AssemblyNet: A large ensemble of CNNs for 3D whole brain MRI segmentation

Pathological Aging of Patients With Amyotrophic Lateral Sclerosis: A Preliminary Longitudinal Study

OBJECTIVE

This longitudinal study investigated pathological brain aging in amyotrophic lateral sclerosis (ALS) by evaluating disparities between chronological age and deep learning-derived brain structure age (BSA) and exploring associations with cognitive and functional decline.

METHODS

Ten limb-onset ALS patients (seven males) and 10 demographically matched healthy controls (HCs) underwent structural magnetic resonance imaging (sMRI) and cognitive assessments at baseline and follow-up. The BSA was estimated using the validated volBrain platform. Cognitive domains (language, verbal fluency, executive function, memory, and visuospatial skills) and global cognition (Persian adaptive Edinburgh Cognitive and Behavioral ALS Screen [ECAS] total score) were assessed along with functional status (ALSFRS-R).

RESULTS

ALS patients exhibited significant BSA-chronological age disparities at baseline (Δ = +7.31 years, p = 0.009) and follow-up (Δ = +8.39 years, p = 0.003), with accelerated BSA progression over time (p = 0.004). The HCs showed no such disparities (p = 0.931). Longitudinal BSA increases were correlated with executive function decline (r = -0.651, p = 0.042). Higher education predicted preserved language (r = 0.831, p = 0.003) and verbal fluency (r = 0.738, p = 0.015). ALSFRS-R decline paralleled visuospatial (r = 0.642, p = 0.045) and global cognitive deterioration (r = 0.667, p = 0.035).

CONCLUSIONS

ALS is characterized by accelerated structural brain aging that progresses independently of chronological age and is correlated with executive dysfunction. Education may mitigate cognitive decline, while motor functional deterioration aligns with visuospatial and global cognitive impairments. BSA has emerged as a potential biomarker for tracking pathological aging trajectories in ALS, warranting validation using larger cohorts.

Evolution of Chronic Lesion Tissue in Relapsing-Remitting Patients With Multiple Sclerosis: An Association With Disease Progression

BACKGROUND AND OBJECTIVES

In this study, we examine the long-term changes in chronic lesion tissue (CLT) among patients with relapsing-remitting MS (RRMS), focusing on its impact on clinical and radiologic disease progression indicators.

METHODS

The study involved 72 patients with multiple sclerosis with at least a 5-year follow-up. Annual assessments used 3D fluid-attenuated inversion recovery (FLAIR), precontrast and postcontrast 3D T1, and diffusion-weighted MRI. Lesion segmentation was conducted using iQ-MS software, while brain structures were segmented using AssemblyNet. Volumetric changes in CLT were tracked using a novel custom-designed pipeline that estimates longitudinal volumetric changes in CLT using serial MRI data.

RESULTS

Throughout the follow-up period, the volume of CLT in the entire cohort increased continuously and steadily, averaging 7.75% ± 8.2% or 315 ± 465 mm³ per year. Patients with expanding CLT experienced significantly faster brain atrophy, affecting both white and gray matter, particularly in the brain's central area. Expanded CLT was also associated with higher and worsening Expanded Disability Status Scale (EDSS) scores, in contrast to the stable CLT group, where EDSS remained unchanged. Sample size calculation for a clinical trial investigating the effect of treatment on slow expansion of chronic lesions demonstrated that a relatively small cohort of patients with RRMS, ranging from 24 to 69 patients per arm, would be required.

DISCUSSION

This study demonstrates that, over a period of up to 5 years, patient-specific enlargement of CLT, when present, progresses at a constant rate and significantly influences brain atrophy and disease progression. In addition, the study underscores CLT as a promising biomarker for RRMS progression and suggests the feasibility of smaller, targeted clinical trials to evaluate treatments aimed at reducing chronic lesion expansion.

Brain Age Prediction in Type II GM1 Gangliosidosis

GM1 gangliosidosis is an inherited, progressive, and fatal neurodegenerative lysosomal storage disorder with no approved treatment. We calculated a predicted brain ages and Brain Structures Age Gap Estimation (BSAGE) for 81 MRI scans from 41 Type II GM1 gangliosidosis patients and 897 MRI scans from 556 neurotypical controls (NC) utilizing BrainStructuresAges , a machine learning MRI analysis pipeline. NC showed whole brain aging at a rate of 0.83 per chronological year compared with 1.57 in juvenile GM1 patients and 12.25 in late-infantile GM1 patients, accurately reflecting the clinical trajectories of the two disease subtypes. Accelerated and distinct brain aging was also observed throughout midbrain structures including the thalamus and caudate nucleus, hindbrain structures including the cerebellum and brainstem, and the ventricles in juvenile and late-infantile GM1 patients compared to NC. Predicted brain age and BSAGE both correlated with cross-sectional and longitudinal clinical assessments, indicating their importance as a surrogate neuroimaging outcome measures for clinical trials in GM1 gangliosidosis.

Artificial intelligence for brain neuroanatomical segmentation in magnetic resonance imaging: A literature review

PURPOSE

This literature review aims to synthesise current research on the application of artificial intelligence (AI) for the segmentation of brain neuroanatomical structures in magnetic resonance imaging (MRI).

METHODS

A literature search was conducted using the databases Embase, Medline, Scopus, and Web of Science, and captured articles were assessed for inclusion in the review. Data extraction was performed for the summary of the AI model used, and key findings of each article, advantages and disadvantages were identified.

RESULTS

Following full-text screening, 21 articles were included in the review. The review covers models for segmentation models applied to the whole brain, cerebral cortex, subcortical structures, the cerebellum, blood vessels, perivascular spaces, and the ventricles. Accuracy of segmentation was generally high, particularly for segmenting neuroanatomical structures in healthy cohorts.

CONCLUSION

The use of AI for automatic brain segmentation is generally highly accurate and fast for all regions of the human brain. Challenges include robustness to anatomical variability and pathology, largely due to difficulties with accessing sufficient training data.

MRI Voxel Morphometry Shows Brain Volume Changes in Breast Cancer Survivors: Implications for Treatment

Chemotherapy-related cognitive impairment termed «chemobrain» is a prevalent complication in breast cancer survivors that requires early detection for the development of novel therapeutic approaches. Magnetic resonance voxel morphometry (MR morphometry), due to its high sensitivity, might be employed for the evaluation of the early changes in the volumes of brain structures in order to explore the «chemobrain» condition.

METHODS

The open, prospective, single-center study enrolled 86 breast cancer survivors (43.3 ± 4.4 years) and age-matched 28 healthy female volunteers (44.0 ± 5.68). Conventional MR sequences (T1- and T2-weighted, TIRM, DWI, MPRAGE) were obtained in three mutually perpendicular planes to exclude an organ pathology of the brain. Additionally, the MPRAGE sequence was performed for subsequent MR morphometry of the volume of brain structures using the open VolBrain program. The evaluation was performed at two follow-up visits 6 months and 3 years after the completion of BC treatment.

RESULTS

According to the MR morphometry, breast cancer survivors presented with significantly decreased volumes of brain structures (including total brain volume, cerebellum volume, subcortical gray matter, etc.) as compared to healthy volunteers. Evaluation over the follow-up period of 3 years did not show the restoration of brain volume structures.

CONCLUSIONS

The data obtained employing MR morphometry revealed significant reductions (that were not detected on the conventional MR sequences) in both gray and white matter in breast cancer survivors following chemotherapy. This comprehensive analysis indicated the utility of MR morphometry in detecting subtle yet statistically significant neuroanatomical changes associated with cognitive and motor impairments in patients, which can in turn provide valuable insights into the extent of structural brain alterations, helping to identify specific regions that are most affected by treatment.

Intensity-Based Assessment of Hippocampal Segmentation Algorithms Using Paired Precontrast and Postcontrast MRI

Hippocampal segmentation is essential in neuroimaging for evaluating conditions like Alzheimer's dementia and mesial temporal sclerosis, where small volume changes can significantly impact normative percentiles. However, inaccurate segmentation is common due to the inclusion of non-hippocampal structures such as choroid plexus and cerebrospinal fluid (CSF), leading to volumetric overestimation and confounding of functional analyses. Current methods of assessment largely rely on virtual or manual ground truth labels, which can fail to capture these inaccuracies. To address this shortcoming, this study introduces a more direct voxel intensity-based method of segmentation assessment. Using paired precontrast and postcontrast T1-weighted MRIs, hippocampal segmentations were refined by adding marginal gray matter and removing marginal CSF and enhancement to determine a total required correction volume. Six segmentation algorithms-e2dhipseg, HippMapp3r, hippodeep, AssemblyNet, FastSurfer, and QuickNat-were implemented and compared. HippMapp3r and e2dhipseg, followed closely by hippodeep, exhibited the least total correction volumes, indicating superior accuracy. Dedicated hippocampal segmentation algorithms outperformed whole-brain methods.

