Unveiling convergent and divergent intrinsic brain network alternations in depressed adolescents engaged in non-suicidal self-injurious behaviors with and without suicide attempts.

AIMS: Limited understanding exists regarding the neurobiological mechanisms underlying non-suicidal self-injury (NSSI) and suicide attempts (SA) in depressed adolescents. The maturation of brain network is crucial during adolescence, yet the abnormal alternations in depressed adolescents with NSSI or NSSI+SA remain poorly understood. METHODS: Resting-state functional magnetic resonance imaging data were collected from 114 depressed adolescents, classified into three groups: clinical control (non-self-harm), NSSI only, and NSSI+SA based on self-harm history. The alternations of resting-state functional connectivity (RSFC) were identified through support vector machine-based classification. RESULTS: Convergent alterations in NSSI and NSSI+SA predominantly centered on the inter-network RSFC between the Limbic network and the three core neurocognitive networks (SalVAttn, Control, and Default networks). Divergent alterations in the NSSI+SA group primarily focused on the Visual, Limbic, and Subcortical networks. Additionally, the severity of depressive symptoms only showed a significant correlation with altered RSFCs between Limbic and DorsAttn or Visual networks, strengthening the fact that increased depression severity alone does not fully explain observed FC alternations in the NSSI+SA group. CONCLUSION: Convergent alterations suggest a shared neurobiological mechanism along the self-destructiveness continuum. Divergent alterations may indicate biomarkers differentiating risk for SA, informing neurobiologically guided interventions.

Structural and functional brain alterations in subthreshold depression: A multimodal coordinate-based meta-analysis.

Imaging studies of subthreshold depression (StD) have reported structural and functional abnormalities in a variety of spatially diverse brain regions. However, there is no consensus among different studies. In the present study, we applied a multimodal meta-analytic approach, the Activation Likelihood Estimation (ALE), to test the hypothesis that StD exhibits spatially convergent structural and functional brain abnormalities compared to healthy controls. A total of 31 articles with 25 experiments were included, collectively representing 1001 subjects with StD. We found consistent differences between StD and healthy controls mainly in the left insula across studies with various neuroimaging methods. Further exploratory analyses found structural atrophy and decreased functional activities in the right pallidum and thalamus in StD, and abnormal spontaneous activity converged to the middle frontal gyrus. Coordinate-based meta-analysis found spatially convergent structural and functional impairments in StD. These findings provide novel insights for understanding the neural underpinnings of subthreshold depression and enlighten the potential targets for its early screening and therapeutic interventions in the future.

Individualized prediction of anxiety and depressive symptoms using gray matter volume in a non-clinical population.

Machine learning is an emerging tool in clinical psychology and neuroscience for the individualized prediction of psychiatric symptoms. However, its application in non-clinical populations is still in its infancy. Given the widespread morphological changes observed in psychiatric disorders, our study applies five supervised machine learning regression algorithms-ridge regression, support vector regression, partial least squares regression, least absolute shrinkage and selection operator regression, and Elastic-Net regression-to predict anxiety and depressive symptom scores. We base these predictions on the whole-brain gray matter volume in a large non-clinical sample (n = 425). Our results demonstrate that machine learning algorithms can effectively predict individual variability in anxiety and depressive symptoms, as measured by the Mood and Anxiety Symptoms Questionnaire. The most discriminative features contributing to the prediction models were primarily located in the prefrontal-parietal, temporal, visual, and sub-cortical regions (e.g. amygdala, hippocampus, and putamen). These regions showed distinct patterns for anxious arousal and high positive affect in three of the five models (partial least squares regression, support vector regression, and ridge regression). Importantly, these predictions were consistent across genders and robust to demographic variability (e.g. age, parental education, etc.). Our findings offer critical insights into the distinct brain morphological patterns underlying specific components of anxiety and depressive symptoms, supporting the existing tripartite theory from a neuroimaging perspective.

Low Functional network integrity in cognitively unimpaired and MCI subjects with depressive symptoms: results from a multi-center fMRI study.

