Multicenter dataset of multi-shell diffusion MRI in healthy traveling adults with identical settings

Macroscale connectome topographical structure reveals the biomechanisms of brain dysfunction in Alzheimer's disease

The intricate spatial configurations of brain networks offer essential insights into understanding the specific patterns of brain abnormalities and the underlying biological mechanisms associated with Alzheimer's disease (AD), normal aging, and other neurodegenerative disorders. This study investigated alterations in the topographical structure of the brain related to aging and neurodegenerative diseases by analyzing brain gradients derived from structural MRI data across multiple cohorts (n = 7323). The analysis identified distinct gradient patterns in AD, aging, and other neurodegenerative conditions. Gene enrichment analysis indicated that inorganic ion transmembrane transport was the most significant term in normal aging, while chemical synaptic transmission is a common enrichment term across various neurodegenerative diseases. Moreover, the findings show that each disorder exhibits unique dysfunctional neurophysiological characteristics. These insights are pivotal for elucidating the distinct biological mechanisms underlying AD, thereby enhancing our understanding of its unique clinical phenotypes in contrast to normal aging and other neurodegenerative disorders.

Advances of surgical robotics: image-guided classification and application

Surgical robotics application in the field of minimally invasive surgery has developed rapidly and has been attracting increasingly more research attention in recent years. A common consensus has been reached that surgical procedures are to become less traumatic and with the implementation of more intelligence and higher autonomy, which is a serious challenge faced by the environmental sensing capabilities of robotic systems. One of the main sources of environmental information for robots are images, which are the basis of robot vision. In this review article, we divide clinical image into direct and indirect based on the object of information acquisition, and into continuous, intermittent continuous, and discontinuous according to the target-tracking frequency. The characteristics and applications of the existing surgical robots in each category are introduced based on these two dimensions. Our purpose in conducting this review was to analyze, summarize, and discuss the current evidence on the general rules on the application of image technologies for medical purposes. Our analysis gives insight and provides guidance conducive to the development of more advanced surgical robotics systems in the future.

Brain tissue segmentation in neurosurgery: a systematic analysis for quantitative tractography approaches

Diffusion magnetic resonance imaging (dMRI) is a cutting-edge imaging method that provides a macro-scale in vivo map of the white matter pathways in the brain. The measurement of brain microstructure and the enhancement of tractography rely heavily on dMRI tissue segmentation. Anatomical MRI technique (e.g., T1- and T2-weighted imaging) is the most widely used method for segmentation in dMRI. In comparison to anatomical MRI, dMRI suffers from higher image distortions, lower image quality, and making inter-modality registration more difficult. The dMRI tractography study of brain connectivity has become a major part of the neuroimaging landscape in recent years. In this research, we provide a high-level overview of the methods used to segment several brain tissues types, including grey and white matter and cerebrospinal fluid, to enable quantitative studies of structural connectivity in the brain in health and illness. In the first part of our review, we discuss the three main phases in the quantitative analysis of tractography, which are correction, segmentation, and quantification. Methodological possibilities are described for each phase, along with their popularity and potential benefits and drawbacks. After that, we will look at research that used quantitative tractography approaches to examine the white and grey matter of the brain, with an emphasis on neurodevelopment, ageing, neurological illnesses, mental disorders, and neurosurgery as possible applications. Even though there have been substantial advancements in methodological technology and the spectrum of applications, there is still no consensus regarding the "optimal" approach in the quantitative analysis of tractography. As a result, researchers should tread carefully when interpreting the findings of quantitative analysis of tractography.

A radiomics-based brain network in T1 images: construction, attributes, and applications

T1 image is a widely collected imaging sequence in various neuroimaging datasets, but it is rarely used to construct an individual-level brain network. In this study, a novel individualized radiomics-based structural similarity network was proposed from T1 images. In detail, it used voxel-based morphometry to obtain the preprocessed gray matter images, and radiomic features were then extracted on each region of interest in Brainnetome atlas, and an individualized radiomics-based structural similarity network was finally built using the correlational values of radiomic features between any pair of regions of interest. After that, the network characteristics of individualized radiomics-based structural similarity network were assessed, including graph theory attributes, test-retest reliability, and individual identification ability (fingerprinting). At last, two representative applications for individualized radiomics-based structural similarity network, namely mild cognitive impairment subtype discrimination and fluid intelligence prediction, were exemplified and compared with some other networks on large open-source datasets. The results revealed that the individualized radiomics-based structural similarity network displays remarkable network characteristics and exhibits advantageous performances in mild cognitive impairment subtype discrimination and fluid intelligence prediction. In summary, the individualized radiomics-based structural similarity network provides a distinctive, reliable, and informative individualized structural brain network, which can be combined with other networks such as resting-state functional connectivity for various phenotypic and clinical applications.