DeepCERES: A deep learning method for cerebellar lobule segmentation using ultra-high resolution multimodal MRI

This paper introduces a novel multimodal and high-resolution human brain cerebellum lobule segmentation method. Unlike current tools that operate at standard resolution (1 mm3) or using mono-modal data, the proposed method improves cerebellum lobule segmentation through the use of a multimodal and ultra-high resolution (0.125 mm3) training dataset. To develop the method, first, a database of semi-automatically labelled cerebellum lobules was created to train the proposed method with ultra-high resolution T1 and T2 MR images. Then, an ensemble of deep networks has been designed and developed, allowing the proposed method to excel in the complex cerebellum lobule segmentation task, improving precision while being memory efficient. Notably, our approach deviates from the traditional U-Net model by exploring alternative architectures. We have also integrated deep learning with classical machine learning methods incorporating a priori knowledge from multi-atlas segmentation which improved precision and robustness. Finally, a new online pipeline, named DeepCERES, has been developed to make available the proposed method to the scientific community requiring as input only a single T1 MR image at standard resolution.

Automated segmentation of deep brain structures from Inversion-Recovery MRI

Methods for the automated segmentation of brain structures are a major subject of medical research. The small structures of the deep brain have received scant attention, notably for lack of manual delineations by medical experts. In this study, we assessed an automated segmentation of a novel clinical dataset containing White Matter Attenuated Inversion-Recovery (WAIR) MRI images and five manually segmented structures (substantia nigra (SN), subthalamic nucleus (STN), red nucleus (RN), mammillary body (MB) and mammillothalamic fascicle (MT-fa)) in 53 patients with severe Parkinson's disease. T1 and DTI images were additionally used. We also assessed the reorientation of DTI diffusion vectors with reference to the ACPC line. A state-of-the-art nnU-Net method was trained and tested on subsets of 38 and 15 image datasets respectively. We used Dice similarity coefficient (DSC), 95% Hausdorff distance (95HD), and volumetric similarity (VS) as metrics to evaluate network efficiency in reproducing manual contouring. Random-effects models statistically compared values according to structures, accounting for between- and within-participant variability. Results show that WAIR significantly outperformed T1 for DSC (0.739 ± 0.073), 95HD (1.739 ± 0.398), and VS (0.892 ± 0.044). The DSC values for automated segmentation of MB, RN, SN, STN, and MT-fa decreased in that order, in line with the increasing complexity observed in manual segmentation. Based on training results, the reorientation of DTI vectors improved the automated segmentation.

Volumetric Analysis of Motor Cortex and Basal Ganglia in Pediatric Celiac Disease Patients Using volBrain: Implications for Neurological Dysfunction-Preliminary Results

BACKGROUND/OBJECTIVES

Celiac disease (CD) is a common immune-mediated, chronic systemic disorder that is treated with a strict, life-long gluten-free diet (GFD). In addition to gastrointestinal manifestations, CD also presents with a variety of extraintestinal symptoms, including significant neurological and neuropsychiatric symptoms. Among these neurological manifestations, motor dysfunctions are particularly notable. The aim of this study is to investigate the potential volumetric differences in brain structures, particularly the motor cortex and basal ganglia, between pediatric CD patients and healthy controls using the volBrain software AssemblyNet version 1.0.

METHODS

This prospective study included pediatric patients with CD who complained of neurological symptoms and were scheduled for brain magnetic resonance imaging (MRI). All children had been previously diagnosed with CD and their adherence to GFD was evaluated using the Biagi score. Brain MRIs were performed on all included patients to obtain volumetry at the onset of the disease. For volumetric and segmentation data, the volBrain software was used.

RESULTS

In total, 12 pediatric patients with CD were included, with a median duration of a GFD of 5.3 years at the time of the MRI examination. There were no statistically significant differences between patients compliant with the GFD and those non-compliant in terms of age or duration of GFD. Volumetric analysis revealed deviations in all patients analyzed, which involved either a decrease or increase in the volume of the structures studied.

CONCLUSION

Despite the limited number of patients in this study, the initial findings support previously described neurological manifestations in patients with CD. Newly developed MRI tools have the potential to enable a more detailed analysis of disease progression and its impact on the motor cortex.

OpenMAP-T1: A Rapid Deep-Learning Approach to Parcellate 280 Anatomical Regions to Cover the Whole Brain

This study introduces OpenMAP-T1, a deep-learning-based method for rapid and accurate whole-brain parcellation in T1- weighted brain MRI, which aims to overcome the limitations of conventional normalization-to-atlas-based approaches and multi-atlas label-fusion (MALF) techniques. Brain image parcellation is a fundamental process in neuroscientific and clinical research, enabling a detailed analysis of specific cerebral regions. Normalization-to-atlas-based methods have been employed for this task, but they face limitations due to variations in brain morphology, especially in pathological conditions. The MALF techniques improved the accuracy of the image parcellation and robustness to variations in brain morphology, but at the cost of high computational demand that requires a lengthy processing time. OpenMAP-T1 integrates several convolutional neural network models across six phases: preprocessing; cropping; skull-stripping; parcellation; hemisphere segmentation; and final merging. This process involves standardizing MRI images, isolating the brain tissue, and parcellating it into 280 anatomical structures that cover the whole brain, including detailed gray and white matter structures, while simplifying the parcellation processes and incorporating robust training to handle various scan types and conditions. The OpenMAP-T1 was validated on the Johns Hopkins University atlas library and eight available open resources, including real-world clinical images, and the demonstration of robustness across different datasets with variations in scanner types, magnetic field strengths, and image processing techniques, such as defacing. Compared with existing methods, OpenMAP-T1 significantly reduced the processing time per image from several hours to less than 90 s without compromising accuracy. It was particularly effective in handling images with intensity inhomogeneity and varying head positions, conditions commonly seen in clinical settings. The adaptability of OpenMAP-T1 to a wide range of MRI datasets and its robustness to various scan conditions highlight its potential as a versatile tool in neuroimaging.

Intravenous arachnoid granulation hypertrophy in patients with Parkinson disease

Intravenous arachnoid granulations (AGs) are protrusions of the arachnoid membrane into the venous lumen and function as contributors to the cerebrospinal fluid (CSF) flow circuit. Patients with Parkinson disease (PD) often present with accumulation of alpha synuclein. Previous works have provided evidence for neurofluid circulation dysfunction in neurodegenerative diseases associated with changes in CSF egress, which may have implications regarding AG morphology. The present study aims to investigate group differences in AG volumetrics between healthy and PD participants, as well as relationships between AG characteristics and clinical assessments. Generalized linear models revealed significant increases in AG volumetrics and number in PD compared to healthy controls. Partial Spearman-rank correlation analyses demonstrated significant relationships between AG metrics and motor and cognitive assessments. Finally, AG volumetrics were positively correlated with objective actigraphy measures of sleep dysfunction, but not self-report sleep symptoms.

Advancements in remote sensing for active fire detection: A review of datasets and methods

This study comprehensively and critically reviews active fire detection advancements in remote sensing from 1975 to the present, focusing on two main perspectives: datasets and corresponding instruments, and detection algorithms. The study highlights the increasing role of machine learning, particularly deep learning techniques, in active fire detection. Looking forward, the review outlines current challenges and future research opportunities in remote sensing for active fire detection. These include exploring data quality management and multi-modal learning, developing spatiotemporally explicit models, investigating self-supervised learning models, improving explainable and interpretable models, integrating physical-process based models with machine learning, and building digital twins to replicate wildfire dynamics and perform what-if scenario analysis. The review aims to serve as a valuable resource for informing natural resource management and enhancing environmental protection efforts through the application of remote sensing technology.

Comparative assessment of established and deep learning-based segmentation methods for hippocampal volume estimation in brain magnetic resonance imaging analysis

In this study, our objective was to assess the performance of two deep learning-based hippocampal segmentation methods, SynthSeg and TigerBx, which are readily available to the public. We contrasted their performance with that of two established techniques, FreeSurfer-Aseg and FSL-FIRST, using three-dimensional T1-weighted MRI scans (n = 1447) procured from public databases. Our evaluation focused on the accuracy and reproducibility of these tools in estimating hippocampal volume. The findings suggest that both SynthSeg and TigerBx are on a par with Aseg and FIRST in terms of segmentation accuracy and reproducibility, but offer a significant advantage in processing speed, generating results in less than 1 min compared with several minutes to hours for the latter tools. In terms of Alzheimer's disease classification based on the hippocampal atrophy rate, SynthSeg and TigerBx exhibited superior performance. In conclusion, we evaluated the capabilities of two deep learning-based segmentation techniques. The results underscore their potential value in clinical and research environments, particularly when investigating neurological conditions associated with hippocampal structures.

A brain subcortical segmentation tool based on anatomy attentional fusion network for developing macaques

Magnetic Resonance Imaging (MRI) plays a pivotal role in the accurate measurement of brain subcortical structures in macaques, which is crucial for unraveling the complexities of brain structure and function, thereby enhancing our understanding of neurodegenerative diseases and brain development. However, due to significant differences in brain size, structure, and imaging characteristics between humans and macaques, computational tools developed for human neuroimaging studies often encounter obstacles when applied to macaques. In this context, we propose an Anatomy Attentional Fusion Network (AAF-Net), which integrates multimodal MRI data with anatomical constraints in a multi-scale framework to address the challenges posed by the dynamic development, regional heterogeneity, and age-related size variations of the juvenile macaque brain, thus achieving precise subcortical segmentation. Specifically, we generate a Signed Distance Map (SDM) based on the initial rough segmentation of the subcortical region by a network as an anatomical constraint, providing comprehensive information on positions, structures, and morphology. Then we construct AAF-Net to fully fuse the SDM anatomical constraints and multimodal images for refined segmentation. To thoroughly evaluate the performance of our proposed tool, over 700 macaque MRIs from 19 datasets were used in this study. Specifically, we employed two manually labeled longitudinal macaque datasets to develop the tool and complete four-fold cross-validations. Furthermore, we incorporated various external datasets to demonstrate the proposed tool's generalization capabilities and promise in brain development research. We have made this tool available as an open-source resource at https://github.com/TaoZhong11/Macaque_subcortical_segmentation for direct application.