Evidence suggests that depressive symptomatology is a consequence of network dysfunction rather than lesion pathology. We studied whole-brain functional connectivity using a Minimum Spanning Tree as a graph-theoretical approach. Furthermore, we examined functional connectivity in the Default Mode Network, the Frontolimbic Network (FLN), the Salience Network, and the Cognitive Control Network. All 183 elderly subjects underwent a comprehensive neuropsychological evaluation and a 3 Tesla brain MRI scan. To assess the potential presence of depressive symptoms, the 13-item version of the Beck Depression Inventory (BDI) or the Geriatric Depression Scale (GDS) was utilized. Participants were assigned into three groups based on their cognitive status: amnestic mild cognitive impairment (MCI), non-amnestic MCI, and healthy controls. Regarding affective symptoms, subjects were categorized into depressed and non-depressed groups. An increased mean eccentricity and network diameter were found in patients with depressive symptoms relative to non-depressed ones, and both measures showed correlations with depressive symptom severity. In patients with depressive symptoms, a functional hypoconnectivity was detected between the Anterior Cingulate Cortex (ACC) and the right amygdala in the FLN, which impairment correlated with depressive symptom severity. While no structural difference was found in subjects with depressive symptoms, the volume of the hippocampus and the thickness of the precuneus and the entorhinal cortex were decreased in subjects with MCI, especially in amnestic MCI. The increase in eccentricity and diameter indicates a more path-like functional network configuration that may lead to an impaired functional integration in depression, a possible cause of depressive symptomatology in the elderly.

Structural characteristics of amygdala subregions in type 2 diabetes mellitus.

Type 2 diabetes mellitus (T2DM) patients often suffer from depressive symptoms, which seriously affect cooperation in treatment and nursing. The amygdala plays a significant role in depression. This study aims to explore the microstructural alterations of the amygdala in T2DM and to investigate the relationship between the alterations and depressive symptoms. Fifty T2DM and 50 healthy controls were included. Firstly, the volumes of subcortical regions and subregions of amygdala were calculated by FreeSurfer. Covariance analysis (ANCOVA) was conducted between the two groups with covariates of age, sex, and estimated total intracranial volume to explore the differences in volume of subcortical regions and subregions of amygdala. Furthermore, the structural covariance within the amygdala subregions was performed. Moreover, we investigate the correlation between depressive symptoms and the volume of subcortical regions and amygdala subregions in T2DM. We observed a reduction in the volume of the bilateral cortico-amygdaloid transition area, left basal nucleus, bilateral accessory basal nucleus, left anterior amygdaloid area of amygdala, the left thalamus and left hippocampus in T2DM. T2DM patients showed decreased structural covariance connectivity between left paralaminar nucleus and the right central nucleus. Moreover, there was a negative correlation between self-rating depression scale scores and the volume of the bilateral cortico-amygdaloid transition area in T2DM. This study reveals extensive structural alterations in the amygdala subregions of T2DM patients. The reduction in the volume of the bilateral cortico-amygdaloid transition area may be a promising imaging marker for early recognition of depressive symptoms in T2DM.

Distinct global brain connectivity alterations in depressed adolescents with subthreshold mania and the relationship with processing speed: Evidence from sBEAD Cohort.

