Registration by Regression (RbR): a framework for interpretable and flexible atlas registration.

In human neuroimaging studies, atlas registration enables mapping MRI scans to a common coordinate frame, which is necessary to aggregate data from multiple subjects. Machine learning registration methods have achieved excellent speed and accuracy but lack interpretability and flexibility at test time (since their deformation model is fixed). More recently, keypoint-based methods have been proposed to tackle these issues, but their accuracy is still subpar, particularly when fitting nonlinear transforms.

: Persistence-based Counting of White Matter Hyperintensities in Brain MRI.

White matter hyperintensities (WMH) are a hallmark of cerebrovascular disease and multiple sclerosis. Automated WMH segmentation methods enable quantitative analysis via estimation of total lesion load, spatial distribution of lesions, and number of lesions (i.e.

Head and shoulders-The impact of an extended head model on the simulation and optimization of transcranial electric stimulation.

Electric field calculations are increasingly used for dose characterization of transcranial electrical stimulation (tES), but existing open-source head models are inaccurate for extracephalic montages that include electrodes placed on the neck or shoulder. We introduce the "Ernie Extended" model, an MRI- and CT-derived open-source head model extending to the upper shoulder region. Simulations of extracephalic tES targeting the cerebellum and supplementary motor area show significant differences in electric fields when using Ernie Extended compared to the non-extended Ernie model.

Towards quantitative intensity analysis of conventional T1-weighted images in multiple sclerosis.

Conventional T1-weighted (T1w) magnetic resonance imaging (MRI) is commonly used in multiple sclerosis (MS) morphometry and volumetry research. However, arbitrary intensity scales preclude interpretation of signal values across patients, sites, and time. This requires quantitative MRI techniques, which are not always available.

Visualizing cortical laminar architecture in the living human brain using next-generation ultra-high-gradient diffusion MRI.

Characterizing cortical laminar microstructure is essential for understanding human brain function. Leveraging the next-generation Connectome MRI scanner (maximum gradient strength = 500mT/m, slew rate = 600T/m/s), we characterized cortical laminar cytoarchitecture and myeloarchitecture through cortical depth-dependent analyses of soma and neurite density imaging (SANDI) metrics derived from diffusion MRI, enhanced by a super-resolution technique. SANDI revealed distinct laminar profiles: intra-soma signal fraction peaked at ~ 55% cortical depth, while intra-neurite signal fraction increased toward deeper layers, consistent with histological patterns.

Fast FEM-based electric field calculations for transcranial magnetic stimulation.

. To provide a finite-element method (FEM) for rapid, repeated evaluations of the electric field induced by transcranial magnetic stimulation (TMS) in the brain for changing coil positions..

"Recon-all-clinical": Cortical surface reconstruction and analysis of heterogeneous clinical brain MRI.

Surface-based analysis of the cerebral cortex is ubiquitous in human neuroimaging with MRI. It is crucial for tasks like cortical registration, parcellation, and thickness estimation. Traditionally, such analyses require high-resolution, isotropic scans with good gray-white matter contrast, typically a T1-weighted scan with 1 mm resolution.

Enhancing transcranial ultrasound stimulation planning with MRI-derived skull masks: a comparative analysis with CT-based processing.

Transcranial ultrasound stimulation (TUS) presents challenges in ultrasound wave transmission through the skull, affecting study outcomes due to aberration and attenuation. While planning strategies incorporating 3D computed tomography (CT) scans help mitigate these issues, they expose participants to radiation, which can raise ethical concerns. A solution involves generating skull masks from participants' anatomical magnetic resonance imaging (MRI).

Synthetic data in generalizable, learning-based neuroimaging.

Synthetic data have emerged as an attractive option for developing machine-learning methods in human neuroimaging, particularly in magnetic resonance imaging (MRI)-a modality where image contrast depends enormously on acquisition hardware and parameters. This retrospective paper reviews a family of recently proposed methods, based on synthetic data, for generalizable machine learning in brain MRI analysis. Central to this framework is the concept of domain randomization, which involves training neural networks on a vastly diverse array of synthetically generated images with random contrast properties.