Radiomics evaluation for the early detection of Alzheimer's dementia using T1-weighted MRI

INTRODUCTION

Alzheimer's disease (AD), the most common cause of dementia, presents a global health crisis with its prevalence expected to triple worldwide by 2050, emphasizing the urgent need for early diagnosis to delay progression and improve patient quality of life. Our project aims to detect AD in its early phase by identifying subtle neuroanatomical changes with Radiomics features, offering a more accurate diagnosis.

METHODS

The AssemblyNet segmentation model was used to analyze brain changes by employing anonymized T1 MRI scans from 416 patients. For each segmented label we extracted Radiomic features. After preprocessing of Radiomic features we trained four models, Gradient Booster, Random Forest, Support Vector Classifier, and XGBoost, in a 70%/20%/10% train, validation and test split. All models were hyperparameter tuned with GridSearch, Cross validation and evaluated with accuracy on the test data.

RESULTS

208 T1-weighted MRI scans were segmented, with 132 segmentation labels per patient, 1130 Radiomic features per segmentation, totalling in over 31 million features. For all four models we achieved accuracies between 0.71 and 0.86, and the machine learning model with highest accuracy were XGBoost, achieving an accuracy at 0.86 on the segmentation of the left inferior lateral ventricle.

CONCLUSION

Our study's use of segmentation on T1-weighted MRI scans resulted promising accuracies for early AD diagnosis with the machine learning model XGBoost, peaking at 0.86 accuracy. Future research should aim to expand datasets and refine methodologies for broader applicability.

IMPLICATION FOR PRACTICE

Implementing Radiomics for early AD detection using T1-weighted MRI scans could substantially improve diagnostic accuracy, enabling earlier interventions that may delay disease progression and improve outcomes, thereby requiring radiographers to adopt more advanced imaging techniques and analysis tools, as well as additional training to effectively interpret complex Radiomic data.

A comprehensive survey on the use of deep learning techniques in glioblastoma

Glioblastoma, characterized as a grade 4 astrocytoma, stands out as the most aggressive brain tumor, often leading to dire outcomes. The challenge of treating glioblastoma is exacerbated by the convergence of genetic mutations and disruptions in gene expression, driven by alterations in epigenetic mechanisms. The integration of artificial intelligence, inclusive of machine learning algorithms, has emerged as an indispensable asset in medical analyses. AI is becoming a necessary tool in medicine and beyond. Current research on Glioblastoma predominantly revolves around non-omics data modalities, prominently including magnetic resonance imaging, computed tomography, and positron emission tomography. Nonetheless, the assimilation of omic data-encompassing gene expression through transcriptomics and epigenomics-offers pivotal insights into patients' conditions. These insights, reciprocally, hold significant value in refining diagnoses, guiding decision- making processes, and devising efficacious treatment strategies. This survey's core objective encompasses a comprehensive exploration of noteworthy applications of machine learning methodologies in the domain of glioblastoma, alongside closely associated research pursuits. The study accentuates the deployment of artificial intelligence techniques for both non-omics and omics data, encompassing a range of tasks. Furthermore, the survey underscores the intricate challenges posed by the inherent heterogeneity of Glioblastoma, delving into strategies aimed at addressing its multifaceted nature.

Associations between the choroid plexus and tau in Alzheimer's disease using an active learning segmentation pipeline

BACKGROUND

The cerebrospinal fluid (CSF), primarily generated by the choroid plexus (ChP), is the major carrier of the glymphatic system. The alternations of CSF production and the ChP can be associated with the Alzheimer's disease (AD). The present work investigated the roles of the ChP in the AD based on a proposed ChP image segmentation pipeline.

METHODS

A human-in-the-loop ChP image segmentation pipeline was implemented with intermediate and active learning datasets. The performance of the proposed pipeline was evaluated on manual contours by five radiologists, compared to the FreeSurfer and FastSurfer toolboxes. The ChP volume and blood flow were investigated among AD groups. The correlations between the ChP volume and AD CSF biomarkers including phosphorylated tau (p-tau), total tau (t-tau), amyloid-β42 (Aβ42), and amyloid-β40 (Aβ40) was investigated using three models (univariate, multiple variables, and stepwise regression) on two datasets with 806 and 320 subjects.

RESULTS

The proposed ChP segmentation pipeline achieved superior performance with a Dice coefficient of 0.620 on the test dataset, compared to the FreeSurfer (0.342) and FastSurfer (0.371). Significantly larger volumes (p < 0.001) and higher perfusion (p = 0.032) at the ChP were found in AD compared to CN groups. Significant correlations were found between the tau and the relative ChP volume (the ChP volume and ChP/parenchyma ratio) in each patient groups and in the univariate regression analysis (p < 0.001), the multiple regression model (p < 0.05 except for the t-tau in the LMCI), and in the step-wise regression model (p < 0.021). In addition, the correlation coefficients changed from - 0.32 to - 0.21 along with the AD progression in the multiple regression model. In contrast, the Aβ42 and Aβ40 shows consistent and significant associations with the lateral ventricle related measures in the step-wise regression model (p < 0.027).

CONCLUSIONS

The proposed pipeline provided accurate ChP segmentation which revealed the associations between the ChP and tau level in the AD. The proposed pipeline is available on GitHub ( https://github.com/princeleeee/ChP-Seg ).

Quantifying chronic lesion expansion in multiple sclerosis: Exploring imaging markers for longitudinal assessment

OBJECTIVES

Gradual expansion of multiple sclerosis lesions over time is known to have a significant impact on disease progression. However, accurately quantifying the volume changes in chronic lesions presents challenges due to their slow rate of progression and the need for longitudinal segmentation. Our study addresses this by estimating the expansion of chronic lesions using data collected over a 1-2 year period and exploring imaging markers that do not require longitudinal lesion segmentation.

METHODS

Pre- and post-gadolinium 3D-T1, 3D FLAIR and diffusion tensor images were acquired from 42 patients with MS. Lesion expansion, stratified by the severity of tissue damage as measured by mean diffusivity change, was analysed between baseline and 48 months (Progressive Volume/Severity Index, PVSI). Central brain atrophy (CBA) and the degree of tissue loss inside chronic lesions (measured by the change of T1 intensity and mean diffusivity (MD)) were used as surrogate markers.

RESULTS

CBA measured after 2 years of follow-up estimated lesion expansion at 4 years with a high degree of accuracy (r = 0.82, p < 0.001, ROC area under the curve 0.92, sensitivity of 94 %, specificity of 85 %). Increased MD within chronic lesions measured over 2 years was strongly associated with future expansion (r = 0.77, p < 0.001, ROC area under the curve 0.87, sensitivity of 81 % and specificity of 81 %). In contrast, change in lesion T1 hypointensity poorly explained future PVSI (best sensitivity and specificity 60 % and 59 % respectively).

INTERPRETATION

CBA and, to a lesser extent, the change in MD within chronic MS lesions, measured over a period of 2 years, can provide a reliable and sensitive estimate of the extent and severity of chronic lesion expansion.

Regional Burden of Enlarged Perivascular Spaces and Cognition and Neuropsychiatric Symptoms in Drug-Naive Patients With Parkinson Disease

BACKGROUND AND OBJECTIVES

Although the potential role of enlarged perivascular spaces (EPVSs) in Parkinson disease (PD) is increasingly recognized, whether EPVSs located in different anatomical regions exert differential effects on clinical manifestation remains uncertain. We investigated the regional EPVS burden and its association with cognition and neuropsychiatric symptoms (NPSs) in newly diagnosed PD population.

METHODS

In this retrospective, cross-sectional study, EPVS in the temporal lobe (T-EPVS), centrum semiovale (CS-EPVS), and basal ganglia (BG-EPVS) were visually rated in drug-naive patients with PD who underwent magnetic resonance imaging, dopamine transporter (DAT) scans, neuropsychological assessments, and Neuropsychiatric Inventory Questionnaire at baseline. Cognitive performance, NPS burden, vascular risk factors, small vessel disease (SVD) imaging markers, and DAT availability were compared across groups dichotomized by their regional EPVS burden (cutoff for high-degree vs low-degree: >10 for T-EPVS/BG-EPVS and >20 for CS-EPVS).

RESULTS

A total of 480 patients with PD (123 without cognitive impairment, 291 with mild cognitive impairment, and 66 with dementia) were included. The proportion of high-degree T-EPVS (p for trend <0.001) and BG-EPVS (p for trend = 0.001) exhibited an increasing trend across the cognitive spectrum, corresponding to worsening cognition. Compared with the low-degree group, the high-degree BG-EPVS group showed higher SVD burden (moderate-to-severe white matter hyperintensity [14.8% vs 40.5%, p < 0.001], lacune [10.3% vs 30.7%, p < 0.001], and cerebral microbleeds [8.1% vs 22.2%, p < 0.001]), greater atrophy in cortical gray matter (40.73% ± 1.09% vs 39.96% ± 1.20% of intracranial volume, p < 0.001), and lower cognitive performance (in language [-0.22 ± 1.18 vs -0.53 ± 1.29, p = 0.013], and visual memory domains [-0.24 ± 0.97 vs -0.61 ± 0.96, p = 0.009]). The high-degree T-EPVS group presented with greater NPS burden in decreased motivation (0.61 ± 1.78 vs 1.35 ± 2.36, p = 0.007), affective dysregulation (0.88 ± 2.13 vs 2.36 ± 3.53, p < 0.001), and impulse dyscontrol (0.43 ± 1.67 vs 1.74 ± 4.29, p < 0.001), compared with the low-degree T-EPVS group. Meanwhile, the burden of CS-EPVS did not reveal any differences in cognition or NPS.

