U-net model for brain extraction: Trained on humans for transfer to non-human primates

Multimodal Connectivity-Based Individual Parcellation and Analysis for Humans and Rhesus Monkeys

Individual brains vary greatly in morphology, connectivity and organization. Individualized brain parcellation is capable of precisely localizing subject-specific functional regions. However, most individualization approaches have examined single modalities of data and have not generalized to nonhuman primates. The present study proposed a novel multimodal connectivity-based individual parcellation (MCIP) method, which optimizes within-region homogeneity, spatial continuity and similarity to a reference atlas with the fusion of personal functional and anatomical connectivity. Comprehensive evaluation demonstrated that MCIP outperformed state-of-the-art multimodal individualization methods in terms of functional and anatomical homogeneity, predictability of cognitive measures, heritability, reproducibility and generalizability across species. Comparative investigation showed a higher topographic variability in humans than that in macaques. Therefore, MCIP provides improved accurate and reliable mapping of brain functional regions over existing methods at an individual level across species, and could facilitate comparative and translational neuroscience research.

nBEST: Deep-learning-based non-human primates Brain Extraction and Segmentation Toolbox across ages, sites and species

Accurate processing and analysis of non-human primate (NHP) brain magnetic resonance imaging (MRI) serves an indispensable role in understanding brain evolution, development, aging, and diseases. Despite the accumulation of diverse NHP brain MRI datasets at various developmental stages and from various imaging sites/scanners, existing computational tools designed for human MRI typically perform poor on NHP data, due to huge differences in brain sizes, morphologies, and imaging appearances across species, sites, and ages, highlighting the imperative for NHP-specialized MRI processing tools. To address this issue, in this paper, we present a robust, generic, and fully automated computational pipeline, called non-human primates Brain Extraction and Segmentation Toolbox (nBEST), whose main functionality includes brain extraction, non-cerebrum removal, and tissue segmentation. Building on cutting-edge deep learning techniques by employing lifelong learning to flexibly integrate data from diverse NHP populations and innovatively constructing 3D U-NeXt architecture, nBEST can well handle structural NHP brain MR images from multi-species, multi-site, and multi-developmental-stage (from neonates to the elderly). We extensively validated nBEST based on, to our knowledge, the largest assemblage dataset in NHP brain studies, encompassing 1,469 scans with 11 species (e.g., rhesus macaques, cynomolgus macaques, chimpanzees, marmosets, squirrel monkeys, etc.) from 23 independent datasets. Compared to alternative tools, nBEST outperforms in precision, applicability, robustness, comprehensiveness, and generalizability, greatly benefiting downstream longitudinal, cross-sectional, and cross-species quantitative analyses. We have made nBEST an open-source toolbox (https://github.com/TaoZhong11/nBEST) and we are committed to its continual refinement through lifelong learning with incoming data to greatly contribute to the research field.

Deep brain stimulation induces white matter remodeling and functional changes to brain-wide networks

Deep brain stimulation (DBS) is an emerging therapeutic option for treatment resistant neurological and psychiatric disorders, most notably depression. Despite this, little is known about the anatomical and functional mechanisms that underlie this therapy. Here we targeted stimulation to the white matter adjacent to the subcallosal anterior cingulate cortex (SCC-DBS) in macaques, modeling the location in the brain proven effective for depression. We demonstrate that SCC-DBS has a selective effect on white matter macro- and micro-structure in the cingulum bundle distant to where stimulation was delivered. SCC-DBS also decreased functional connectivity between subcallosal and posterior cingulate cortex, two areas linked by the cingulum bundle and implicated in depression. Our data reveal that white matter remodeling as well as functional effects contribute to DBS's therapeutic efficacy.

The neural basis of resting-state fMRI functional connectivity in fronto-limbic circuits revealed by chemogenetic manipulation

Measures of fMRI resting-state functional connectivity (rs-FC) are an essential tool for basic and clinical investigations of fronto-limbic circuits. Understanding the relationship between rs-FC and the underlying patterns of neural activity in these circuits is therefore vital. Here we introduced inhibitory designer receptors exclusively activated by designer drugs (DREADDs) into the amygdala of two male macaques. We evaluated the causal effect of activating the DREADD receptors on rs-FC and neural activity within circuits connecting amygdala and frontal cortex. Activating the inhibitory DREADD increased rs-FC between amygdala and ventrolateral prefrontal cortex. Neurophysiological recordings revealed that the DREADD-induced increase in fMRI rs-FC was associated with increased local field potential coherency in the alpha band (6.5-14.5 Hz) between amygdala and ventrolateral prefrontal cortex. Thus, our multi-modal approach reveals the specific signature of neuronal activity that underlies rs-FC in fronto-limbic circuits.

