A5032648713- Functional Brain Connectivity Studies
- Health, Environment, Cognitive Aging
- Advanced Neuroimaging Techniques and Applications
- Mental Health Research Topics
- Neural dynamics and brain function
- Schizophrenia research and treatment
- EEG and Brain-Computer Interfaces
- Dementia and Cognitive Impairment Research
- Face Recognition and Perception
- Health Systems, Economic Evaluations, Quality of Life
- Neural Networks and Applications
- Autism Spectrum Disorder Research
- Emotion and Mood Recognition
- Blind Source Separation Techniques
- Machine Learning in Healthcare
- Advanced MRI Techniques and Applications
- Mental Health and Psychiatry
- Face recognition and analysis
- Context-Aware Activity Recognition Systems
- Face and Expression Recognition
- Assistive Technology in Communication and Mobility
- Innovative Energy Harvesting Technologies
- Mental Health Treatment and Access
- Multisensory perception and integration
- Artificial Intelligence in Healthcare and Education
Radboud University Nijmegen
2017-2024
Radboud University Medical Center
2017-2024
University Medical Center Utrecht
2021-2024
Tilburg University
2023-2024
Utrecht University
2021-2024
Tongmyong University
2023
University College London
2023
University Medical Center
2021-2022
The University of Melbourne
2021
University of Trento
2013-2017
In this work, we present DECAF-a multimodal data set for decoding user physiological responses to affective multimedia content. Different from sets such as DEAP [15] and MAHNOB-HCI [31], DECAF contains (1) brain signals acquired using the Magnetoencephalogram (MEG) sensor, which requires little physical contact with user's scalp consequently facilitates naturalistic response, (2) explicit implicit emotional of 30 participants 40 one-minute music video segments used in 36 movie clips, thereby...
Defining reference models for population variation, and the ability to study individual deviations is essential understanding inter-individual variability its relation onset progression of medical conditions. In this work, we assembled a cohort neuroimaging data from 82 sites (N=58,836; ages 2-100) used normative modeling characterize lifespan trajectories cortical thickness subcortical volume. Models are validated against manually quality checked subset (N=24,354) provide an interface...
The substantial individual heterogeneity that characterizes people with mental illness is often ignored by classical case-control research, which relies on group mean comparisons. Here we present a comprehensive, multiscale characterization of the gray matter volume (GMV) differences in 1,294 cases diagnosed one six conditions (attention-deficit/hyperactivity disorder, autism spectrum bipolar depression, obsessive-compulsive disorder and schizophrenia) 1,465 matched controls. Normative...
Abstract Identifying brain processes involved in the risk and development of mental disorders is a major aim. We recently reported substantial interindividual heterogeneity structural aberrations among patients with schizophrenia bipolar disorder. Estimating normative range voxel‐based morphometry (VBM) data healthy individuals using Gaussian process regression (GPR) enables us to map individual deviations from unseen datasets. Here, we aim replicate our previous results two independent...
Clinical neuroimaging data availability has grown substantially in the last decade, providing potential for studying heterogeneity clinical cohorts on a previously unprecedented scale. Normative modeling is an emerging statistical tool dissecting complex brain disorders. However, its application remains technically challenging due to medical privacy issues and difficulties dealing with nuisance variation, such as variability image acquisition process. Here, we approach problem of estimating...
The potential of normative modeling to make individualized predictions from neuroimaging data has enabled inferences that go beyond the case-control approach. However, site effects are often confounded with variables interest in a complex manner and can bias estimates models, which impeded application models large multi-site sets. In this study, we suggest accommodating for these by including them as random hierarchical Bayesian model. We compared performance linear non-linear model effect...
Abstract Environmental adversities constitute potent risk factors for psychiatric disorders. Evidence suggests the brain adapts to adversity, possibly in an adversity-type and region-specific manner. However, long-term effects of adversity on structure association individual neurobiological heterogeneity with behavior have yet be elucidated. Here we estimated normative models structural development based a lifespan profile longitudinal at-risk cohort aged 25 years ( n = 169). This revealed...
Alzheimer disease (AD) is highly heterogeneous, with marked individual differences in clinical presentation and neurobiology. To explore this, we used neuroanatomical normative modeling to index regional patterns of variability cortical thickness. We aimed characterize outliers thickness patients AD, people mild cognitive impairment (MCI), controls. Furthermore, assessed the relationships between heterogeneity function, β-amyloid, phosphorylated-tau, ApoE genotype. Finally, examined whether...
