Spherical demons: fast diffeomorphic landmark-free surface registration

JOSA: Joint surface-based registration and atlas construction of brain geometry and function

Surface-based cortical registration is an important topic in medical image analysis and facilitates many downstream applications. Current approaches for cortical registration are mainly driven by geometric features, such as sulcal depth and curvature, and often assume that registration of folding patterns leads to alignment of brain function. However, functional variability of anatomically corresponding areas across subjects has been widely reported, particularly in higher-order cognitive areas. In this work, we present JOSA, a novel cortical registration framework that jointly models the mismatch between geometry and function while simultaneously learning an unbiased population-specific atlas. Using a semi-supervised training strategy, JOSA achieves superior registration performance in both geometry and function to the state-of-the-art methods but without requiring functional data at inference. This learning framework can be extended to any auxiliary data to guide spherical registration that is available during training but is difficult or impossible to obtain during inference, such as parcellations, architectonic identity, transcriptomic information, and molecular profiles. By recognizing the mismatch between geometry and function, JOSA provides new insights into the future development of registration methods using joint analysis of brain structure and function.

Longitudinally consistent registration and parcellation of cortical surfaces using semi-supervised learning

Temporally consistent and accurate registration and parcellation of longitudinal cortical surfaces is of great importance in studying longitudinal morphological and functional changes of human brains. However, most existing methods are developed for registration or parcellation of a single cortical surface. When applying to longitudinal studies, these methods independently register/parcellate each surface from longitudinal scans, thus often generating longitudinally inconsistent and inaccurate results, especially in small or ambiguous cortical regions. Essentially, longitudinal cortical surface registration and parcellation are highly correlated tasks with inherently shared constraints on both spatial and temporal feature representations, which are unfortunately ignored in existing methods. To this end, we unprecedentedly propose a novel semi-supervised learning framework to exploit these inherent relationships from limited labeled data and extensive unlabeled data for more robust and consistent registration and parcellation of longitudinal cortical surfaces. Our method utilizes the spherical topology characteristic of cortical surfaces. It employs a spherical network to function as an encoder, which extracts high-level cortical features. Subsequently, we build two specialized decoders dedicated to the tasks of registration and parcellation, respectively. To extract more meaningful spatial features, we design a novel parcellation map similarity loss to utilize the relationship between registration and parcellation tasks, i.e., the parcellation map warped by the deformation field in registration should match the atlas parcellation map, thereby providing extra supervision for the registration task and augmented data for parcellation task by warping the atlas parcellation map to unlabeled surfaces. To enable temporally more consistent feature representation, we additionally enforce longitudinal consistency among longitudinal surfaces after registering them together using their concatenated features. Experiments on two longitudinal datasets of infants and adults have shown that our method achieves significant improvements on both registration/parcellation accuracy and longitudinal consistency compared to existing methods, especially in small and challenging cortical regions.

Simulating tDCS electrode placement to stimulate both M1 and SMA enhances motor performance and modulates cortical excitability depending on current flow direction

Introduction

The conventional method of placing transcranial direct current stimulation (tDCS) electrodes is just above the target brain area. However, this strategy for electrode placement often fails to improve motor function and modulate cortical excitability. We investigated the effects of optimized electrode placement to induce maximum electrical fields in the leg regions of both M1 and SMA, estimated by electric field simulations in the T1and T2-weighted MRI-based anatomical models, on motor performance and cortical excitability in healthy individuals.

Methods

A total of 36 healthy volunteers participated in this randomized, triple-blind, sham-controlled experiment. They were stratified by sex and were randomly assigned to one of three groups according to the stimulation paradigm, including tDCS with (1) anodal and cathodal electrodes positioned over FCz and POz, respectively, (A-P tDCS), (2) anodal and cathodal electrodes positioned over POz and FCz, respectively, (P-A tDCS), and (3) sham tDCS. The sit-to-stand training following tDCS (2 mA, 10 min) was conducted every 3 or 4 days over 3 weeks (5 sessions total).

Results

Compared to sham tDCS, A-P tDCS led to significant increases in the number of sit-to-stands after 3 weeks training, whereas P-A tDCS significantly increased knee flexor peak torques after 3 weeks training, and decreased short-interval intracortical inhibition (SICI) immediately after the first session of training and maintained it post-training.

Discussion

These results suggest that optimized electrode placement of the maximal EF estimated by electric field simulation enhances motor performance and modulates cortical excitability depending on the direction of current flow.

Functional Hierarchy of the Human Neocortex from Cradle to Grave

Recent evidence indicates that the organization of the human neocortex is underpinned by smooth spatial gradients of functional connectivity (FC). These gradients provide crucial insight into the relationship between the brain's topographic organization and the texture of human cognition. However, no studies to date have charted how intrinsic FC gradient architecture develops across the entire human lifespan. In this work, we model developmental trajectories of the three primary gradients of FC using a large, high-quality, and temporally-dense functional MRI dataset spanning from birth to 100 years of age. The gradient axes, denoted as sensorimotor-association (SA), visual-somatosensory (VS), and modulation-representation (MR), encode crucial hierarchical organizing principles of the brain in development and aging. By tracking their evolution throughout the human lifespan, we provide the first ever comprehensive low-dimensional normative reference of global FC hierarchical architecture. We observe significant age-related changes in global network features, with global markers of hierarchical organization increasing from birth to early adulthood and decreasing thereafter. During infancy and early childhood, FC organization is shaped by primary sensory processing, dense short-range connectivity, and immature association and control hierarchies. Functional differentiation of transmodal systems supported by long-range coupling drives a convergence toward adult-like FC organization during late childhood, while adolescence and early adulthood are marked by the expansion and refinement of SA and MR hierarchies. While gradient topographies remain stable during late adulthood and aging, we observe decreases in global gradient measures of FC differentiation and complexity from 30 to 100 years. Examining cortical microstructure gradients alongside our functional gradients, we observed that structure-function gradient coupling undergoes differential lifespan trajectories across multiple gradient axes.

Automatic cortical surface parcellation in the fetal brain using attention-gated spherical U-net

Cortical surface parcellation for fetal brains is essential for the understanding of neurodevelopmental trajectories during gestations with regional analyses of brain structures and functions. This study proposes the attention-gated spherical U-net, a novel deep-learning model designed for automatic cortical surface parcellation of the fetal brain. We trained and validated the model using MRIs from 55 typically developing fetuses [gestational weeks: 32.9 ± 3.3 (mean ± SD), 27.4-38.7]. The proposed model was compared with the surface registration-based method, SPHARM-net, and the original spherical U-net. Our model demonstrated significantly higher accuracy in parcellation performance compared to previous methods, achieving an overall Dice coefficient of 0.899 ± 0.020. It also showed the lowest error in terms of the median boundary distance, 2.47 ± 1.322 (mm), and mean absolute percent error in surface area measurement, 10.40 ± 2.64 (%). In this study, we showed the efficacy of the attention gates in capturing the subtle but important information in fetal cortical surface parcellation. Our precise automatic parcellation model could increase sensitivity in detecting regional cortical anomalies and lead to the potential for early detection of neurodevelopmental disorders in fetuses.

Early autism diagnosis based on path signature and Siamese unsupervised feature compressor

Autism spectrum disorder has been emerging as a growing public health threat. Early diagnosis of autism spectrum disorder is crucial for timely, effective intervention and treatment. However, conventional diagnosis methods based on communications and behavioral patterns are unreliable for children younger than 2 years of age. Given evidences of neurodevelopmental abnormalities in autism spectrum disorder infants, we resort to a novel deep learning-based method to extract key features from the inherently scarce, class-imbalanced, and heterogeneous structural MR images for early autism diagnosis. Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features. We also proposed weight constraints to cope with sample heterogeneity by giving different samples different voting weights during validation, and used Path Signature to unravel meaningful developmental features from the two-time point data longitudinally. We further extracted machine learning focused brain regions for autism diagnosis. Extensive experiments have shown that our method performed well under practical scenarios, transcending existing machine learning methods and providing anatomical insights for autism early diagnosis.

ENHANCING 3T RETINOTOPIC MAPS USING DIFFEOMORPHIC REGISTRATION

Retinotopic mapping aims to uncover the relationship between visual stimuli on the retina and neural responses on the visual cortical surface. This study advances retinotopic mapping by applying diffeomorphic registration to the 3T NYU retinotopy dataset, encompassing analyze-PRF and mrVista data. Diffeomorphic Registration for Retinotopic Maps (DRRM) quantifies the diffeomorphic condition, ensuring accurate alignment of retinotopic maps without topological violations. Leveraging the Beltrami coefficient and topological condition, DRRM significantly enhances retinotopic map accuracy. Evaluation against existing methods demonstrates DRRM's superiority on various datasets, including 3T and 7T retinotopy data. The application of diffeomorphic registration improves the interpretability of low-quality retinotopic maps, holding promise for clinical applications.