DISCUSSION

BG-EPVS and T-EPVS seem to exert differential effects on cognition and NPS in patients with PD. Investigating the EPVS profile in distinct anatomical regions may be useful in disentangling the heterogeneity within PD.

Application of AI-assisted MRI for the identification of surgical target areas in pediatric hip and periarticular infections

OBJECTIVE

To develop an AI-assisted MRI model to identify surgical target areas in pediatric hip and periarticular infections.

METHODS

A retrospective study was conducted on the pediatric patients with hip and periarticular infections who underwent Magnetic Resonance Imaging(MRI)examinations from January 2010 to January 2023 in three hospitals in China. A total of 7970 axial Short Tau Inversion Recovery (STIR) images were selected, and the corresponding regions of osteomyelitis (label 1) and abscess (label 2) were labeled using the Labelme software. The images were randomly divided into training group, validation group, and test group at a ratio of 7:2:1. A Mask R-CNN model was constructed and optimized, and the performance of identifying label 1 and label 2 was evaluated using receiver operating characteristic (ROC) curves. Calculation of the average time it took for the model and specialists to process an image in the test group. Comparison of the accuracy of the model in the interpretation of MRI images with four orthopaedic surgeons, with statistical significance set at P < 0.05.

RESULTS

A total of 275 patients were enrolled, comprising 197 males and 78 females, with an average age of 7.10 ± 3.59 years, ranging from 0.00 to 14.00 years. The area under curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score for the model to identify label 1 were 0.810, 0.976, 0.995, 0.969, 0.922, and 0.957, respectively. The AUC, accuracy, sensitivity, specificity, precision, and F1 score for the model to identify label 2 were 0.890, 0.957, 0.969, 0.915, 0.976, and 0.972, respectively. The model demonstrated a significant speed advantage, taking only 0.2 s to process an image compared to average 10 s required by the specialists. The model identified osteomyelitis with an accuracy of 0.976 and abscess with an accuracy of 0.957, both statistically better than the four orthopaedic surgeons, P < 0.05.

CONCLUSION

The Mask R-CNN model is reliable for identifying surgical target areas in pediatric hip and periarticular infections, offering a more convenient and rapid option. It can assist unexperienced physicians in pre-treatment assessments, reducing the risk of missed and misdiagnosis.

A deep learning model for brain segmentation across pediatric and adult populations

Automated quantification of brain tissues on MR images has greatly contributed to the diagnosis and follow-up of neurological pathologies across various life stages. However, existing solutions are specifically designed for certain age ranges, limiting their applicability in monitoring brain development from infancy to late adulthood. This retrospective study aims to develop and validate a brain segmentation model across pediatric and adult populations. First, we trained a deep learning model to segment tissues and brain structures using T1-weighted MR images from 390 patients (age range: 2-81 years) across four different datasets. Subsequently, the model was validated on a cohort of 280 patients from six distinct test datasets (age range: 4-90 years). In the initial experiment, the proposed deep learning-based pipeline, icobrain-dl, demonstrated segmentation accuracy comparable to both pediatric and adult-specific models across diverse age groups. Subsequently, we evaluated intra- and inter-scanner variability in measurements of various tissues and structures in both pediatric and adult populations computed by icobrain-dl. Results demonstrated significantly higher reproducibility compared to similar brain quantification tools, including childmetrix, FastSurfer, and the medical device icobrain v5.9 (p-value< 0.01). Finally, we explored the potential clinical applications of icobrain-dl measurements in diagnosing pediatric patients with Cerebral Visual Impairment and adult patients with Alzheimer's Disease.

Reduced cerebrospinal fluid motion in patients with Parkinson's disease revealed by magnetic resonance imaging with low b-value diffusion weighted imaging

BACKGROUND

Parkinson's disease is characterized by dopamine-responsive symptoms as well as aggregation of α-synuclein protofibrils. New diagnostic methods assess α-synuclein aggregation characteristics from cerebrospinal fluid (CSF) and recent pathophysiologic mechanisms suggest that CSF circulation disruptions may precipitate α-synuclein retention. Here, diffusion-weighted MRI with low-to-intermediate diffusion-weightings was applied to test the hypothesis that CSF motion is reduced in Parkinson's disease relative to healthy participants.

METHODS

Multi-shell diffusion weighted MRI (spatial resolution = 1.8 × 1.8 × 4.0 mm) with low-to-intermediate diffusion weightings (b-values = 0, 50, 100, 200, 300, 700, and 1000 s/mm2) was applied over the approximate kinetic range of suprasellar cistern fluid motion at 3 Tesla in Parkinson's disease (n = 27; age = 66 ± 6.7 years) and non-Parkinson's control (n = 32; age = 68 ± 8.9 years) participants. Wilcoxon rank-sum tests were applied to test the primary hypothesis that the noise floor-corrected decay rate of CSF signal as a function of b-value, which reflects increasing fluid motion, is reduced within the suprasellar cistern of persons with versus without Parkinson's disease and inversely relates to choroid plexus activity assessed from perfusion-weighted MRI (significance-criteria: p < 0.05).

RESULTS

Consistent with the primary hypothesis, CSF decay rates were higher in healthy (D = 0.00673 ± 0.00213 mm2/s) relative to Parkinson's disease (D = 0.00517 ± 0.00110 mm2/s) participants. This finding was preserved after controlling for age and sex and was observed in the posterior region of the suprasellar cistern (p < 0.001). An inverse correlation between choroid plexus perfusion and decay rate in the voxels within the suprasellar cistern (Spearman's-r=-0.312; p = 0.019) was observed.

CONCLUSIONS

Multi-shell diffusion MRI was applied to identify reduced CSF motion at the level of the suprasellar cistern in adults with versus without Parkinson's disease; the strengths and limitations of this methodology are discussed in the context of the growing literature on CSF flow.

VINNA for neonates: Orientation independence through latent augmentations

A robust, fast, and accurate segmentation of neonatal brain images is highly desired to better understand and detect changes during development and disease, specifically considering the rise in imaging studies for this cohort. Yet, the limited availability of ground truth datasets, lack of standardized acquisition protocols, and wide variations of head positioning in the scanner pose challenges for method development. A few automated image analysis pipelines exist for newborn brain Magnetic Resonance Image (MRI) segmentation, but they often rely on time-consuming non-linear spatial registration procedures and require resampling to a common resolution, subject to loss of information due to interpolation and down-sampling. Without registration and image resampling, variations with respect to head positions and voxel resolutions have to be addressed differently. In deep learning, external augmentations such as rotation, translation, and scaling are traditionally used to artificially expand the representation of spatial variability, which subsequently increases both the training dataset size and robustness. However, these transformations in the image space still require resampling, reducing accuracy specifically in the context of label interpolation. We recently introduced the concept of resolution-independence with the Voxel-size Independent Neural Network framework, VINN. Here, we extend this concept by additionally shifting all rigid-transforms into the network architecture with a four degree of freedom (4-DOF) transform module, enabling resolution-aware internal augmentations (VINNA) for deep learning. In this work, we show that VINNA (i) significantly outperforms state-of-the-art external augmentation approaches, (ii) effectively addresses the head variations present specifically in newborn datasets, and (iii) retains high segmentation accuracy across a range of resolutions (0.5-1.0 mm). Furthermore, the 4-DOF transform module together with internal augmentations is a powerful, general approach to implement spatial augmentation without requiring image or label interpolation. The specific network application to newborns will be made publicly available as VINNA4neonates.

An end-to-end infant brain parcellation pipeline

Objective

Accurate infant brain parcellation is crucial for understanding early brain development; however, it is challenging due to the inherent low tissue contrast, high noise, and severe partial volume effects in infant magnetic resonance images (MRIs). The aim of this study was to develop an end-to-end pipeline that enabled accurate parcellation of infant brain MRIs.

Methods

We proposed an end-to-end pipeline that employs a two-stage global-to-local approach for accurate parcellation of infant brain MRIs. Specifically, in the global regions of interest (ROIs) localization stage, a combination of transformer and convolution operations was employed to capture both global spatial features and fine texture features, enabling an approximate localization of the ROIs across the whole brain. In the local ROIs refinement stage, leveraging the position priors from the first stage along with the raw MRIs, the boundaries o the ROIs are refined for a more accurate parcellation.

Results

We utilized the Dice ratio to evaluate the accuracy of parcellation results. Results on 263 subjects from National Database for Autism Research (NDAR), Baby Connectome Project (BCP) and Cross-site datasets demonstrated the better accuracy and robustness of our method than other competing methods.

Conclusion

Our end-to-end pipeline may be capable of accurately parcellating 6-month-old infant brain MRIs.

Vulnerability of Thalamic Nuclei at CSF Interface During the Entire Course of Multiple Sclerosis

BACKGROUND AND OBJECTIVES

Thalamic atrophy can be used as a proxy for neurodegeneration in multiple sclerosis (MS). Some data point toward thalamic nuclei that could be affected more than others. However, the dynamic of their changes during MS evolution and the mechanisms driving their differential alterations are still uncertain.

