Volume-Based Analysis of 6-Month-Old Infant Brain MRI for Autism Biomarker Identification and Early Diagnosis

Severe Bronchopulmonary Dysplasia Adversely Affects Brain Growth in Preterm Infants

INTRODUCTION

Bronchopulmonary dysplasia (BPD) is associated with neurodevelopmental outcomes of preterm infants, but its effect on brain growth in preterm infants after the neonatal period is unknown. This study aimed to evaluate the effect of severe BPD on brain growth of preterm infants from term to 18 months of corrected age (CA).

METHODS

Sixty-three preterm infants (42 with severe BPD and 21 without severe BPD) who underwent magnetic resonance imaging at term equivalent age (TEA) and 18 months of CA were studied by using the Infant Brain Extraction and Analysis Toolbox (iBEAT). We measured segmented brain volumes and compared brain volume and brain growth velocity between the severe BPD group and the non-severe BPD group.

RESULTS

There was no significant difference in brain volumes at TEA between the groups. However, the brain volumes of the total brain and cerebral white matter in the severe BPD group were significantly smaller than those in the non-severe BPD group at 18 months of CA. The brain growth velocities from TEA to 18 months of CA in the total brain, cerebral cortex, and cerebral white matter in the severe BPD group were lower than those in the non-severe BPD group.

CONCLUSION

Brain growth in preterm infants with severe BPD from TEA age to 18 months of CA is less than that in preterm infants without severe BPD.

Cortical growth from infancy to adolescence in preterm and term-born children

Early life experiences can exert a significant influence on cortical and cognitive development. Very preterm birth exposes infants to several adverse environmental factors during hospital admission, which affect cortical architecture. However, the subsequent consequence of very preterm birth on cortical growth from infancy to adolescence has never been defined; despite knowledge of critical periods during childhood for establishment of cortical networks. Our aims were to: chart typical longitudinal cortical development and sex differences in cortical development from birth to adolescence in healthy term-born children; estimate differences in cortical development between children born at term and very preterm; and estimate differences in cortical development between children with normal and impaired cognition in adolescence. This longitudinal cohort study included children born at term (≥37 weeks' gestation) and very preterm (<30 weeks' gestation) with MRI scans at ages 0, 7 and 13 years (n = 66 term-born participants comprising 34 with one scan, 18 with two scans and 14 with three scans; n = 201 very preterm participants comprising 56 with one scan, 88 with two scans and 57 with three scans). Cognitive assessments were performed at age 13 years. Cortical surface reconstruction and parcellation were performed with state-of-the-art, equivalent MRI analysis pipelines for all time points, resulting in longitudinal cortical volume, surface area and thickness measurements for 62 cortical regions. Developmental trajectories for each region were modelled in term-born children, contrasted between children born at term and very preterm, and contrasted between all children with normal and impaired cognition. In typically developing term-born children, we documented anticipated patterns of rapidly increasing cortical volume, area and thickness in early childhood, followed by more subtle changes in later childhood, with smaller cortical size in females than males. In contrast, children born very preterm exhibited increasingly reduced cortical volumes, relative to term-born children, particularly during ages 0-7 years in temporal cortical regions. This reduction in cortical volume in children born very preterm was largely driven by increasingly reduced cortical thickness rather than area. This resulted in amplified cortical volume and thickness reductions by age 13 years in individuals born very preterm. Alterations in cortical thickness development were found in children with impaired language and memory. This study shows that the neurobiological impact of very preterm birth on cortical growth is amplified from infancy to adolescence. These data further inform the long-lasting impact on cortical development from very preterm birth, providing broader insights into neurodevelopmental consequences of early life experiences.