SUGAR: Spherical ultrafast graph attention framework for cortical surface registration

Cortical surface registration plays a crucial role in aligning cortical functional and anatomical features across individuals. However, conventional registration algorithms are computationally inefficient. Recently, learning-based registration algorithms have emerged as a promising solution, significantly improving processing efficiency. Nonetheless, there remains a gap in the development of a learning-based method that exceeds the state-of-the-art conventional methods simultaneously in computational efficiency, registration accuracy, and distortion control, despite the theoretically greater representational capabilities of deep learning approaches. To address the challenge, we present SUGAR, a unified unsupervised deep-learning framework for both rigid and non-rigid registration. SUGAR incorporates a U-Net-based spherical graph attention network and leverages the Euler angle representation for deformation. In addition to the similarity loss, we introduce fold and multiple distortion losses to preserve topology and minimize various types of distortions. Furthermore, we propose a data augmentation strategy specifically tailored for spherical surface registration to enhance the registration performance. Through extensive evaluation involving over 10,000 scans from 7 diverse datasets, we showed that our framework exhibits comparable or superior registration performance in accuracy, distortion, and test-retest reliability compared to conventional and learning-based methods. Additionally, SUGAR achieves remarkable sub-second processing times, offering a notable speed-up of approximately 12,000 times in registering 9,000 subjects from the UK Biobank dataset in just 32 min. This combination of high registration performance and accelerated processing time may greatly benefit large-scale neuroimaging studies.

Cross-modality mapping using image varifolds to align tissue-scale atlases to molecular-scale measures with application to 2D brain sections

This paper explicates a solution to building correspondences between molecular-scale transcriptomics and tissue-scale atlases. This problem arises in atlas construction and cross-specimen/technology alignment where specimens per emerging technology remain sparse and conventional image representations cannot efficiently model the high dimensions from subcellular detection of thousands of genes. We address these challenges by representing spatial transcriptomics data as generalized functions encoding position and high-dimensional feature (gene, cell type) identity. We map onto low-dimensional atlas ontologies by modeling regions as homogeneous random fields with unknown transcriptomic feature distribution. We solve simultaneously for the minimizing geodesic diffeomorphism of coordinates through LDDMM and for these latent feature densities. We map tissue-scale mouse brain atlases to gene-based and cell-based transcriptomics data from MERFISH and BARseq technologies and to histopathology and cross-species atlases to illustrate integration of diverse molecular and cellular datasets into a single coordinate system as a means of comparison and further atlas construction.

Neural deformation fields for template-based reconstruction of cortical surfaces from MRI

The reconstruction of cortical surfaces is a prerequisite for quantitative analyses of the cerebral cortex in magnetic resonance imaging (MRI). Existing segmentation-based methods separate the surface registration from the surface extraction, which is computationally inefficient and prone to distortions. We introduce Vox2Cortex-Flow (V2C-Flow), a deep mesh-deformation technique that learns a deformation field from a brain template to the cortical surfaces of an MRI scan. To this end, we present a geometric neural network that models the deformation-describing ordinary differential equation in a continuous manner. The network architecture comprises convolutional and graph-convolutional layers, which allows it to work with images and meshes at the same time. V2C-Flow is not only very fast, requiring less than two seconds to infer all four cortical surfaces, but also establishes vertex-wise correspondences to the template during reconstruction. In addition, V2C-Flow is the first approach for cortex reconstruction that models white matter and pial surfaces jointly, therefore avoiding intersections between them. Our comprehensive experiments on internal and external test data demonstrate that V2C-Flow results in cortical surfaces that are state-of-the-art in terms of accuracy. Moreover, we show that the established correspondences are more consistent than in FreeSurfer and that they can directly be utilized for cortex parcellation and group analyses of cortical thickness.

Joint cortical registration of geometry and function using semi-supervised learning

Brain surface-based image registration, an important component of brain image analysis, establishes spatial correspondence between cortical surfaces. Existing iterative and learning-based approaches focus on accurate registration of folding patterns of the cerebral cortex, and assume that geometry predicts function and thus functional areas will also be well aligned. However, structure/functional variability of anatomically corresponding areas across subjects has been widely reported. In this work, we introduce a learning-based cortical registration framework, JOSA, which jointly aligns folding patterns and functional maps while simultaneously learning an optimal atlas. We demonstrate that JOSA can substantially improve registration performance in both anatomical and functional domains over existing methods. By employing a semi-supervised training strategy, the proposed framework obviates the need for functional data during inference, enabling its use in broad neuroscientific domains where functional data may not be observed. The source code of JOSA will be released to the public at https://voxelmorph.net.

Automatic landmark detection and registration of brain cortical surfaces via quasi-conformal geometry and convolutional neural networks

In medical imaging, surface registration is extensively used for performing systematic comparisons between anatomical structures, with a prime example being the highly convoluted brain cortical surfaces. To obtain a meaningful registration, a common approach is to identify prominent features on the surfaces and establish a low-distortion mapping between them with the feature correspondence encoded as landmark constraints. Prior registration works have primarily focused on using manually labeled landmarks and solving highly nonlinear optimization problems, which are time-consuming and hence hinder practical applications. In this work, we propose a novel framework for the automatic landmark detection and registration of brain cortical surfaces using quasi-conformal geometry and convolutional neural networks. We first develop a landmark detection network (LD-Net) that allows for the automatic extraction of landmark curves given two prescribed starting and ending points based on the surface geometry. We then utilize the detected landmarks and quasi-conformal theory for achieving the surface registration. Specifically, we develop a coefficient prediction network (CP-Net) for predicting the Beltrami coefficients associated with the desired landmark-based registration and a mapping network called the disk Beltrami solver network (DBS-Net) for generating quasi-conformal mappings from the predicted Beltrami coefficients, with the bijectivity guaranteed by quasi-conformal theory. Experimental results are presented to demonstrate the effectiveness of our proposed framework. Altogether, our work paves a new way for surface-based morphometry and medical shape analysis.

Mapping Genetic Topography of Cortical Thickness and Surface Area in Neonatal Brains

Adult twin neuroimaging studies have revealed that cortical thickness (CT) and surface area (SA) are differentially influenced by genetic information, leading to their spatially distinct genetic patterning and topography. However, the postnatal origins of the genetic topography of CT and SA remain unclear, given the dramatic cortical development from neonates to adults. To fill this critical gap, this study unprecedentedly explored how genetic information differentially regulates the spatial topography of CT and SA in the neonatal brain by leveraging brain magnetic resonance (MR) images from 202 twin neonates with minimal influence by the complicated postnatal environmental factors. We capitalized on infant-dedicated computational tools and a data-driven spectral clustering method to parcellate the cerebral cortex into a set of distinct regions purely according to the genetic correlation of cortical vertices in terms of CT and SA, respectively, and accordingly created the first genetically informed cortical parcellation maps of neonatal brains. Both genetic parcellation maps exhibit bilaterally symmetric and hierarchical patterns, but distinct spatial layouts. For CT, regions with closer genetic relationships demonstrate an anterior-posterior (A-P) division, while for SA, regions with greater genetic proximity are typically within the same lobe. Certain genetically informed regions exhibit strong similarities between neonates and adults, with the most striking similarities in the medial surface in terms of SA, despite their overall substantial differences in genetic parcellation maps. These results greatly advance our understanding of the development of genetic influences on the spatial patterning of cortical morphology.SIGNIFICANCE STATEMENT Genetic influences on cortical thickness (CT) and surface area (SA) are complex and could evolve throughout the lifespan. However, studies revealing distinct genetic topography of CT and SA have been limited to adults. Using brain structural magnetic resonance (MR) images of twins, we unprecedentedly discovered the distinct genetically-informed parcellation maps of CT and SA in neonatal brains, respectively. Each genetic parcellation map comprises a distinct spatial layout of cortical regions, where vertices within the same region share high genetic correlation. These genetic parcellation maps of CT and SA of neonates largely differ from those of adults, despite their highly remarkable similarities in the medial cortex of SA. These discoveries provide important insights into the genetic organization of the early cerebral cortex development.