Initiating PeriCBD to probe perinatal influences on neurodevelopment during 3-10 years in China

Adverse perinatal factors can interfere with the normal development of the brain, potentially resulting in long-term effects on the comprehensive development of children. Presently, the understanding of cognitive and neurodevelopmental processes under conditions of adverse perinatal factors is substantially limited. There is a critical need for an open resource that integrates various perinatal factors with the development of the brain and mental health to facilitate a deeper understanding of these developmental trajectories. In this Data Descriptor, we introduce a multicenter database containing information on perinatal factors that can potentially influence children's brain-mind development, namely, periCBD, that combines neuroimaging and behavioural phenotypes with perinatal factors at county/region/central district hospitals. PeriCBD was designed to establish a platform for the investigation of individual differences in brain-mind development associated with perinatal factors among children aged 3-10 years. Ultimately, our goal is to help understand how different adverse perinatal factors specifically impact cognitive development and neurodevelopment. Herein, we provide a systematic overview of the data acquisition/cleaning/quality control/sharing, processes of periCBD.

FFCM-MRF: An accurate and generalizable cerebrovascular segmentation pipeline for humans and rhesus monkeys based on TOF-MRA

PURPOSE

Cerebrovascular segmentation and quantification of vascular morphological features in humans and rhesus monkeys are essential for prevention, diagnosis, and treatment of brain diseases. However, current automated whole-brain vessel segmentation methods are often not generalizable to independent datasets, limiting their usefulness in real-world environments with their heterogeneity in participants, scanners, and species.

MATERIALS AND METHODS

In this study, we proposed an automated, accurate and generalizable segmentation method for magnetic resonance angiography images called FFCM-MRF. This method integrated fast fuzzy c-means clustering and Markov random field optimization by vessel shape priors and spatial constraints. We used a total of 123 human and 44 macaque MRA images scanned at 1.5 T, 3 T, and 7 T MRI from 9 datasets to develop and validate the method.

RESULTS

FFCM-MRF achieved average Dice similarity coefficients ranging from 69.16 % to 89.63 % across multiple independent datasets, with improvements ranging from 3.24 % to 7.3 % compared to state-of-the-art methods. Quantitative analysis showed that FFCM-MRF can accurately segment major arteries in the Circle of Willis at the base of the brain and small distal pial arteries while effectively reducing noise. Test-retest analysis showed that the model yielded high vascular volume and diameter reliability.

CONCLUSIONS

Our results have demonstrated that FFCM-MRF is highly accurate and reliable and largely independent of variations in field strength, scanner platforms, acquisition parameters, and species. The macaque MRA data and user-friendly open-source toolbox are freely available at OpenNeuro and GitHub to facilitate studies of imaging biomarkers for cerebrovascular and neurodegenerative diseases.

Pharmacological modulation of dopamine D1 and D2 receptors reveals distinct neural networks related to probabilistic learning in non-human primates

The neurotransmitter dopamine (DA) has a multifaceted role in healthy and disordered brains through its action on multiple subtypes of dopaminergic receptors. How modulation of these receptors controls behavior by altering connectivity across intrinsic brain-wide networks remains elusive. Here we performed parallel behavioral and resting-state functional MRI experiments after administration of two different DA receptor antagonists in macaque monkeys. Systemic administration of SCH-23390 (D1 antagonist) disrupted probabilistic learning when subjects had to learn new stimulus-reward associations and diminished functional connectivity (FC) in cortico-cortical and fronto-striatal connections. By contrast, haloperidol (D2 antagonist) improved learning and broadly enhanced FC in cortical connections. Further comparison between the effect of SCH-23390/haloperidol on behavioral and resting-state FC revealed specific cortical and subcortical networks associated with the cognitive and motivational effects of DA, respectively. Thus, we reveal the distinct brain-wide networks that are associated with the dopaminergic control of learning and motivation via DA receptors.

Pseudo-Label Assisted nnU-Net enables automatic segmentation of 7T MRI from a single acquisition

Introduction

Automatic whole brain and lesion segmentation at 7T presents challenges, primarily from bias fields, susceptibility artifacts including distortions, and registration errors. Here, we sought to use deep learning algorithms (D/L) to do both skull stripping and whole brain segmentation on multiple imaging contrasts generated in a single Magnetization Prepared 2 Rapid Acquisition Gradient Echoes (MP2RAGE) acquisition on participants clinically diagnosed with multiple sclerosis (MS), bypassing registration errors.

