions like amygdala and orbitofrontal cortex indicated the relationships between emotional processing and resilience. No common brain regions or neural pathways were identified across studies. The emotional network appears to be studied the most in association with resilience. Matching fMRI modalities and operational definitions of resilience across studies are essential for meta-analysis.

Associations with youth psychotic-like experiences over time: Evidence for trans-symptom and specific cognitive and neural risk factors

The current study examined whether impairments in cognitive and neural factors at baseline (ages 9-10) predict initial levels or changes in psychotic-like experiences (PLEs) and whether such impairments generalize to other psychopathology symptoms (i.e., internalizing and externalizing symptoms). Using unique longitudinal Adolescent Brain Cognitive Development Study data, the study examined three time points from ages 9 to 13. Univariate latent growth models examined associations between baseline cognitive and neural metrics with symptom measures using discovery (n = 5,926) and replication (n = 5,952) data sets. For symptom measures (i.e., PLEs, internalizing, externalizing), we examined mean initial levels (i.e., intercepts) and changes over time (i.e., slopes). Predictors included neuropsychological test performance, global structural MRI, and several a priori within-network resting-state functional connectivity metrics. Results showed a pattern whereby baseline cognitive and brain metric impairments showed the strongest associations with PLEs over time. Lower cognitive, volume, surface area, and cingulo-opercular within-network connectivity metrics showed associations with increased PLEs and higher initial levels of externalizing and internalizing symptoms. Several metrics were uniquely associated with PLEs, including lower cortical thickness with higher initial PLEs and lower default mode network connectivity with increased PLEs slopes. Neural and cognitive impairments in middle childhood were broadly associated with increased PLEs over time, and showed stronger associations with PLEs compared with other psychopathology symptoms. The current study also identified markers potentially uniquely associated with PLEs (e.g., cortical thickness). Impairments in broad cognitive metrics, brain volume and surface area, and a network associated with information integration may represent risk factors for general psychopathology. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

PREDICTING DEPRESSION RISK IN EARLY ADOLESCENCE VIA MULTIMODAL BRAIN IMAGING

Depression is an incapacitating psychiatric disorder with high prevalence in adolescent populations that is influenced by many risk factors, including family history of depression. The ability to predict who may develop depression before adolescence, when rates of depression increase markedly, is important for early intervention and prevention. Using a large longitudinal sample from the Adolescent Brain Cognitive Development (ABCD) Study (2658 participants after imaging quality control, between 9-10 years at baseline), we applied machine learning methods on a set of comprehensive multimodal neuroimaging features to predict depression risk at the two-year follow-up from the baseline visit. Features include derivatives from structural MRI, diffusion tensor imaging, and task and rest functional MRI. A rigorous cross-validation method of leave-one-site-out was used. Additionally, we tested the prediction models in a high-risk group of participants with parental history of depression (N=625). The results showed all brain features had prediction scores significantly better than expected by chance. When predicting depression onset in the high-risk group, brain features from resting-state functional connectomes showed the best classification performance, outperforming other brain features based on structural MRI and task-based fMRI. Results demonstrate that the functional connectivity of the brain can predict the risk of depression in early adolescence better than other univariate neuroimaging derivatives, highlighting the key role of the interacting elements of the connectome capturing more individual variability in psychopathology compared to measures of single brain regions.

Predicting Future Depressive Episodes from Resting-State fMRI with Generative Embedding