Fine-grained functional parcellation maps of the infant cerebral cortex

Resting-state functional MRI (rs-fMRI) is widely used to examine the dynamic brain functional development of infants, but these studies typically require precise cortical parcellation maps, which cannot be directly borrowed from adult-based functional parcellation maps due to the substantial differences in functional brain organization between infants and adults. Creating infant-specific cortical parcellation maps is thus highly desired but remains challenging due to difficulties in acquiring and processing infant brain MRIs. In this study, we leveraged 1064 high-resolution longitudinal rs-fMRIs from 197 typically developing infants and toddlers from birth to 24 months who participated in the Baby Connectome Project to develop the first set of infant-specific, fine-grained, surface-based cortical functional parcellation maps. To establish meaningful cortical functional correspondence across individuals, we performed cortical co-registration using both the cortical folding geometric features and the local gradient of functional connectivity (FC). Then we generated both age-related and age-independent cortical parcellation maps with over 800 fine-grained parcels during infancy based on aligned and averaged local gradient maps of FC across individuals. These parcellation maps reveal complex functional developmental patterns, such as changes in local gradient, network size, and local efficiency, especially during the first 9 postnatal months. Our generated fine-grained infant cortical functional parcellation maps are publicly available at https://www.nitrc.org/projects/infantsurfatlas/ for advancing the pediatric neuroimaging field.

Gyral peaks and patterns in human brains

Cortical folding patterns are related to brain function, cognition, and behavior. Since the relationship has not been fully explained on a coarse scale, many efforts have been devoted to the identification of finer grained cortical landmarks, such as sulcal pits and gyral peaks, which were found to remain invariant across subjects and ages and the invariance may be related to gene mediated proto-map. However, gyral peaks were only investigated on macaque monkey brains, but not on human brains where the investigation is challenged due to high inter-individual variabilities. To this end, in this work, we successfully identified 96 gyral peaks both on the left and right hemispheres of human brains, respectively. These peaks are spatially consistent across individuals. Higher or sharper peaks are more consistent across subjects. Both structural and functional graph metrics of peaks are significantly different from other cortical regions, and more importantly, these nodal graph metrics are anti-correlated with the spatial consistency metrics within peaks. In addition, the distribution of peaks and various cortical anatomical, structural/functional connective features show hemispheric symmetry. These findings provide new clues to understanding the cortical landmarks, as well as their relationship with brain functions, cognition, behavior in both healthy and aberrant brains.

Identification of overlapping and interacting networks reveals intrinsic spatiotemporal organization of the human brain

The human brain is a complex network that exhibits dynamic fluctuations in activity across space and time. Depending on the analysis method, canonical brain networks identified from resting-state fMRI (rs-fMRI) are typically constrained to be either orthogonal or statistically independent in their spatial and/or temporal domains. We avoid imposing these potentially unnatural constraints through the combination of a temporal synchronization process ("BrainSync") and a three-way tensor decomposition method ("NASCAR") to jointly analyze rs-fMRI data from multiple subjects. The resulting set of interacting networks comprises minimally constrained spatiotemporal distributions, each representing one component of functionally coherent activity across the brain. We show that these networks can be clustered into six distinct functional categories and naturally form a representative functional network atlas for a healthy population. This functional network atlas could help explore group and individual differences in neurocognitive function, as we demonstrate in the context of ADHD and IQ prediction.

A Universal Method for Crossing Molecular and Atlas Modalities using Simplex-Based Image Varifolds and Quadratic Programming

This paper explicates a solution to the problem of building correspondences between molecular-scale transcriptomics and tissue-scale atlases. The central model represents spatial transcriptomics as generalized functions encoding molecular position and high-dimensional transcriptomic-based (gene, cell type) identity. We map onto low-dimensional atlas ontologies by modeling each atlas compartment as a homogeneous random field with unknown transcriptomic feature distribution. The algorithm presented solves simultaneously for the minimizing geodesic diffeomorphism of coordinates and latent atlas transcriptomic feature fractions by alternating LDDMM optimization for coordinate transformations and quadratic programming for the latent transcriptomic variables. We demonstrate the universality of the algorithm in mapping tissue atlases to gene-based and cell-based MERFISH datasets as well as to other tissue scale atlases. The joint estimation of diffeomorphisms and latent feature distributions allows integration of diverse molecular and cellular datasets into a single coordinate system and creates an avenue of comparison amongst atlas ontologies for continued future development.

iBEAT V2.0: a multisite-applicable, deep learning-based pipeline for infant cerebral cortical surface reconstruction

The human cerebral cortex undergoes dramatic and critical development during early postnatal stages. Benefiting from advances in neuroimaging, many infant brain magnetic resonance imaging (MRI) datasets have been collected from multiple imaging sites with different scanners and imaging protocols for the investigation of normal and abnormal early brain development. However, it is extremely challenging to precisely process and quantify infant brain development with these multisite imaging data because infant brain MRI scans exhibit (a) extremely low and dynamic tissue contrast caused by ongoing myelination and maturation and (b) inter-site data heterogeneity resulting from the use of diverse imaging protocols/scanners. Consequently, existing computational tools and pipelines typically perform poorly on infant MRI data. To address these challenges, we propose a robust, multisite-applicable, infant-tailored computational pipeline that leverages powerful deep learning techniques. The main functionality of the proposed pipeline includes preprocessing, brain skull stripping, tissue segmentation, topology correction, cortical surface reconstruction and measurement. Our pipeline can handle both T1w and T2w structural infant brain MR images well in a wide age range (from birth to 6 years of age) and is effective for different imaging protocols/scanners, despite being trained only on the data from the Baby Connectome Project. Extensive comparisons with existing methods on multisite, multimodal and multi-age datasets demonstrate superior effectiveness, accuracy and robustness of our pipeline. We have maintained a website, iBEAT Cloud, for users to process their images with our pipeline ( http://www.ibeat.cloud ), which has successfully processed over 16,000 infant MRI scans from more than 100 institutions with various imaging protocols/scanners.

A neurostructural biomarker of dissociative amnesia: a hippocampal study in dissociative identity disorder

BACKGROUND

Little is known about the neural correlates of dissociative amnesia, a transdiagnostic symptom mostly present in the dissociative disorders and core characteristic of dissociative identity disorder (DID). Given the vital role of the hippocampus in memory, a prime candidate for investigation is whether total and/or subfield hippocampal volume can serve as biological markers of dissociative amnesia.

METHODS

A total of 75 women, 32 with DID and 43 matched healthy controls (HC), underwent structural magnetic resonance imaging (MRI). Using Freesurfer (version 6.0), volumes were extracted for bilateral global hippocampus, cornu ammonis (CA) 1-4, the granule cell molecular layer of the dentate gyrus (GC-ML-DG), fimbria, hippocampal-amygdaloid transition area (HATA), parasubiculum, presubiculum and subiculum. Analyses of covariance showed volumetric differences between DID and HC. Partial correlations exhibited relationships between the three factors of the dissociative experience scale scores (dissociative amnesia, absorption, depersonalisation/derealisation) and traumatisation measures with hippocampal global and subfield volumes.

RESULTS

Hippocampal volumes were found to be smaller in DID as compared with HC in bilateral global hippocampus and bilateral CA1, right CA4, right GC-ML-DG, and left presubiculum. Dissociative amnesia was the only dissociative symptom that correlated uniquely and significantly with reduced bilateral hippocampal CA1 subfield volumes. Regarding traumatisation, only emotional neglect correlated negatively with bilateral global hippocampus, bilateral CA1, CA4 and GC-ML-DG, and right CA3.

CONCLUSION

We propose decreased CA1 volume as a biomarker for dissociative amnesia. We also propose that traumatisation, specifically emotional neglect, is interlinked with dissociative amnesia in having a detrimental effect on hippocampal volume.

Multifaceted atlases of the human brain in its infancy

Brain atlases are spatial references for integrating, processing, and analyzing brain features gathered from different individuals, sources, and scales. Here we introduce a collection of joint surface-volume atlases that chart postnatal development of the human brain in a spatiotemporally dense manner from two weeks to two years of age. Our month-specific atlases chart normative patterns and capture key traits of early brain development and are therefore conducive to identifying aberrations from normal developmental trajectories. These atlases will enhance our understanding of early structural and functional development by facilitating the mapping of diverse features of the infant brain to a common reference frame for precise multifaceted quantification of cortical and subcortical changes.