A neuroimaging biomarker for Individual Brain-Related Abnormalities In Neurodegeneration (IBRAIN): a cross-sectional study

Background

Alzheimer's disease (AD) is a prevalent neurodegenerative disorder that poses a worldwide public health challenge. A neuroimaging biomarker would significantly improve early diagnosis and intervention, ultimately enhancing the quality of life for affected individuals and reducing the burden on healthcare systems.

Methods

Cross-sectional and longitudinal data (10,099 participants with 13,380 scans) from 12 independent datasets were used in the present study (this study was performed between September 1, 2021 and February 15, 2023). The Individual Brain-Related Abnormalities In Neurodegeneration (IBRAIN) score was developed via integrated regional- and network-based measures under an ensemble machine learning model based on structural MRI data. We systematically assessed whether IBRAIN could be a neuroimaging biomarker for AD.

Findings

IBRAIN accurately differentiated individuals with AD from NCs (AUC = 0.92) and other neurodegenerative diseases, including Frontotemporal dementia (FTD), Parkinson's disease (PD), Vascular dementia (VaD) and Amyotrophic Lateral Sclerosis (ALS) (AUC = 0.92). IBRAIN was significantly correlated to clinical measures and gene expression, enriched in immune process and protein metabolism. The IBRAIN score exhibited a significant ability to reveal the distinct progression of prodromal AD (i.e., Mild cognitive impairment, MCI) (Hazard Ratio (HR) = 6.52 [95% CI: 4.42∼9.62], p < 1 × 10-16), which offers similar powerful performance with Cerebrospinal Fluid (CSF) Aβ (HR = 3.78 [95% CI: 2.63∼5.43], p = 2.13 × 10-14) and CSF Tau (HR = 3.77 [95% CI: 2.64∼5.39], p = 9.53 × 10-15) based on the COX and Log-rank test. Notably, the IBRAIN shows comparable sensitivity (beta = -0.70, p < 1 × 10-16) in capturing longitudinal changes in individuals with conversion to AD than CSF Aβ (beta = -0.26, p = 4.40 × 10-9) and CSF Tau (beta = 0.12, p = 1.02 × 10-5).

Interpretation

Our findings suggested that IBRAIN is a biologically relevant, specific, and sensitive neuroimaging biomarker that can serve as a clinical measure to uncover prodromal AD progression. It has strong potential for application in future clinical practice and treatment trials.

Funding

Science and Technology Innovation 2030 Major Projects, the National Natural Science Foundation of China, Beijing Natural Science Funds, the Fundamental Research Funds for the CentralUniversity, and the Startup Funds for Talents at Beijing Normal University.

Structural Fingerprinting of the Frontal Aslant Tract: Predicting Cognitive Control Capacity and Obsessive-Compulsive Symptoms

White matter of the human brain is influenced by common genetic variations and shaped by neural activity-dependent experiences. Variations in microstructure of cerebral white matter across individuals and even across fiber tracts might underlie differences in cognitive capacity and vulnerabilities to mental disorders. The frontoparietal and cingulo-opercular networks of the brain constitute the central system supporting cognitive functions, and functional connectivity of these networks has been used to distinguish individuals known as "functional fingerprinting." The frontal aslant tract (FAT) that passes through the two networks has been implicated in executive functions. However, whether FAT can be used as a "structural fingerprint" to distinguish individuals and predict an individual's cognitive function and dysfunction is unknown. Here we investigated the fingerprinting property of FAT microstructural profiles using three independent diffusion MRI datasets with repeated scans on human participants including both females and males. We found that diffusion and geometric profiles of FAT can be used to distinguish individuals with a high accuracy. Next, we demonstrated that fractional anisotropy in different FAT segments predicted distinct cognitive functions, including working memory, inhibitory control, and relational reasoning. Finally, we assessed the contribution of altered FAT microstructural profiles to cognitive dysfunction in unmedicated patients with obsessive-compulsive disorders. We found that the altered microstructure in FAT was associated with the severity of obsessive-compulsive symptoms. Collectively, our findings suggest that the microstructural profiles of FAT can identify individuals with a high accuracy and may serve as an imaging marker for predicting an individual's cognitive capacity and disease severity.SIGNIFICANCE STATEMENT The frontoparietal network and cingulo-opercular network of the brain constitute a dual-network architecture for human cognitive functions, and functional connectivity of these two networks can be used as a "functional fingerprint" to distinguish individuals. However, the structural underpinnings of these networks subserving individual heterogeneities in their functional connectivity and cognitive ability remain unknown. We show here that the frontal aslant tract (FAT) that passes through the two networks distinguishes individuals with a high accuracy. Further, we demonstrate that the diffusion profiles of FAT predict distinct cognitive functions in healthy subjects and are associated with the clinical symptoms in patients with obsessive-compulsive disorders. Our findings suggest that the FAT may serve as a unique structural fingerprint underlying individual cognitive capability.