Methods

Brain scans Segmentation from 3T and 7T scanners were analyzed with software packages such as FreeSurfer, Classification using Derivative-based Features (C-DEF), nnU-net, and a novel 3T-to-7T transfer learning method, Pseudo-Label Assisted nnU-Net (PLAn). 3T and 7T MRIs acquired within 9 months from 25 study participants with MS (Cohort 1) were used for training and optimizing. Eight MS patients (Cohort 2) scanned only at 7T, but with expert annotated lesion segmentation, was used to further validate the algorithm on a completely unseen dataset. Segmentation results were rated visually by experts in a blinded fashion and quantitatively using Dice Similarity Coefficient (DSC).

Results

Of the methods explored here, nnU-Net and PLAn produced the best tissue segmentation at 7T for all tissue classes. In both quantitative and qualitative analysis, PLAn significantly outperformed nnU-Net (and other methods) in lesion detection in both cohorts. PLAn's lesion DSC improved by 16% compared to nnU-Net.

Discussion

Limited availability of labeled data makes transfer learning an attractive option, and pre-training a nnUNet model using readily obtained 3T pseudo-labels was shown to boost lesion detection capabilities at 7T.

Brain tumor image segmentation based on improved FPN

PURPOSE

Automatic segmentation of brain tumors by deep learning algorithm is one of the research hotspots in the field of medical image segmentation. An improved FPN network for brain tumor segmentation is proposed to improve the segmentation effect of brain tumor.

MATERIALS AND METHODS

Aiming at the problem that the traditional full convolutional neural network (FCN) has weak processing ability, which leads to the loss of details in tumor segmentation, this paper proposes a brain tumor image segmentation method based on the improved feature pyramid networks (FPN) convolutional neural network. In order to improve the segmentation effect of brain tumors, we improved the model, introduced the FPN structure into the U-Net structure, captured the context multi-scale information by using the different scale information in the U-Net model and the multi receptive field high-level features in the FPN convolutional neural network, and improved the adaptability of the model to different scale features.

RESULTS

Performance evaluation indicators show that the proposed improved FPN model has 99.1% accuracy, 92% DICE rating and 86% Jaccard index. The performance of the proposed method outperforms other segmentation models in each metric. In addition, the schematic diagram of the segmentation results shows that the segmentation results of our algorithm are closer to the ground truth, showing more brain tumour details, while the segmentation results of other algorithms are smoother.

CONCLUSIONS

The experimental results show that this method can effectively segment brain tumor regions and has certain generalization, and the segmentation effect is better than other networks. It has positive significance for clinical diagnosis of brain tumors.

The neural basis of resting-state fMRI functional connectivity in fronto-limbic circuits revealed by chemogenetic manipulation

Measures of fMRI resting-state functional connectivity (rs-FC) are an essential tool for basic and clinical investigations of fronto-limbic circuits. Understanding the relationship between rs-FC and neural activity in these circuits is therefore vital. Here we introduced inhibitory designer receptors exclusively activated by designer drugs (DREADDs) into the macaque amygdala and activated them with a highly selective and potent DREADD agonist, deschloroclozapine. We evaluated the causal effect of activating the DREADD receptors on rs-FC and neural activity within circuits connecting amygdala and frontal cortex. Interestingly, activating the inhibitory DREADD increased rs-FC between amygdala and ventrolateral prefrontal cortex. Neurophysiological recordings revealed that the DREADD-induced increase in fMRI rs-FC was associated with increased local field potential coherency in the alpha band (6.5-14.5Hz) between amygdala and ventrolateral prefrontal cortex. Thus, our multi-disciplinary approach reveals the specific signature of neuronal activity that underlies rs-FC in fronto-limbic circuits.

versaFlow: a versatile pipeline for resolution adapted diffusion MRI processing and its application to studying the variability of the PRIME-DE database