Hierarchical particle optimization for cortical shape correspondence in temporal lobe resection

BACKGROUND

Anterior temporal lobe resection is an effective treatment for temporal lobe epilepsy. The post-surgical structural changes could influence the follow-up treatment. Capturing post-surgical changes necessitates a well-established cortical shape correspondence between pre- and post-surgical surfaces. Yet, most cortical surface registration methods are designed for normal neuroanatomy. Surgical changes can introduce wide ranging artifacts in correspondence, for which conventional surface registration methods may not work as intended.

METHODS

In this paper, we propose a novel particle method for one-to-one dense shape correspondence between pre- and post-surgical surfaces with temporal lobe resection. The proposed method can handle partial structural abnormality involving non-rigid changes. Unlike existing particle methods using implicit particle adjacency, we consider explicit particle adjacency to establish a smooth correspondence. Moreover, we propose hierarchical optimization of particles rather than full optimization of all particles at once to avoid trappings of locally optimal particle update.

RESULTS

We evaluate the proposed method on 25 pairs of T1-MRI with pre- and post-simulated resection on the anterior temporal lobe and 25 pairs of patients with actual resection. We show improved accuracy over several cortical regions in terms of ROI boundary Hausdorff distance with 4.29 mm and Dice similarity coefficients with average value 0.841, compared to existing surface registration methods on simulated data. In 25 patients with actual resection of the anterior temporal lobe, our method shows an improved shape correspondence in qualitative and quantitative evaluation on parcellation-off ratio with average value 0.061 and cortical thickness changes. We also show better smoothness of the correspondence without self-intersection, compared with point-wise matching methods which show various degrees of self-intersection.

CONCLUSION

The proposed method establishes a promising one-to-one dense shape correspondence for temporal lobe resection. The resulting correspondence is smooth without self-intersection. The proposed hierarchical optimization strategy could accelerate optimization and improve the optimization accuracy. According to the results on the paired surfaces with temporal lobe resection, the proposed method outperforms the compared methods and is more reliable to capture cortical thickness changes.

Gyral peaks: Novel gyral landmarks in developing macaque brains

Cerebral cortex development undergoes a variety of processes, which provide valuable information for the study of the developmental mechanism of cortical folding as well as its relationship to brain structural architectures and brain functions. Despite the variability in the anatomy-function relationship on the higher-order cortex, recent studies have succeeded in identifying typical cortical landmarks, such as sulcal pits, that bestow specific functional and cognitive patterns and remain invariant across subjects and ages with their invariance being related to a gene-mediated proto-map. Inspired by the success of these studies, we aim in this study at defining and identifying novel cortical landmarks, termed gyral peaks, which are the local highest foci on gyri. By analyzing data from 156 MRI scans of 32 macaque monkeys with the age spanned from 0 to 36 months, we identified 39 and 37 gyral peaks on the left and right hemispheres, respectively. Our investigation suggests that these gyral peaks are spatially consistent across individuals and relatively stable within the age range of this dataset. Moreover, compared with other gyri, gyral peaks have a thicker cortex, higher mean curvature, more pronounced hub-like features in structural connective networks, and are closer to the borders of structural connectivity-based cortical parcellations. The spatial distribution of gyral peaks was shown to correlate with that of other cortical landmarks, including sulcal pits. These results provide insights into the spatial arrangement and temporal development of gyral peaks as well as their relation to brain structure and function.

SPHARM-Net: Spherical Harmonics-Based Convolution for Cortical Parcellation

We present a spherical harmonics-based convolutional neural network (CNN) for cortical parcellation, which we call SPHARM-Net. Recent advances in CNNs offer cortical parcellation on a fine-grained triangle mesh of the cortex. Yet, most CNNs designed for cortical parcellation employ spatial convolution that depends on extensive data augmentation and allows only predefined neighborhoods of specific spherical tessellation. On the other hand, a rotation-equivariant convolutional filter avoids data augmentation, and rotational equivariance can be achieved in spectral convolution independent of a neighborhood definition. Nevertheless, the limited resources of a modern machine enable only a finite set of spectral components that might lose geometric details. In this paper, we propose (1) a constrained spherical convolutional filter that supports an infinite set of spectral components and (2) an end-to-end framework without data augmentation. The proposed filter encodes all the spectral components without the full expansion of spherical harmonics. We show that rotational equivariance drastically reduces the training time while achieving accurate cortical parcellation. Furthermore, the proposed convolution is fully composed of matrix transformations, which offers efficient and fast spectral processing. In the experiments, we validate SPHARM-Net on two public datasets with manual labels: Mindboggle-101 (N=101) and NAMIC (N=39). The experimental results show that the proposed method outperforms the state-of-the-art methods on both datasets even with fewer learnable parameters without rigid alignment and data augmentation. Our code is publicly available at https://github.com/Shape-Lab/SPHARM-Net.

Deep residual-SVD network for brain image registration

Objective. Medical image registration aims to find the deformation field that can align two images in a spatial position. A medical image registration method based on U-Net architecture has been proposed currently. However, U-Net architecture has few training parameters, which leads to weak learning ability, and it ignores the adverse effects of image noise on the registration accuracy. The article aims at addressing the problem of weak network learning ability and the adverse effects of noisy images on registration. Approach. Here we propose a novel unsupervised 3D brain image registration framework, which introduces the residual unit and singular value decomposition (SVD) denoising layer on the U-Net architecture. Residual unit solves the problem of network degradation, that is, registration accuracy becomes saturated and then degrades rapidly with the increase in network depth. SVD denoising layer uses the estimated model order for SVD-based low-rank image reconstruction. we use Akaike information criterion to estimate the appropriate model order, which is used to remove noise components. We use the exponential linear unit (ELU) as the activation function, which is more robust to noise than other peers. Main results. The proposed method is evaluated on the publicly available brain MRI datasets: Mindboggle101 and LPBA40. Experimental results demonstrate our method outperforms several state-of-the-art methods for the metric of Dice Score. The mean number of folding voxels and registration time are comparable to state-of-the-art methods. Significance. This study shows that Deep Residual-SVD Network can improve registration accuracy. This study also demonstrate that the residual unit can enhance the learning ability of the network, the SVD denoising layer can denoise effectively, and the ELU is more robust to noise.

TopoFit: Rapid Reconstruction of Topologically-Correct Cortical Surfaces

Mesh-based reconstruction of the cerebral cortex is a fundamental component in brain image analysis. Classical, iterative pipelines for cortical modeling are robust but often time-consuming, mostly due to expensive procedures that involve topology correction and spherical mapping. Recent attempts to address reconstruction with machine learning methods have accelerated some components in these pipelines, but these methods still require slow processing steps to enforce topological constraints that comply with known anatomical structure. In this work, we introduce a novel learning-based strategy, TopoFit, which rapidly fits a topologically-correct surface to the white-matter tissue boundary. We design a joint network, employing image and graph convolutions and an efficient symmetric distance loss, to learn to predict accurate deformations that map a template mesh to subject-specific anatomy. This technique encompasses the work of current mesh correction, fine-tuning, and inflation processes and, as a result, offers a 150× faster solution to cortical surface reconstruction compared to traditional approaches. We demonstrate that TopoFit is 1.8× more accurate than the current state-of-the-art deep-learning strategy, and it is robust to common failure modes, such as white-matter tissue hypointensities.

Characterization of surface motion patterns in highly deformable soft tissue organs from dynamic MRI: An application to assess 4D bladder motion

BACKGROUND AND OBJECTIVES

Dynamic Magnetic Resonance Imaging (MRI) may capture temporal anatomical changes in soft tissue organs with high-contrast but the obtained sequences usually suffer from limited volume coverage which makes the high-resolution reconstruction of organ shape trajectories a major challenge in temporal studies. Because of the variability of abdominal organ shapes across time and subjects, the objective of the present study is to go towards 3D dense velocity measurements to fully cover the entire surface and to extract meaningful features characterizing the observed organ deformations and enabling clinical action or decision.

METHODS

We present a pipeline for characterization of bladder surface dynamics during deep respiratory movements. For a compact shape representation, the reconstructed temporal volumes were first used to establish subject-specific dynamical 4D mesh sequences using the large deformation diffeomorphic metric mapping (LDDMM) framework. Then, we performed a statistical characterization of organ dynamics from mechanical parameters such as mesh elongations and distortions. Since we refer to organs as non-flat surfaces, we have also used the mean curvature change as metric to quantify surface evolution. However, the numerical computation of curvature is strongly dependant on the surface parameterization (i.e. the mesh resolution). To cope with this dependency, we employed a non-parametric method for surface deformation analysis. Independent of parameterization and minimizing the length of the geodesic curves, it stretches smoothly the surface curves towards a sphere by minimizing a Dirichlet energy. An Eulerian PDE approach is used to derive a shape descriptor from the curve-shortening flow. Intercorrelations between individuals' motion patterns are computed using the Laplace-Beltrami Operator (LBO) eigenfunctions for spherical mapping.

