The age-related heterogeneity in major depressive disorder (MDD) has received significant attention. However, the neural mechanisms underlying such heterogeneity still need further investigation. This study aimed to explore the common and distinct functional brain abnormalities across different age groups of MDD patients from a large-sample, multicenter analysis.

The analyzed sample consisted of a total of 1238 individuals including 617 MDD patients (108 adolescents, 12–17 years old; 411 early-middle adults, 18–54 years old; and 98 late adults, > = 55 years old) and 621 demographically matched healthy controls (60 adolescents, 449 early-middle adults, and 112 late adults). MDD-related abnormalities in brain functional connectivity (FC) patterns were investigated in each age group separately and using the whole pooled sample, respectively.

We found shared FC reductions among the sensorimotor, visual, and auditory networks across all three age groups of MDD patients. Furthermore, adolescent patients uniquely exhibited increased sensorimotor-subcortical FC; early-middle adult patients uniquely exhibited decreased visual-subcortical FC; and late adult patients uniquely exhibited wide FC reductions within the subcortical, default-mode, cingulo-opercular, and attention networks. Analysis of covariance models using the whole pooled sample further revealed: (1) significant main effects of age group on FCs within most brain networks, suggesting that they are decreased with aging; and (2) a significant age group × MDD diagnosis interaction on FC within the default-mode network, which may be reflective of an accelerated aging-related decline in default-mode FCs.

To summarize, these findings may deepen our understanding of the age-related biological and clinical heterogeneity in MDD.

Previous analyses of grey and white matter volumes have reported that schizophrenia is associated with structural changes. Deep learning is a data-driven approach that can capture highly compact hierarchical non-linear relationships among high-dimensional features, and therefore can facilitate the development of clinical tools for making a more accurate and earlier diagnosis of schizophrenia.

To identify consistent grey matter abnormalities in patients with schizophrenia, 662 people with schizophrenia and 613 healthy controls were recruited from eight centres across China, and the data from these independent sites were used to validate deep-learning classifiers.

We used a prospective image-based meta-analysis of whole-brain voxel-based morphometry. We also automatically differentiated patients with schizophrenia from healthy controls using combined grey matter, white matter and cerebrospinal fluid volumetric features, incorporated a deep neural network approach on an individual basis, and tested the generalisability of the classification models using independent validation sites.

We found that statistically reliable schizophrenia-related grey matter abnormalities primarily occurred in regions that included the superior temporal gyrus extending to the temporal pole, insular cortex, orbital and middle frontal cortices, middle cingulum and thalamus. Evaluated using leave-one-site-out cross-validation, the performance of the classification of schizophrenia achieved by our findings from eight independent research sites were: accuracy, 77.19–85.74%; sensitivity, 75.31–89.29% and area under the receiver operating characteristic curve, 0.797–0.909.

These results suggest that, by using deep-learning techniques, multidimensional neuroanatomical changes in schizophrenia are capable of robustly discriminating patients with schizophrenia from healthy controls, findings which could facilitate clinical diagnosis and treatment in schizophrenia.

Network approach has been applied to a wide variety of psychiatric disorders. The aim of the present study was to identify network structures of remitters and non-remitters in patients with first-episode psychosis (FEP) at baseline and the 6-month follow-up.

Participants (n = 252) from the Korean Early Psychosis Study (KEPS) were enrolled. They were classified as remitters or non-remitters using Andreasen's criteria. We estimated network structure with 10 symptoms (three symptoms from the Positive and Negative Syndrome Scale, one depressive symptom, and six symptoms related to schema and rumination) as nodes using a Gaussian graphical model. Global and local network metrics were compared within and between the networks over time.

Global network metrics did not differ between the remitters and non-remitters at baseline or 6 months. However, the network structure and nodal strengths associated with positive-self and positive-others scores changed significantly in the remitters over time. Unique central symptoms for remitters and non-remitters were cognitive brooding and negative-self, respectively. The correlation stability coefficients for nodal strength were within the acceptable range.

Our findings indicate that network structure and some nodal strengths were more flexible in remitters. Negative-self could be an important target for therapeutic intervention.

Our previous genome-wide association study (CONVERGE sample) identified significant association between single nucleotide polymorphisms (SNPs) near the SIRT1 gene and major depressive disorder (MDD) in Chinese populations.

To investigate whether SNPs across the SIRT1 gene locus affect regional grey matter density in the Han Chinese population.

T1-weighted structural magnetic resonance imaging was conducted on 92 healthy participants from Eastern China. Grey matter was segmented from the image, which consisted of voxel-wise grey matter density. The effect of SIRT1 SNPs on grey matter density was determined by a multiple linear regression framework.

SNP rs4746720 was significantly associated with grey matter density in two brain cortical regions: the orbital part of the right inferior frontal gyrus and the orbital part of the left inferior frontal gyrus (family-wise error-corrected P < 0.05; voxel-wise P < 0.001). Also, rs4746720 exceeded genome-wide significance in association with MDD in our CONVERGE sample (P = 3.32 × 10−08, odds ratio 1.161).

Our results provided evidence for a potential role of the SIRT1 gene in the brain, implying a possible pathophysiological mechanism underlying susceptibility to MDD.