Style transfer generative adversarial networks to harmonize multisite MRI to a single reference image to avoid overcorrection

Recent work within neuroimaging consortia have aimed to identify reproducible, and often subtle, brain signatures of psychiatric or neurological conditions. To allow for high-powered brain imaging analyses, it is often necessary to pool MR images that were acquired with different protocols across multiple scanners. Current retrospective harmonization techniques have shown promise in removing site-related image variation. However, most statistical approaches may over-correct for technical, scanning-related, variation as they cannot distinguish between confounded image-acquisition based variability and site-related population variability. Such statistical methods often require that datasets contain subjects or patient groups with similar clinical or demographic information to isolate the acquisition-based variability. To overcome this limitation, we consider site-related magnetic resonance (MR) imaging harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a single reference image, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multisite datasets with varied demographics. Results demonstrated that our style-encoding model can harmonize MR images, and match intensity profiles, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. We highlight the effectiveness of our method for clinical research by comparing extracted cortical and subcortical features, brain-age estimates, and case-control effect sizes before and after the harmonization. We showed that our harmonization removed the site-related variances, while preserving the anatomical information and clinical meaningful patterns. We further demonstrated that with a diverse training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising tool for ongoing collaborative studies. Source code is released in USC-IGC/style_transfer_harmonization (github.com).

Child Developmental MRI (CDM) project: protocol for a multi-centre, cross-sectional study on elucidating the pathophysiology of attention-deficit/hyperactivity disorder and autism spectrum disorder through a multi-dimensional approach

INTRODUCTION

Neuroimaging studies on attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) have demonstrated differences in extensive brain structure, activity and network. However, there remains heterogeneity and inconsistency across these findings, presumably because of the diversity of the disorders themselves, small sample sizes, and site and parameter differences in MRI scanners, and their overall pathogenesis remains unclear. To address these gaps in the literature, we will apply the travelling-subject approach to correct site differences in MRI scanners and clarify brain structure and network characteristics of children with ADHD and ASD using large samples collected in a multi-centre collaboration. In addition, we will investigate the relationship between these characteristics and genetic, epigenetic, biochemical markers, and behavioural and psychological measures.

METHODS AND ANALYSIS

We will collect resting-state functional MRI (fMRI) and T1-weighted and diffusion-weighted MRI data from 15 healthy adults as travelling subjects and 300 children (ADHD, n=100; ASD, n=100; and typical development, n=100) with multi-dimensional assessments. We will also apply data from more than 1000 samples acquired in our previous neuroimaging studies on ADHD and ASD.

ETHICS AND DISSEMINATION

The study protocol has been approved by the Research Ethics Committee of the University of Fukui Hospital (approval no: 20220601). Our study findings will be submitted to scientific peer-reviewed journals and conferences.