RESULTS

Application to extracting characterization correlation curves for locally-controlled simulated shape trajectories demonstrates the stability of the proposed shape descriptor. Its usability was shown on MRI acquired for seven healthy participants for which the bladder was highly deformed by maximum of inspiration. As expected, the study showed that deformations occured essentially on the top lateral regions.

CONCLUSION

Promising results were obtained, showing the organ in its 3D complexity during deformation due to strain conditions. Smooth genus-0 manifold reconstruction from sparse dynamic MRI data is employed to perform a statistical shape analysis for the determination of bladder deformation.

Landmark-guided region-based spatial normalization for functional magnetic resonance imaging

As the size of the neuroimaging cohorts being increased to address key questions in the field of cognitive neuroscience, cognitive aging, and neurodegenerative diseases, the accuracy of the spatial normalization as an essential preprocessing step becomes extremely important. Existing spatial normalization methods have poor accuracy particularly when dealing with the highly convoluted human cerebral cortex and when brain morphology is severely altered (e.g., aging populations). To address this shortcoming, we propose a novel spatial normalization technique that takes advantage of the existing surface‐based human brain parcellation to automatically identify and match regional landmarks. To simplify the nonlinear whole brain registration, the identified landmarks of each region and its counterpart are registered independently with topology‐preserving deformation. Next, the regional warping fields are combined by an inverse distance weighted interpolation technique to have a global warping field for the whole brain. To ensure that the final warping field is topology‐preserving, we used simultaneously forward and reverse maps with certain symmetric constraints to yield bijectivity. We have evaluated our proposed solution using both simulated and real (structural and functional) human brain images. Our evaluation shows that our solution can enhance structural correspondence compared to the existing methods. Such improvement also increases the sensitivity and specificity of the functional imaging studies, reducing the required number of subjects and subsequent study costs. We conclude that our proposed solution can effectively substitute existing substandard spatial normalization methods to deal with the demand of large cohorts which is now common in clinical and aging studies.

Diffeomorphic registration for retinotopic maps of multiple visual regions

Retinotopic map, the mapping between visual inputs on the retina and neuronal responses on the cortical surface, is one of the central topics in vision science. Typically, human retinotopic maps are constructed by analyzing functional magnetic resonance responses to designed visual stimuli on the cortical surface. Although it is widely used in visual neuroscience, retinotopic maps are limited by the signal-to-noise ratio and spatial resolution of fMRI. One promising approach to improve the quality of retinotopic maps is to register individual subject's retinotopic maps to a retinotopic template. However, none of the existing retinotopic registration methods has explicitly quantified the diffeomorphic condition, that is, retinotopic maps shall be aligned by stretching/compressing without tearing up the cortical surface. Here, we developed Diffeomorphic Registration for Retinotopic Maps (DRRM) to simultaneously align retinotopic maps in multiple visual regions under the diffeomorphic condition. Specifically, we used the Beltrami coefficient to model the diffeomorphic condition and performed surface registration based on retinotopic coordinates. The overall framework preserves the topological condition defined in the template. We further developed a unique evaluation protocol and compared the performance of the new method with several existing registration methods on both synthetic and real datasets. The results showed that DRRM is superior to the existing methods in achieving diffeomorphic  registration in synthetic and empirical data from 3T and 7T MRI systems. DRRM may improve the interpretation of low-quality retinotopic maps and facilitate applications of retinotopic maps in clinical settings.

A 4D infant brain volumetric atlas based on the UNC/UMN baby connectome project (BCP) cohort

Spatiotemporal (four-dimensional) infant-dedicated brain atlases are essential for neuroimaging analysis of early dynamic brain development. However, due to the substantial technical challenges in the acquisition and processing of infant brain MR images, 4D atlases densely covering the dynamic brain development during infancy are still scarce. Few existing ones generally have fuzzy tissue contrast and low spatiotemporal resolution, leading to degraded accuracy of atlas-based normalization and subsequent analyses. To address this issue, in this paper, we construct a 4D structural MRI atlas for infant brains based on the UNC/UMN Baby Connectome Project (BCP) dataset, which features a high spatial resolution, extensive age-range coverage, and densely sampled time points. Specifically, 542 longitudinal T1w and T2w scans from 240 typically developing infants up to 26-month of age were utilized for our atlas construction. To improve the co-registration accuracy of the infant brain images, which typically exhibit dynamic appearance with low tissue contrast, we employed the state-of-the-art registration method and leveraged our generated reliable brain tissue probability maps in addition to the intensity images to improve the alignment of individual images. To achieve consistent region labeling on both infant and adult brain images for facilitating region-based analysis across ages, we mapped the widely used Desikan cortical parcellation onto our atlas by following an age-decreasing mapping manner. Meanwhile, the typical subcortical structures were manually delineated to facilitate the studies related to the subcortex. Compared with the existing infant brain atlases, our 4D atlas has much higher spatiotemporal resolution and preserves more structural details, and thus can boost accuracy in neurodevelopmental analysis during infancy.

Performance Evaluation of Deformable Image Registration Algorithms Using Computed Tomography of Multiple Lung Metastases

Purpose: Various deformable image registration (DIR) methods have been used to evaluate organ deformations in 4-dimensional computed tomography (4D CT) images scanned during the respiratory motions of a patient. This study assesses the performance of 10 DIR algorithms using 4D CT images of 5 patients with fiducial markers (FMs) implanted during the postoperative radiosurgery of multiple lung metastases. Methods: To evaluate DIR algorithms, 4D CT images of 5 patients were used, and ground-truths of FMs and tumors were generated by physicians based on their medical expertise. The positions of FMs and tumors in each 4D CT phase image were determined using 10 DIR algorithms, and the deformed results were compared with ground-truth data. Results: The target registration errors (TREs) between the FM positions estimated by optical flow algorithms and the ground-truth ranged from 1.82 ± 1.05 to 1.98 ± 1.17 mm, which is within the uncertainty of the ground-truth position. Two algorithm groups, namely, optical flow and demons, were used to estimate tumor positions with TREs ranging from 1.29 ± 1.21 to 1.78 ± 1.75 mm. With respect to the deformed position for tumors, for the 2 DIR algorithm groups, the maximum differences of the deformed positions for gross tumor volume tracking were approximately 4.55 to 7.55 times higher than the mean differences. Errors caused by the aforementioned difference in the Hounsfield unit values were also observed. Conclusions: We quantitatively evaluated 10 DIR algorithms using 4D CT images of 5 patients and compared the results with ground-truth data. The optical flow algorithms showed reasonable FM-tracking results in patient 4D CT images. The iterative optical flow method delivered the best performance in this study. With respect to the tumor volume, the optical flow and demons algorithms delivered the best performance.

Learnable Pooling in Graph Convolutional Networks for Brain Surface Analysis

Brain surface analysis is essential to neuroscience, however, the complex geometry of the brain cortex hinders computational methods for this task. The difficulty arises from a discrepancy between 3D imaging data, which is represented in Euclidean space, and the non-Euclidean geometry of the highly-convoluted brain surface. Recent advances in machine learning have enabled the use of neural networks for non-Euclidean spaces. These facilitate the learning of surface data, yet pooling strategies often remain constrained to a single fixed-graph. This paper proposes a new learnable graph pooling method for processing multiple surface-valued data to output subject-based information. The proposed method innovates by learning an intrinsic aggregation of graph nodes based on graph spectral embedding. We illustrate the advantages of our approach with in-depth experiments on two large-scale benchmark datasets. The ablation study in the paper illustrates the impact of various factors affecting our learnable pooling method. The flexibility of the pooling strategy is evaluated on four different prediction tasks, namely, subject-sex classification, regression of cortical region sizes, classification of Alzheimer's disease stages, and brain age regression. Our experiments demonstrate the superiority of our learnable pooling approach compared to other pooling techniques for graph convolutional networks, with results improving the state-of-the-art in brain surface analysis.