METHODS

We paired a large cohort of 1,123 patients with MS with the same number of healthy controls, all scanned with conventional 3D-T1 MRI. To highlight the main atrophic regions at the thalamic nuclei level, we validated a segmentation strategy consisting of deep learning-based synthesis of sequences, which were used for automatic multiatlas segmentation. Then, through a lifespan-based approach, we could model the dynamics of the 4 main thalamic nuclei groups.

RESULTS

All analyses converged toward a higher rate of atrophy for the posterior and medial groups compared with the anterior and lateral groups. We also demonstrated that focal MS white matter lesions were associated with atrophy of groups of nuclei when specifically located within the associated thalamocortical projections. The volumes of the most affected posterior group, but also of the anterior group, were better associated with clinical disability than the volume of the whole thalamus.

DISCUSSION

These findings point toward the thalamic nuclei adjacent to the third ventricle as more susceptible to neurodegeneration during the entire course of MS through potentiation of disconnection effects by regional factors. Because this information can be obtained even from standard T1-weighted MRI, this paves the way toward such an approach for future monitoring of patients with MS.

Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data

Many clinical and research studies of the human brain require accurate structural MRI segmentation. While traditional atlas-based methods can be applied to volumes from any acquisition site, recent deep learning algorithms ensure high accuracy only when tested on data from the same sites exploited in training (i.e., internal data). Performance degradation experienced on external data (i.e., unseen volumes from unseen sites) is due to the inter-site variability in intensity distributions, and to unique artefacts caused by different MR scanner models and acquisition parameters. To mitigate this site-dependency, often referred to as the scanner effect, we propose LOD-Brain, a 3D convolutional neural network with progressive levels-of-detail (LOD), able to segment brain data from any site. Coarser network levels are responsible for learning a robust anatomical prior helpful in identifying brain structures and their locations, while finer levels refine the model to handle site-specific intensity distributions and anatomical variations. We ensure robustness across sites by training the model on an unprecedentedly rich dataset aggregating data from open repositories: almost 27,000 T1w volumes from around 160 acquisition sites, at 1.5 - 3T, from a population spanning from 8 to 90 years old. Extensive tests demonstrate that LOD-Brain produces state-of-the-art results, with no significant difference in performance between internal and external sites, and robust to challenging anatomical variations. Its portability paves the way for large-scale applications across different healthcare institutions, patient populations, and imaging technology manufacturers. Code, model, and demo are available on the project website.

Longitudinal enlargement of choroid plexus is associated with chronic lesion expansion and neurodegeneration in RRMS patients

BACKGROUND AND OBJECTIVE

We explored dynamic changes in the choroid plexus (CP) in patients with relapsing-remitting multiple sclerosis (RRMS) and assessed its relationship with chronic lesion expansion and atrophy in various brain compartments.

METHODS

Fifty-seven RRMS patients were annually assessed for a minimum of 48 months with 3D FLAIR, pre- and post-contrast 3D T1 and diffusion-weighted magnetic resonance imaging (MRI). The CP was manually segmented at baseline and last follow-up.

RESULTS

The volume of CP significantly increased by 1.4% annually. However, the extent of CP enlargement varied considerably among individuals (ranging from -3.6 to 150.8 mm3 or -0.2% to 6.3%). The magnitude of CP enlargement significantly correlated with central (r = 0.70, p < 0.001) and total brain atrophy (r = -0.57, p < 0.001), white (r = -0.61, p < 0.001) and deep grey matter atrophy (r = -0.60, p < 0.001). Progressive CP enlargement was significantly associated with the volume and extent of chronic lesion expansion (r = 0.60, p < 0.001), but not with the number or volume of new lesions.

CONCLUSION

This study provides evidence of progressive CP enlargement in patients with RRMS. Our findings also demonstrate that enlargement of the CP volume is linked to the expansion of chronic lesions and neurodegeneration of periventricular white and grey matter in RRMS patients.

Data-driven normative values based on generative manifold learning for quantitative MRI

In medicine, abnormalities in quantitative metrics such as the volume reduction of one brain region of an individual versus a control group are often provided as deviations from so-called normal values. These normative reference values are traditionally calculated based on the quantitative values from a control group, which can be adjusted for relevant clinical co-variables, such as age or sex. However, these average normative values do not take into account the globality of the available quantitative information. For example, quantitative analysis of T1-weighted magnetic resonance images based on anatomical structure segmentation frequently includes over 100 cerebral structures in the quantitative reports, and these tend to be analyzed separately. In this study, we propose a global approach to personalized normative values for each brain structure using an unsupervised Artificial Intelligence technique known as generative manifold learning. We test the potential benefit of these personalized normative values in comparison with the more traditional average normative values on a population of patients with drug-resistant epilepsy operated for focal cortical dysplasia, as well as on a supplementary healthy group and on patients with Alzheimer's disease.

Deep learning segmentation of the choroid plexus from structural magnetic resonance imaging (MRI): validation and normative ranges across the adult lifespan

BACKGROUND

The choroid plexus functions as the blood-cerebrospinal fluid (CSF) barrier, plays an important role in CSF production and circulation, and has gained increased attention in light of the recent elucidation of CSF circulation dysfunction in neurodegenerative conditions. However, methods for routinely quantifying choroid plexus volume are suboptimal and require technical improvements and validation. Here, we propose three deep learning models that can segment the choroid plexus from commonly-acquired anatomical MRI data and report performance metrics and changes across the adult lifespan.

METHODS

Fully convolutional neural networks were trained from 3D T1-weighted, 3D T2-weighted, and 2D T2-weighted FLAIR MRI using gold-standard manual segmentations in control and neurodegenerative participants across the lifespan (n = 50; age = 21-85 years). Dice coefficients, 95% Hausdorff distances, and area-under-curve (AUCs) were calculated for each model and compared to segmentations from FreeSurfer using two-tailed Wilcoxon tests (significance criteria: p < 0.05 after false discovery rate multiple comparisons correction). Metrics were regressed against lateral ventricular volume using generalized linear models to assess model performance for varying levels of atrophy. Finally, models were applied to an expanded cohort of adult controls (n = 98; age = 21-89 years) to provide an exemplar of choroid plexus volumetry values across the lifespan.

RESULTS

Deep learning results yielded Dice coefficient = 0.72, Hausdorff distance = 1.97 mm, AUC = 0.87 for T1-weighted MRI, Dice coefficient = 0.72, Hausdorff distance = 2.22 mm, AUC = 0.87 for T2-weighted MRI, and Dice coefficient = 0.74, Hausdorff distance = 1.69 mm, AUC = 0.87 for T2-weighted FLAIR MRI; values did not differ significantly between MRI sequences and were statistically improved compared to current commercially-available algorithms (p < 0.001). The intraclass coefficients were 0.95, 0.95, and 0.96 between T1-weighted and T2-weighted FLAIR, T1-weighted and T2-weighted, and T2-weighted and T2-weighted FLAIR models, respectively. Mean lateral ventricle choroid plexus volume across all participants was 3.20 ± 1.4 cm3; a significant, positive relationship (R2 = 0.54-0.60) was observed between participant age and choroid plexus volume for all MRI sequences (p < 0.001).

CONCLUSIONS

Findings support comparable performance in choroid plexus delineation between standard, clinically available, non-contrasted anatomical MRI sequences. The software embedding the evaluated models is freely available online and should provide a useful tool for the growing number of studies that desire to quantitatively evaluate choroid plexus structure and function ( https://github.com/hettk/chp_seg ).

Staging of progressive supranuclear palsy-Richardson syndrome using MRI brain charts for the human lifespan

Brain charts for the human lifespan have been recently proposed to build dynamic models of brain anatomy in normal aging and various neurological conditions. They offer new possibilities to quantify neuroanatomical changes from preclinical stages to death, where longitudinal MRI data are not available. In this study, we used brain charts to model the progression of brain atrophy in progressive supranuclear palsy-Richardson syndrome. We combined multiple datasets (n = 8170 quality controlled MRI of healthy subjects from 22 cohorts covering the entire lifespan, and n = 62 MRI of progressive supranuclear palsy-Richardson syndrome patients from the Four Repeat Tauopathy Neuroimaging Initiative (4RTNI)) to extrapolate lifetime volumetric models of healthy and progressive supranuclear palsy-Richardson syndrome brain structures. We then mapped in time and space the sequential divergence between healthy and progressive supranuclear palsy-Richardson syndrome charts. We found six major consecutive stages of atrophy progression: (i) ventral diencephalon (including subthalamic nuclei, substantia nigra, and red nuclei), (ii) pallidum, (iii) brainstem, striatum and amygdala, (iv) thalamus, (v) frontal lobe, and (vi) occipital lobe. The three structures with the most severe atrophy over time were the thalamus, followed by the pallidum and the brainstem. These results match the neuropathological staging of tauopathy progression in progressive supranuclear palsy-Richardson syndrome, where the pathology is supposed to start in the pallido-nigro-luysian system and spreads rostrally via the striatum and the amygdala to the cerebral cortex, and caudally to the brainstem. This study supports the use of brain charts for the human lifespan to study the progression of neurodegenerative diseases, especially in the absence of specific biomarkers as in PSP.