Removing the effects of the site in brain imaging machine-learning - Measurement and extendable benchmark

Multisite machine-learning neuroimaging studies, such as those conducted by the ENIGMA Consortium, need to remove the differences between sites to avoid effects of the site (EoS) that may prevent or fraudulently help the creation of prediction models, leading to impoverished or inflated prediction accuracy. Unfortunately, we have shown earlier that current Methods Aiming to Remove the EoS (MAREoS, e.g., ComBat) cannot remove complex EoS (e.g., including interactions between regions). And complex EoS may bias the accuracy. To overcome this hurdle, groups worldwide are developing novel MAREoS. However, we cannot assess their effectiveness because EoS may either inflate or shrink the accuracy, and MAREoS may both remove the EoS and degrade the data. In this work, we propose a strategy to measure the effectiveness of a MAREoS in removing different types of EoS. FOR MAREOS DEVELOPERS, we provide two multisite MRI datasets with only simple true effects (i.e., detectable by most machine-learning algorithms) and two with only simple EoS (i.e., removable by most MAREoS). First, they should use these datasets to fit machine-learning algorithms after applying the MAREoS. Second, they should use the formulas we provide to calculate the relative accuracy change associated with the MAREoS in each dataset and derive an EoS-removal effectiveness statistic. We also offer similar datasets and formulas for complex true effects and EoS that include first-order interactions. FOR MACHINE-LEARNING RESEARCHERS, we provide an extendable benchmark website to show: a) the types of EoS they should remove for each given machine-learning algorithm and b) the effectiveness of each MAREoS for removing each type of EoS. Relevantly, a MAREoS only able to remove the simple EoS may suffice for simple machine-learning algorithms, whereas more complex algorithms need a MAREoS that can remove more complex EoS. For instance, ComBat removes all simple EoS as needed for predictions based on simple lasso algorithms, but it leaves residual complex EoS that may bias the predictions based on standard support vector machine algorithms.

DORIS: A diffusion MRI-based 10 tissue class deep learning segmentation algorithm tailored to improve anatomically-constrained tractography

Modern tractography algorithms such as anatomically-constrained tractography (ACT) are based on segmentation maps of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). These maps are generally estimated from a T1-weighted (T1w) image and then registered in diffusion weighted images (DWI) space. Registration of T1w to diffusion space and partial volume estimation are challenging and rarely voxel-perfect. Diffusion-based segmentation would, thus, potentially allow not to have higher quality anatomical priors injected in the tractography process. On the other hand, even if FA-based tractography is possible without T1 registration, the literature shows that this technique suffers from multiple issues such as holes in the tracking mask and a high proportion of generated broken and anatomically implausible streamlines. Therefore, there is an important need for a tissue segmentation algorithm that works directly in the native diffusion space. We propose DORIS, a DWI-based deep learning segmentation algorithm. DORIS outputs 10 different tissue classes including WM, GM, CSF, ventricles, and 6 other subcortical structures (putamen, pallidum, hippocampus, caudate, amygdala, and thalamus). DORIS was trained and validated on a wide range of subjects, including 1,000 individuals from 22 to 90 years old from clinical and research DWI acquisitions, from 5 public databases. In the absence of a "true" ground truth in diffusion space, DORIS used a silver standard strategy from Freesurfer output registered onto the DWI. This strategy is extensively evaluated and discussed in the current study. Segmentation maps provided by DORIS are quantitatively compared to Freesurfer and FSL-fast and the impacts on tractography are evaluated. Overall, we show that DORIS is fast, accurate, and reproducible and that DORIS-based tractograms produce bundles with a longer mean length and fewer anatomically implausible streamlines.

FOD-Net: A deep learning method for fiber orientation distribution angular super resolution

Mapping the human connectome using fiber-tracking permits the study of brain connectivity and yields new insights into neuroscience. However, reliable connectome reconstruction using diffusion magnetic resonance imaging (dMRI) data acquired by widely available clinical protocols remains challenging, thus limiting the connectome/tractography clinical applications. Here we develop fiber orientation distribution (FOD) network (FOD-Net), a deep-learning-based framework for FOD angular super-resolution. Our method enhances the angular resolution of FOD images computed from common clinical-quality dMRI data, to obtain FODs with quality comparable to those produced from advanced research scanners. Super-resolved FOD images enable superior tractography and structural connectome reconstruction from clinical protocols. The method was trained and tested with high-quality data from the Human Connectome Project (HCP) and further validated with a local clinical 3.0T scanner as well as with another public available multicenter-multiscanner dataset. Using this method, we improve the angular resolution of FOD images acquired with typical single-shell low-angular-resolution dMRI data (e.g., 32 directions, b=1000s/mm²) to approximate the quality of FODs derived from time-consuming, multi-shell high-angular-resolution dMRI research protocols. We also demonstrate tractography improvement, removing spurious connections and bridging missing connections. We further demonstrate that connectomes reconstructed by super-resolved FODs achieve comparable results to those obtained with more advanced dMRI acquisition protocols, on both HCP and clinical 3.0T data. Advances in deep-learning approaches used in FOD-Net facilitate the generation of high quality tractography/connectome analysis from existing clinical MRI environments. Our code is freely available at https://github.com/ruizengalways/FOD-Net.

