Deep multimodal saliency parcellation of cerebellar pathways: Linking microstructure and individual function through explainable multitask learning.

Parcellation of human cerebellar pathways is essential for advancing our understanding of the human brain. Existing diffusion magnetic resonance imaging tractography parcellation methods have been successful in defining major cerebellar fibre tracts, while relying solely on fibre tract structure. However, each fibre tract may relay information related to multiple cognitive and motor functions of the cerebellum. Hence, it may be beneficial for parcellation to consider the potential importance of the fibre tracts for individual motor and cognitive functional performance measures. In this work, we propose a multimodal data-driven method for cerebellar pathway parcellation, which incorporates both measures of microstructure and connectivity, and measures of individual functional performance. Our method involves first training a multitask deep network to predict various cognitive and motor measures from a set of fibre tract structural features. The importance of each structural feature for predicting each functional measure is then computed, resulting in a set of structure-function saliency values that are clustered to parcellate cerebellar pathways. We refer to our method as Deep Multimodal Saliency Parcellation (DeepMSP), as it computes the saliency of structural measures for predicting cognitive and motor functional performance, with these saliencies being applied to the task of parcellation. Applying DeepMSP to a large-scale dataset from the Human Connectome Project Young Adult study (n = 1065), we found that it was feasible to identify multiple cerebellar pathway parcels with unique structure-function saliency patterns that were stable across training folds. We thoroughly experimented with all stages of the DeepMSP pipeline, including network selection, structure-function saliency representation, clustering algorithm, and cluster count. We found that a 1D convolutional neural network architecture and a transformer network architecture both performed comparably for the multitask prediction of endurance, strength, reading decoding, and vocabulary comprehension, with both architectures outperforming a fully connected network architecture. Quantitative experiments demonstrated that a proposed low-dimensional saliency representation with an explicit measure of motor versus cognitive category bias achieved the best parcellation results, while a parcel count of four was most successful according to standard cluster quality metrics. Our results suggested that motor and cognitive saliencies are distributed across the cerebellar white matter pathways. Inspection of the final k = 4 parcellation revealed that the highest-saliency parcel was most salient for the prediction of both motor and cognitive performance scores and included parts of the middle and superior cerebellar peduncles. Our proposed saliency-based parcellation framework, DeepMSP, enables multimodal, data-driven tractography parcellation. Through utilising both structural features and functional performance measures, this parcellation strategy may have the potential to enhance the study of structure-function relationships of the cerebellar pathways.

Time-division multiplexing (TDM) sequence removes bias in T2 estimation and relaxation-diffusion measurements.

PURPOSE: To compare the performance of multi-echo (ME) and time-division multiplexing (TDM) sequences for accelerated relaxation-diffusion MRI (rdMRI) acquisition and to examine their reliability in estimating accurate rdMRI microstructure measures. METHOD: The ME, TDM, and the reference single-echo (SE) sequences with six TEs were implemented using Pulseq with single-band (SB) and multi-band 2 (MB2) acceleration factors. On a diffusion phantom, the image intensities of the three sequences were compared, and the differences were quantified using the normalized RMS error (NRMSE). Shinnar-Le Roux (SLR) pulses were implemented for the SB-ME and SB-SE sequences to investigate the impact of slice profiles on ME sequences. For the in-vivo brain scan, besides the image intensity comparison and T2-estimates, different methods were used to assess sequence-related effects on microstructure estimation, including the relaxation diffusion imaging moment (REDIM) and the maximum-entropy relaxation diffusion distribution (MaxEnt-RDD). RESULTS: TDM performance was similar to the gold standard SE acquisition, whereas ME showed greater biases (3-4× larger NRMSEs for phantom, 2× for in-vivo). T2 values obtained from TDM closely matched SE, whereas ME sequences underestimated the T2 relaxation time. TDM provided similar diffusion and relaxation parameters as SE using REDIM, whereas SB-ME exhibited a 60% larger bias in the map and on average 3.5× larger bias in the covariance between relaxation-diffusion coefficients. CONCLUSION: Our analysis demonstrates that TDM provides a more accurate estimation of relaxation-diffusion measurements while accelerating the acquisitions by a factor of 2 to 3.