After a first episode of major depressive disorder (MDD), there is substantial risk for a long-term remitting-relapsing course. Prevention and early interventions are thus critically important. Various studies have examined the feasibility of detecting at-risk individuals based on out-of-sample predictions about the future occurrence of depression. However, functional magnetic resonance imaging (MRI) has received very little attention for this purpose so far. Here, we explored the utility of generative models (i.e. different dynamic causal models, DCMs) as well as functional connectivity (FC) for predicting future episodes of depression in never-depressed adults, using a large dataset (N=906) of task-free ("resting state") fMRI data from the UK Biobank. Connectivity analyses were conducted using timeseries from pre-computed spatially independent components of different dimensionalities. Over a three year period, 50% of participants showed indications of at least one depressive episode, while the other 50% did not. Using nested cross-validation for training and a held-out test set (80/20 split), we systematically examined the combination of 8 connectivity feature sets and 17 classifiers. We found that a generative embedding procedure based on combining regression DCM (rDCM) with a support vector machine (SVM) enabled the best predictions, both on the training set (0.63 accuracy, 0.66 area under the curve, AUC) and the test set (0.62 accuracy, 0.64 AUC; p<0.001). However, on the test set, rDCM was only slightly superior to predictions based on FC (0.59 accuracy, 0.61 AUC). Interpreting model predictions based on SHAP (SHapley Additive exPlanations) values suggested that the most predictive connections were widely distributed and not confined to specific networks. Overall, our analyses suggest (i) ways of improving future fMRI-based generative embedding approaches for the early detection of individuals at-risk for depression and that (ii) achieving accuracies of clinical utility may require combination of fMRI with other data modalities.

Decreased functional connectivity in patients with major depressive disorder and a history of childhood traumatization through experiences of abuse

BACKGROUND

Childhood trauma (CT) increases vulnerability for the development of major depressive disorder (MDD). Alterations in resting-state functional connectivity (RSFC) have frequently been reported for MDD. These alterations may be much more prominent in depressive patients with a history of CT. The present study aims to compare RSFC in different brain networks of patients with MDD and CT (MDD+CT) vs. MDD and no CT compared to healthy controls.

METHODS

45 patients (22 with CT) were compared to 23 age-and-gender-matched healthy control subjects. Demographic parameters, severity of MDD, severity of CT and comorbid anxiety disorders were assessed. For assessment of RSFC alterations, a seed-based approach within five well-established RSFC networks was used.

RESULTS

CT in MDD patients predicts severity of comorbid anxiety. A significant decrease in in-between network RSFC-values of MDD patients compared to controls was found in the network pairs of default mode network (DMN) - dorsal attention network (DAN), ventral attention network (VAN) - DMN and DAN - affective network (AN). MDD+CT patients presented more aberrant RSFC than MDD-CT patients. MDD scores predicted the decrease in RSFC for MDD patients. Higher Childhood Trauma Questionnaire (CTQ) scores are linked to reduced functional connectivity (FC) between DMN - DAN.

CONCLUSIONS

Our study shows reduced RSFC in MDD patients for DMN - DAN, VAN - DMN, DAN - AN and MDD+CT patients presented more aberrant RSFC so that we suspect CT to be a considerable factor in the etiology of MDD. Through dysregulated neural circuits, CT is likely to contribute to a distinct MDD pathophysiology.

The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network

Introduction

The early diagnosis of major depressive disorder (MDD) is very important for patients that suffer from severe and irreversible consequences of depression. It has been indicated that functional connectivity (FC) analysis based on functional magnetic resonance imaging (fMRI) data can provide valuable biomarkers for clinical diagnosis. However, previous studies mainly focus on brain disease classification in small sample sizes, which may lead to dramatic divergences in classification accuracy.

Methods

This paper attempts to address this limitation by applying the deep graph convolutional neural network (DGCNN) method on a large multi-site MDD dataset. The resting-state fMRI data are acquired from 830 MDD patients and 771 normal controls (NC) shared by the REST-meta-MDD consortium.

Results

The DGCNN model trained with the binary network after thresholding, identified MDD patients from normal controls and achieved an accuracy of 72.1% with 10-fold cross-validation, which is 12.4%, 9.8%, and 7.6% higher than SVM, RF, and GCN, respectively. Moreover, the process of dataset reading and model training is faster. Therefore, it demonstrates the advantages of the DGCNN model with low time complexity and sound classification performance.

Discussion

Based on a large, multi-site dataset from MDD patients, the results expressed that DGCNN is not an extremely accurate method for MDD diagnosis. However, there is an improvement over previous methods with our goal of better understanding brain function and ultimately providing a biomarker or diagnostic capability for MDD diagnosis.

Can machine learning identify childhood characteristics that predict future development of bipolar disorder a decade later?