BACKGROUND: Bipolar disorder (BD) is a progressive condition. Investigating the neuroimaging mechanisms in depressed adolescents with subthreshold mania (SubMD) facilitates the early identification of BD. However, the global brain connectivity (GBC) patterns in SubMD patients, as well as the relationship with processing speed before the onset of full-blown BD, remain unclear. METHODS: The study involved 72 SubMD, 77 depressed adolescents without subthreshold mania (nSubMD), and 69 gender- and age-matched healthy adolescents (HCs). All patients underwent a clinical follow-up ranging from six to twelve months. We calculated the voxel-based graph theory analysis of the GBC map and conducted the TMT-A test to measure the processing speed. RESULTS: Compared to HCs and nSubMD, SubMD patients displayed distinctive GBC index patterns: GBC index decreased in the right Medial Superior Frontal Gyrus (SFGmed.R)/Superior Frontal Gyrus (SFG) while increased in the right Precuneus and left Postcentral Gyrus. Both patient groups showed increased GBC index in the right Inferior Temporal Gyrus. An increased GBC value in the right Supplementary Motor Area was exclusively observed in the nSubMD-group. There were opposite changes in the GBC index in SFGmed.R/SFG between two patient groups, with an AUC of 0.727. Additionally, GBC values in SFGmed.R/SFG exhibited a positive correlation with TMT-A scores in SubMD-group. LIMITATIONS: Relatively shorter follow-up duration, medications confounding, and modest sample size. CONCLUSION: These findings suggest that adolescents with subthreshold BD have specific impairments patterns at the whole brain connectivity level associated with processing speed impairments, providing insights into early identification and intervention strategies for BD.

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.

Altered functional-structural coupling may predict Parkinson's patient's depression.

We aimed to elucidate the neurobiological basis of depression in Parkinson's disease and identify potential imaging markers for depression in patients with Parkinson's disease. We recruited 43 normal controls (NC), 46 depressed Parkinson's disease patients (DPD) and 56 non-depressed Parkinson's disease (NDPD). All participants underwent routine T2-weighted, T2Flair, and resting-state scans on the same 3.0 T magnetic resonance imaging (MRI) scanner at our hospital. Pre-processing includes calculating surface-based Regional Homogeneity (2DReHo) and cortical thickness. Then we defined the correlation coefficient between 2DReHo and cortical thickness as the functional-structural coupling index. Between-group comparisons were conducted on the Fisher's Z-transformed correlation coefficients. To identify specific regions of decoupling, the 2DReHo for each participant were divided by cortical thickness at each vertex, followed by threshold-free cluster enhancement (TFCE) multiple comparison correction. Binary logistic regression analysis was performed with DPD as the dependent variable, and significantly altered indicators as the independent variables. Receiver operating characteristic curves were constructed to compare the diagnostic performance of individual predictors and combinations using R and MedCalc software. DPD patients exhibited a significantly lower whole-brain functional-structural coupling index than NDPD patients and NC. Abnormal functional-structural coupling was primarily observed in the left inferior parietal lobule and right primary and early visual cortices in DPD patients. Receiver operating characteristic analysis revealed that the combination of cortical functional-structural coupling, surface-based ReHo, and thickness had the best diagnostic performance, achieving a sensitivity of 65% and specificity of 77.7%. This is the first study to explore the relationship between functional and structural changes in DPD patients and evaluate the diagnostic performance of these altered correlations to predict depression in Parkinson's disease patients. We posit that these changes in functional-structural relationships may serve as imaging biomarkers for depression in Parkinson's disease patients, potentially aiding in the classification and diagnosis of Parkinson's disease. Additionally, our findings provide functional and structural imaging evidence for exploring the neurobiological basis of depression in Parkinson's disease.

Lower cerebrovascular reactivity in prefrontal cortex and weaker negative functional connectivity between prefrontal cortex and insula contribute to white matter hyperintensity-related anxiety or depression.