Repetitive Head Impacts and Perivascular Space Volume in Former American Football Players.

Importance: Exposure to repetitive head impacts (RHI) is associated with increased risk for neurodegeneration. Accumulation of toxic proteins due to impaired brain clearance is suspected to play a role. Objective: To investigate whether perivascular space (PVS) volume is associated with lifetime exposure to RHI in individuals at risk for RHI-associated neurodegeneration. Design, Setting, and Participants: This cross-sectional study was part of the Diagnostics, Imaging, and Genetics Network for the Objective Study and Evaluation of Chronic Traumatic Encephalopathy (DIAGNOSE CTE) Research Project, a 7-year multicenter study consisting of 4 US study sites. Data were collected from September 2016 to February 2020 and analyses were performed between May 2021 and October 2023. After controlling for magnetic resonance image (MRI) and processing quality, former American football players and unexposed asymptomatic control participants were included in analyses. Exposure: Prior exposure to RHI while participating in American football was estimated using the 3 cumulative head impact indices (CHII-G, linear acceleration; CHII-R, rotational acceleration; and CHII, number of head impacts). Main Outcomes and Measures: Individual PVS volume was calculated in the white matter of structural MRI. Cognitive impairment was based on neuropsychological assessment. Linear regression models were used to assess associations of PVS volume with neuropsychological assessments in former American football players. All analyses were adjusted for confounders associated with PVS volume. Results: Analyses included 224 participants (median [IQR] age, 57 [51-65] years), with 170 male former football players (114 former professional athletes, 56 former collegiate athletes) and 54 male unexposed control participants. Former football players had larger PVS volume compared with the unexposed group (mean difference, 0.28 [95% CI, 0.00-0.56]; P = .05). Within the football group, PVS volume was associated with higher CHII-R (ß = 2.71 × 10-8 [95% CI, 0.50 × 10-8 to 4.93 × 10-8]; P = .03) and CHII-G (ß = 2.24 × 10-6 [95% CI, 0.35 × 10-6 to 4.13 × 10-6]; P = .03). Larger PVS volume was also associated with worse performance on cognitive functioning in former American football players (ß = -0.74 [95% CI, -1.35 to -0.13]; P = .04). Conclusions and Relevance: These findings suggest that impaired perivascular brain clearance, as indicated by larger PVS volume, may contribute to the association observed between RHI exposure and neurodegeneration.

An Introduction to the Human Connectome Project for Early Psychosis.

BACKGROUND: The time following a recent onset of psychosis is a critical period during which intervention may be maximally effective. Studying individuals in this period also offers an opportunity to investigate putative brain biomarkers of illness prior to the long-term effects of chronicity and medication. The Human Connectome Project for Early Psychosis (HCP-EP) was funded by the National Institutes of Mental Health (NIMH) as an extension of the original Human Connectome Project's approach to understanding the human brain and its structural and functional connections. DESIGN: The HCP-EP data were collected at 3 sites in Massachusetts (Beth Israel Deaconess Medical Center, McLean Hospital, and Massachusetts General Hospital), and one site in Indiana (Indiana University). Brigham and Women's Hospital served as the data coordination center and as an imaging site. RESULTS: The HCP-EP dataset includes high-quality clinical, cognitive, functional, neuroimaging, and blood specimen data acquired from 303 individuals between the ages of 16-35 years old with affective psychosis (n = 75), non-affective psychosis (n = 148), and healthy controls (n = 80). Participants with early psychosis were within 5 years of illness onset (mean duration = 1.9 years, standard deviation = 1.4 years). All data and novel or modified analytic tools developed as part of the study are publicly available to the research community through the NIMH Data Archive (NDA) or GitHub (https://github.com/pnlbwh). CONCLUSIONS: This paper provides an overview of the specific HCP-EP procedures, assessments, and protocols, as well as a brief characterization of the study participants to make it easier for researchers to use this rich dataset. Although we focus here on discussing and comparing affective and non-affective psychosis groups, the HCP-EP dataset also provides sufficient information for investigators to group participants differently.

