Richard Dinga

This paper establishes a normative model of hippocampal geometry across the lifespan using data from 27,000 individuals, revealing age-related changes and disease-specific alterations.

The paper establishes a normative reference for large-scale human brain dynamics using resting-state fMRI data from over 10,000 individuals, revealing systematic reorganization across development and ageing and disorder-specific deviations in mental health conditions.

MEGaNorm models lifespan trajectories of resting-state MEG brain oscillations, revealing disease-related abnormalities in Parkinson's disease patients.

The paper replicates a brain age gap in depression using a large-scale multisite study, finding a similar effect size to a prior study.

This paper develops a hierarchical Bayesian model to account for site effects in neuroimaging data, showing improved predictive performance compared to harmonization techniques.

This work develops normative models of brain growth and aging using neuroimaging data to quantify variability across disorders and improve case-control inferences.

This paper introduces a warped Bayesian Linear Regression framework for normative modelling, improving scalability and non-Gaussian distribution handling in neuroimaging data.

This paper introduces a standardized protocol for normative modeling in computational psychiatry using the PCNtoolkit, enabling analysis of biological heterogeneity without relying on case-control comparisons.

Generalized additive models for location, scale and shape (GAMLSS) using SHASH distributions beat Gaussian brain normative models on log score and calibration in most of 150 UK Biobank cortical-thickness regions.

This paper introduces a federated probabilistic framework using hierarchical Bayesian regression for multi-site normative modeling of neuroimaging data, showing improved accuracy and adaptability.

The paper learns interpretable latent representations of task-fMRI data from large-scale datasets, capturing demographic and behavioral variability through a three-dimensional autoencoder and normative modeling.

Regressing confounds from inputs leaves confound information machine learning models exploit; adjusting the predictions post hoc instead held false-positive rates near 5%, versus up to 100% with input adjustment.

This paper examines brain aging in major depressive disorder (MDD) using a large dataset, finding that MDD patients show increased brain age differences compared to controls.

The paper identifies neurovegetative symptom subtypes in young people with MDD and finds structural brain correlates in the anterior insula.

This study identifies subcortical shape differences in MDD patients using ENIGMA data, highlighting region-specific changes in surface area and thickness.

Evaluating four families of machine learning performance metrics on simulated and public neuroimaging data shows classification accuracy performs worst for statistical power, model comparison, feature selection, and reliability.

This paper attempts to replicate a study on depression subtypes using brain connectivity and clinical data but fails to find statistically significant results or distinct subtypes.