Parenting Influences on Frontal Lobe Gray Matter and Preterm Toddlers' Problem-Solving Skills

Children born preterm often face challenges with self-regulation during toddlerhood. This study examined the relationship between prematurity, supportive parent behaviors, frontal lobe gray matter volume (GMV), and emotion regulation (ER) among toddlers during a parent-assisted, increasingly complex problem-solving task, validated for this age range. Data were collected from preterm toddlers (n = 57) ages 15-30 months corrected for prematurity and their primary caregivers. MRI data were collected during toddlers' natural sleep. The sample contained three gestational groups: 22-27 weeks (extremely preterm; EPT), 28-33 weeks (very preterm; VPT), and 34-36 weeks (late preterm; LPT). Older toddlers became more compliant as the Tool Task increased in difficulty, but this pattern varied by gestational group. Engagement was highest for LPT toddlers, for older toddlers, and for the easiest task condition. Parents did not differentiate their support depending on task difficulty or their child's age or gestational group. Older children had greater frontal lobe GMV, and for EPT toddlers only, more parent support was related to larger right frontal lobe GMV. We found that parent support had the greatest impact on high birth risk (≤27 gestational weeks) toddler brain development, thus early parent interventions may normalize preterm child neurodevelopment and have lasting impacts.

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.

Self-supervised learning with application for infant cerebellum segmentation and analysis

Accurate tissue segmentation is critical to characterize early cerebellar development in the first two postnatal years. However, challenges in tissue segmentation arising from tightly-folded cortex, low and dynamic tissue contrast, and large inter-site data heterogeneity have limited our understanding of early cerebellar development. In this paper, we propose an accurate self-supervised learning framework for infant cerebellum segmentation. We validate its accuracy using 358 subjects from three datasets. Our results suggest the first six months exhibit the most rapid and dynamic changes, with gray matter (GM) playing a dominant role in cerebellar growth over white matter (WM). We also find both GM and WM volumes are larger in males than females, and GM and WM volumes are larger in autistic males than neurotypical males. Application of our method to a larger population will fuel more cerebellar studies, ultimately advancing our comprehension of its structure and function in neurotypical and disordered 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.

Volumetric Analysis of Amygdala and Hippocampal Subfields for Infants with Autism

Previous studies have demonstrated abnormal brain overgrowth in children with autism spectrum disorder (ASD), but the development of specific brain regions, such as the amygdala and hippocampal subfields in infants, is incompletely documented. To address this issue, we performed the first MRI study of amygdala and hippocampal subfields in infants from 6 to 24 months of age using a longitudinal dataset. A novel deep learning approach, Dilated-Dense U-Net, was proposed to address the challenge of low tissue contrast and small structural size of these subfields. We performed a volume-based analysis on the segmentation results. Our results show that infants who were later diagnosed with ASD had larger left and right volumes of amygdala and hippocampal subfields than typically developing controls.

3D-MASNet: 3D mixed-scale asymmetric convolutional segmentation network for 6-month-old infant brain MR images

Precise segmentation of infant brain magnetic resonance (MR) images into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) are essential for studying neuroanatomical hallmarks of early brain development. However, for 6-month-old infants, the extremely low-intensity contrast caused by inherent myelination hinders accurate tissue segmentation. Existing convolutional neural networks (CNNs) based segmentation models for this task generally employ single-scale symmetric convolutions, which are inefficient for encoding the isointense tissue boundaries in baby brain images. Here, we propose a 3D mixed-scale asymmetric convolutional segmentation network (3D-MASNet) framework for brain MR images of 6-month-old infants. We replaced the traditional convolutional layer of an existing to-be-trained network with a 3D mixed-scale convolution block consisting of asymmetric kernels (MixACB) during the training phase and then equivalently converted it into the original network. Five canonical CNN segmentation models were evaluated using both T1- and T2-weighted images of 23 6-month-old infants from iSeg-2019 datasets, which contained manual labels as ground truth. MixACB significantly enhanced the average accuracy of all five models and obtained the most considerable improvement in the fully convolutional network model (CC-3D-FCN) and the highest performance in the Dense U-Net model. This approach further obtained Dice coefficient accuracies of 0.931, 0.912, and 0.961 in GM, WM, and CSF, respectively, ranking first among 30 teams on the validation dataset of the iSeg-2019 Grand Challenge. Thus, the proposed 3D-MASNet can improve the accuracy of existing CNNs-based segmentation models as a plug-and-play solution that offers a promising technique for future infant brain MRI studies.

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.