Early identification of bipolar disorder may provide appropriate support and treatment, however there is no current evidence for statistically predicting whether a child will develop bipolar disorder. Machine learning methods offer an opportunity for developing empirically-based predictors of bipolar disorder. This study examined whether bipolar disorder can be predicted using clinical data and machine learning algorithms. 492 children, ages 6-18 at baseline, were recruited from longitudinal case-control family studies. Participants were assessed at baseline, then followed-up after 10 years. In addition to sociodemographic data, children were assessed with psychometric scales, structured diagnostic interviews, and cognitive and social functioning assessments. Using the Balanced Random Forest algorithm, we examined whether the diagnostic outcome of full or subsyndromal bipolar disorder could be predicted from baseline data. 45 children (10%) developed bipolar disorder at follow-up. The model predicted subsequent bipolar disorder with 75% sensitivity, 76% specificity, and an Area Under the Receiver Operating Characteristics of 75%. Predictors best differentiating between children who did or did not develop bipolar disorder were the Child Behavioral Checklist Externalizing and Internalizing behaviors, the Child Behavioral Checklist Total t-score, problematic school functions indexed through the Child Behavioral Checklist School Competence scale, and the Child Behavioral Checklist Anxiety/Depression and Aggression scales. Our study provides the first quantitative model to predict bipolar disorder. Longitudinal prediction may help clinicians assess children with emergent psychopathology for future risk of bipolar disorder, an area of clinical and scientific importance. Machine learning algorithms could be implemented to alert clinicians to risk for bipolar disorder.

Structural and Functional Brain Alterations in Populations with Familial Risk for Depression: A Narrative Review

LEARNING OBJECTIVES

After completing this activity, practitioners will be better able to:• Discuss the association between brain alterations and vulnerability or resilience to MDD in people with familial risk• Define how structural and functional brain alterations associated with vulnerability or resilience could lead to a better understanding of the pathophysiology of MDD.

AIM

Familial history is associated with an increased risk for major depressive disorder (MDD). Despite the increased risk, some members of the familial high-risk population remain healthy, that is, resilient. Defining the structural and functional brain alterations associated with vulnerability or resilience could lead to a better understanding of the pathophysiology of MDD. This study aimed to review the current literature and discuss the association between brain alterations and vulnerability or resilience to MDD in people with familial risk.

METHODS

A literature search on MRI studies investigating structural and functional alterations in populations at familial risk for MDD was performed using the PubMed and SCOPUS databases. The search was conducted through June 13, 2022.

RESULTS

We reviewed and summarized the data of 72 articles (25 structural MRI, 35 functional MRI, 10 resting-state fMRI, one structural/functional MRI combined, and one structural/functional/resting-state fMRI combined). These findings suggested that resilience in high-risk individuals is related to the amygdala structure, frontal lobe activity, and functional connectivity between the amygdala and multiple frontal regions.

CONCLUSION

Resilient and vulnerable individuals exhibit structural and functional differences in multiple frontal and limbic regions. However, further systematic longitudinal research incorporating environmental factors is required to validate the current findings.

Neural markers of familial risk for depression - A systematic review

Structural and functional brain alterations are found in adults with depression. It is not known whether these changes are a result of illness or exist prior to disorder onset. Asymptomatic offspring of parents with depression offer a unique opportunity to research neural markers of familial risk to depression and clarify the temporal sequence between brain changes and disorder onset. We conducted a systematic review to investigate whether asymptomatic offspring at high familial risk have structural and functional brain changes like those reported in adults with depression. Our literature search resulted in 44 studies on 18,645 offspring ranging from 4 weeks to 25 years old. Reduced cortical thickness and white matter integrity, and altered striatal reward processing were the most consistent findings in high-risk offspring across ages. These alterations are also present in adults with depression, suggesting the existence of neural markers of familial risk for depression. Additional studies reproducing current results, streamlining fMRI data analyses, and investigating underexplored topics (i.e intracortical myelin, gyrification, subcortical shape) may be among the next steps required to improve our understanding of neural markers indexing the vulnerability to depression.