Tractography methods and findings in brain tumors and traumatic brain injury

White matter fiber tracking using diffusion magnetic resonance imaging (dMRI) provides a noninvasive approach to map brain connections, but improving anatomical accuracy has been a significant challenge since the birth of tractography methods. Utilizing tractography in brain studies therefore requires understanding of its technical limitations to avoid shortcomings and pitfalls. This review explores tractography limitations and how different white matter pathways pose different challenges to fiber tracking methodologies. We summarize the pros and cons of commonly-used methods, aiming to inform how tractography and its related analysis may lead to questionable results. Extending these experiences, we review the clinical utilization of tractography in patients with brain tumors and traumatic brain injury, starting from tensor-based tractography to more advanced methods. We discuss current limitations and highlight novel approaches in the context of these two conditions to inform future tractography developments.

MASiVar: Multisite, multiscanner, and multisubject acquisitions for studying variability in diffusion weighted MRI

PURPOSE

Diffusion-weighted imaging allows investigators to identify structural, microstructural, and connectivity-based differences between subjects, but variability due to session and scanner biases is a challenge.

METHODS

To investigate DWI variability, we present MASiVar, a multisite data set consisting of 319 diffusion scans acquired at 3 T from b = 1000 to 3000 s/mm2 across 14 healthy adults, 83 healthy children (5 to 8 years), three sites, and four scanners as a publicly available, preprocessed, and de-identified data set. With the adult data, we demonstrate the capacity of MASiVar to simultaneously quantify the intrasession, intersession, interscanner, and intersubject variability of four common DWI processing approaches: (1) a tensor signal representation, (2) a multi-compartment neurite orientation dispersion and density model, (3) white-matter bundle segmentation, and (4) structural connectomics. Respectively, we evaluate region-wise fractional anisotropy, mean diffusivity, and principal eigenvector; region-wise CSF volume fraction, intracellular volume fraction, and orientation dispersion index; bundle-wise shape, volume, fractional anisotropy, and length; and whole connectome correlation and maximized modularity, global efficiency, and characteristic path length.

RESULTS

We plot the variability in these measures at each level and find that it consistently increases with intrasession to intersession to interscanner to intersubject effects across all processing approaches and that sometimes interscanner variability can approach intersubject variability.

CONCLUSIONS

This study demonstrates the potential of MASiVar to more globally investigate DWI variability across multiple levels and processing approaches simultaneously and suggests harmonization between scanners for multisite analyses should be considered before inference of group differences on subjects.

Fiber tractography bundle segmentation depends on scanner effects, vendor effects, acquisition resolution, diffusion sampling scheme, diffusion sensitization, and bundle segmentation workflow

When investigating connectivity and microstructure of white matter pathways of the brain using diffusion tractography bundle segmentation, it is important to understand potential confounds and sources of variation in the process. While cross-scanner and cross-protocol effects on diffusion microstructure measures are well described (in particular fractional anisotropy and mean diffusivity), it is unknown how potential sources of variation effect bundle segmentation results, which features of the bundle are most affected, where variability occurs, nor how these sources of variation depend upon the method used to reconstruct and segment bundles. In this study, we investigate six potential sources of variation, or confounds, for bundle segmentation: variation (1) across scan repeats, (2) across scanners, (3) across vendors (4) across acquisition resolution, (5) across diffusion schemes, and (6) across diffusion sensitization. We employ four different bundle segmentation workflows on two benchmark multi-subject cross-scanner and cross-protocol databases, and investigate reproducibility and biases in volume overlap, shape geometry features of fiber pathways, and microstructure features within the pathways. We find that the effects of acquisition protocol, in particular acquisition resolution, result in the lowest reproducibility of tractography and largest variation of features, followed by vendor-effects, scanner-effects, and finally diffusion scheme and b-value effects which had similar reproducibility as scan-rescan variation. However, confounds varied both across pathways and across segmentation workflows, with some bundle segmentation workflows more (or less) robust to sources of variation. Despite variability, bundle dissection is consistently able to recover the same location of pathways in the deep white matter, with variation at the gray matter/ white matter interface. Next, we show that differences due to the choice of bundle segmentation workflows are larger than any other studied confound, with low-to-moderate overlap of the same intended pathway when segmented using different methods. Finally, quantifying microstructure features within a pathway, we show that tractography adds variability over-and-above that which exists due to noise, scanner effects, and acquisition effects. Overall, these confounds need to be considered when harmonizing diffusion datasets, interpreting or combining data across sites, and when attempting to understand the successes and limitations of different methodologies in the design and development of new tractography or bundle segmentation methods.