Existence of Functional Connectome Fingerprint during Infancy and Its Stability over Months

The functional connectome fingerprint is a cluster of individualized brain functional connectivity patterns that are capable of distinguishing one individual from others. Although its existence has been demonstrated in adolescents and adults, whether such individualized patterns exist during infancy is barely investigated despite its importance in identifying the origin of the intrinsic connectome patterns that potentially mirror distinct behavioral phenotypes. To fill this knowledge gap, capitalizing on a longitudinal high-resolution structural and resting-state functional MRI dataset with 104 human infants (53 females) with 806 longitudinal scans (age, 16-876 d) and infant-specific functional parcellation maps, we observe that the brain functional connectome fingerprint may exist since infancy and keeps stable over months during early brain development. Specifically, we achieve an ∼78% individual identification rate by using ∼5% selected functional connections, compared with the best identification rate of 60% without connection selection. The frontoparietal networks recognized as the most contributive networks in adult functional connectome fingerprinting retain their superiority in infants despite being widely acknowledged as rapidly developing systems during childhood. The existence and stability of the functional connectome fingerprint are further validated on adjacent age groups. Moreover, we show that the infant frontoparietal networks can reach similar accuracy in predicting individual early learning composite scores as the whole-brain connectome, again resembling the observations in adults and highlighting the relevance of functional connectome fingerprint to cognitive performance. For the first time, these results suggest that each individual may retain a unique and stable marker of functional connectome during early brain development.SIGNIFICANCE STATEMENT Functional connectome fingerprinting during infancy featuring rapid brain development remains almost uninvestigated even though it is essential for understanding the early individual-level intrinsic pattern of functional organization and its relationship with distinct behavioral phenotypes. With an infant-tailored functional connection selection and validation strategy, we strive to provide the delineation of the infant functional connectome fingerprint by examining its existence, stability, and relationship with early cognitive performance. We observe that the brain functional connectome fingerprint may exist since early infancy and remains stable over months during the first 2 years. The identified key contributive functional connections and networks for fingerprinting are also verified to be highly predictive for cognitive score prediction, which reveals the association between infant connectome fingerprint and cognitive performance.

Cortical development coupling between surface area and sulcal depth on macaque brains

Postnatal development of cerebral cortex is associated with a variety of neuronal processes and is thus critical to development of brain function and cognition. Longitudinal changes of cortical morphology and topology, such as postnatal cortical thinning and flattening have been widely studied. However, thorough and systematic investigation of such cortical change, including how to quantify it from multiple spatial directions and how to relate it to surface topology, is rarely found. In this work, based on a longitudinal macaque neuroimaging dataset, we quantified local changes in gyral white matter's surface area and sulcal depth during early development. We also investigated how these two metrics are coupled and how this coupling is linked to cortical surface topology, underlying white matter, and positions of functional areas. Semi-parametric generalized additive models were adopted to quantify the longitudinal changes of surface area (A) and sulcal depth (D), and the coupling patterns between them. This resulted in four classes of regions, according to how they change compared with global change throughout early development: slower surface area change and slower sulcal depth change (slowA_slowD), slower surface area change and faster sulcal depth change (slowA_fastD), faster surface area change and slower sulcal depth change (fastA_slowD), and faster surface area change and faster sulcal depth change (fastA_fastD). We found that cortex-related metrics, including folding pattern and cortical thickness, vary along slowA_fastD-fastA_slowD axis, and structural connection-related metrics vary along fastA_fastD-slowA_slowD axis, with which brain functional sites align better. It is also found that cortical landmarks, including sulcal pits and gyral hinges, spatially reside on the borders of the four patterns. These findings shed new lights on the relationship between cortex development, surface topology, axonal wiring pattern and brain functions.

Mapping the subcortical connectivity of the human default mode network

The default mode network (DMN) mediates self-awareness and introspection, core components of human consciousness. Therapies to restore consciousness in patients with severe brain injuries have historically targeted subcortical sites in the brainstem, thalamus, hypothalamus, basal forebrain, and basal ganglia, with the goal of reactivating cortical DMN nodes. However, the subcortical connectivity of the DMN has not been fully mapped, and optimal subcortical targets for therapeutic neuromodulation of consciousness have not been identified. In this work, we created a comprehensive map of DMN subcortical connectivity by combining high-resolution functional and structural datasets with advanced signal processing methods. We analyzed 7 Tesla resting-state functional MRI (rs-fMRI) data from 168 healthy volunteers acquired in the Human Connectome Project. The rs-fMRI blood-oxygen-level-dependent (BOLD) data were temporally synchronized across subjects using the BrainSync algorithm. Cortical and subcortical DMN nodes were jointly analyzed and identified at the group level by applying a novel Nadam-Accelerated SCAlable and Robust (NASCAR) tensor decomposition method to the synchronized dataset. The subcortical connectivity map was then overlaid on a 7 Tesla 100 µm ex vivo MRI dataset for neuroanatomic analysis using automated segmentation of nuclei within the brainstem, thalamus, hypothalamus, basal forebrain, and basal ganglia. We further compared the NASCAR subcortical connectivity map with its counterpart generated from canonical seed-based correlation analyses. The NASCAR method revealed that BOLD signal in the central lateral nucleus of the thalamus and ventral tegmental area of the midbrain is strongly correlated with that of the DMN. In an exploratory analysis, additional subcortical sites in the median and dorsal raphe, lateral hypothalamus, and caudate nuclei were correlated with the cortical DMN. We also found that the putamen and globus pallidus are negatively correlated (i.e., anti-correlated) with the DMN, providing rs-fMRI evidence for the mesocircuit hypothesis of human consciousness, whereby a striatopallidal feedback system modulates anterior forebrain function via disinhibition of the central thalamus. Seed-based analyses yielded similar subcortical DMN connectivity, but the NASCAR result showed stronger contrast and better spatial alignment with dopamine immunostaining data. The DMN subcortical connectivity map identified here advances understanding of the subcortical regions that contribute to human consciousness and can be used to inform the selection of therapeutic targets in clinical trials for patients with disorders of consciousness.

Three-dimensional reconstruction of In Vivo human lumbar spine from biplanar radiographs

We present a method for three dimensional (3D) reconstruction of in vivo human lumbar spine from biplanar radiographs with comparable results to Computerised Tomography (CT) scans or Magnetic Resonance Imaging (MRI) models. In this work, we used uncalibrated radiographs to reconstruct the 3D vertebrae and a priori information stored in an Active Shape Model (ASM) that is constructed using the Spherical Demons Algorithm. The method is semi-automatic as bounding boxes are required to delimit the positions of the vertebrae on biplanar radiographs of a patient. Optimisation is based on comparisons between simulated and actual radiographs. Finally, we compare the results to the models generated from MRI and CT scans. The results show the feasibility of generating personalised models of patients from biplanar radiographs.

Inter-species cortical registration between macaques and humans using a functional network property under a spherical demons framework

Systematic evaluation of cortical differences between humans and macaques calls for inter-species registration of the cortex that matches homologous regions across species. For establishing homology across brains, structural landmarks and biological features have been used without paying sufficient attention to functional homology. The present study aimed to determine functional homology between the human and macaque cortices, defined in terms of functional network properties, by proposing an iterative functional network-based registration scheme using surface-based spherical demons. The functional connectivity matrix of resting-state functional magnetic resonance imaging (rs-fMRI) among cortical parcellations was iteratively calculated for humans and macaques. From the functional connectivity matrix, the functional network properties such as principal network components were derived to estimate a deformation field between the human and macaque cortices. The iterative registration procedure updates the parcellation map of macaques, corresponding to the human connectome project’s multimodal parcellation atlas, which was used to derive the macaque’s functional connectivity matrix. To test the plausibility of the functional network-based registration, we compared cortical registration using structural versus functional features in terms of cortical regional areal change. We also evaluated the interhemispheric asymmetry of regional area and its inter-subject variability in humans and macaques as an indirect validation of the proposed method. Higher inter-subject variability and interhemispheric asymmetry were found in functional homology than in structural homology, and the assessed asymmetry and variations were higher in humans than in macaques. The results emphasize the significance of functional network-based cortical registration across individuals within a species and across species.

A Deep Network for Joint Registration and Parcellation of Cortical Surfaces

Cortical surface registration and parcellation are two essential steps in neuroimaging analysis. Conventionally, they are performed independently as two tasks, ignoring the inherent connections of these two closely-related tasks. Essentially, both tasks rely on meaningful cortical feature representations, so they can be jointly optimized by learning shared useful cortical features. To this end, we propose a deep learning framework for joint cortical surface registration and parcellation. Specifically, our approach leverages the spherical topology of cortical surfaces and uses a spherical network as the shared encoder to first learn shared features for both tasks. Then we train two task-specific decoders for registration and parcellation, respectively. We further exploit the more explicit connection between them by incorporating the novel parcellation map similarity loss to enforce the boundary consistency of regions, thereby providing extra supervision for the registration task. Conversely, parcellation network training also benefits from the registration, which provides a large amount of augmented data by warping one surface with manual parcellation map to another surface, especially when only few manually-labeled surfaces are available. Experiments on a dataset with more than 600 cortical surfaces show that our approach achieves large improvements on both parcellation and registration accuracy (over separately trained networks) and enables training high-quality parcellation and registration models using much fewer labeled data.