Brain Connectivity Based Graph Convolutional Networks and Its Application to Infant Age Prediction

Infancy is a critical period for the human brain development, and brain age is one of the indices for the brain development status associated with neuroimaging data. The difference between the predicted age based on neuroimaging and the chronological age can provide an important early indicator of deviation from the normal developmental trajectory. In this study, we utilize the Graph Convolutional Network (GCN) to predict the infant brain age based on resting-state fMRI data. The brain connectivity obtained from rs-fMRI can be represented as a graph with brain regions as nodes and functional connections as edges. However, since the brain connectivity is a fully connected graph with features on edges, current GCN cannot be directly used for it is a node-based method for sparse graphs. Hence, we propose an edge-based Graph Path Convolution (GPC) method, which aggregates the information from different paths and can be naturally applied on dense graphs. We refer the whole model as Brain Connectivity Graph Convolutional Networks (BC-GCN). Further, two upgraded network structures are proposed by including the residual and attention modules, referred as BC-GCN-Res and BC-GCN-SE to emphasize the information of the original data and enhance influential channels. Moreover, we design a two-stage coarse-to-fine framework, which determines the age group first and then predicts the age using group-specific BC-GCN-SE models. To avoid accumulated errors from the first stage, a cross-group training strategy is adopted for the second stage regression models. We conduct experiments on infant fMRI scans from 6 to 811 days of age. The coarse-to-fine framework shows significant improvements when being applied to several models (reducing error over 10 days). Comparing with state-of-the-art methods, our proposed model BC-GCN-SE with coarse-to-fine framework reduces the mean absolute error of the prediction from >70 days to 49.9 days. The code is now available at https://github.com/SCUT-Xinlab/BC-GCN.

PTNet3D: A 3D High-Resolution Longitudinal Infant Brain MRI Synthesizer Based on Transformers

An increased interest in longitudinal neurodevelopment during the first few years after birth has emerged in recent years. Noninvasive magnetic resonance imaging (MRI) can provide crucial information about the development of brain structures in the early months of life. Despite the success of MRI collections and analysis for adults, it remains a challenge for researchers to collect high-quality multimodal MRIs from developing infant brains because of their irregular sleep pattern, limited attention, inability to follow instructions to stay still during scanning. In addition, there are limited analytic approaches available. These challenges often lead to a significant reduction of usable MRI scans and pose a problem for modeling neurodevelopmental trajectories. Researchers have explored solving this problem by synthesizing realistic MRIs to replace corrupted ones. Among synthesis methods, the convolutional neural network-based (CNN-based) generative adversarial networks (GANs) have demonstrated promising performance. In this study, we introduced a novel 3D MRI synthesis framework- pyramid transformer network (PTNet3D)- which relies on attention mechanisms through transformer and performer layers. We conducted extensive experiments on high-resolution Developing Human Connectome Project (dHCP) and longitudinal Baby Connectome Project (BCP) datasets. Compared with CNN-based GANs, PTNet3D consistently shows superior synthesis accuracy and superior generalization on two independent, large-scale infant brain MRI datasets. Notably, we demonstrate that PTNet3D synthesized more realistic scans than CNN-based models when the input is from multi-age subjects. Potential applications of PTNet3D include synthesizing corrupted or missing images. By replacing corrupted scans with synthesized ones, we observed significant improvement in infant whole brain segmentation.

Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects approximately 1% of the population and causes significant burdens. ASD's pathogenesis remains elusive; hence, diagnosis is based on a constellation of behaviors. Structural magnetic resonance imaging (sMRI) studies have shown several abnormalities in volumetric and geometric features of the autistic brain. However, inconsistent findings prevented most contributions from being translated into clinical practice. Establishing reliable biomarkers for ASD using sMRI is crucial for the correct diagnosis and treatment. In recent years, machine learning (ML) and specifically deep learning (DL) have quickly extended to almost every sector, notably in disease diagnosis. Thus, this has led to a shift and improvement in ASD diagnostic methods, fulfilling most clinical diagnostic requirements. However, ASD discovery remains difficult. This review examines the ML-based ASD diagnosis literature over the past 5 years. A literature-based taxonomy of the research landscape has been mapped, and the major aspects of this topic have been covered. First, we provide an overview of ML's general classification pipeline and the features of sMRI. Next, representative studies are highlighted and discussed in detail with respect to methods, and biomarkers. Finally, we highlight many common challenges and make recommendations for future directions. In short, the limited sample size was the main obstacle; Thus, comprehensive data sets and rigorous methods are necessary to check the generalizability of the results. ML technologies are expected to advance significantly in the coming years, contributing to the diagnosis of ASD and helping clinicians soon.