The lack of "gold standards" in Diffusion Weighted Imaging (DWI) makes validation cumbersome. To tackle this task, studies use translational analysis where results in humans are benchmarked against findings in other species. Non-Human Primates (NHP) are particularly interesting for this, as their cytoarchitecture is closely related to humans. However, tools used for processing and analysis must be adapted and finely tuned to work well on NHP images. Here, we propose versaFlow, a modular pipeline implemented in Nextflow, designed for robustness and scalability. The pipeline is tailored to in vivo NHP DWI at any spatial resolution; it allows for maintainability and customization. Processes and workflows are implemented using cutting-edge and state-of-the-art Magnetic Resonance Imaging (MRI) processing technologies and diffusion modeling algorithms, namely Diffusion Tensor Imaging (DTI), Constrained Spherical Deconvolution (CSD), and DIstribution of Anisotropic MicrOstructural eNvironments in Diffusion-compartment imaging (DIAMOND). Using versaFlow, we provide an in-depth study of the variability of diffusion metrics computed on 32 subjects from 3 sites of the Primate Data Exchange (PRIME-DE), which contains anatomical T1-weighted (T1w) and T2-weighted (T2w) images, functional MRI (fMRI), and DWI of NHP brains. This dataset includes images acquired over a range of resolutions, using single and multi-shell gradient samplings, on multiple scanner vendors. We perform a reproducibility study of the processing of versaFlow using the Aix-Marseilles site's data, to ensure that our implementation has minimal impact on the variability observed in subsequent analyses. We report very high reproducibility for the majority of metrics; only gamma distribution parameters of DIAMOND display less reproducible behaviors, due to the absence of a mechanism to enforce a random number seed in the software we used. This should be taken into consideration when future applications are performed. We show that the PRIME-DE diffusion data exhibits a great level of variability, similar or greater than results obtained in human studies. Its usage should be done carefully to prevent instilling uncertainty in statistical analyses. This hints at a need for sufficient harmonization in acquisition protocols and for the development of robust algorithms capable of managing the variability induced in imaging due to differences in scanner models and/or vendors.

Mapping cross-species connectome atlas of human and macaque striatum

Cross-species connectome atlas (CCA) that can provide connectionally homogeneous and homologous brain nodes is essential and customized for cross-species neuroscience. However, existing CCAs were flawed in design and coarse-grained in results. In this study, a normative mapping framework of CCA was proposed and applied on human and macaque striatum. Specifically, all striatal voxels in the 2 species were mixed together and classified based on their represented and characterized feature of within-striatum resting-state functional connectivity, which was shared between the species. Six pairs of striatal parcels in these species were delineated in both hemispheres. Furthermore, this striatal parcellation was demonstrated by the best-matched whole-brain functional and structural connectivity between interspecies corresponding subregions. Besides, detailed interspecies differences in whole-brain multimodal connectivities and involved brain functions of these subregions were described to flesh out this CCA of striatum. In particular, this flexible and scalable mapping framework enables reliable construction of CCA of the whole brain, which would enable reliable findings in future cross-species research and advance our understandings into how the human brain works.

Automated identification of piglet brain tissue from MRI images using Region-based Convolutional Neural Networks

Magnetic resonance imaging is an important tool for characterizing volumetric changes of the piglet brain during development. Typically, an early step of an imaging analysis pipeline is brain extraction, or skull stripping. Brain extractions are usually performed manually; however, this approach is time-intensive and can lead to variation between brain extractions when multiple raters are used. Automated brain extractions are important for reducing the time required for analyses and improving the uniformity of the extractions. Here we demonstrate the use of Mask R-CNN, a Region-based Convolutional Neural Network (R-CNN), for automated brain extractions of piglet brains. We validate our approach using Nested Cross-Validation on six sets of training/validation data drawn from 32 pigs. Visual inspection of the extractions shows acceptable accuracy, Dice coefficients are in the range of 0.95-0.97, and Hausdorff Distance values in the range of 4.1-8.3 voxels. These results demonstrate that R-CNNs provide a viable tool for skull stripping of piglet brains.

A novel methodology for exact targeting of human and non-human primate brain structures and skull implants using atlas-based 3D reconstruction

BACKGROUND

Accurate targeting of brain areas for stimulation and/or electrophysiological recording is key in many therapeutic applications and basic neuroscience research. Nevertheless, there are currently no end-to-end packages that accommodate all steps required for exact localization, visualization and targeting regions of interest (ROIs) using standard atlases and for designing skull implants.

NEW METHOD

We have implemented a new processing pipeline that addresses this issue in macaques and humans including various preprocessing, registration, warping procedures and 3D reconstructions and provide a noncommercial open-source graphical software which we refer to as the MATLAB-based reconstruction for recording and stimulation (MATres).

RESULTS

The results of skull stripping were shown to work seamlessly in humans and monkeys. Linear and nonlinear warping of the standard atlas to the native space outperformed state-of-the-art using AFNI with improvements being more prominent in humans which had a more complex gyration geometry. The skull surface extracted by MATres using MRI images had more than 90% match with CT ground truth and could be used to design skull implants that conformed well to the skull's local curvature.