Adolescent depression and resting-state fMRI brain networks: a scoping review of longitudinal studies

The neurobiological factors associated with the emergence of major depressive disorder (MDD) in adolescence are still unclear. Previous cross-sectional studies have documented aberrant connectivity in resting-state functional magnetic resonance imaging (rs-fMRI) networks. However, whether these findings precede MDD onset has not been established. This scoping review mapped key methodological aspects and main findings of longitudinal rs-fMRI studies of MDD in adolescence. Three sets of neuroimaging methods to analyze rs-fMRI data were identified: seed-based analysis, independent component analysis, and network-based approaches. Main findings involved aberrant connectivity within and between the default mode network (DMN), the cognitive control network (CCN), and the salience network (SN). Accordingly, we utilized Menon's (2011) triple-network model for neuropsychiatric disorders to summarize key results. Adolescent MDD was associated with hyperconnectivity within the SN and between DMN and SN, as well as hypoconectivity within the CCN. These findings suggested that dysfunctional connectivity among the three main large-scale brain networks preceded MDD onset. However, there was high heterogeneity in neuroimaging methods and sampling procedures, which may limit comparisons between studies. Future studies should consider some level of harmonization for clinical instruments and neuroimaging methods.

C-reactive protein is related to a distinct set of alterations in resting-state functional connectivity contributing to a differential pathophysiology of major depressive disorder

BACKGROUND

Several studies in major depressive disorder (MDD) have found inflammation, especially C-reactive protein (CRP), to be consistently associated with MDD and network dysfunction. The aim was to investigate whether CRP is linked to a distinct set of resting-state functional connectivity (RSFC) alterations.

METHODS

For this reason, we investigated the effects of diagnosis and elevated blood plasma CRP levels on the RSFC in 63 participants (40 females, mean age 31.4 years) of which were 27 patients with a primary diagnosis of MDD and 36 healthy control-subjects (HC), utilizing a seed-based approach within five well-established RSFC networks obtained using fMRI.

RESULTS

Of the ten network pairs examined, five showed increased between-network RSFC-values unambiguously connected either to a diagnosis of MDD or elevated CRP levels. For elevated CRP levels, increased RSFC between DMN and AN was found. Patients showed increased RSFC within DMN areas and between the DMN and ECN and VAN, ECN and AN and AN and DAN.

CONCLUSIONS

The results of this study show dysregulated neural circuits specifically connected to elevated plasma CRP levels and independent of other alterations of RSFC in MDD. This dysfunction in neural circuits might in turn result in a certain immune-inflammatory subtype of MDD.

Neural connectivity biotypes: associations with internalizing problems throughout adolescence

BACKGROUND

Neurophysiological patterns may distinguish which youth are at risk for the well-documented increase in internalizing symptoms during adolescence. Adolescents with internalizing problems exhibit altered resting-state functional connectivity (RSFC) of brain regions involved in socio-affective processing. Whether connectivity-based biotypes differentiate adolescents' levels of internalizing problems remains unknown.

METHOD

Sixty-eight adolescents (37 females) reported on their internalizing problems at ages 14, 16, and 18 years. A resting-state functional neuroimaging scan was collected at age 16. Time-series data of 15 internalizing-relevant brain regions were entered into the Subgroup-Group Iterative Multi-Model Estimation program to identify subgroups based on RSFC maps. Associations between internalizing problems and connectivity-based biotypes were tested with regression analyses.

RESULTS

Two connectivity-based biotypes were found: a Diffusely-connected biotype (N = 46), with long-range fronto-parietal paths, and a Hyper-connected biotype (N = 22), with paths between subcortical and medial frontal areas (e.g. affective and default-mode network regions). Higher levels of past (age 14) internalizing problems predicted a greater likelihood of belonging to the Hyper-connected biotype at age 16. The Hyper-connected biotype showed higher levels of concurrent problems (age 16) and future (age 18) internalizing problems.

