arXiv subjects

Christian F. Beckmann

Publications and source records attributed to Christian F. Beckmann.

7 recordsLinked to original sources

arXiv2026

Charting the velocity of brain growth and development

Brain charts have emerged as a highly useful approach for understanding brain development and aging on the basis of brain imaging and have shown substantial utility in describing typical and atypical brain development with respect to a given reference model. However, all existing models are fundamentally cross-sectional and cannot capture change over time at the individual level. We address this using velocity centiles, which directly map change over time and can be overlaid onto cross-sectionally derived population centiles. We demonstrate this by modelling rates of change for 24062 scans from 10795 healthy individuals with up to 8 longitudinal measurements across the lifespan. We provide a method to detect individual deviations from a stable trajectory, generalising the notion of thrive lines, which are used in pediatric medicine to declare failure to thrive. Using this approach, we predict transition from mild cognitive impairment to dementia more accurately than by using either time point alone, replicated across two datasets. Last, by taking into account multiple time points, we improve the sensitivity of velocity models for predicting the future trajectory of brain change. This highlights the value of predicting change over time and makes a fundamental step towards precision medicine.

q-bio.NC↗

arXiv2024

To which reference class do you belong? Measuring racial fairness of reference classes with normative modeling

Reference classes in healthcare establish healthy norms, such as pediatric growth charts of height and weight, and are used to chart deviations from these norms which represent potential clinical risk. How the demographics of the reference class influence clinical interpretation of deviations is unknown. Using normative modeling, a method for building reference classes, we evaluate the fairness (racial bias) in reference models of structural brain images that are widely used in psychiatry and neurology. We test whether including race in the model creates fairer models. We predict self-reported race using the deviation scores from three different reference class normative models, to better understand bias in an integrated, multivariate sense. Across all of these tasks, we uncover racial disparities that are not easily addressed with existing data or commonly used modeling techniques. Our work suggests that deviations from the norm could be due to demographic mismatch with the reference class, and assigning clinical meaning to these deviations should be done with caution. Our approach also suggests that acquiring more representative samples is an urgent research priority.

cs.LG↗

arXiv2024

Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping

The detection of heterogeneous mental disorders based on brain readouts remains challenging due to the complexity of symptoms and the absence of reliable biomarkers. This paper introduces CAM (Cortical Anomaly Detection through Masked Image Modeling), a novel self-supervised framework designed for the unsupervised detection of complex brain disorders using cortical surface features. We employ this framework for the detection of individuals on the psychotic spectrum and demonstrate its capabilities compared to state-of-the-art methods, achieving an AUC of 0.696 for Schizoaffective and 0.769 for Schizophreniform, without the need for any labels. Furthermore, the analysis of atypical cortical regions, including Pars Triangularis and several frontal areas often implicated in schizophrenia, provides further confidence in our approach. Altogether, we demonstrate a scalable approach for anomaly detection of complex brain disorders based on cortical abnormalities. The code will be made available at https://github.com/chadHGY/CAM.

eess.IV↗

arXiv2020

Hierarchical Bayesian Regression for Multi-Site Normative Modeling of Neuroimaging Data

Clinical neuroimaging has recently witnessed explosive growth in data availability which brings studying heterogeneity in clinical cohorts to the spotlight. Normative modeling is an emerging statistical tool for achieving this objective. However, its application remains technically challenging due to difficulties in properly dealing with nuisance variation, for example due to variability in image acquisition devices. Here, in a fully probabilistic framework, we propose an application of hierarchical Bayesian regression (HBR) for multi-site normative modeling. Our experimental results confirm the superiority of HBR in deriving more accurate normative ranges on large multi-site neuroimaging data compared to widely used methods. This provides the possibility i) to learn the normative range of structural and functional brain measures on large multi-site data; ii) to recalibrate and reuse the learned model on local small data; therefore, HBR closes the technical loop for applying normative modeling as a medical tool for the diagnosis and prognosis of mental disorders.

stat.ML↗

arXiv2018

Scalable Multi-Task Gaussian Process Tensor Regression for Normative Modeling of Structured Variation in Neuroimaging Data

Most brain disorders are very heterogeneous in terms of their underlying biology and developing analysis methods to model such heterogeneity is a major challenge. A promising approach is to use probabilistic regression methods to estimate normative models of brain function using (f)MRI data then use these to map variation across individuals in clinical populations (e.g., via anomaly detection). To fully capture individual differences, it is crucial to statistically model the patterns of correlation across different brain regions and individuals. However, this is very challenging for neuroimaging data because of high-dimensionality and highly structured patterns of correlation across multiple axes. Here, we propose a general and flexible multi-task learning framework to address this problem. Our model uses a tensor-variate Gaussian process in a Bayesian mixed-effects model and makes use of Kronecker algebra and a low-rank approximation to scale efficiently to multi-way neuroimaging data at the whole brain level. On a publicly available clinical fMRI dataset, we show that our computationally affordable approach substantially improves detection sensitivity over both a mass-univariate normative model and a classifier that --unlike our approach-- has full access to the clinical labels.

stat.ML↗

arXiv2017

Connectopic mapping with resting-state fMRI

Brain regions are often topographically connected: nearby locations within one brain area connect with nearby locations in another area. Mapping these connection topographies, or 'connectopies' in short, is crucial for understanding how information is processed in the brain. Here, we propose principled, fully data-driven methods for mapping connectopies using functional magnetic resonance imaging (fMRI) data acquired at rest by combining spectral embedding of voxel-wise connectivity 'fingerprints' with a novel approach to spatial statistical inference. We applied the approach in human primary motor and visual cortex, and show that it can trace biologically plausible, overlapping connectopies in individual subjects that follow these regions' somatotopic and retinotopic maps. As a generic mechanism to perform inference over connectopies, the new spatial statistics approach enables rigorous statistical testing of hypotheses regarding the fine-grained spatial profile of functional connectivity and whether that profile is different between subjects or between experimental conditions. The combined framework offers a fundamental alternative to existing approaches to investigating functional connectivity in the brain, from voxel- or seed-pair wise characterizations of functional association, towards a full, multivariate characterization of spatial topography.

q-bio.QM↗

arXiv2016

Human brain parcellation using time courses of instantaneous connectivity

Functional neuroimaging studies have lead to understanding the brain as a collection of spatially segregated functional networks. It is thought that each of these networks is in turn composed of a set of distinct sub-regions that together support each network's function. Considering the sub-regions to be an essential part of the brain's functional architecture, several strategies have been put forward that aim at identifying the functional sub-units of the brain by means of functional parcellations. Current parcellation strategies typically employ a bottom-up strategy, creating a parcellation by clustering smaller units. We propose a novel top-down parcellation strategy, using time courses of instantaneous connectivity to subdivide an initial region of interest into sub-regions. We use split-half reproducibility to choose the optimal number of sub-regions. We apply our Instantaneous Connectivity Parcellation (ICP) strategy on high-quality resting-state FMRI data, and demonstrate the ability to generate parcellations for thalamus, entorhinal cortex, motor cortex, and subcortex including brainstem and striatum. We evaluate the subdivisions against available cytoarchitecture maps to show that the our parcellation strategy recovers biologically valid subdivisions that adhere to known cytoarchitectural features.

q-bio.QM↗