A diffusion MRI tractography atlas for concurrent white matter mapping across Eastern and Western populations.

The study of brain differences across Eastern and Western populations provides vital insights for understanding potential cultural and genetic influences on cognition and mental health. Diffusion MRI (dMRI) tractography is an important tool in assessing white matter (WM) connectivity and brain tissue microstructure across different populations. However, a comprehensive investigation into WM fiber tracts between Eastern and Western populations is challenged due to the lack of a cross-population WM atlas and the large site-specific variability of dMRI data. This study presents a dMRI tractography atlas, namely the East-West WM Atlas, for concurrent WM mapping between Eastern and Western populations and creates a large, harmonized dMRI dataset (n=306) based on the Human Connectome Project and the Chinese Human Connectome Project. The curated WM atlas, as well as subject-specific data including the harmonized dMRI data, the whole brain tractography data, and parcellated WM fiber tracts and their diffusion measures, are publicly released. This resource is a valuable addition to facilitating the exploration of brain commonalities and differences across diverse cultural backgrounds.

TractoSCR: a novel supervised contrastive regression framework for prediction of neurocognitive measures using multi-site harmonized diffusion MRI tractography.

Neuroimaging-based prediction of neurocognitive measures is valuable for studying how the brain's structure relates to cognitive function. However, the accuracy of prediction using popular linear regression models is relatively low. We propose a novel deep regression method, namely TractoSCR, that allows full supervision for contrastive learning in regression tasks using diffusion MRI tractography. TractoSCR performs supervised contrastive learning by using the absolute difference between continuous regression labels (i.e., neurocognitive scores) to determine positive and negative pairs. We apply TractoSCR to analyze a large-scale dataset including multi-site harmonized diffusion MRI and neurocognitive data from 8,735 participants in the Adolescent Brain Cognitive Development (ABCD) Study. We extract white matter microstructural measures using a fine parcellation of white matter tractography into fiber clusters. Using these measures, we predict three scores related to domains of higher-order cognition (general cognitive ability, executive function, and learning/memory). To identify important fiber clusters for prediction of these neurocognitive scores, we propose a permutation feature importance method for high-dimensional data. We find that TractoSCR obtains significantly higher accuracy of neurocognitive score prediction compared to other state-of-the-art methods. We find that the most predictive fiber clusters are predominantly located within the superficial white matter and projection tracts, particularly the superficial frontal white matter and striato-frontal connections. Overall, our results demonstrate the utility of contrastive representation learning methods for regression, and in particular for improving neuroimaging-based prediction of higher-order cognitive abilities. Our code will be available at: https://github.com/SlicerDMRI/TractoSCR.

Intimate partner violence perpetration among veterans: associations with neuropsychiatric symptoms and limbic microstructure.