BACKGROUND: White matter hyperintensities (WMHs) are associated with higher anxiety or depression (A/D) incidence. We investigated associations of WMHs with A/D, cerebrovascular reactivity (CVR), and functional connectivity (FC) to identify potential pathomechanisms. METHODS: Participants with WMH (n = 239) and normal controls (NCs, n = 327) were assessed for A/D using the Hamilton Anxiety Rating Scale (HAMA) and Hamilton Depression Rating Scale (HAMD). The CVR and FC maps were constructed from resting-state functional MRI. Two-way analysis of covariance with fixed factors A/D and WMH was performed to identify regional CVR abnormalities. Seed-based FC analyses were then conducted on regions with WMH × A/D interaction effects on CVR. Logistic regression models were constructed to examine the utility of these measurements for identifying WMH-related A/D. RESULTS: Participants with WMH related A/D exhibited significantly greater CVR in left insula and lower CVR in right superior frontal gyrus (SFG.R), and HAMA scores were negatively correlated with CVR in SFG.R (r = -0.156, P = 0.016). Insula-SFG.R negative FC was significantly weaker in WMH patients with suspected or definite A/D. A model including CVR plus FC changes identified WMH-associated A/D with highest sensitivity and specificity. In contrast, NCs with A/D exhibited greater CVR in prefrontal cortex and stronger FC within the default mode network (DMN) and between the DMN and executive control network. LIMITATIONS: This cross-sectional study requires validation by longitudinal and laboratory studies. CONCLUSIONS: Impaired CVR in SFG.R and weaker negative FC between prefrontal cortex and insula may contribute to WMH-related A/D, providing potential diagnostic imaging markers and therapeutic targets.

Hybrid representation learning for cognitive diagnosis in late-life depression over 5 years with structural MRI.

Late-life depression (LLD) is a highly prevalent mood disorder occurring in older adults and is frequently accompanied by cognitive impairment (CI). Studies have shown that LLD may increase the risk of Alzheimer's disease (AD). However, the heterogeneity of presentation of geriatric depression suggests that multiple biological mechanisms may underlie it. Current biological research on LLD progression incorporates machine learning that combines neuroimaging data with clinical observations. There are few studies on incident cognitive diagnostic outcomes in LLD based on structural MRI (sMRI). In this paper, we describe the development of a hybrid representation learning (HRL) framework for predicting cognitive diagnosis over 5 years based on T1-weighted sMRI data. Specifically, we first extract prediction-oriented MRI features via a deep neural network, and then integrate them with handcrafted MRI features via a Transformer encoder for cognitive diagnosis prediction. Two tasks are investigated in this work, including (1) identifying cognitively normal subjects with LLD and never-depressed older healthy subjects, and (2) identifying LLD subjects who developed CI (or even AD) and those who stayed cognitively normal over five years. We validate the proposed HRL on 294 subjects with T1-weighted MRIs from two clinically harmonized studies. Experimental results suggest that the HRL outperforms several classical machine learning and state-of-the-art deep learning methods in LLD identification and prediction tasks.

Brain connectivity changes underlying depression and fatigue in relapsing-remitting multiple sclerosis: A systematic review.

Multiple Sclerosis (MS) is an autoimmune disease affecting the central nervous system, characterised by neuroinflammation and neurodegeneration. Fatigue and depression are common, debilitating, and intertwined symptoms in people with relapsing-remitting MS (pwRRMS). An increased understanding of brain changes and mechanisms underlying fatigue and depression in RRMS could lead to more effective interventions and enhancement of quality of life. To elucidate the relationship between depression and fatigue and brain connectivity in pwRRMS we conducted a systematic review. Searched databases were PubMed, Web-of-Science and Scopus. Inclusion criteria were: studied participants with RRMS (n ≥ 20; ≥ 18 years old) and differentiated between MS subtypes; published between 2001-01-01 and 2023-01-18; used fatigue and depression assessments validated for MS; included brain structural, functional magnetic resonance imaging (fMRI) or diffusion MRI (dMRI). Sixty studies met the criteria: 18 dMRI (15 fatigue, 5 depression) and 22 fMRI (20 fatigue, 5 depression) studies. The literature was heterogeneous; half of studies reported no correlation between brain connectivity measures and fatigue or depression. Positive findings showed that abnormal cortico-limbic structural and functional connectivity was associated with depression. Fatigue was linked to connectivity measures in cortico-thalamic-basal-ganglial networks. Additionally, both depression and fatigue were related to altered cingulum structural connectivity, and functional connectivity involving thalamus, cerebellum, frontal lobe, ventral tegmental area, striatum, default mode and attention networks, and supramarginal, precentral, and postcentral gyri. Qualitative analysis suggests structural and functional connectivity changes, possibly due to axonal and/or myelin loss, in the cortico-thalamic-basal-ganglial and cortico-limbic network may underlie fatigue and depression in pwRRMS, respectively, but the overall results were inconclusive, possibly explained by heterogeneity and limited number of studies. This highlights the need for further studies including advanced MRI to detect more subtle brain changes in association with depression and fatigue. Future studies using optimised imaging protocols and validated depression and fatigue measures are required to clarify the substrates underlying these symptoms in pwRRMS.