Deep learning segmentation of peri-sinus structures from structural magnetic resonance imaging: validation and normative ranges across the adult lifespan

BACKGROUND

Peri-sinus structures such as arachnoid granulations (AG) and the parasagittal dural (PSD) space have gained much recent attention as sites of cerebral spinal fluid (CSF) egress and neuroimmune surveillance. Neurofluid circulation dysfunction may manifest as morphological changes in these structures, however, automated quantification of these structures is not possible and rather characterization often requires exogenous contrast agents and manual delineation.

METHODS

We propose a deep learning architecture to automatically delineate the peri-sinus space (e.g., PSD and intravenous AG structures) using two cascaded 3D fully convolutional neural networks applied to submillimeter 3D T2-weighted non-contrasted MRI images, which can be routinely acquired on all major MRI scanner vendors. The method was evaluated through comparison with gold-standard manual tracing from a neuroradiologist (n = 80; age range = 11-83 years) and subsequently applied in healthy participants (n = 1,872; age range = 5-100 years), using data from the Human Connectome Project, to provide exemplar metrics across the lifespan. Dice-Sørensen and a generalized linear model was used to assess PSD and AG changes across the human lifespan using quadratic restricted splines, incorporating age and sex as covariates.

RESULTS

Findings demonstrate that the PSD and AG volumes can be segmented using T2-weighted MRI with a Dice-Sørensen coefficient and accuracy of 80.7 and 74.6, respectively. Across the lifespan, we observed that total PSD volume increases with age with a linear interaction of gender and age equal to 0.9 cm3 per year (p < 0.001). Similar trends were observed in the frontal and parietal, but not occipital, PSD. An increase in AG volume was observed in the third to sixth decades of life, with a linear effect of age equal to 0.64 mm3 per year (p < 0.001) for total AG volume and 0.54 mm3 (p < 0.001) for maximum AG volume.

CONCLUSIONS

A tool that can be applied to quantify PSD and AG volumes from commonly acquired T2-weighted MRI scans is reported and exemplar volumetric ranges of these structures are provided, which should provide an exemplar for studies of neurofluid circulation dysfunction. Software and training data are made freely available online ( https://github.com/hettk/spesis ).

Growing importance of brain morphometry analysis in the clinical routine: The hidden impact of MR sequence parameters

Volumetric assessment based on structural MRI is increasingly recognized as an auxiliary tool to visual reading, also in examinations acquired in the clinical routine. However, MRI acquisition parameters can significantly influence these measures, which must be considered when interpreting the results on an individual patient level. This Technical Note shall demonstrate the problem. Using data from a dedicated experiment, we show the influence of two crucial sequence parameters on the GM/WM contrast and their impact on the measured volumes. A simulated contrast derived from acquisition parameters TI/TR may serve as surrogate and is highly correlated (r=0.96) with the measured contrast.

Development of the next-generation functional neuro-cognitive imaging protocol - Part 1: A 3D sliding-window convolutional neural net for automated brain parcellation

Functional MRI has emerged as a powerful tool to assess the severity of Post-concussion syndrome (PCS) and to provide guidance for neuro-cognitive therapists during treatment. The next-generation functional neuro-cognitive imaging protocol (fNCI2) has been developed to provide this assessment. This paper covers the first step in the analysis process, the development of a rapidly re-trainable, machine-learning, brain parcellation tool. The use of a sufficiently deep U-Net architecture encompassing a small (39 × 39 × 39 voxel input, 27 × 27 × 27 voxel output) sliding window to sample the entirety of the 3D image allows for the prediction of the entire image using only a single trained network. A large number of training, validating, and testing windows are thus generated from the 101 manually-labeled Mindboggle images, and full-image prediction is provided via a voxel-vote method using overlapping windows. Our method produces parcellated images that are highly consistent with standard atlas-based methods in under 3 min on a modern GPU, and the single network architecture allows for rapid retraining (<36 hr) as needed.

Brain structure ages-A new biomarker for multi-disease classification

Age is an important variable to describe the expected brain's anatomy status across the normal aging trajectory. The deviation from that normative aging trajectory may provide some insights into neurological diseases. In neuroimaging, predicted brain age is widely used to analyze different diseases. However, using only the brain age gap information (i.e., the difference between the chronological age and the estimated age) can be not enough informative for disease classification problems. In this paper, we propose to extend the notion of global brain age by estimating brain structure ages using structural magnetic resonance imaging. To this end, an ensemble of deep learning models is first used to estimate a 3D aging map (i.e., voxel-wise age estimation). Then, a 3D segmentation mask is used to obtain the final brain structure ages. This biomarker can be used in several situations. First, it enables to accurately estimate the brain age for the purpose of anomaly detection at the population level. In this situation, our approach outperforms several state-of-the-art methods. Second, brain structure ages can be used to compute the deviation from the normal aging process of each brain structure. This feature can be used in a multi-disease classification task for an accurate differential diagnosis at the subject level. Finally, the brain structure age deviations of individuals can be visualized, providing some insights about brain abnormality and helping clinicians in real medical contexts.

Lifespan neurodegeneration of the human brain in multiple sclerosis

Atrophy related to multiple sclerosis (MS) has been found at the early stages of the disease. However, the archetype dynamic trajectories of the neurodegenerative process, even prior to clinical diagnosis, remain unknown. We modeled the volumetric trajectories of brain structures across the entire lifespan using 40,944 subjects (38,295 healthy controls and 2649 MS patients). Then, we estimated the chronological progression of MS by assessing the divergence of lifespan trajectories between normal brain charts and MS brain charts. Chronologically, the first affected structure was the thalamus, then the putamen and the pallidum (around 4 years later), followed by the ventral diencephalon (around 7 years after thalamus) and finally the brainstem (around 9 years after thalamus). To a lesser extent, the anterior cingulate gyrus, insular cortex, occipital pole, caudate and hippocampus were impacted. Finally, the precuneus and accumbens nuclei exhibited a limited atrophy pattern. Subcortical atrophy was more pronounced than cortical atrophy. The thalamus was the most impacted structure with a very early divergence in life. Our experiments showed that lifespan models of most impacted structures could be an important tool for future preclinical/prodromal prognosis and monitoring of MS.

Increased microglia activation in late non-central nervous system cancer survivors links to chronic systemic symptomatology

Prolonged inflammatory expression within the central nervous system (CNS) is recognized by the brain as a molecular signal of "sickness", that has knock-on effects to the blood-brain barrier, brain-spinal barrier, blood-cerebrospinal fluid barrier, neuro-axonal structures, neurotransmitter activity, synaptic plasticity, neuroendocrine function, and resultant systemic symptomatology. It is concurred that the inflammatory process associated with cancer and cancer treatments underline systemic symptoms present in a large portion of survivors, although this concept is largely theoretical from disparate and indirect evidence and/or clinical anecdotal reports. We conducted a proof-of-concept study to link for the first time late non-CNS cancer survivors presenting chronic systemic symptoms and the presence of centralized inflammation, or neuroinflammation, using TSPO-binding PET tracer [11 C]-PBR28 to visualize microglial activation. We compared PBR28 SUVR in 10 non-CNS cancer survivors and 10 matched healthy controls. Our data revealed (1) microglial activation was significantly higher in caudate, temporal, and occipital regions in late non-central nervous system/CNS cancer survivors compared to healthy controls; (2) increased neuroinflammation in cancer survivors was not accompanied by significant differences in plasma cytokine markers of peripheral inflammation; (3) increased neuroinflammation was not accompanied by reduced fractional anisotropy, suggesting intact white matter microstructural integrity, a marker of neurovascular fiber tract organization; and (4) the presentation of chronic systemic symptoms in cancer survivors was significantly connected with microglial activation. We present the first data empirically supporting the concept of a peripheral-to-centralized inflammatory response in non-CNS cancer survivors, specifically those previously afflicted with head and neck cancer. Following resolution of the initial peripheral inflammation from the cancer/its treatments, in some cases damage/toxification to the central nervous system occurs, ensuing chronic systemic symptoms.

Cerebrospinal Fluid Flow in Patients with Huntington's Disease

OBJECTIVE

Investigations of cerebrospinal fluid (CSF) flow aberrations in Huntington's disease (HD) are of growing interest, as impaired CSF flow may contribute to mutant Huntington retention and observed heterogeneous responsiveness to intrathecally administered therapies.

METHOD

We assessed net cerebral aqueduct CSF flow and velocity in 29 HD participants (17 premanifest and 12 manifest) and 51 age- and sex matched non-HD control participants using 3-Tesla magnetic resonance imaging methods. Regression models were applied to test hypotheses regarding: (i) net CSF flow and cohort, (ii) net CSF flow and disease severity (CAP-score), and (iii) CSF volume after correcting for age and sex.

RESULTS

Group-wise analyses support a decrease in net CSF flow in HD (mean 0.14 ± 0.27 mL/min) relative to control (mean 0.32 ± 0.20 mL/min) participants (p = 0.02), with lowest flow in the manifest HD cohort (mean 0.04 ± 0.25 mL/min). This finding was explained by hyperdynamic CSF movement, manifesting as higher caudal systolic CSF flow velocity and higher diastolic cranial CSF flow velocity across the cardiac cycle, in HD (caudal flow: 0.17 ± 0.07 mL/s, cranial flow: 0.14 ± 0.08 mL/s) compared to control (caudal flow: 0.13 ± 0.06 mL/s, cranial flow: 0.11 ± 0.04 mL/s) participants. A positive correlation between cranial diastolic flow and disease severity was observed (p = 0.02).