Background: Intimate partner violence (IPV) perpetration is highly prevalent among veterans. Suggested risk factors of IPV perpetration include combat exposure, post-traumatic stress disorder (PTSD), depression, alcohol use, and mild traumatic brain injury (mTBI). While the underlying brain pathophysiological characteristics associated with IPV perpetration remain largely unknown, previous studies have linked aggression and violence to alterations of the limbic system. Here, we investigate whether IPV perpetration is associated with limbic microstructural abnormalities in military veterans. Further, we test the effect of potential risk factors (i.e., PTSD, depression, substance use disorder, mTBI, and war zone-related stress) on the prevalence of IPV perpetration. Methods: Structural and diffusion-weighted magnetic resonance imaging (dMRI) data were acquired from 49 male veterans of the Iraq and Afghanistan wars (Operation Enduring Freedom/Operation Iraqi Freedom; OEF/OIF) of the Translational Research Center for TBI and Stress Disorders (TRACTS) study. IPV perpetration was assessed using the psychological aggression and physical assault sub-scales of the Revised Conflict Tactics Scales (CTS2). Odds ratios were calculated to assess the likelihood of IPV perpetration in veterans with either of the following diagnoses: PTSD, depression, substance use disorder, or mTBI. Fractional anisotropy tissue (FA) measures were calculated for limbic gray matter structures (amygdala-hippocampus complex, cingulate, parahippocampal gyrus, entorhinal cortex). Partial correlations were calculated between IPV perpetration, neuropsychiatric symptoms, and FA. Results: Veterans with a diagnosis of PTSD, depression, substance use disorder, or mTBI had higher odds of perpetrating IPV. Greater war zone-related stress, and symptom severity of PTSD, depression, and mTBI were significantly associated with IPV perpetration. CTS2 (psychological aggression), a measure of IPV perpetration, was associated with higher FA in the right amygdala-hippocampus complex (r = 0.400, p = 0.005). Conclusion: Veterans with psychiatric disorders and/or mTBI exhibit higher odds of engaging in IPV perpetration. Further, the more severe the symptoms of PTSD, depression, or TBI, and the greater the war zone-related stress, the greater the frequency of IPV perpetration. Moreover, we report a significant association between psychological aggression against an intimate partner and microstructural alterations in the right amygdala-hippocampus complex. These findings suggest the possibility of a structural brain correlate underlying IPV perpetration that requires further research.

Posttraumatic survivor guilt is associated with white matter microstructure alterations.

BACKGROUND: Military veterans with posttraumatic stress disorder (PTSD) commonly experience posttraumatic guilt. Guilt over commission or omission evolves when responsibility is assumed for an unfortunate outcome (e.g., the death of a fellow combatant). Survivor guilt is a state of intense emotional distress experienced by the weight of knowing that one survived while others did not. METHODS: This study of the Translational Research Center for TBI and Stress Disorders (TRACTS) analyzed structural and diffusion-weighted magnetic resonance imaging data from 132 male Iraq/Afghanistan veterans with PTSD. The Clinician-Administered PTSD Scale for DSM-IV (CAPS-IV) was employed to classify guilt. Thirty (22.7 %) veterans experienced guilt over acts of commission or omission, 34 (25.8 %) experienced survivor guilt, and 68 (51.5 %) had no posttraumatic guilt. White matter microstructure (fractional anisotropy, FA), cortical thickness, and cortical volume were compared between veterans with guilt over acts of commission or omission, veterans with survivor guilt, and veterans without guilt. RESULTS: Veterans with survivor guilt had significantly lower white matter FA compared to veterans who did not experience guilt (p < .001), affecting several regions of major white matter fiber bundles. There were no significant differences in white matter FA, cortical thickness, or volumes between veterans with guilt over acts of commission or omission and veterans without guilt (p > .050). LIMITATIONS: This cross-sectional study with exclusively male veterans precludes inferences of causality between the studied variables and generalizability to the larger veteran population that includes women. CONCLUSION: Survivor guilt may be a particularly impactful form of posttraumatic guilt that requires specific treatment efforts targeting brain health.

Time-division multiplexing (TDM) sequence removes bias in T2 estimation and relaxation-diffusion measurements.