Abstract Autism is a complex neurodevelopmental condition with substantial phenotypic, biological, and etiologic heterogeneity. It remains challenge to identify biomarkers stratify autism into replicable cognitive or biological subtypes. Here, we aim introduce novel methodological framework for parsing neuroanatomical subtypes within large cohort of individuals autism. We used cortical thickness (CT) in well-characterized sample 316 participants (88 female, age mean: 17.2 ± 5.7) 206...
Abstract Normative modeling aims to quantify the degree which an individual’s brain deviates from a reference sample with respect one or more variables, can be used as potential biomarker of healthy and tool study heterogeneity psychiatric disorders. The application normative models is hindered by methodological challenges lacks standards for usage evaluation models. In this paper, we present generalized additive location scale shape (GAMLSS) neuroimaging data, flexible framework that model...
This work illustrates the use of normative models in a longitudinal neuroimaging study children aged 6-17 years and demonstrates how such can be used to make meaningful comparisons studies, even when individuals are scanned with different scanners across successive waves. More specifically, we first estimated large-scale reference model using Hierarchical Bayesian Regression from N = 42,993 lifespan dozens sites. We then transfer these developmental cohort (N 6285) three measurement waves...
Abstract INTRODUCTION Overlooking the heterogeneity in Alzheimer's disease (AD) may lead to diagnostic delays and failures. Neuroanatomical normative modeling captures individual brain variation inform our understanding of differences AD‐related atrophy. METHODS We applied neuroanatomical magnetic resonance imaging from a real‐world clinical cohort with confirmed AD ( n = 86). Regional cortical thickness was compared healthy reference 33,072) number outlying regions summed (total outlier...
ABSTRACT BACKGROUND Predicting outcomes in schizophrenia spectrum disorders is challenging due to the variability of individual trajectories. While machine learning (ML) shows promise outcome prediction, has not yet been integrated into clinical practice. Understanding how ML models (MLMs) can complement psychiatrists’ predictions and bridge gap between MLM capabilities practical use key. OBJECTIVE This study aims compare performance psychiatrists MLMs predicting short-term symptomatic...
A bstract Clinical neuroimaging data availability has grown substantially in the last decade, providing potential for studying heterogeneity clinical cohorts on a previously unprecedented scale. Normative modeling is an emerging statistical tool dissecting complex brain disorders. However, its application remains technically challenging due to medical privacy issues and difficulties dealing with nuisance variation, such as variability image acquisition process. Here, we introduce federated...
Abstract Background Disruptive behavior disorders (DBD) are heterogeneous at the clinical and biological level. Therefore, aims were to dissect neurodevelopmental deviations of affective brain circuitry provide an integration these differences across modalities. Methods We combined two novel approaches. First, normative modeling map from typical age-related pattern level individual (i) activity during emotion matching (ii) anatomical images derived DBD cases ( n = 77) controls 52) aged 8–18...
Brain decoding is a data analysis paradigm for neuroimaging experiments that based on predicting the stimulus presented to subject from concurrent brain activity. In order make inference at group level, straightforward but sometimes unsuccessful approach train classifier trials of subjects and then test it unseen new subjects. The extreme difficulty related structural functional variability across We call this work, we address problem magnetoen-cephalographic (MEG) provide following...
Schizophrenia and related disorders have heterogeneous outcomes. Individualized prediction of long-term outcomes may be helpful in improving treatment decisions. Utilizing extensive baseline data 523 patients with a psychotic disorder variable illness duration, we predicted symptomatic global at 3-year 6-year follow-ups. We classified as (1) symptomatic: remission or not remission, (2) outcome, using the Global Assessment Functioning (GAF) scale, divided into good (GAF ≥ 65) poor < 65)....
Abstract Background Schizophrenia is associated with an increased risk of aggressive behaviour, which may partly be explained by illness-related changes in brain structure. However, previous studies have been limited group-level analyses, small and selective samples inpatients long time lags between exposure outcome. Methods This cross-sectional study pooled data from 20 sites participating the international ENIGMA-Schizophrenia Working Group. Sites acquired T1-weighted diffusion-weighted...