CONCLUSIONS

Differential patterns of RSFC among socio-affective brain regions were predicted by earlier internalizing problems and predicted future internalizing problems in adolescence. Measuring connectivity-based biotypes in adolescence may offer insight into which youth face an elevated risk for internalizing disorders during this critical developmental period.

No associations in preregistered study of youth depression and functional connectivity of fronto-parietal and default mode networks

Adolescence is characterized by vulnerability to the onset of major depressive disorder (MDD). The goal of this preregistered study was to assess neural correlates of depression symptoms in young adolescents, both cross-sectionally and longitudinally. The default mode network (DMN) is believed to support internal attention towards self-referential thoughts, while the fronto-parietal network (FPN) is theorized to support cognitive control and regulation of attention. As MDD diagnosis has been associated with heightened connectivity within DMN regions and diminished connectivity within FPN regions relative to healthy controls, our study builds upon group-difference analyses by using dimensional measures of depression severity. Our preregistered hypotheses were that within-DMN functional connectivity would be positively associated with concurrent depression severity, while within-FPN functional connectivity would be negatively associated with concurrent depression severity. Preregistered analyses also examined between DMN-FPN connectivity as an alternative predictor variable, and assessed the longitudinal associations between all three functional connectivity measures and change in depression severity over three subsequent waves. Multiple regression models tested cross-sectional analyses and hierarchical linear models tested longitudinal analyses. One hundred and twenty-four youth completed a resting state functional MRI. Their depression severity was assessed at the time of the scan and at three follow-up sessions. None of the predictor variables were associated with concurrent depression severity, nor with the slope of depression symptom trajectories in longitudinal analyses. These negative results add to extant cross-sectional studies, and may inform future investigations of brain correlates of depression psychopathology in youth.

Contributions from resting state functional connectivity and familial risk to early adolescent-onset MDD: Results from the Adolescent Brain Cognitive Development study

BACKGROUND

Family history of Major Depressive Disorder (MDD) is a robust predictor of MDD onset, especially in early adolescence. We examined the relationships between familial risk for depression and alterations to resting state functional connectivity (rsFC) within the default mode network (wDMN) and between the DMN and the left/right hippocampus (DMN-LHIPP/DMN-RHIPP) to the risk for early adolescent MDD onset.

METHODS

We examined 9403 youth aged nine to eleven from the Adolescent Brain Cognitive Development study. Depressive symptoms were measured with the parent-reported Child Behavior Checklist. Both youth and their parents completed the Kiddie Schedule for Affective Disorders and Schizophrenia, which provided MDD diagnoses. A family history screen was administered to determine familial risk for depression. Youth underwent a resting state functional magnetic resonance imaging scan, providing us with rsFC data.

RESULTS

Negative wDMN rsFC was associated with child-reported current depression, both child- and parent-reported past depression, and parent-reported current depressive symptoms. No difference was found in wDMN, DMN-LHIPP or DMN-RHIPP rsFC in children with or without familial risk for depression. Familial risk for depression interacted with wDMN rsFC in association with child-reported past MDD diagnosis and parent-reported current depressive symptoms.

LIMITATIONS

Information such as length of depressive episodes and age of onset of depression was not collected.

CONCLUSIONS

Altered wDMN rsFC in youth at familial risk for depression may be associated with increased risk for MDD onset in adolescence, but longitudinal studies are needed to test this hypothesis.

Neuroimaging markers of adolescent depression in the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) study

BACKGROUND

Adolescents are at increased risk of developing major depressive disorder (MDD) than many other age groups. Although the neural correlates of MDD in adults have been studied prospectively, such adolescent depression studies are mainly cross-sectional. We extracted data regarding the relationship between cortical thickness and later development of adolescent MDD from a national community study that uses an accelerated longitudinal design to examine the psychological, environmental, and neural differences related to drinking and brain development.

METHODS

692 subjects (age 12-21 years; 50% female) without a history of MDD were assessed with structural neuroimaging at baseline. We compared those 101 subjects who transitioned to MDD by 1-year follow-up to those who remained non-depressed over the same time period. FreeSurfer's autosegmentation process estimated vertex-wide cortical thicknesses and its Query, Design, Estimate, Contrast (Qdec) application investigated cortical thickness between those who later developed MDD and those who remained without MDD (Monte Carlo corrected for multiple comparisons, vertex-wise cluster threshold of 1.3, p < 0.01).

