Mark Jenkinson

This paper introduces a deep-learning method for creating age-dependent brain templates using diffeomorphic transformations, showing it produces high-fidelity spatial templates but struggles to capture all age-related morphological changes.

UniFed addresses harmonisation and privacy in neuroimaging by enabling federated learning with partially labelled distributed data, producing high-quality segmentations.

The paper develops a resource to evaluate MRI harmonisation approaches by comparing variability across scanners, within-scanners, and biological differences using multimodal data from multiple sites.

This study evaluates normative models for neuroimaging data, showing that larger sample sizes reduce variance but not bias, and flexible models perform better for nonlinear data.

The paper introduces an automated pipeline for registering stand-alone histology sections to whole-brain MRI data with sub-voxel accuracy.

STAMP trains and prunes a UNet for medical image segmentation with online pruning, achieving higher performance and reducing parameters by over 85% with fewer labels.

The paper develops a CNN for automated segmentation of fetal brain structures in 3D ultrasound using few-shot learning, achieving performance close to intra-observer variability with minimal manual annotations.

This study compares domain adaptation techniques to improve white matter hyperintensity segmentation across different MRI datasets, finding that unsupervised domain adversarial training performs best.

This paper proposes a triplanar ensemble U-Net model for WMH segmentation on MR images, achieving robust performance comparable to existing methods.

This paper harmonises white matter hyperintensity measurements across two neuroimaging datasets by standardising preprocessing and modelling demographic and physiological differences.

This paper introduces a deep learning framework to reduce scanner bias and other confounds in MRI data, improving harmonization and generalizability across datasets.

This paper uses a 3D CNN to predict brain age from MRI data and finds that prediction errors correlate with clinical measurements and image-derived phenotypes.

This paper introduces an automated pipeline for processing neonatal resting-state fMRI data, improving motion correction and quality assurance in the developing Human Connectome Project.

The paper introduces a pipeline for automatically aligning histological images with whole-brain MRI data, achieving sub-millimetre accuracy and outperforming manual methods.

This paper improves the BIANCA tool for WMH segmentation by introducing a locally adaptive thresholding method, LOCATE, which significantly enhances segmentation performance compared to global thresholding.

This study identifies genetic loci specific to periventricular and deep white matter hyperintensities, revealing distinct genetic architectures and potential biological mechanisms.

This paper evaluates FNIRT, a nonlinear image registration tool, showing its effectiveness in handling intensity differences and producing diffeomorphic warps across simulated and experimental data.

This study investigates white matter degeneration in the perforant path of ALS patients using diffusion MRI, polarized light imaging, and immunohistochemistry, finding significant changes in fractional anisotropy and myelin density.

The paper derives age-related normative percentiles for hippocampal and grey matter volume using UK Biobank data to aid in clinical and research assessments of brain health.

This paper develops a Bayesian spline method to model the spatio-temporal distribution of white matter hyperintensities with respect to age and validates it on simulated and real datasets.

This study uses arterial spin labelling to investigate perfusion changes in patients with musculoskeletal pain during arm repositioning, finding increased perfusion in brain regions associated with pain processing.

The paper introduces a fully automated pipeline for neonatal cortical surface reconstruction from MRI, achieving high accuracy in 85% of cases.

This paper introduces a new regularization method for cortical surface alignment in brain imaging, improving the robustness and biological interpretability of multi-modal data alignment.

The paper describes an automated processing and quality control pipeline for brain imaging data from the first 10,000 UK Biobank participants.

This paper introduces BIDS Apps, a framework for creating portable neuroimaging analysis tools compatible with BIDS data, improving reproducibility and ease of use.

This paper introduces NIDM-Results, a standardized format for sharing neuroimaging statistical results, enabling reproducibility and meta-analysis.