INTERPRETATIONS

Findings support aqueductal CSF flow dynamics changing with disease severity in HD. These accelerated changes are consistent with changes observed over the typical adult lifespan, and may have relevance to mutant Huntington retention and intrathecally administered therapeutics responsiveness. ANN NEUROL 2023;94:885-894.

Deep grading for MRI-based differential diagnosis of Alzheimer's disease and Frontotemporal dementia

Alzheimer's disease and Frontotemporal dementia are common forms of neurodegenerative dementia. Behavioral alterations and cognitive impairments are found in the clinical courses of both diseases, and their differential diagnosis can sometimes pose challenges for physicians. Therefore, an accurate tool dedicated to this diagnostic challenge can be valuable in clinical practice. However, current structural imaging methods mainly focus on the detection of each disease but rarely on their differential diagnosis. In this paper, we propose a deep learning-based approach for both disease detection and differential diagnosis. We suggest utilizing two types of biomarkers for this application: structure grading and structure atrophy. First, we propose to train a large ensemble of 3D U-Nets to locally determine the anatomical patterns of healthy people, patients with Alzheimer's disease and patients with Frontotemporal dementia using structural MRI as input. The output of the ensemble is a 2-channel disease's coordinate map, which can be transformed into a 3D grading map that is easily interpretable for clinicians. This 2-channel disease's coordinate map is coupled with a multi-layer perceptron classifier for different classification tasks. Second, we propose to combine our deep learning framework with a traditional machine learning strategy based on volume to improve the model discriminative capacity and robustness. After both cross-validation and external validation, our experiments, based on 3319 MRIs, demonstrated that our method produces competitive results compared to state-of-the-art methods for both disease detection and differential diagnosis.

Analysis of Genetic and MRI Changes, Blood Markers, and Risk Factors in a Twin Pair Discordant of Progressive Supranuclear Palsy

Background and Objectives: Progressive supranuclear palsy (PSP) is a neurodegenerative disease, a tauopathy, which results in a wide clinical spectrum of neurological symptoms. The diagnosis is mostly based on clinical signs and neuroimaging; however, possible biomarkers for screening have been under investigation, and the role of the gut microbiome is unknown. The aim of our study was to identify potential blood biomarkers and observe variations in the gut microbiome within a PSP discordant monozygotic twin pair. Materials and Methods: Anthropometric measurements, neuropsychological tests, and the neurological state were evaluated. Blood was collected for metabolic profiling and for the detection of neurodegenerative and vascular biomarkers. Both the gut microbiome and brain MRI results were thoroughly examined. Results: We found a relevant difference between alpha-synuclein levels and moderate difference in the levels of MMP-2, MB, Apo-A1, Apo-CIII, and Apo-H. With respect to the ratios, a small difference was observed for ApoA1/SAA and ApoB/ApoA1. Using a microbiome analysis, we also discovered a relative dysbiosis, and the MRI results revealed midbrain and frontoparietal cortical atrophy along with a reduction in overall brain volumes and an increase in white matter lesions in the affected twin. Conclusions: We observed significant differences between the unaffected and affected twins in some risk factors and blood biomarkers, along with disparities in the gut microbiome. Additionally, we detected abnormalities in brain MRI results and alterations in cognitive functions.

Deep learning segmentation of the choroid plexus from structural magnetic resonance imaging (MRI): validation and normative ranges across the adult lifespan

Background

The choroid plexus functions as the blood-cerebrospinal fluid barrier, plays an important role in neurofluid production and circulation, and has gained increased attention in light of the recent elucidation of neurofluid circulation dysfunction in neurodegenerative conditions. However, methods for routinely quantifying choroid plexus volume are suboptimal and require technical improvements and validation. Here, we propose three deep learning models that can segment the choroid plexus from commonly-acquired anatomical MRI data and report performance metrics and changes across the adult lifespan.

Methods

Fully convolutional neural networks were trained from 3-D T1-weighted, 3-D T2-weighted, and 2-D T2-weighted FLAIR MRI and gold-standard manual segmentations in healthy and neurodegenerative participants across the lifespan (n=50; age=21-85 years). Dice coefficients, 95% Hausdorff distances, and area-under-curve (AUCs) were calculated for each model and compared to segmentations from FreeSurfer using two-tailed Wilcoxon tests (significance criteria: p<0.05 after false discovery rate multiple comparisons correction). Metrics were regressed against lateral ventricular volume using generalized linear models to assess model performance for varying levels of atrophy. Finally, models were applied to an expanded cohort of healthy adults (n=98; age=21-89 years) to provide an exemplar of choroid plexus volumetry values across the lifespan.

Results

Deep learning results yielded Dice coefficient=0.72, Hausdorff distance=1.97 mm, AUC=0.87 for T1-weighted MRI, Dice coefficient=0.72, Hausdorff distance=2.22 mm, AUC=0.87 for T2-weighted MRI, and Dice coefficient=0.74, Hausdorff distance=1.69 mm, AUC=0.87 for T2-weighted FLAIR MRI; values did not differ significantly between2 MRI sequences and were statistically improved compared to current commercially-available algorithms (p<0.001). The intraclass coefficients were 0.95, 0.95, and 0.96 between T1-weighted and T2-FLAIR, T1-weighted and T2-weighted, and T2-weighted and T2-FLAIR models, respectively. Mean lateral ventricle choroid plexus volume across all participants was 3.20±1.4 cm3; a significant, positive relationship (R2=0.54; slope=0.047) was observed between participant age and choroid plexus volume for all MRI sequences (p<0.001).

Conclusions

Findings support comparable performance in choroid plexus delineation between standard, clinically available, non-contrasted anatomical MRI sequences. The software embedding the evaluated models is freely available online and should provide a useful tool for the growing number of studies that desire to quantitatively evaluate choroid plexus structure and function (https://github.com/hettk/chp_seg).

Corticostriatal beta oscillation changes associated with cognitive function in Parkinson's disease

Cognitive impairment is the most frequent non-motor symptom in Parkinson's disease and is associated with deficits in a number of cognitive functions including working memory. However, the pathophysiology of Parkinson's disease cognitive impairment is poorly understood. Beta oscillations have previously been shown to play an important role in cognitive functions including working memory encoding. Decreased dopamine in motor cortico-striato-thalamo-cortical (CSTC) circuits increases the spectral power of beta oscillations and results in Parkinson's disease motor symptoms. Analogous changes in parallel cognitive CSTC circuits involving the caudate and dorsolateral prefrontal cortex (DLPFC) may contribute to Parkinson's disease cognitive impairment. The objective of our study is to evaluate whether changes in beta oscillations in the caudate and DLPFC contribute to cognitive impairment in Parkinson's disease patients. To investigate this, we used local field potential recordings during deep brain stimulation surgery in 15 patients with Parkinson's disease. Local field potentials were recorded from DLPFC and caudate at rest and during a working memory task. We examined changes in beta oscillatory power during the working memory task as well as the relationship of beta oscillatory activity to preoperative cognitive status, as determined from neuropsychological testing results. We additionally conducted exploratory analyses on the relationship between cognitive impairment and task-based changes in spectral power in additional frequency bands. Spectral power of beta oscillations decreased in both DLPFC and caudate during working memory encoding and increased in these structures during feedback. Subjects with cognitive impairment had smaller decreases in caudate and DLPFC beta oscillatory power during encoding. In our exploratory analysis, we found that similar differences occurred in alpha frequencies in caudate and theta and alpha in DLPFC. Our findings suggest that oscillatory power changes in cognitive CSTC circuits may contribute to cognitive symptoms in patients with Parkinson's disease. These findings may inform the future development of novel neuromodulatory treatments for cognitive impairment in Parkinson's disease.

Anatomical MRI staging of frontotemporal dementia variants

INTRODUCTION

The three clinical variants of frontotemporal dementia (behavioral variant [bvFTD], semantic dementia, and progressive non-fluent aphasia [PNFA]) are likely to develop over decades, from the preclinical stage to death.

METHODS

To describe the long-term chronological anatomical progression of FTD variants, we built lifespan brain charts of normal aging and FTD variants by combining 8022 quality-controlled MRIs from multiple large-scale data-bases, including 107 bvFTD, 44 semantic dementia, and 38 PNFA.

RESULTS

We report in this manuscript the anatomical MRI staging schemes of the three FTD variants by describing the sequential divergence of volumetric trajectories between normal aging and FTD variants. Subcortical atrophy precedes focal cortical atrophy in specific behavioral and/or language networks, with a "radiological" prodromal phase lasting 8-10 years (time elapsed between the first structural alteration and canonical cortical atrophy).

DISCUSSION

Amygdalar and striatal atrophy can be candidate biomarkers for future preclinical/prodromal FTD variants definitions.

HIGHLIGHTS

We describe the chronological MRI staging of the most affected structures in the three frontotemporal dementia (FTD) syndromic variants. In behavioral variant of FTD (bvFTD): bilateral amygdalar, striatal, and insular atrophy precedes fronto-temporal atrophy. In semantic dementia: bilateral amygdalar atrophy precedes left temporal and hippocampal atrophy. In progressive non-fluent aphasia (PNFA): left striatal, insular, and thalamic atrophy precedes opercular atrophy.