RESULTS

Those who transitioned in the next year to MDD had, at baseline, thinner cortices in the superior frontal cortex, precentral and postcentral regions, and superior temporal cortex, above and beyond effects attributable to age and sex. No cortical thickness sex differences or sex-by-depression interactions were observed.

LIMITATIONS

A larger sample size could improve statistical power and future investigations will be needed to confirm our results.

CONCLUSIONS

Thinner cortices over frontal and temporal regions may be linked to enhanced vulnerability for future depression during the adolescent-young adulthood transition.

Translational application of neuroimaging in major depressive disorder: a review of psychoradiological studies

Major depressive disorder (MDD) causes great decrements in health and quality of life with increments in healthcare costs, but the causes and pathogenesis of depression remain largely unknown, which greatly prevent its early detection and effective treatment. With the advancement of neuroimaging approaches, numerous functional and structural alterations in the brain have been detected in MDD and more recently attempts have been made to apply these findings to clinical practice. In this review, we provide an updated summary of the progress in translational application of psychoradiological findings in MDD with a specified focus on potential clinical usage. The foreseeable clinical applications for different MRI modalities were introduced according to their role in disorder classification, subtyping, and prediction. While evidence of cerebral structural and functional changes associated with MDD classification and subtyping was heterogeneous and/or sparse, the ACC and hippocampus have been consistently suggested to be important biomarkers in predicting treatment selection and treatment response. These findings underlined the potential utility of brain biomarkers for clinical practice.

Functional neuroimaging biomarkers of resilience in major depressive disorder

PURPOSE OF REVIEW

In this review we provide an overview of definitions and determinants of resilience in the context of neuroimaging research in major depressive disorder (MDD). We summarize emerging literature on functional neuroimaging biomarkers of resilience in MDD and discuss their clinical relevance and implications for future research.

RECENT FINDINGS

Resilience in MDD is characterized by dissociable profiles of activation and functional connectivity within brain networks involved in cognitive control, emotion regulation, and reward processing. Increased activation of frontal cortical brain regions implicated in cognitive appraisal and emotion regulation is a common characteristic of resilient individuals at high risk for MDD and of individuals with MDD with a favorable illness course. Furthermore, significant associations between fronto-striato-limbic functional connectivity and both positively interpreted stressful life events in resilient high-risk individuals and a favorable response to first-line treatments in depressed individuals suggest that neuro-compensatory changes and experience-dependent plasticity underlie resilience in MDD.

SUMMARY

Emerging research has identified functional neuroimaging biomarkers of resilience in MDD. A continued focus on identifying neurobiological underpinnings of resilience, in the context of dynamic environmental and developmental influences, will advance our understanding of resilience and improve approaches to prevention and treatment of MDD.

The Application of a Machine Learning-Based Brain Magnetic Resonance Imaging Approach in Major Depression

Major depressive disorder (MDD) shows a high prevalence and is associated with increased disability. While traditional studies aimed to investigate global characteristic neurobiological substrates of MDD, machine learning-based approaches focus on individual people rather than a group. Therefore, machine learning has been increasingly conducted and applied to clinical practice. Several previous neuroimaging studies used machine learning for stratifying MDD patients from healthy controls as well as in differentially diagnosing MDD apart from other psychiatric disorders. Also, machine learning has been used to predict treatment response using magnetic resonance imaging (MRI) results. Despite the recent accomplishments of machine learning-based MRI studies, small sample sizes and the heterogeneity of the depression group limit the generalizability of a machine learning-based predictive model. Future neuroimaging studies should integrate various materials such as genetic, peripheral, and clinical phenotypes for more accurate predictability of diagnosis and treatment response.