Brain network hierarchy reorganization in subthreshold depression.

BACKGROUND: Hierarchy is the organizing principle of human brain network. How network hierarchy changes in subthreshold depression (StD) is unclear. The aim of this study was to investigate the altered brain network hierarchy and its clinical significance in patients with StD. METHODS: A total of 43 patients with StD and 43 healthy controls matched for age, gender and years of education participated in this study. Alterations in the hierarchy of StD brain networks were depicted by connectome gradient analysis. We assessed changes in network hierarchy by comparing gradient scores in each network in patients with StD and healthy controls. The study compared different brain subdivisions if there was a different network. Finally, we analysed the relationship between the altered gradient scores and clinical characteristics. RESULTS: Patients with StD had contracted network hierarchy and suppressed cortical range gradients. In the principal gradient, the gradient scores of default mode network were significantly reduced in patients with StD compared to controls. In the default network, the subdivisions of reduced gradient scores were mainly located in the precuneus, superior temporal gyrus, and anterior and posterior cingulate gyrus. Reduced gradient scores in the default mode network, the anterior and posterior cingulate gyrus were correlated with severity of depression. CONCLUSIONS: The network hierarchy of the StD changed and was significantly correlated with depressive symptoms and severity. These results provided new insights into further understanding of the neural mechanisms of StD.

Abnormally decreased functional connectivity of the right nucleus basalis of Meynert in Alzheimer's disease patients with depression symptoms.

Dysfunction of the basal forebrain is the main pathological feature in patients with Alzheimer's disease (AD). The aim of this study was to explore whether depressive symptoms cause changes in the functional network of the basal forebrain in AD patients. We collected MRI data from depressed AD patients (n = 24), nondepressed AD patients (n = 14) and healthy controls (n = 20). Resting-state functional magnetic resonance imaging data and functional connectivity analysis were used to study the characteristics of the basal forebrain functional network of the three groups of participants. The functional connectivity differences among the three groups were compared using ANCOVA and post hoc analyses. Compared to healthy controls, depressed AD patients showed reduced functional connectivity between the right nucleus basalis of Meynert and the left supramarginal gyrus and the supplementary motor area. These results increase our understanding of the neural mechanism of depressive symptoms in AD patients.

Preliminary evidence for preserved synaptic density in late-life depression.

Late-life depression has been consistently associated with lower gray matter volume, the origin of which remains largely unexplained. Recent in-vivo PET findings in early-onset depression and Alzheimer's Disease suggest that synaptic deficits contribute to the pathophysiology of these disorders and may therefore contribute to lower gray matter volume in late-life depression. Here, we investigate synaptic density in vivo for the first time in late-life depression using the synaptic vesicle glycoprotein 2A receptor radioligand 11C-UCB-J. We included 24 currently depressed adults with late-life depression (73.0 ± 6.2 years, 16 female, geriatric depression scale = 19.5 ± 6.8) and 36 age- and gender-matched healthy controls (70.4 ± 6.2 years, 21 female, geriatric depression scale = 2.7 ± 2.9) that underwent simultaneous 11C-UCB-J positron emission tomography (PET) and 3D T1- and T2-FLAIR weighted magnetic resonance (MR) imaging on a 3-tesla PET-MR scanner. We used analyses of variance to test for 11C-UCB-J binding and gray matter volumes differences in regions implicated in depression. The late-life depression group showed a trend in lower gray matter volumes in the hippocampus (p = 0.04), mesial temporal (p = 0.02) and prefrontal cortex (p = 0.02) compared to healthy control group without surviving correction for multiple comparison. However, no group differences in 11C-UCB-J binding were found in these regions nor were any associations between 11C-UCB-J and depressive symptoms. Our data suggests that, in contrast to Alzheimer's Disease, lower gray matter volume in late-life depression is not associated with synaptic density changes. From a therapeutic standpoint, preserved synaptic density in late-life depression may be an encouraging finding.

