Schizophrenia (SZ) is associated with an increased risk of life-long cognitive impairments, age-related chronic disease, and premature mortality. We investigated evidence for advanced brain ageing in adult SZ patients, and whether this was associated with clinical characteristics in a prospective meta-analytic study conducted by the ENIGMA Schizophrenia Working Group. The study included data from 26 cohorts worldwide, with a total of 2803 SZ patients (mean age 34.2 years; range 18–72 years; 67% male) and 2598 healthy controls (mean age 33.8 years, range 18–73 years, 55% male). Brain-predicted age was individually estimated using a model trained on independent data based on 68 measures of cortical thickness and surface area, 7 subcortical volumes, lateral ventricular volumes and total intracranial volume, all derived from T1-weighted brain magnetic resonance imaging (MRI) scans. Deviations from a healthy brain ageing trajectory were assessed by the difference between brain-predicted age and chronological age (brain-predicted age difference [brain-PAD]). On average, SZ patients showed a higher brain-PAD of +3.55 years (95% CI: 2.91, 4.19; I2 = 57.53%) compared to controls, after adjusting for age, sex and site (Cohen’s d = 0.48). Among SZ patients, brain-PAD was not associated with specific clinical characteristics (age of onset, duration of illness, symptom severity, or antipsychotic use and dose). This large-scale collaborative study suggests advanced structural brain ageing in SZ. Longitudinal studies of SZ and a range of mental and somatic health outcomes will help to further evaluate the clinical implications of increased brain-PAD and its ability to be influenced by interventions.

Objective: Schizophrenia is associated with widespread brain-morphological alterations, believed to be shaped by the underlying connectome architecture. This study tests whether large-scale structural reorganization in schizophrenia relates to normative network architecture, in particular regional centrality/hubness and connectivity patterns. We examine network effects in schizophrenia across different disease stages, and transdiagnostically explore consistency of such relationships in patients with bipolar and major depressive disorder. Methods: We studied anatomical MRI scans from 2,439 adults with schizophrenia and 2,867 healthy controls from 26 ENIGMA sites. Case-control patterns of structural alterations were evaluated against two network susceptibility models: 1) hub vulnerability, which examines associations between regional network centrality and magnitude of disease-related alterations; 2) epicenter models, which identify regions whose typical connectivity profile most closely resembles the disease-related morphological alteration patterns. Both susceptibility models were tested across schizophrenia disease stages and compared to meta-analytic bipolar and major depressive disorder case-control maps. Results: In schizophrenia, regional gray matter reductions co-localized with interconnected hubs, in both the functional (r=0.58, pspin<0.0001) and structural connectome (r=0.32, pspin=0.01). Epicenters were identified in temporo-paralimbic regions, extending to frontal areas. We found unique epicenters for first-episode and early stages, and a shift from occipital to temporal-frontal epicenters in chronic stages. Transdiagnostic comparisons revealed shared epicenters in schizophrenia and bipolar, but not major depressive disorders. Conclusions: Cortical reorganization over the course of schizophrenia closely reflects brain network architecture, emphasizing marked hub susceptibility and temporo-frontal epicenters. The observed overlapping epicenters for schizophrenia and bipolar disorder furthermore suggest shared pathophysiological processes within the schizophrenia-bipolar-spectrum.

Schizophrenia (SZ) is associated with an increased risk of life-long cognitive impairments, age-related chronic disease, and premature mortality. We investigated evidence for advanced brain ageing in adult SZ patients, and whether this was associated with clinical characteristics in a prospective meta-analytic study conducted by the ENIGMA Schizophrenia Working Group. The study included data from 26 cohorts worldwide, with a total of 2803 SZ patients (mean age 34.2 years; range 18-72 years; 67% male) and 2598 healthy controls (mean age 33.8 years, range 18-73 years, 55% male). Brain-predicted age was individually estimated using a model trained on independent data based on 68 measures of cortical thickness and surface area, 7 subcortical volumes, lateral ventricular volumes and total intracranial volume, all derived from T1-weighted brain magnetic resonance imaging (MRI) scans. Deviations from a healthy brain ageing trajectory were assessed by the difference between brain-predicted age and chronological age (brain-predicted age difference [brain-PAD]). On average, SZ patients showed a higher brain-PAD of +3.64 years (95% CI: 3.01, 4.26; I2 = 55.28%) compared to controls, after adjusting for age and sex (Cohen's d = 0.50). Among SZ patients, brain-PAD was not associated with specific clinical characteristics (age of onset, duration of illness, symptom severity, or antipsychotic use and dose). This large-scale collaborative study suggests advanced structural brain ageing in SZ. Longitudinal studies of SZ and a range of mental and somatic health outcomes will help to further evaluate the clinical implications of increased brain-PAD and its ability to be influenced by interventions.

Normative modeling is a statistical approach to quantify the degree to which a particular individual-level measure deviates from the pattern observed in a normative reference population. When applied to human brain morphometric measures it has the potential to inform about the significance of normative deviations for health and disease. Normative models can be implemented using a variety of algorithms that have not been systematically appraised. To address this gap, eight algorithms were compared in terms of performance and computational efficiency using brain regional morphometric data from 37,407 healthy individuals (53.33% female; aged 3 to 90 years) collated from 86 international MRI datasets. Performance was assessed with the mean absolute error (MAE) and computational efficiency was inferred from central processing unit (CPU) time. The algorithms evaluated were Ordinary Least Squares Regression (OLSR), Bayesian Linear Regression (BLR), Generalized Additive Models for Location, Scale, and Shape (GAMLSS), Parametric Lambda, Mu, Sigma (LMS), Multivariable Fractional Polynomial Regression (MFPR), Warped Bayesian Linear Regression (WBLG), and Hierarchical Bayesian Regression (HBR). Model optimization involved testing 9 covariate combinations pertaining to acquisition features, parcellation software versions, and global neuroimaging measures (i.e., total intracranial volume, mean cortical thickness, and mean cortical surface area). Statistical comparisons across models at PFDR<0.05 indicated that MFPR-derived sex and region-specific models with nonlinear polynomials for age and linear effect of global measures had superior predictive accuracy; for models of regional subcortical volume the MAE range was 70-80 mm3 and the corresponding range for regional cortical thickness and regional cortical surface area was 0.09-0.26 mm; and 24-660 mm2 respectively. The MFPR-derived models were also computationally more efficient with a CPU time below one second compared to a range of 2 seconds to 60 minutes for the other algorithms. MFPR-derived models were robust across distinct age groups when sample sizes exceeded 3,000. These results support CentileBrain (https://centilebrain.org/) an empirically benchmarked framework for normative modeling that is freely available to the scientific community.

Recent advances in Computer Vision and Artificial Intelligence have brought the opportunity to automate facial attractiveness evaluation. A range of studies have been addressed to the task and have achieved reasonable prediction accuracy. However, most of these methods work well only on photos with restrictions on expression, posture, illumination, but not on real-world face photos. This work is aimed to improve the attractiveness assessment state-of-the-art in both cases. To this end, an approach that employs transfer learning methodology as well as shallow machine learning was proposed for highly accurate facial attractiveness prediction. Specifically, a Convolutional Neural Network (CNN), Facenet, originally designed and pre-trained for the face recognition task is utilized. High-level facial features were extracted by using the network and then fed into Support Vector Regression in order to predict facial attractiveness. Extensive experiments conducted on widely used facial beauty datasets Gray and SCUT-FBP5500 demonstrated that the proposed method outperformed other attractiveness prediction approaches. The experimental results also confirmed the effectiveness of the method in both constrained and unconstrained environment.