The alteration of cognitive function networks in remitted patients with major depressive disorder: an independent component analysis

INTRODUCTION

Dysfunctional connectivity of resting-state functional networks has been observed in patients with major depressive disorder (MDD), particularly in cognitive function networks including the central executive network (CEN), default mode network (DMN) and salience network (SN). Findings from studies examining how aberrant functional connectivity (FC) changed after antidepressant treatment, however, have been inconsistent. Thus, the purpose of the present study was to explore potential mechanisms of altered cognitive function networks during resting-state between remitted major depressive disorder (rMDD) patients and healthy controls (HCs) and furthermore, the relationship between dysfunctional connectivity patterns in rMDD and clinical symptoms.

METHODOLOGY

In this study, 19 HCs and 19 rMDD patients were recruited for resting-state functional magnetic resonance imaging (fMRI) scanning. FC was evaluated with independent component analysis for CEN, DMN and SN. Two sample t tests were conducted to compare differences between rMDD and HCs. A Pearson correlation analysis was also performed to examine the relationship between connectivity of networks and cognitive function scores and clinical symptoms.

RESULTS

Compared to healthy controls, remitted patients showed lower connectivity in CEN, mostly in the superior frontal gyrus (SFG), middle frontal gyrus (MFG), inferior parietal lobule (IPL) and part of the supramarginal gyrus (SMG). Conversely, the bilateral insula, part of the SMG (a key node of the CEN) and dorsal anterior cingulate cortex (dACC) of the DMN showed higher connectivity in rMDD patients. Pearson correlation results demonstrated that connectivity of the right IPL in CEN was positively correlated with cognitive function scores, and connectivity of the left insula was negatively correlated with BDI scores.

CONCLUSIONS

Though rMDD patients reached the standard of clinal remission, unique impairments of FC in cognitive function networks remained. Aberrant FC between cognitive function networks responsible for executive control was observed in rMDD and may be associated with residual clinical symptoms.

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.

Balancing act: Neural correlates of affect dysregulation in youth depression and substance use - A systematic review of functional neuroimaging studies

Both depression and substance use problems have their highest incidence during youth (i.e., adolescence and emerging adulthood), and are characterized by emotion regulation deficits. Influential neurodevelopmental theories suggest that alterations in the function of limbic and frontal regions render youth susceptible to these deficits. However, whether depression and substance use in youth are associated with similar alterations in emotion regulation neural circuitry is unknown. In this systematic review we synthesized the results of functional magnetic resonance imaging (fMRI) studies investigating the neural correlates of emotion regulation in youth depression and substance use. Resting-state fMRI studies focusing on limbic connectivity were also reviewed. While findings were largely inconsistent within and between studies of depression and substance use, some patterns emerged. First, youth depression appears to be associated with exaggerated amygdala activity in response to negative stimuli; second, both depression and substance use appear to be associated with lower functional connectivity between the amygdala and prefrontal cortex during rest. Findings are discussed in relation to support for existing neurodevelopmental models, and avenues for future work are suggested, including studying neurodevelopmental trajectories from a network perspective.

Neuroplasticity in cognitive and psychological mechanisms of depression: an integrative model

Chronic stress and depressive-like behaviors in basic neuroscience research have been associated with impairments of neuroplasticity, such as neuronal atrophy and synaptic loss in the medial prefrontal cortex (mPFC) and hippocampus. The current review presents a novel integrative model of neuroplasticity as a multi-domain neurobiological, cognitive, and psychological construct relevant in depression and other related disorders of negative affect (e.g., anxiety). We delineate a working conceptual model in which synaptic plasticity deficits described in animal models are integrated and conceptually linked with human patient findings from cognitive science and clinical psychology. We review relevant reports including neuroimaging findings (e.g., decreased functional connectivity in prefrontal-limbic circuits), cognitive deficits (e.g., executive function and memory impairments), affective information processing patterns (e.g., rigid, negative biases in attention, memory, interpretations, and self-associations), and patient-reported symptoms (perseverative, inflexible thought patterns; inflexible and maladaptive behaviors). Finally, we incorporate discussion of integrative research methods capable of building additional direct empirical support, including using rapid-acting treatments (e.g., ketamine) as a means to test this integrative model by attempting to simultaneously reverse these deficits across levels of analysis.