Purpose: To compare the performance of multi-echo (ME) and time-division multiplexing (TDM) sequences for accelerated relaxation-diffusion MRI (rdMRI) acquisition and to examine their reliability in estimating accurate rdMRI microstructure measures. Method: The ME, TDM, and the reference single-echo (SE) sequences with six echo times (TE) were implemented using Pulseq with single-band (SB-) and multi-band 2 (MB2-) acceleration factors. On a diffusion phantom, the image intensities of the three sequences were compared, and the differences were quantified using the normalized root mean squared error (NRMSE). For the in-vivo brain scan, besides the image intensity comparison and T2-estimates, different methods were used to assess sequence-related effects on microstructure estimation, including the relaxation diffusion imaging moment (REDIM) and the maximum-entropy relaxation diffusion distribution (MaxEnt-RDD). Results: TDM performance was similar to the gold standard SE acquisition, whereas ME showed greater biases (3-4× larger NRMSEs for phantom, 2× for in-vivo). T2 values obtained from TDM closely matched SE, whereas ME sequences underestimated the T2 relaxation time. TDM provided similar diffusion and relaxation parameters as SE using REDIM, whereas SB-ME exhibited a 60% larger bias in the map and on average 3.5× larger bias in the covariance between relaxation-diffusion coefficients. Conclusion: Our analysis demonstrates that TDM provides a more accurate estimation of relaxation-diffusion measurements while accelerating the acquisitions by a factor of 2 to 3.

Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction.

Shape plays an important role in computer graphics, offering informative features to convey an object's morphology and functionality. Shape analysis in brain imaging can help interpret structural and functionality correlations of the human brain. In this work, we investigate the shape of the brain's 3D white matter connections and its potential predictive relationship to human cognitive function. We reconstruct brain connections as sequences of 3D points using diffusion magnetic resonance imaging (dMRI) tractography. To describe each connection, we extract 12 shape descriptors in addition to traditional dMRI connectivity and tissue microstructure features. We introduce a novel framework, Shape--fused Fiber Cluster Transformer (SFFormer), that leverages a multi-head cross-attention feature fusion module to predict subject-specific language performance based on dMRI tractography. We assess the performance of the method on a large dataset including 1065 healthy young adults. The results demonstrate that both the transformer-based SFFormer model and its inter/intra feature fusion with shape, microstructure, and connectivity are informative, and together, they improve the prediction of subject-specific language performance scores. Overall, our results indicate that the shape of the brain's connections is predictive of human language function.

Investigating the structural network underlying brain-immune interactions using combined histopathology and neuroimaging: a critical review for its relevance in acute and long COVID-19.

Current views on immunity support the idea that immunity extends beyond defense functions and is tightly intertwined with several other fields of biology such as virology, microbiology, physiology and ecology. It is also critical for our understanding of autoimmunity and cancer, two topics of great biological relevance and for critical public health considerations such as disease prevention and treatment. Central to this review, the immune system is known to interact intimately with the nervous system and has been recently hypothesized to be involved not only in autonomic and limbic bio-behaviors but also in cognitive function. Herein we review the structural architecture of the brain network involved in immune response. Furthermore, we elaborate upon the implications of inflammatory processes affecting brain-immune interactions as reported recently in pathological conditions due to SARS-Cov-2 virus infection, namely in acute and post-acute COVID-19. Moreover, we discuss how current neuroimaging techniques combined with ad hoc clinical autopsies and histopathological analyses could critically affect the validity of clinical translation in studies of human brain-immune interactions using neuroimaging. Advances in our understanding of brain-immune interactions are expected to translate into novel therapeutic avenues in a vast array of domains including cancer, autoimmune diseases or viral infections such as in acute and post-acute or Long COVID-19.

Executive functioning, behavior, and white matter microstructure in the chronic phase after pediatric mild traumatic brain injury: results from the adolescent brain cognitive development study.