COMPARISON WITH EXISTING METHOD(S)

The accuracy of the various steps including skull stripping, standard atlas registration and skull reconstruction in MATres was compared with and shown to outperform the AFNI. The localization accuracy of the recording chambers designed with MATres and implanted in two macaque monkeys was further confirmed using MRI imaging.

CONCLUSIONS

Precise localization of ROIs offered by MATres can be used for planning electrode penetrations for recording and for shallow or deep brain stimulation (DBS).

HC-Net: A hybrid convolutional network for non-human primate brain extraction

Brain extraction (skull stripping) is an essential step in the magnetic resonance imaging (MRI) analysis of brain sciences. However, most of the current brain extraction methods that achieve satisfactory results for human brains are often challenged by non-human primate brains. Due to the small sample characteristics and the nature of thick-slice scanning of macaque MRI data, traditional deep convolutional neural networks (DCNNs) are unable to obtain excellent results. To overcome this challenge, this study proposed a symmetrical end-to-end trainable hybrid convolutional neural network (HC-Net). It makes full use of the spatial information between adjacent slices of the MRI image sequence and combines three consecutive slices from three axes for 3D convolutions, which reduces the calculation consumption and promotes accuracy. The HC-Net consists of encoding and decoding structures of 3D convolutions and 2D convolutions in series. The effective use of 2D convolutions and 3D convolutions relieves the underfitting of 2D convolutions to spatial features and the overfitting of 3D convolutions to small samples. After evaluating macaque brain data from different sites, the results showed that HC-Net performed better in inference time (approximately 13 s per volume) and accuracy (mean Dice coefficient reached 95.46%). The HC-Net model also had good generalization ability and stability in different modes of brain extraction tasks.

Methods of Brain Extraction from Magnetic Resonance Images of Human Head: A Review

Medical images are providing vital information to aid physicians in diagnosing a disease afflicting the organ of a human body. Magnetic resonance imaging is an important imaging modality in capturing the soft tissues of the brain. Segmenting and extracting the brain is essential in studying the structure and pathological condition of brain. There are several methods that are developed for this purpose. Researchers in brain extraction or segmentation need to know the current status of the work that have been done. Such an information is also important for improving the existing method to get more accurate results or to reduce the complexity of the algorithm. In this paper we review the classical methods and convolutional neural network-based deep learning brain extraction methods.

Fusion of quantitative susceptibility maps and T1-weighted images improve brain tissue contrast in primates

Recent progress in quantitative susceptibility mapping (QSM) has enabled the accurate delineation of submillimeter-scale subcortical brain structures in humans. However, the simultaneous visualization of cortical, subcortical, and white matter structure remains challenging, utilizing QSM data solely. Here we present TQ-SILiCON, a fusion method that enhances the contrast of cortex and subcortical structures and provides an excellent white matter delineation by combining QSM and conventional T1-weighted (T1w) images. In this study, we first applied QSM in the macaque monkey to map iron-rich subcortical structures. Implementing the same QSM acquisition and analysis methods allowed a similar accurate delineation of subcortical structures in humans. However, the QSM contrast of white and cortical gray matter was not sufficient for appropriate segmentation. Applying automatic brain tissue segmentation to TQ-SILiCON images of the macaque improved the classification of subcortical brain structures as compared to the single T1 contrast by maintaining an excellent white to cortical gray matter contrast. Furthermore, we validated our dual-contrast fusion approach in humans and similarly demonstrated improvements in automated segmentation of the cortex and subcortical structures. We believe the proposed contrast will facilitate translational studies in nonhuman primates to investigate the pathophysiology of neurodegenerative diseases that affect subcortical structures such as the basal ganglia in humans.

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

Resting-State fMRI-Based Screening of Deschloroclozapine in Rhesus Macaques Predicts Dosage-Dependent Behavioral Effects