Learning 4D Infant Cortical Surface Atlas with Unsupervised Spherical Networks

Spatiotemporal (4D) cortical surface atlas during infancy plays an important role for surface-based visualization, normalization and analysis of the dynamic early brain development. Conventional atlas construction methods typically rely on classical group-wise registration on sub-populations and ignore longitudinal constraints, thus having three main issues: 1) constructing templates at discrete time points; 2) resulting in longitudinal inconsistency among different age's atlases; and 3) taking extremely long runtime. To address these issues, in this paper, we propose a fast unsupervised learning-based surface atlas construction framework incorporating longitudinal constraints to enforce the within-subject temporal correspondence in the atlas space. To well handle the difficulties of learning large deformations, we propose a multi-level multimodal spherical registration network to perform cortical surface registration in a coarse-to-fine manner. Thus, only small deformations need to be estimated at each resolution level using the registration network, which further improves registration accuracy and atlas quality. Our constructed 4D infant cortical surface atlas based on 625 longitudinal scans from 291 infants is temporally continuous, in contrast to the state-of-the-art UNC 4D Infant Surface Atlas, which only provides the atlases at a few discrete sparse time points. By evaluating the intra- and inter-subject spatial normalization accuracy after alignment onto the atlas, our atlas demonstrates more detailed and fine-grained cortical patterns, thus leading to higher accuracy in surface registration.

Individual-Specific Areal-Level Parcellations Improve Functional Connectivity Prediction of Behavior

Resting-state functional magnetic resonance imaging (rs-fMRI) allows estimation of individual-specific cortical parcellations. We have previously developed a multi-session hierarchical Bayesian model (MS-HBM) for estimating high-quality individual-specific network-level parcellations. Here, we extend the model to estimate individual-specific areal-level parcellations. While network-level parcellations comprise spatially distributed networks spanning the cortex, the consensus is that areal-level parcels should be spatially localized, that is, should not span multiple lobes. There is disagreement about whether areal-level parcels should be strictly contiguous or comprise multiple noncontiguous components; therefore, we considered three areal-level MS-HBM variants spanning these range of possibilities. Individual-specific MS-HBM parcellations estimated using 10 min of data generalized better than other approaches using 150 min of data to out-of-sample rs-fMRI and task-fMRI from the same individuals. Resting-state functional connectivity derived from MS-HBM parcellations also achieved the best behavioral prediction performance. Among the three MS-HBM variants, the strictly contiguous MS-HBM exhibited the best resting-state homogeneity and most uniform within-parcel task activation. In terms of behavioral prediction, the gradient-infused MS-HBM was numerically the best, but differences among MS-HBM variants were not statistically significant. Overall, these results suggest that areal-level MS-HBMs can capture behaviorally meaningful individual-specific parcellation features beyond group-level parcellations. Multi-resolution trained models and parcellations are publicly available (https://github.com/ThomasYeoLab/CBIG/tree/master/stable_projects/brain_parcellation/Kong2022_ArealMSHBM).

S3Reg: Superfast Spherical Surface Registration Based on Deep Learning

Cortical surface registration is an essential step and prerequisite for surface-based neuroimaging analysis. It aligns cortical surfaces across individuals and time points to establish cross-sectional and longitudinal cortical correspondences to facilitate neuroimaging studies. Though achieving good performance, available methods are either time consuming or not flexible to extend to multiple or high dimensional features. Considering the explosive availability of large-scale and multimodal brain MRI data, fast surface registration methods that can flexibly handle multimodal features are desired. In this study, we develop a Superfast Spherical Surface Registration (S3Reg) framework for the cerebral cortex. Leveraging an end-to-end unsupervised learning strategy, S3Reg offers great flexibility in the choice of input feature sets and output similarity measures for registration, and meanwhile reduces the registration time significantly. Specifically, we exploit the powerful learning capability of spherical Convolutional Neural Network (CNN) to directly learn the deformation fields in spherical space and implement diffeomorphic design with "scaling and squaring" layers to guarantee topology-preserving deformations. To handle the polar-distortion issue, we construct a novel spherical CNN model using three orthogonal Spherical U-Nets. Experiments are performed on two different datasets to align both adult and infant multimodal cortical features. Results demonstrate that our S3Reg shows superior or comparable performance with state-of-the-art methods, while improving the registration time from 1 min to 10 sec.

Enhanced detection of cortical atrophy in Alzheimer's disease using structural MRI with anatomically constrained longitudinal registration

Cortical atrophy is a defining feature of Alzheimer's disease (AD), often detectable before symptoms arise. In surface-based analyses, studies have commonly focused on cortical thinning while overlooking the impact of loss in surface area. To capture the impact of both cortical thinning and surface area loss, we used anatomically constrained Multimodal Surface Matching (aMSM), a recently developed tool for mapping change in surface area. We examined cortical atrophy over 2 years in cognitively normal subjects and subjects with diagnoses of stable mild cognitive impairment, mild cognitive impairment that converted to AD, and AD. Magnetic resonance imaging scans were segmented and registered to a common atlas using previously described techniques (FreeSurfer and ciftify), then longitudinally registered with aMSM. Changes in cortical thickness, surface area, and volume were mapped within each diagnostic group, and groups were compared statistically. Changes in thickness and surface area detected atrophy at similar levels of significance, though regions of atrophy somewhat differed. Furthermore, we found that surface area maps offered greater consistency across scanners (3.0 vs. 1.5 T). Comparisons to the FreeSurfer longitudinal pipeline and parcellation-based (region-of-interest) analysis suggest that aMSM may allow more robust detection of atrophy, particularly in earlier disease stages and using smaller sample sizes.

Disease Burden Affects Aging Brain Function

BACKGROUND

Most older adults live with multiple chronic disease conditions, yet the effect of multiple diseases on brain function remains unclear.

METHODS

We examine the relationship between disease multimorbidity and brain activity using regional cerebral blood flow (rCBF) 15O-water PET scans from 97 cognitively normal participants (mean baseline age 76.5) in the Baltimore Longitudinal Study of Aging (BLSA). Multimorbidity index scores, generated from the presence of 13 health conditions, were correlated with PET data at baseline and in longitudinal change (n=74) over 5.05 (2.74 SD) years.

RESULTS

At baseline, voxel-based analysis showed that higher multimorbidity scores were associated with lower relative activity in orbitofrontal, superior frontal, temporal pole and parahippocampal regions, and greater activity in lateral temporal, occipital and cerebellar regions. Examination of the individual health conditions comprising the index score showed hypertension and chronic kidney disease individually contributed to the overall multimorbidity pattern of altered activity. Longitudinally, both increases and decreases in activity were seen in relation to increasing multimorbidity over time. These associations were identified in orbitofrontal, lateral temporal, brainstem, and cerebellar areas.

CONCLUSION

Together, these results show that greater multimorbidity is associated with widespread areas of altered brain activity, supporting a link between health and changes in aging brain function.

Bayesian Fully Convolutional Networks for Brain Image Registration

The purpose of medical image registration is to find geometric transformations that align two medical images so that the corresponding voxels on two images are spatially consistent. Nonrigid medical image registration is a key step in medical image processing, such as image comparison, data fusion, target recognition, and pathological change analysis. Existing registration methods only consider registration accuracy but largely neglect the uncertainty of registration results. In this work, a method based on the Bayesian fully convolutional neural network is proposed for nonrigid medical image registration. The proposed method can generate a geometric uncertainty map to calculate the uncertainty of registration results. This uncertainty can be interpreted as a confidence interval, which is essential for judging whether the source data are abnormal. Moreover, the proposed method introduces group normalization, which is conducive to the network convergence of the Bayesian neural network. Some representative learning-based image registration methods are compared with the proposed method on different image datasets. Experimental results show that the registration accuracy of the proposed method is better than that of the methods, and its antifolding performance is comparable to that of fast image registration and VoxelMorph. Furthermore, the proposed method can evaluate the uncertainty of registration results.