BACKGROUND: Mild traumatic brain injury (mTBI) is common in children. Long-term cognitive and behavioral outcomes as well as underlying structural brain alterations following pediatric mTBI have yet to be determined. In addition, the effect of age-at-injury on long-term outcomes is largely unknown. METHODS: Children with a history of mTBI (n = 406; Mage = 10 years, SDage = 0.63 years) who participated in the Adolescent Brain Cognitive Development (ABCD) study were matched (1:2 ratio) with typically developing children (TDC; n = 812) and orthopedic injury (OI) controls (n = 812). Task-based executive functioning, parent-rated executive functioning and emotion-regulation, and self-reported impulsivity were assessed cross-sectionally. Regression models were used to examine the effect of mTBI on these domains. The effect of age-at-injury was assessed by comparing children with their first mTBI at either 0-3, 4-7, or 8-10 years to the respective matched TDC controls. Fractional anisotropy (FA) and mean diffusivity (MD), both MRI-based measures of white matter microstructure, were compared between children with mTBI and controls. RESULTS: Children with a history of mTBI displayed higher parent-rated executive dysfunction, higher impulsivity, and poorer self-regulation compared to both control groups. At closer investigation, these differences to TDC were only present in one respective age-at-injury group. No alterations were found in task-based executive functioning or white matter microstructure. CONCLUSIONS: Findings suggest that everyday executive function, impulsivity, and emotion-regulation are affected years after pediatric mTBI. Outcomes were specific to the age at which the injury occurred, suggesting that functioning is differently affected by pediatric mTBI during vulnerable periods. Groups did not differ in white matter microstructure.

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance.

We propose a geometric deep-learning-based framework, TractGeoNet, for performing regression using diffusion magnetic resonance imaging (dMRI) tractography and associated pointwise tissue microstructure measurements. By employing a point cloud representation, TractGeoNet can directly utilize tissue microstructure and positional information from all points within a fiber tract without the need to average or bin data along the streamline as traditionally required by dMRI tractometry methods. To improve regression performance, we propose a novel loss function, the Paired-Siamese Regression loss, which encourages the model to focus on accurately predicting the relative differences between regression label scores rather than just their absolute values. In addition, to gain insight into the brain regions that contribute most strongly to the prediction results, we propose a Critical Region Localization algorithm. This algorithm identifies highly predictive anatomical regions within the white matter fiber tracts for the regression task. We evaluate the effectiveness of the proposed method by predicting individual performance on two neuropsychological assessments of language using a dataset of 20 association white matter fiber tracts from 806 subjects from the Human Connectome Project Young Adult dataset. The results demonstrate superior prediction performance of TractGeoNet compared to several popular regression models that have been applied to predict individual cognitive performance based on neuroimaging features. Of the twenty tracts studied, we find that the left arcuate fasciculus tract is the most highly predictive of the two studied language performance assessments. Within each tract, we localize critical regions whose microstructure and point information are highly and consistently predictive of language performance across different subjects and across multiple independently trained models. These critical regions are widespread and distributed across both hemispheres and all cerebral lobes, including areas of the brain considered important for language function such as superior and anterior temporal regions, pars opercularis, and precentral gyrus. Overall, TractGeoNet demonstrates the potential of geometric deep learning to enhance the study of the brain's white matter fiber tracts and to relate their structure to human traits such as language performance.

Reduced cross-scanner variability using vendor-agnostic sequences for single-shell diffusion MRI.

PURPOSE: To reduce the inter-scanner variability of diffusion MRI (dMRI) measures between scanners from different vendors by developing a vendor-neutral dMRI pulse sequence using the open-source vendor-agnostic Pulseq platform. METHODS: We implemented a standard EPI based dMRI sequence in Pulseq. We tested it on two clinical scanners from different vendors (Siemens Prisma and GE Premier), systematically evaluating and comparing the within- and inter-scanner variability across the vendors, using both the vendor-provided and Pulseq dMRI sequences. Assessments covered both a diffusion phantom and three human subjects, using standard error (SE) and Lin's concordance correlation to measure the repeatability and reproducibility of standard DTI metrics including fractional anisotropy (FA) and mean diffusivity (MD). RESULTS: Identical dMRI sequences were executed on both scanners using Pulseq. On the phantom, the Pulseq sequence showed more than a 2.5× reduction in SE (variability) across Siemens and GE scanners. Furthermore, Pulseq sequences exhibited markedly reduced SE in-vivo, maintaining scan-rescan repeatability while delivering lower variability in FA and MD (more than 50% reduction in cortical/subcortical regions) compared to vendor-provided sequences. CONCLUSION: The Pulseq diffusion sequence reduces the cross-scanner variability for both phantom and in-vivo data, which will benefit multi-center neuroimaging studies and improve the reproducibility of neuroimaging studies.