Chemogenetic techniques, such as designer receptors exclusively activated by designer drugs (DREADDs), enable transient, reversible, and minimally invasive manipulation of neural activity in vivo Their development in nonhuman primates is essential for uncovering neural circuits contributing to cognitive functions and their translation to humans. One key issue that has delayed the development of chemogenetic techniques in primates is the lack of an accessible drug-screening method. Here, we use resting-state fMRI, a noninvasive neuroimaging tool, to assess the impact of deschloroclozapine (DCZ) on brainwide resting-state functional connectivity in 7 rhesus macaques (6 males and 1 female) without DREADDs. We found that systemic administration of 0.1 mg/kg DCZ did not alter the resting-state functional connectivity. Conversely, 0.3 mg/kg of DCZ was associated with a prominent increase in functional connectivity that was mainly confined to the connections of frontal regions. Additional behavioral tests confirmed a negligible impact of 0.1 mg/kg DCZ on socio-emotional behaviors as well as on reaction time in a probabilistic learning task; 0.3 mg/kg DCZ did, however, slow responses in the probabilistic learning task, suggesting attentional or motivational deficits associated with hyperconnectivity in fronto-temporo-parietal networks. Our study highlights both the excellent selectivity of DCZ as a DREADD actuator, and the side effects of its excess dosage. The results demonstrate the translational value of resting-state fMRI as a drug-screening tool to accelerate the development of chemogenetics in primates.SIGNIFICANCE STATEMENT Chemogenetics, such as designer receptors exclusively activated by designer drugs (DREADDs), can afford control over neural activity with unprecedented spatiotemporal resolution. Accelerating the translation of chemogenetic neuromodulation from rodents to primates requires an approach to screen novel DREADD actuators in vivo Here, we assessed brainwide activity in response to a DREADD actuator deschloroclozapine (DCZ) using resting-state fMRI in macaque monkeys. We demonstrated that low-dose DCZ (0.1 mg/kg) did not change whole-brain functional connectivity or affective behaviors, while a higher dose (0.3 mg/kg) altered frontal functional connectivity and slowed response in a learning task. Our study highlights the excellent selectivity of DCZ at proper dosing, and demonstrates the utility of resting-state fMRI to screen novel chemogenetic actuators in primates.

Early Alzheimer's disease-like reductions in gray matter and cognitive function with aging in nonhuman primates

Introduction

Age-related neuropathology associated with sporadic Alzheimer's disease (AD) often develops well before the onset of symptoms. Given AD's long preclinical period, translational models are needed to identify early signatures of pathological decline.

Methods

Using structural magnetic resonance imaging and cognitive assessments, we examined the relationships among age, cognitive performance, and neuroanatomy in 48 vervet monkeys (Chlorocebus aethiops sabaeus) ranging from young adults to very old.

Results

We found negative associations of age with cortical gray matter volume (P = .003) and the temporal-parietal cortical thickness meta-region of interest (P = .001). Additionally, cortical gray matter volumes predicted working memory at approximately 1-year follow-up (correct trials at the 20s delay [P = .008]; correct responses after longer delays [P = .004]).

Discussion

Cortical gray matter diminishes with age in vervets in regions relevant to AD, which may increase risk of cognitive impairment. This study lays the groundwork for future investigations to test therapeutics to delay or slow pathological decline.

Transfer Learning Approaches for Neuroimaging Analysis: A Scoping Review

Deep learning algorithms have been moderately successful in diagnoses of diseases by analyzing medical images especially through neuroimaging that is rich in annotated data. Transfer learning methods have demonstrated strong performance in tackling annotated data. It utilizes and transfers knowledge learned from a source domain to target domain even when the dataset is small. There are multiple approaches to transfer learning that result in a range of performance estimates in diagnosis, detection, and classification of clinical problems. Therefore, in this paper, we reviewed transfer learning approaches, their design attributes, and their applications to neuroimaging problems. We reviewed two main literature databases and included the most relevant studies using predefined inclusion criteria. Among 50 reviewed studies, more than half of them are on transfer learning for Alzheimer's disease. Brain mapping and brain tumor detection were second and third most discussed research problems, respectively. The most common source dataset for transfer learning was ImageNet, which is not a neuroimaging dataset. This suggests that the majority of studies preferred pre-trained models instead of training their own model on a neuroimaging dataset. Although, about one third of studies designed their own architecture, most studies used existing Convolutional Neural Network architectures. Magnetic Resonance Imaging was the most common imaging modality. In almost all studies, transfer learning contributed to better performance in diagnosis, classification, segmentation of different neuroimaging diseases and problems, than methods without transfer learning. Among different transfer learning approaches, fine-tuning all convolutional and fully-connected layers approach and freezing convolutional layers and fine-tuning fully-connected layers approach demonstrated superior performance in terms of accuracy. These recent transfer learning approaches not only show great performance but also require less computational resources and time.