Automated hippocampal segmentation algorithms evaluated in stroke patients

Deep learning segmentation algorithms can produce reproducible results in a matter of seconds. However, their application to more complex datasets is uncertain and may fail in the presence of severe structural abnormalities-such as those commonly seen in stroke patients. In this investigation, six recent, deep learning-based hippocampal segmentation algorithms were tested on 641 stroke patients of a multicentric, open-source dataset ATLAS 2.0. The comparisons of the volumes showed that the methods are not interchangeable with concordance correlation coefficients from 0.266 to 0.816. While the segmentation algorithms demonstrated an overall good performance (volumetric similarity [VS] 0.816 to 0.972, DICE score 0.786 to 0.921, and Hausdorff distance [HD] 2.69 to 6.34), no single out-performing algorithm was identified: FastSurfer performed best in VS, QuickNat in DICE and average HD, and Hippodeep in HD. Segmentation performance was significantly lower for ipsilesional segmentation, with a decrease in performance as a function of lesion size due to the pathology-based domain shift. Only QuickNat showed a more robust performance in volumetric similarity. Even though there are many pre-trained segmentation methods, it is important to be aware of the possible decrease in performance for the segmentation results on the lesion side due to the pathology-based domain shift. The segmentation algorithm should be selected based on the research question and the evaluation parameter needed. More research is needed to improve current hippocampal segmentation methods.

Deep Learning for Medical Image-Based Cancer Diagnosis

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images.

Deriving a robust deep-learning model for subcortical brain segmentation by using a large-scale database: Preprocessing, reproducibility, and accuracy of volume estimation

Increasing the accuracy and reproducibility of subcortical brain segmentation is advantageous in various related clinical applications. In this study, we derived a segmentation method based on a convolutional neural network (i.e., U-Net) and a large-scale database consisting of 7039 brain T1-weighted MRI data samples. We evaluated the method by using experiments focused on three distinct topics, namely, the necessity of preprocessing steps, cross-institutional and longitudinal reproducibility, and volumetric accuracy. The optimized model, MX_RW-where "MX" is a mix of RW and nonuniform intensity normalization data and "RW" is raw data with basic preprocessing-did not require time-consuming preprocessing steps, such as nonuniform intensity normalization or image registration, for brain MRI before segmentation. Cross-institutional testing revealed that MX_RW (Dice similarity coefficient: 0.809, coefficient of variation: 4.6%, and Pearson's correlation coefficient: 0.979) exhibited a performance comparable with that of FreeSurfer (Dice similarity coefficient: 0.798, coefficient of variation: 5.6%, and Pearson's correlation coefficient: 0.973). The computation time per dataset of MX_RW was generally less than 5 s (even when tested without graphics processing units), which was notably faster than FreeSurfer. Thus, for time-restricted applications, MX_RW represents a competitive alternative to FreeSurfer.

Parasagittal dural space hypertrophy and amyloid-β deposition in Alzheimer's disease

One of the pathological hallmarks of Alzheimer's and related diseases is the increased accumulation of protein amyloid-β in the brain parenchyma. As such, recent studies have focused on characterizing protein and related clearance pathways involving perivascular flow of neurofluids, but human studies of these pathways are limited owing to limited methods for evaluating neurofluid circulation non-invasively in vivo. Here, we utilize non-invasive MRI methods to explore surrogate measures of CSF production, bulk flow and egress in the context of independent PET measures of amyloid-β accumulation in older adults. Participants (N = 23) were scanned at 3.0 T with 3D T2-weighted turbo spin echo, 2D perfusion-weighted pseudo-continuous arterial spin labelling and phase-contrast angiography to quantify parasagittal dural space volume, choroid plexus perfusion and net CSF flow through the aqueduct of Sylvius, respectively. All participants also underwent dynamic PET imaging with amyloid-β tracer 11C-Pittsburgh Compound B to quantify global cerebral amyloid-β accumulation. Spearman's correlation analyses revealed a significant relationship between global amyloid-β accumulation and parasagittal dural space volume (rho = 0.529, P = 0.010), specifically in the frontal (rho = 0.527, P = 0.010) and parietal (rho = 0.616, P = 0.002) subsegments. No relationships were observed between amyloid-β and choroid plexus perfusion nor net CSF flow. Findings suggest that parasagittal dural space hypertrophy, and its possible role in CSF-mediated clearance, may be closely related to global amyloid-β accumulation. These findings are discussed in the context of our growing understanding of the physiological mechanisms of amyloid-β aggregation and clearance via neurofluids.

Lifespan Neurodegeneration Of The Human Brain In Multiple Sclerosis

Background

Atrophy related to Multiple Sclerosis (MS) has been found at the early stages of the disease. However, the archetype dynamic trajectories of the neurodegenerative process, even prior to clinical diagnosis, remain unknown.

Methods

We modeled the volumetric trajectories of brain structures across the entire lifespan using 40944 subjects (38295 healthy controls and 2649 MS patients). Then, we estimated the chronological progression of MS by assessing the divergence of lifespan trajectories between normal brain charts and MS brain charts.

Results

Chronologically, the first affected structure was the thalamus, then the putamen and the pallidum (3 years later), followed by the ventral diencephalon (7 years after thalamus) and finally the brainstem (9 years after thalamus). To a lesser extent, the anterior cingulate gyrus, insular cortex, occipital pole, caudate and hippocampus were impacted. Finally, the precuneus and accumbens nuclei exhibited a limited atrophy pattern.

Conclusion

Subcortical atrophy was more pronounced than cortical atrophy. The thalamus was the most impacted structure with a very early divergence in life. It paves the way toward utilization of these lifespan models for future preclinical/prodromal prognosis and monitoring of MS.

Towards better interpretable and generalizable AD detection using collective artificial intelligence

Alzheimer's Disease is the most common cause of dementia. Accurate diagnosis and prognosis of this disease are essential to design an appropriate treatment plan, increasing the life expectancy of the patient. Intense research has been conducted on the use of machine learning to identify Alzheimer's Disease from neuroimaging data, such as structural magnetic resonance imaging. In recent years, advances of deep learning in computer vision suggest a new research direction for this problem. Current deep learning-based approaches in this field, however, have a number of drawbacks, including the interpretability of model decisions, a lack of generalizability information and a lower performance compared to traditional machine learning techniques. In this paper, we design a two-stage framework to overcome these limitations. In the first stage, an ensemble of 125 U-Nets is used to grade the input image, producing a 3D map that reflects the disease severity at voxel-level. This map can help to localize abnormal brain areas caused by the disease. In the second stage, we model a graph per individual using the generated grading map and other information about the subject. We propose to use a graph convolutional neural network classifier for the final classification. As a result, our framework demonstrates comparative performance to the state-of-the-art methods in different datasets for both diagnosis and prognosis. We also demonstrate that the use of a large ensemble of U-Nets offers a better generalization capacity for our framework.

High-resolution atlasing and segmentation of the subcortex: Review and perspective on challenges and opportunities created by machine learning

This paper reviews almost three decades of work on atlasing and segmentation methods for subcortical structures in human brain MRI. In writing this survey, we have three distinct aims. First, to document the evolution of digital subcortical atlases of the human brain, from the early MRI templates published in the nineties, to the complex multi-modal atlases at the subregion level that are available today. Second, to provide a detailed record of related efforts in the automated segmentation front, from earlier atlas-based methods to modern machine learning approaches. And third, to present a perspective on the future of high-resolution atlasing and segmentation of subcortical structures in in vivo human brain MRI, including open challenges and opportunities created by recent developments in machine learning.

Anatomically curated segmentation of human subcortical structures in high resolution magnetic resonance imaging: An open science approach

Magnetic resonance imaging (MRI)-based brain segmentation has recently been revolutionized by deep learning methods. These methods use large numbers of annotated segmentations to train algorithms that have the potential to perform brain segmentations reliably and quickly. However, training data for these algorithms are frequently obtained from automated brain segmentation systems, which may contain inaccurate neuroanatomy. Thus, the neuroimaging community would benefit from an open source database of high quality, neuroanatomically curated and manually edited MRI brain images, as well as the publicly available tools and detailed procedures for generating these curated data. Manual segmentation approaches are regarded as the gold standard for brain segmentation and parcellation. These approaches underpin the construction of neuroanatomically accurate human brain atlases. In addition, neuroanatomically precise definitions of MRI-based regions of interest (ROIs) derived from manual brain segmentation are essential for accuracy in structural connectivity studies and in surgical planning for procedures such as deep brain stimulation. However, manual segmentation procedures are time and labor intensive, and not practical in studies utilizing very large datasets, large cohorts, or multimodal imaging. Automated segmentation methods were developed to overcome these issues, and provide high data throughput, increased reliability, and multimodal imaging capability. These methods utilize manually labeled brain atlases to automatically parcellate the brain into different ROIs, but do not have the anatomical accuracy of skilled manual segmentation approaches. In the present study, we developed a custom software module for manual editing of brain structures in the freely available 3D Slicer software platform that employs principles and tools based on pioneering work from the Center for Morphometric Analysis (CMA) at Massachusetts General Hospital. We used these novel 3D Slicer segmentation tools and techniques in conjunction with well-established neuroanatomical definitions of subcortical brain structures to manually segment 50 high resolution T1w MRI brains from the Human Connectome Project (HCP) Young Adult database. The structural definitions used herein are associated with specific neuroanatomical ontologies to systematically interrelate histological and MRI-based morphometric definitions. The resulting brain datasets are publicly available and will provide the basis for a larger database of anatomically curated brains as an open science resource.