Harmonized diffusion MRI data and white matter measures from the Adolescent Brain Cognitive Development Study.

The Adolescent Brain Cognitive Development (ABCD) Study® has collected data from over 10,000 children across 21 sites, providing insights into adolescent brain development. However, site-specific scanner variability has made it challenging to use diffusion MRI (dMRI) data from this study. To address this, a dataset of harmonized and processed ABCD dMRI data (from release 3) has been created, comprising quality-controlled imaging data from 9,345 subjects, focusing exclusively on the baseline session, i.e., the first time point of the study. This resource required substantial computational time (approx. 50,000 CPU hours) for harmonization, whole-brain tractography, and white matter parcellation. The dataset includes harmonized dMRI data, 800 white matter clusters, 73 anatomically labeled white matter tracts in full and low resolution, and 804 different dMRI-derived measures per subject (72.3 TB total size). Accessible via the NIMH Data Archive, it offers a large-scale dMRI dataset for studying structural connectivity in child and adolescent neurodevelopment. Additionally, several post-harmonization experiments were conducted to demonstrate the success of the harmonization process on the ABCD dataset.

Neural orientation distribution fields for estimation and uncertainty quantification in diffusion MRI.

Inferring brain connectivity and structure in-vivo requires accurate estimation of the orientation distribution function (ODF), which encodes key local tissue properties. However, estimating the ODF from diffusion MRI (dMRI) signals is a challenging inverse problem due to obstacles such as significant noise, high-dimensional parameter spaces, and sparse angular measurements. In this paper, we address these challenges by proposing a novel deep-learning based methodology for continuous estimation and uncertainty quantification of the spatially varying ODF field. We use a neural field (NF) to parameterize a random series representation of the latent ODFs, implicitly modeling the often ignored but valuable spatial correlation structures in the data, and thereby improving efficiency in sparse and noisy regimes. An analytic approximation to the posterior predictive distribution is derived which can be used to quantify the uncertainty in the ODF estimate at any spatial location, avoiding the need for expensive resampling-based approaches that are typically employed for this purpose. We present empirical evaluations on both synthetic and real in-vivo diffusion data, demonstrating the advantages of our method over existing approaches.

Tractography-based automated identification of the retinogeniculate visual pathway with novel microstructure-informed supervised contrastive learning.

The retinogeniculate visual pathway (RGVP) is responsible for carrying visual information from the retina to the lateral geniculate nucleus. Identification and visualization of the RGVP are important in studying the anatomy of the visual system and can inform the treatment of related brain diseases. Diffusion MRI (dMRI) tractography is an advanced imaging method that uniquely enables in vivo mapping of the 3D trajectory of the RGVP. Currently, identification of the RGVP from tractography data relies on expert (manual) selection of tractography streamlines, which is time-consuming, has high clinical and expert labor costs, and is affected by inter-observer variability. In this paper, we present a novel deep learning framework, DeepRGVP , to enable fast and accurate identification of the RGVP from dMRI tractography data. We design a novel microstructure-informed supervised contrastive learning method that leverages both streamline label and tissue microstructure information to determine positive and negative pairs. We propose a simple and successful streamline-level data augmentation method to address highly imbalanced training data, where the number of RGVP streamlines is much lower than that of non-RGVP streamlines. We perform comparisons with several state-of-the-art deep learning methods that were designed for tractography parcellation, and we show superior RGVP identification results using DeepRGVP. In addition, we demonstrate a good generalizability of DeepRGVP to dMRI tractography data from neurosurgical patients with pituitary tumors and we show DeepRGVP can successfully identify RGVPs despite the effect of lesions affecting the RGVPs. Overall, our study shows the high potential of using deep learning to automatically identify the RGVP.