A lightweight generative model for interpretable subject-level prediction.

Recent years have seen a growing interest in methods for predicting an unknown variable of interest, such as a subject's diagnosis, from medical images depicting its anatomical-functional effects. Methods based on discriminative modeling excel at making accurate predictions, but are challenged in their ability to explain their decisions in anatomically meaningful terms. In this paper, we propose a simple technique for single-subject prediction that is inherently interpretable.

A next-generation, histological atlas of the human brain and its application to automated brain MRI segmentation.

Magnetic resonance imaging (MRI) is the standard tool to image the human brain In this domain, digital brain atlases are essential for subject-specific segmentation of anatomical regions of interest (ROIs) and spatial comparison of neuroanatomy from different subjects in a common coordinate frame. High-resolution, digital atlases derived from histology (e.g.

Segmentation of supragranular and infragranular layers in ultra-high-resolution 7T ex vivo MRI of the human cerebral cortex.

Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding of neurodevelopmental and neurodegenerative disorders. Building on recent advancements in ultra-high-resolution ex vivo MRI, we present a novel semi-supervised segmentation model capable of identifying supragranular and infragranular layers in ex vivo MRI with unprecedented precision. On a dataset consisting of 17 whole-hemisphere ex vivo scans at 120 $\mu $m, we propose a Multi-resolution U-Nets framework that integrates global and local structural information, achieving reliable segmentation maps of the entire hemisphere, with Dice scores over 0.

High-resolution segmentations of the hypothalamus and its subregions for training of segmentation models.

Segmentation of brain structures on magnetic resonance imaging (MRI) is a highly relevant neuroimaging topic, as it is a prerequisite for different analyses such as volumetry or shape analysis. Automated segmentation facilitates the study of brain structures in larger cohorts when compared with manual segmentation, which is time-consuming. However, the development of most automated methods relies on large and manually annotated datasets, which limits the generalizability of these methods.

MR imaging of the magnetic fields induced by injected currents can guide improvements of individualized head volume conductor models.

Volume conductor models of the human head are routinely used to estimate the induced electric fields in transcranial brain stimulation (TBS) and for source localization in electro- and magnetoencephalography (EEG and MEG). Magnetic resonance current density imaging (MRCDI) has the potential to act as a non-invasive method for dose control and model validation but requires very sensitive MRI acquisition approaches. A double-echo echo-planar imaging (EPI) method is here introduced.

Exploring an EM-algorithm for banded regression in computational neuroscience.

Regression is a principal tool for relating brain responses to stimuli or tasks in computational neuroscience. This often involves fitting linear models with predictors that can be divided into groups, such as distinct stimulus feature subsets in encoding models or features of different neural response channels in decoding models. When fitting such models, it can be relevant to allow differential shrinkage of the different groups of regression weights.

QUANTIFYING WHITE MATTER HYPERINTENSITY AND BRAIN VOLUMES IN HETEROGENEOUS CLINICAL AND LOW-FIELD PORTABLE MRI.

Brain atrophy and white matter hyperintensity (WMH) are critical neuroimaging features for ascertaining brain injury in cerebrovascular disease and multiple sclerosis. Automated segmentation and quantification is desirable but existing methods require high-resolution MRI with good signal-to-noise ratio (SNR). This precludes application to clinical and low-field portable MRI (pMRI) scans, thus hampering large-scale tracking of atrophy and WMH progression, especially in underserved areas where pMRI has huge potential.

Neuroanatomical Predictors of Transcranial Direct Current Stimulation (tDCS)-Induced Modifications in Neurocognitive Task Performance in Typically Developing Individuals.