Style Transfer Using Generative Adversarial Networks for Multi-Site MRI Harmonization

Large data initiatives and high-powered brain imaging analyses require the pooling of MR images acquired across multiple scanners, often using different protocols. Prospective cross-site harmonization often involves the use of a phantom or traveling subjects. However, as more datasets are becoming publicly available, there is a growing need for retrospective harmonization, pooling data from sites not originally coordinated together. Several retrospective harmonization techniques have shown promise in removing cross-site image variation. However, most unsupervised methods cannot distinguish between image-acquisition based variability and cross-site population variability, so they require that datasets contain subjects or patient groups with similar clinical or demographic information. To overcome this limitation, we consider cross-site MRI image harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a reference image directly, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multi-site datasets with varied demographics. Results demonstrated that our style-encoding model can harmonize MR images, and match intensity profiles, successfully, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. Moreover, we further demonstrated that if we included diverse enough images into the training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising novel tool for ongoing collaborative studies.

Interactions Between Aging and Alzheimer's Disease on Structural Brain Networks

Normative aging and Alzheimer's disease (AD) propagation alter anatomical connections among brain parcels. However, the interaction between the trajectories of age- and AD-linked alterations in the topology of the structural brain network is not well understood. In this study, diffusion-weighted magnetic resonance imaging (MRI) datasets of 139 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were used to document their structural brain networks. The 139 participants consist of 45 normal controls (NCs), 37 with early mild cognitive impairment (EMCI), 27 with late mild cognitive impairment (LMCI), and 30 AD patients. All subjects were further divided into three subgroups based on their age (56-65, 66-75, and 71-85 years). After the structural connectivity networks were built using anatomically-constrained deterministic tractography, their global and nodal topological properties were estimated, including network efficiency, characteristic path length, transitivity, modularity coefficient, clustering coefficient, and betweenness. Statistical analyses were then performed on these metrics using linear regression, and one- and two-way ANOVA testing to examine group differences and interactions between aging and AD propagation. No significant interactions were found between aging and AD propagation in the global topological metrics (network efficiency, characteristic path length, transitivity, and modularity coefficient). However, nodal metrics (clustering coefficient and betweenness centrality) of some cortical parcels exhibited significant interactions between aging and AD propagation, with affected parcels including left superior temporal, right pars triangularis, and right precentral. The results collectively confirm the age-related deterioration of structural networks in MCI and AD patients, providing novel insight into the cross effects of aging and AD disorder on brain structural networks. Some early symptoms of AD may also be due to age-associated anatomic vulnerability interacting with early anatomic changes associated with AD.

Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data

We present a rotation-equivariant self-supervised learning framework for the sparse deconvolution of non-negative scalar fields on the unit sphere. Spherical signals with multiple peaks naturally arise in Diffusion MRI (dMRI), where each voxel consists of one or more signal sources corresponding to anisotropic tissue structure such as white matter. Due to spatial and spectral partial voluming, clinically-feasible dMRI struggles to resolve crossing-fiber white matter configurations, leading to extensive development in spherical deconvolution methodology to recover underlying fiber directions. However, these methods are typically linear and struggle with small crossing-angles and partial volume fraction estimation. In this work, we improve on current methodologies by nonlinearly estimating fiber structures via self-supervised spherical convolutional networks with guaranteed equivariance to spherical rotation. We perform validation via extensive single and multi-shell synthetic benchmarks demonstrating competitive performance against common base-lines. We further show improved downstream performance on fiber tractography measures on the Tractometer benchmark dataset. Finally, we show downstream improvements in terms of tractography and partial volume estimation on a multi-shell dataset of human subjects.