Alterations in cortical volume and complexity in Parkinson's disease with depression.

AIMS: The aim of this study is to investigate differences in gray matter volume and cortical complexity between Parkinson's disease with depression (PDD) patients and Parkinson's disease without depression (PDND) patients. METHODS: A total of 41 PDND patients, 36 PDD patients, and 38 healthy controls (HC) were recruited and analyzed by Voxel-based morphometry (VBM) and surface-based morphometry (SBM). Differences in gray matter volume and cortical complexity were compared using the one-way analysis of variance (ANOVA) and correlated with the Hamilton Depression Scale-17 (HAMD-17) scores. RESULTS: PDD patients exhibited significant cortical atrophy in various regions, including bilateral medial parietal-occipital-temporal lobes, right dorsolateral temporal lobes, bilateral parahippocampal gyrus, and bilateral hippocampus, compared to HC and PDND groups. A negative correlation between the GMV of left precuneus and HAMD-17 scores in the PDD group tended to be significant (r = -0.318, p = 0.059). Decreased gyrification index was observed in the bilateral insular and dorsolateral temporal cortex. However, there were no significant differences found in fractal dimension and sulcal depth. CONCLUSION: Our research shows extensive cortical structural changes in the insular cortex, parietal-occipital-temporal lobes, and hippocampal regions in PDD. This provides a morphological perspective for understanding the pathophysiological mechanism underlying depression in Parkinson's disease.

Associations of depression and perceived physical fatigability with white matter integrity in older adults.

BACKGROUNDS: Fatigability is prevalent in older adults. However, it is often associated with depressed mood. We aim to investigate these two psychobehavioral constructs by examining their underpinning of white matter structures in the brain and their associations with different medical conditions. METHODS: Twenty-seven older adults with late-life depression (LLD) and 34 cognitively normal controls (CN) underwent multi-shell diffusion MRI. Fatigability was measured with the Pittsburgh Fatigability Scale. We examined white matter integrity by measuring the quantitative anisotropy (QA), a fiber tracking parameter with better accuracy than the traditional imaging technique. RESULTS: We found those with LLD had lower QA in the 2nd branch of the left superior longitudinal fasciculus (SLF-II), and those with more physical fatigability had lower QA in more widespread brain regions. In tracts associated with more physical fatigability, the lower QA in left acoustic radiation and left superior thalamic radiation correlated with higher blood glucose (r = - 0.46 and - 0.49). In tracts associated with depression, lower QA in left SLF-II correlated with higher bilirubin level (r = - 0.58). DISCUSSION: Depression and fatigability were associated with various white matter integrity changes, which correlated with biochemistry biomarkers all related to inflammation.

Cerebral MRI in a prospective cohort study on depression and atherosclerosis: the BiDirect sample, processing pipelines, and analysis tools.