A Macaque Brain Extraction Model Based on U-Net Combined with Residual Structure

Accurately extracting brain tissue is a critical and primary step in brain neuroimaging research. Due to the differences in brain size and structure between humans and nonhuman primates, the performance of the existing tools for brain tissue extraction, working on macaque brain MRI, is constrained. A new transfer learning training strategy was utilized to address the limitations, such as insufficient training data and unsatisfactory model generalization ability, when deep neural networks processing the limited samples of macaque magnetic resonance imaging(MRI). First, the project combines two human brain MRI data modes to pre-train the neural network, in order to achieve faster training and more accurate brain extraction. Then, a residual network structure in the U-Net model was added, in order to propose a ResTLU-Net model that aims to improve the generalization ability of multiple research sites data. The results demonstrated that the ResTLU-Net, combined with the proposed transfer learning strategy, achieved comparable accuracy for the macaque brain MRI extraction tasks on different macaque brain MRI volumes that were produced by various medical centers. The mean Dice of the ResTLU-Net was 95.81% (no need for denoise and recorrect), and the method required only approximately 30–60 s for one extraction task on an NVIDIA 1660S GPU.

Patch-based 3D U-Net and transfer learning for longitudinal piglet brain segmentation on MRI

BACKGROUND AND OBJECTIVES

In order to study neural plasticity in immature brain following early brain lesion, large animal model are needed. Because of its morphological similarities with the human developmental brain, piglet is a suitable but little used one. Its study from Magnetic Resonance Imaging (MRI) requires the development of automatic algorithms for the segmentation of the different structures and tissues. A crucial preliminary step consists in automatically segmenting the brain.

METHODS

We propose a fully automatic brain segmentation method applied to piglets by combining a 3D patch-based U-Net and a post-processing pipeline for spatial regularization and elimination of false positives. Our approach also integrates a transfer-learning strategy for managing an automated longitudinal monitoring evaluated for four developmental stages (2, 6, 10 and 18 weeks), facing the issue of MRI changes resulting from the rapid brain development. It is compared to a 2D approach and the Brain Extraction Tool (BET) as well as techniques adapted to other animals (rodents, macaques). The influence of training patches size and distribution is studied as well as the benefits of spatial regularization.

RESULTS

Results show that our approach is efficient in terms of average Dice score (0.952) and Hausdorff distance (8.51), outperforming the use of a 2D U-Net (Dice: 0.919, Hausdorff distance: 11.06) and BET (Dice: 0.764, Hausdorff distance: 25.91). The transfer-learning strategy achieves a good performance on older piglets (Dice of 0.934 at 6 weeks, 0.956 at 10 weeks and 0.958 at 18 weeks) compared to a standard training strategy with few data (Dice of 0.636 at 6 weeks, 0.907 at 10 weeks, not calculable at 18 weeks because of too few training piglets).

CONCLUSIONS

In conclusion, we provide a method for longitudinal MRI piglet brain segmentation based on 3D U-Net and transfer learning which can be used for future morphometric studies and applied to other animals.

A generalizable brain extraction net (BEN) for multimodal MRI data from rodents, nonhuman primates, and humans

Accurate brain tissue extraction on magnetic resonance imaging (MRI) data is crucial for analyzing brain structure and function. While several conventional tools have been optimized to handle human brain data, there have been no generalizable methods to extract brain tissues for multimodal MRI data from rodents, nonhuman primates, and humans. Therefore, developing a flexible and generalizable method for extracting whole brain tissue across species would allow researchers to analyze and compare experiment results more efficiently. Here, we propose a domain-adaptive and semi-supervised deep neural network, named the Brain Extraction Net (BEN), to extract brain tissues across species, MRI modalities, and MR scanners. We have evaluated BEN on 18 independent datasets, including 783 rodent MRI scans, 246 nonhuman primate MRI scans, and 4601 human MRI scans, covering five species, four modalities, and six MR scanners with various magnetic field strengths. Compared to conventional toolboxes, the superiority of BEN is illustrated by its robustness, accuracy, and generalizability. Our proposed method not only provides a generalized solution for extracting brain tissue across species but also significantly improves the accuracy of atlas registration, thereby benefiting the downstream processing tasks. As a novel fully automated deep-learning method, BEN is designed as an open-source software to enable high-throughput processing of neuroimaging data across species in preclinical and clinical applications.