Transcranial direct current stimulation (tDCS) is a noninvasive neuromodulation technique gaining more attention in neurodevelopmental disorders (NDDs). Due to the phenotypic heterogeneity of NDDs, tDCS is unlikely to be equally effective in all individuals. The present study aimed to establish neuroanatomical markers in typically developing (TD) individuals that may be used for the prediction of individual responses to tDCS.

Segmentation of supragranular and infragranular layers in ultra-high resolution 7T MRI of the human cerebral cortex.

Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding of neurodevelopmental and neurodegenerative disorders. Leveraging recent advancements in ultra-high resolution MRI, we present a novel semi-supervised segmentation model capable of identifying supragranular and infragranular layers in MRI with unprecedented precision. On a dataset consisting of 17 whole-hemisphere scans at 120 m, we propose a multi-resolution U-Nets framework (MUS) that integrates global and local structural information, achieving reliable segmentation maps of the entire hemisphere, with Dice scores over 0.

Anatomical details affect electric field predictions for non-invasive brain stimulation in non-human primates.

Non-human primates (NHPs) have become key for translational research in noninvasive brain stimulation (NIBS). However, in order to create comparable stimulation conditions for humans it is vital to study the accuracy of current modeling practices across species. Numerical models to simulate electric fields are an important tool for experimental planning in NHPs and translation to human studies.

Evaluating the influence of anatomical accuracy and electrode positions on EEG forward solutions.

Generating realistic volume conductor models for forward calculations in electroencephalography (EEG) is not trivial and several factors contribute to the accuracy of such models, two of which are its anatomical accuracy and the accuracy with which electrode positions are known. Here, we investigate effects of anatomical accuracy by comparing forward solutions from SimNIBS, a tool which allows state-of-the-art anatomical modeling, with well-established pipelines in MNE-Python and FieldTrip. We also compare different ways of specifying electrode locations when digitized positions are not available such as transformation of measured positions from standard space and transformation of a manufacturer layout.

A head template for computational dose modelling for transcranial focused ultrasound stimulation.

Transcranial focused Ultrasound Stimulation (TUS) at low intensities is emerging as a novel non-invasive brain stimulation method with higher spatial resolution than established transcranial stimulation methods and the ability to selectively stimulate also deep brain areas. Accurate control of the focus position and strength of the TUS acoustic waves is important to enable a beneficial use of the high spatial resolution and to ensure safety. As the human skull causes strong attenuation and distortion of the waves, simulations of the transmitted waves are needed to accurately determine the TUS dose distribution inside the cranial cavity.

SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining.

Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) difficultly generalise to unseen domains. When segmenting brain scans, CNNs are highly sensitive to changes in resolution and contrast: even within the same MRI modality, performance can decrease across datasets. Here we introduce SynthSeg, the first segmentation CNN robust against changes in contrast and resolution.

tDCS induced GABA change is associated with the simulated electric field in M1, an effect mediated by grey matter volume in the MRS voxel.

Background And Objective: Transcranial direct current stimulation (tDCS) has wide ranging applications in neuro-behavioural and physiological research, and in neurological rehabilitation. However, it is currently limited by substantial inter-subject variability in responses, which may be explained, at least in part, by anatomical differences that lead to variability in the electric field (E-field) induced in the cortex. Here, we tested whether the variability in the E-field in the stimulated cortex during anodal tDCS, estimated using computational simulations, explains the variability in tDCS induced changes in GABA, a neurophysiological marker of stimulation effect.

Linking lesions in sensorimotor cortex to contralateral hand function in multiple sclerosis: a 7 T MRI study.

Cortical lesions constitute a key manifestation of multiple sclerosis and contribute to clinical disability and cognitive impairment. Yet it is unknown whether local cortical lesions and cortical lesion subtypes contribute to domain-specific impairments attributable to the function of the lesioned cortex. In this cross-sectional study, we assessed how cortical lesions in the primary sensorimotor hand area relate to corticomotor physiology and sensorimotor function of the contralateral hand.