Deep learning based segmentation of brain tissue from diffusion MRI

Segmentation of brain tissue types from diffusion MRI (dMRI) is an important task, required for quantification of brain microstructure and for improving tractography. Current dMRI segmentation is mostly based on anatomical MRI (e.g., T1- and T2-weighted) segmentation that is registered to the dMRI space. However, such inter-modality registration is challenging due to more image distortions and lower image resolution in dMRI as compared with anatomical MRI. In this study, we present a deep learning method for diffusion MRI segmentation, which we refer to as DDSeg. Our proposed method learns tissue segmentation from high-quality imaging data from the Human Connectome Project (HCP), where registration of anatomical MRI to dMRI is more precise. The method is then able to predict a tissue segmentation directly from new dMRI data, including data collected with different acquisition protocols, without requiring anatomical data and inter-modality registration. We train a convolutional neural network (CNN) to learn a tissue segmentation model using a novel augmented target loss function designed to improve accuracy in regions of tissue boundary. To further improve accuracy, our method adds diffusion kurtosis imaging (DKI) parameters that characterize non-Gaussian water molecule diffusion to the conventional diffusion tensor imaging parameters. The DKI parameters are calculated from the recently proposed mean-kurtosis-curve method that corrects implausible DKI parameter values and provides additional features that discriminate between tissue types. We demonstrate high tissue segmentation accuracy on HCP data, and also when applying the HCP-trained model on dMRI data from other acquisitions with lower resolution and fewer gradient directions.

Brain/MINDS beyond human brain MRI project: A protocol for multi-level harmonization across brain disorders throughout the lifespan

Psychiatric and neurological disorders are afflictions of the brain that can affect individuals throughout their lifespan. Many brain magnetic resonance imaging (MRI) studies have been conducted; however, imaging-based biomarkers are not yet well established for diagnostic and therapeutic use. This article describes an outline of the planned study, the Brain/MINDS Beyond human brain MRI project (BMB-HBM, FY2018 ~ FY2023), which aims to establish clinically-relevant imaging biomarkers with multi-site harmonization by collecting data from healthy traveling subjects (TS) at 13 research sites. Collection of data in psychiatric and neurological disorders across the lifespan is also scheduled at 13 sites, whereas designing measurement procedures, developing and analyzing neuroimaging protocols, and databasing are done at three research sites. A high-quality scanning protocol, Harmonization Protocol (HARP), was established for five high-quality 3 T scanners to obtain multimodal brain images including T1 and T2-weighted, resting-state and task functional and diffusion-weighted MRI. Data are preprocessed and analyzed using approaches developed by the Human Connectome Project. Preliminary results in 30 TS demonstrated cortical thickness, myelin, functional connectivity measures are comparable across 5 scanners, suggesting sensitivity to subject-specific connectome. A total of 75 TS and more than two thousand patients with various psychiatric and neurological disorders are scheduled to participate in the project, allowing a mixed model statistical harmonization. The HARP protocols are publicly available online, and all the imaging, demographic and clinical information, harmonizing database will also be made available by 2024. To the best of our knowledge, this is the first project to implement a prospective, multi-level harmonization protocol with multi-site TS data. It explores intractable brain disorders across the lifespan and may help to identify the disease-specific pathophysiology and imaging biomarkers for clinical practice.

Deep Learning-Based Segmentation to Establish East Asian Normative Volumes Using Multisite Structural MRI

Normative brain magnetic resonance imaging (MRI) is essential to interpret the state of an individual's brain health. However, a normative study is often expensive for small research groups. Although several attempts have been made to establish brain MRI norms, the focus has been limited to certain age ranges. This study aimed to establish East Asian normative brain data using multi-site MRI and determine the robustness of these data for clinical research. Normative MRI was gathered covering a wide range of cognitively normal East Asian populations (age: 18-96 years) from two open sources and three research sites. Eight sub-regional volumes were extracted in the left and right hemispheres using an in-house deep learning-based tool. Repeated measure consistency and multicenter reliability were determined using intraclass correlation coefficients and compared to a widely used tool, FreeSurfer. Our results showed highly consistent outcomes with high reliability across sites. Our method outperformed FreeSurfer in repeated measure consistency for most structures and multicenter reliability for all structures. The normative MRI we constructed was able to identify sub-regional differences in mild cognitive impairments and dementia after covariate adjustments. Our investigation suggests it is possible to provide a sound normative reference for neurodegenerative or aging research.