SlicerTMS: Real-Time Visualization of Transcranial Magnetic Stimulation for Mental Health Treatment.

We present a real-time visualization system for Transcranial Magnetic Stimulation (TMS), a non-invasive neuromodulation technique for treating various brain disorders and mental health diseases. Our solution targets the current challenges of slow and labor-intensive practices in treatment planning. Integrating Deep Learning (DL), our system rapidly predicts electric field (E-field) distributions in 0.2 seconds for precise and effective brain stimulation. The core advancement lies in our tool's real-time neuronavigation visualization capabilities, which support clinicians in making more informed decisions quickly and effectively. We assess our system's performance through three studies: First, a real-world use case scenario in a clinical setting, providing concrete feedback on applicability and usability in a practical environment. Second, a comparative analysis with another TMS tool focusing on computational efficiency across various hardware platforms. Lastly, we conducted an expert user study to measure usability and influence in optimizing TMS treatment planning. The system is openly available for community use and further development on GitHub: https://github.com/lorifranke/SlicerTMS.

DDParcel: Deep Learning Anatomical Brain Parcellation From Diffusion MRI.

Parcellation of anatomically segregated cortical and subcortical brain regions is required in diffusion MRI (dMRI) analysis for region-specific quantification and better anatomical specificity of tractography. Most current dMRI parcellation approaches compute the parcellation from anatomical MRI (T1- or T2-weighted) data, using tools such as FreeSurfer or CAT12, and then register it to the diffusion space. However, the registration is challenging due to image distortions and low resolution of dMRI data, often resulting in mislabeling in the derived brain parcellation. Furthermore, these approaches are not applicable when anatomical MRI data is unavailable. As an alternative we developed the Deep Diffusion Parcellation (DDParcel), a deep learning method for fast and accurate parcellation of brain anatomical regions directly from dMRI data. The input to DDParcel are dMRI parameter maps and the output are labels for 101 anatomical regions corresponding to the FreeSurfer Desikan-Killiany (DK) parcellation. A multi-level fusion network leverages complementary information in the different input maps, at three network levels: input, intermediate layer, and output. DDParcel learns the registration of diffusion features to anatomical MRI from the high-quality Human Connectome Project data. Then, to predict brain parcellation for a new subject, the DDParcel network no longer requires anatomical MRI data but only the dMRI data. Comparing DDParcel's parcellation with T1w-based parcellation shows higher test-retest reproducibility and a higher regional homogeneity, while requiring much less computational time. Generalizability is demonstrated on a range of populations and dMRI acquisition protocols. Utility of DDParcel's parcellation is demonstrated on tractography analysis for fiber tract identification.

Brains of endurance athletes differ in the association areas but not in the primary areas.

Regular participation in sports results in a series of physiological adaptations. However, little is known about the brain adaptations to physical activity. Here we aimed to investigate whether young endurance athletes and non-athletes differ in the gray and white matter of the brain and whether cardiorespiratory fitness (CRF) is associated with these differences. We assessed the CRF, volumes of the gray and white matter of the brain using structural magnetic resonance imaging (sMRI), and brain white matter connections using diffusion magnetic resonance imaging (dMRI) in 20 young male endurance athletes and 21 healthy non-athletes. While total brain volume was similar in both groups, the white matter volume was larger and the gray matter volume was smaller in the athletes compared to non-athletes. The reduction of gray matter was located in the association areas of the brain that are specialized in processing of sensory stimuli. In the microstructure analysis, significant group differences were found only in the association tracts, for example, the inferior occipito-frontal fascicle (IOFF) showing higher fractional anisotropy and lower radial diffusivity, indicating stronger myelination in this tract. Additionally, gray and white matter brain volumes, as well as association tracts correlated with CRF. No changes were observed in other brain areas or tracts. In summary, the brain signature of the endurance athlete is characterized by changes in the integration of sensory and motor information in the association areas.