3D U-Net Improves Automatic Brain Extraction for Isotropic Rat Brain Magnetic Resonance Imaging Data

Brain extraction is a critical pre-processing step in brain magnetic resonance imaging (MRI) analytical pipelines. In rodents, this is often achieved by manually editing brain masks slice-by-slice, a time-consuming task where workloads increase with higher spatial resolution datasets. We recently demonstrated successful automatic brain extraction via a deep-learning-based framework, U-Net, using 2D convolutions. However, such an approach cannot make use of the rich 3D spatial-context information from volumetric MRI data. In this study, we advanced our previously proposed U-Net architecture by replacing all 2D operations with their 3D counterparts and created a 3D U-Net framework. We trained and validated our model using a recently released CAMRI rat brain database acquired at isotropic spatial resolution, including T2-weighted turbo-spin-echo structural MRI and T2*-weighted echo-planar-imaging functional MRI. The performance of our 3D U-Net model was compared with existing rodent brain extraction tools, including Rapid Automatic Tissue Segmentation, Pulse-Coupled Neural Network, SHape descriptor selected External Regions after Morphologically filtering, and our previously proposed 2D U-Net model. 3D U-Net demonstrated superior performance in Dice, Jaccard, center-of-mass distance, Hausdorff distance, and sensitivity. Additionally, we demonstrated the reliability of 3D U-Net under various noise levels, evaluated the optimal training sample sizes, and disseminated all source codes publicly, with a hope that this approach will benefit rodent MRI research community. Significant Methodological Contribution: We proposed a deep-learning-based framework to automatically identify the rodent brain boundaries in MRI. With a fully 3D convolutional network model, 3D U-Net, our proposed method demonstrated improved performance compared to current automatic brain extraction methods, as shown in several qualitative metrics (Dice, Jaccard, PPV, SEN, and Hausdorff). We trust that this tool will avoid human bias and streamline pre-processing steps during 3D high resolution rodent brain MRI data analysis. The software developed herein has been disseminated freely to the community.

Chinese Color Nest Project : An accelerated longitudinal brain-mind cohort

The ongoing Chinese Color Nest Project (CCNP) was established to create normative charts for brain structure and function across the human lifespan, and link age-related changes in brain imaging measures to psychological assessments of behavior, cognition, and emotion using an accelerated longitudinal design. In the initial stage, CCNP aims to recruit 1520 healthy individuals (6-90 years), which comprises three phases: developing (devCCNP: 6-18 years, N = 480), maturing (matCCNP: 20-60 years, N = 560) and aging (ageCCNP: 60-84 years, N = 480). In this paper, we present an overview of the devCCNP, including study design, participants, data collection and preliminary findings. The devCCNP has acquired data with three repeated measurements from 2013 to 2017 in Southwest University, Chongqing, China (CCNP-SWU, N = 201). It has been accumulating baseline data since July 2018 and the second wave data since September 2020 in Chinese Academy of Sciences, Beijing, China (CCNP-CAS, N = 168). Each participant in devCCNP was followed up for 2.5 years at 1.25-year intervals. The devCCNP obtained longitudinal neuroimaging, biophysical, social, behavioral and cognitive data via MRI, parent- and self-reported questionnaires, behavioral assessments, and computer tasks. Additionally, data were collected on children's learning, daily life and emotional states during the COVID-19 pandemic in 2020. We address data harmonization across the two sites and demonstrated its promise of characterizing the growth curves for the overall brain morphometry using multi-center longitudinal data. CCNP data will be shared via the National Science Data Bank and requests for further information on collaboration and data sharing are encouraged.

Species and individual differences and connectional asymmetry of Broca's area in humans and macaques

To reveal the connectional specialization of the Broca's area (or its homologue), voxel-wise inter-species and individual differences, and inter-hemispheric asymmetry were respectively inspected in humans and macaques at both whole-brain connectivity and single tract levels. It was discovered that the developed connectivity blueprint approach is able to localize connectionally comparable voxels between the two species in Broca's area, whereas the quantitative differences between blueprints of locationally or connectionally corresponding voxels enable us to generate inter-hemispheric, inter-subject, and inter-species connectional variabilities, respectively. More importantly, the inter-species and inter-subject variabilities exhibited positive correlation in both two primates, and relatively higher variabilities were detected in the anatomically defined pars triangularis. By contrast, negative relationship was identified between the inter-species variability and hemispheric asymmetry in human brain. In particular, relatively higher asymmetry was revealed in the anatomically defined pars opercularis. Therefore, our novel findings demonstrated that pars triangularis, as compared to pars opercularis, might be a more active area during primate evolution, in which the brain connectivity and possible functions of pars triangularis show relatively higher degree in species specialization, yet lower in hemispheric specialization. Meanwhile, brain connectivity and possible functions of pars opercularis manifested an opposite pattern. At the tract level, functional roles related to the ventral stream in speech comprehension were relatively conservative and bilaterally organized, while those related to the dorsal stream in speech production show relatively higher species and hemispheric specializations.