BACKGROUND: The use of cerebral magnetic resonance imaging (MRI) in observational studies has increased exponentially in recent years, making it critical to provide details about the study sample, image processing, and extracted imaging markers to validate and replicate study results. This article reviews the cerebral MRI dataset from the now-completed BiDirect cohort study, as an update and extension of the feasibility report published after the first two examination time points. METHODS: We report the sample and flow of participants spanning four study sessions and twelve years. In addition, we provide details on the acquisition protocol; the processing pipelines, including standardization and quality control methods; and the analytical tools used and markers available. RESULTS: All data were collected from 2010 to 2021 at a single site in Münster, Germany, starting with a population of 2,257 participants at baseline in 3 different cohorts: a population-based cohort (n = 911 at baseline, 672 with MRI data), patients diagnosed with depression (n = 999, 736 with MRI data), and patients with manifest cardiovascular disease (n = 347, 52 with MRI data). During the study period, a total of 4,315 MRI sessions were performed, and over 535 participants underwent MRI at all 4 time points. CONCLUSIONS: Images were converted to Brain Imaging Data Structure (a standard for organizing and describing neuroimaging data) and analyzed using common tools, such as CAT12, FSL, Freesurfer, and BIANCA to extract imaging biomarkers. The BiDirect study comprises a thoroughly phenotyped study population with structural and functional MRI data. RELEVANCE STATEMENT: The BiDirect Study includes a population-based sample and two patient-based samples whose MRI data can help answer numerous neuropsychiatric and cardiovascular research questions. KEY POINTS: • The BiDirect study included characterized patient- and population-based cohorts with MRI data. • Data were standardized to Brain Imaging Data Structure and processed with commonly available software. • MRI data and markers are available upon request.

Alterations of amygdala volume and functional connectivity in migraine patients comorbid with and without depression.

OBJECTIVE: The comorbid relationship between migraine and depression has been well recognized, but its underlying pathophysiology is unclear. Here, we aimed to explore the structural changes of the amygdala and the abnormal functional connectivity of the centromedial amygdala (CMA) in migraineurs with depression. METHODS: High-resolution T1-weighted and functional magnetic resonance images were acquired from 22 episodic migraineurs with comorbid depression (EMwD), 21 episodic migraineurs without depression (EM), and 17 healthy controls (HC). Voxel-based morphometry and resting-state functional connectivity (rsFC) were applied to examine the intergroup differences in amygdala volume. RESULTS: The bilateral amygdala volume was increased in the EMwD and EM groups compared with the HC group, but there were no differences between the EMwD and EM groups. The right CMA exhibited decreased rsFC in the left dorsolateral prefrontal cortex (DLPFC) in the EMwD group compared with the EM group, while rsFC increased between the CMA and the contralateral DLPFC in the EM group compared with the HC group. In addition, the EM group showed decreased rsFC between the left CMA and the left pallidum compared with the HC group. CONCLUSIONS: Enlarged amygdala is an imaging feature of EM and EMwD. The inconsistency of rsFC between CMA and DLPFC between migraineurs with and without depression might indicate that decreased rsFC between CMA and DLPFC is a neuropathologic marker for the comorbidity of migraine and depression. The core regions might be a potential intervention target for the treatment of EMwD in the future.

Predicting suicidality in late-life depression by 3D convolutional neural network and cross-sample entropy analysis of resting-state fMRI.

BACKGROUND: Predicting suicide is a pressing issue among older adults; however, predicting its risk is difficult. Capitalizing on the recent development of machine learning, considerable progress has been made in predicting complex behavior such as suicide. As depression remained the strongest risk for suicide, we aimed to apply deep learning algorithms to identify suicidality in a group with late-life depression (LLD). METHODS: We enrolled 83 patients with LLD, 35 of which were non-suicidal and 48 were suicidal, including 26 with only suicidal ideation and 22 with past suicide attempts, for resting-state functional magnetic resonance imaging (MRI). Cross-sample entropy (CSE) analysis was conducted to examine the complexity of MRI signals among brain regions. Three-dimensional (3D) convolutional neural networks (CNNs) were used, and the classification accuracy in each brain region was averaged to predict suicidality after sixfold cross-validation. RESULTS: We found brain regions with a mean accuracy above 75% to predict suicidality located mostly in default mode, fronto-parietal, and cingulo-opercular resting-state networks. The models with right amygdala and left caudate provided the most reliable accuracy in all cross-validation folds, indicating their neurobiological importance in late-life suicide. CONCLUSION: Combining CSE analysis and the 3D CNN, several brain regions were found to be associated with suicidality.