The maturation and cognitive relevance of structural brain network organization from early infancy to childhood

The interactions of brain regions with other regions at the network level likely provide the infrastructure necessary for cognitive processes to develop. Specifically, it has been theorized that in infancy brain networks become more modular, or segregated, to support early cognitive specialization, before integration across networks increases to support the emergence of higher-order cognition. The present study examined the maturation of structural covariance networks (SCNs) derived from longitudinal cortical thickness data collected between infancy and childhood (0–6 years). We assessed modularity as a measure of network segregation and global efficiency as a measure of network integration. At the group level, we observed trajectories of increasing modularity and decreasing global efficiency between early infancy and six years. We further examined subject-based maturational coupling networks (sbMCNs) in a subset of this cohort with cognitive outcome data at 8–10 years, which allowed us to relate the network organization of longitudinal cortical thickness maturation to cognitive outcomes in middle childhood. We found that lower global efficiency of sbMCNs throughout early development (across the first year) related to greater motor learning at 8–10 years. Together, these results provide novel evidence characterizing the maturation of brain network segregation and integration across the first six years of life, and suggest that specific trajectories of brain network maturation contribute to later cognitive outcomes.

Labeling lateral prefrontal sulci using spherical data augmentation and context-aware training

The inference of cortical sulcal labels often focuses on deep (primary and secondary) sulcal regions, whereas shallow (tertiary) sulcal regions are largely overlooked in the literature due to the scarcity of manual/well-defined annotations and their large neuroanatomical variability. In this paper, we present an automated framework for regional labeling of both primary/secondary and tertiary sulci of the dorsal portion of lateral prefrontal cortex (LPFC) using spherical convolutional neural networks. We propose two core components that enhance the inference of sulcal labels to overcome such large neuroanatomical variability: (1) surface data augmentation and (2) context-aware training. (1) To take into account neuroanatomical variability, we synthesize training data from the proposed feature space that embeds intermediate deformation trajectories of spherical data in a rigid to non-rigid fashion, which bridges an augmentation gap in conventional rotation data augmentation. (2) Moreover, we design a two-stage training process to improve labeling accuracy of tertiary sulci by informing the biological associations in neuroanatomy: inference of primary/secondary sulci and then their spatial likelihood to guide the definition of tertiary sulci. In the experiments, we evaluate our method on 13 deep and shallow sulci of human LPFC in two independent data sets with different age ranges: pediatric (N=60) and adult (N=36) cohorts. We compare the proposed method with a conventional multi-atlas approach and spherical convolutional neural networks without/with rotation data augmentation. In both cohorts, the proposed data augmentation improves labeling accuracy of deep and shallow sulci over the baselines, and the proposed context-aware training offers further improvement in the labeling of shallow sulci over the proposed data augmentation. We share our tools with the field and discuss applications of our results for understanding neuroanatomical-functional organization of LPFC and the rest of cortex (https://github.com/ilwoolyu/SphericalLabeling).

Spherical Deformable U-Net: Application to Cortical Surface Parcellation and Development Prediction

Convolutional Neural Networks (CNNs) have achieved overwhelming success in learning-related problems for 2D/3D images in the Euclidean space. However, unlike in the Euclidean space, the shapes of many structures in medical imaging have an inherent spherical topology in a manifold space, e.g., the convoluted brain cortical surfaces represented by triangular meshes. There is no consistent neighborhood definition and thus no straightforward convolution/pooling operations for such cortical surface data. In this paper, leveraging the regular and hierarchical geometric structure of the resampled spherical cortical surfaces, we create the 1-ring filter on spherical cortical triangular meshes and accordingly develop convolution/pooling operations for constructing Spherical U-Net for cortical surface data. However, the regular nature of the 1-ring filter makes it inherently limited to model fixed geometric transformations. To further enhance the transformation modeling capability of Spherical U-Net, we introduce the deformable convolution and deformable pooling to cortical surface data and accordingly propose the Spherical Deformable U-Net (SDU-Net). Specifically, spherical offsets are learned to freely deform the 1-ring filter on the sphere to adaptively localize cortical structures with different sizes and shapes. We then apply the SDU-Net to two challenging and scientifically important tasks in neuroimaging: cortical surface parcellation and cortical attribute map prediction. Both applications validate the competitive performance of our approach in accuracy and computational efficiency in comparison with state-of-the-art methods.

Validation of Group-wise Registration for Surface-based Functional MRI Analysis

Resting-state functional MRI (rsfMRI) provides important information for studying and mapping the activities and functions of the brain. Conventionally, rsfMRIs are often registered to structural images in the Euclidean space without considering cortical surface geometry. Meanwhile, a surface-based representation offers a relaxed coordinate chart, but this still requires surface registration for group-wise data analysis. In this work, we investigate the performance of two existing surface registration methods in a surface-based rsfMRI analysis framework: FreeSurfer and Hierarchical Spherical Deformation (HSD). To minimize registration bias, we establish shape correspondence using both methods in a group-wise manner that estimates the unbiased average of a given cohort. To evaluate their performance, we focus on neuroanatomical alignment as well as the amount of distortion that can potentially bias surface tessellation for secondary level rsfMRI data analyses. In the pilot analysis, we examine a single timepoint of imaging data from 100 subjects out of an aging cohort. Overall, HSD establishes improved shape correspondence with reduced mean curvature deviation (10.94% less on average per subject, paired t-test: p <10-10) and reduced registration distortion (FreeSurfer: average 41.91% distortion per subject, HSD: 18.63%, paired t-test: p <10-10). Furthermore, HSD introduces less distortion than FreeSurfer in the areas identified in the individual components that were extracted by surface-based independent component analysis (ICA) after spatial smoothing and time series normalization. Consequently, we show that FreeSurfer capture individual components with globally similar but locally different patterns in ICA in visual inspection.

Establishing Surface Correspondence for Post-surgical Cortical Thickness Changes in Temporal Lobe Epilepsy

In pre- and post-surgical surface shape analysis, establishing shape correspondence is necessary to investigate the postoperative surface changes. However, structural absence after the operation accompanies focal non-rigid changes, which leads to challenges in existing surface registration methods. In this paper, we present a fully automatic particle-based method to establish surface correspondence that can handle partial structural abnormality in the temporal lobe resection. Our method optimizes the coordinates of points which are modeled as particles on surfaces in a hierarchical way to reduce a chance of being trapped in a local minimum during the optimization. In the experiments, we evaluate the effectiveness of our method in comparison with conventional spherical registration (FreeSurfer) on two scenarios: cortical thickness changes in healthy controls within a short scan-rescan time window and patients with temporal lobe resection. The post-surgical scan is acquired at least 1 year after the presurgical scan. In region of interest-wise (ROI-wise) analysis, no changes on cortical thickness are found in both methods on the healthy control group. In patients, since there is no ground truth available, we instead investigated the disagreement between our method and FreeSurfer. We see poorly matched ROIs and large cortical thickness changes using FreeSurfer. On the contrary, our method shows well-matched ROIs and subtle cortical thickness changes. This suggests that the proposed method can establish a stable shape correspondence, which is not fully captured in a conventional spherical registration.

Performance-aware programming for intraoperative intensity-based image registration on graphics processing units

Purpose

Intensity-based image registration has been proven essential in many applications accredited to its unparalleled ability to resolve image misalignments. However, long registration time for image realignment prohibits its use in intra-operative navigation systems. There has been much work on accelerating the registration process by improving the algorithm’s robustness, but the innate computation required by the registration algorithm has been unresolved.

Methods

Intensity-based registration methods involve operations with high arithmetic load and memory access demand, which supposes to be reduced by graphics processing units (GPUs). Although GPUs are widespread and affordable, there is a lack of open-source GPU implementations optimized for non-rigid image registration. This paper demonstrates performance-aware programming techniques, which involves systematic exploitation of GPU features, by implementing the diffeomorphic log-demons algorithm.

Results

By resolving the pinpointed computation bottlenecks on GPU, our implementation of diffeomorphic log-demons on Nvidia GTX Titan X GPU has achieved ~ 95 times speed-up compared to the CPU and registered a 1.3-M voxel image in 286 ms. Even for large 37-M voxel images, our implementation is able to register in 8.56 s, which attained ~ 258 times speed-up. Our solution involves effective employment of GPU computation units, memory, and data bandwidth to resolve computation bottlenecks.

Conclusion

The computation bottlenecks in diffeomorphic log-demons are pinpointed, analyzed, and resolved using various GPU performance-aware programming techniques. The proposed fast computation on basic image operations not only enhances the computation of diffeomorphic log-demons, but is also potentially extended to speed up many other intensity-based approaches. Our implementation is open-source on GitHub at https://bit.ly/2PYZxQz.