Mother’s physical activity during pregnancy and newborn’s brain cortical development

Background

Physical activity is known to improve mental health, and is regarded as safe and desirable for uncomplicated pregnancy. In this novel study, we aim to evaluate whether there are associations between maternal physical activity during pregnancy and neonatal brain cortical development.

Methods

Forty-four mother/newborn dyads were included in this longitudinal study. Healthy pregnant women were recruited and their physical activity throughout pregnancy were documented using accelerometers worn for 3–7 days for each of the 6 time points at 4–10, ∼12, ∼18, ∼24, ∼30, and ∼36 weeks of pregnancy. Average daily total steps and daily total activity count as well as daily minutes spent in sedentary/light/moderate/vigorous activity modes were extracted from the accelerometers for each time point. At ∼2 weeks of postnatal age, their newborns underwent an MRI examination of the brain without sedation, and 3D T1-weighted brain structural images were post-processed by the iBEAT2.0 software utilizing advanced deep learning approaches. Cortical surface maps were reconstructed from the segmented brain images and parcellated to 34 regions in each brain hemisphere, and mean cortical thickness for each region was computed for partial correlation analyses with physical activity measures, with appropriate multiple comparison corrections and potential confounders controlled.

Results

At 4–10 weeks of pregnancy, mother’s daily total activity count positively correlated (FDR corrected P ≤ 0.05) with newborn’s cortical thickness in the left caudal middle frontal gyrus (rho = 0.48, P = 0.04), right medial orbital frontal gyrus (rho = 0.48, P = 0.04), and right transverse temporal gyrus (rho = 0.48, P = 0.04); mother’s daily time in moderate activity mode positively correlated with newborn’s cortical thickness in the right transverse temporal gyrus (rho = 0.53, P = 0.03). At ∼24 weeks of pregnancy, mother’s daily total activity count positively correlated (FDR corrected P ≤ 0.05) with newborn’s cortical thickness in the left (rho = 0.56, P = 0.02) and right isthmus cingulate gyrus (rho = 0.50, P = 0.05).

Conclusion

We identified significant relationships between physical activity in healthy pregnant women during the 1st and 2nd trimester and brain cortical development in newborns. Higher maternal physical activity level is associated with greater neonatal brain cortical thickness, presumably indicating better cortical development.

Spherical Transformer on Cortical Surfaces

Motivated by the recent great success of attention modeling in computer vision, it is highly desired to extend the Transformer architecture from the conventional Euclidean space to non-Euclidean spaces. Given the intrinsic spherical topology of brain cortical surfaces in neuroimaging, in this study, we propose a novel Spherical Transformer, an effective general-purpose backbone using the self-attention mechanism for analysis of cortical surface data represented by triangular meshes. By mapping the cortical surface onto a sphere and splitting it uniformly into overlapping spherical surface patches, we encode the long-range dependency within each patch by the self-attention operation and formulate the cross-patch feature transmission via overlapping regions. By limiting the self-attention computation to local patches, our proposed Spherical Transformer preserves detailed contextual information and enjoys great efficiency with linear computational complexity with respect to the patch size. Moreover, to better process longitudinal cortical surfaces, which are increasingly popular in neuroimaging studies, we unprecedentedly propose the spatiotemporal self-attention operation to jointly extract the spatial context and dynamic developmental patterns within a single layer, thus further enlarging the expressive power of the generated representation. To comprehensively evaluate the performance of our Spherical Transformer, we validate it on a surface-level prediction task and a vertex-level dense prediction task, respectively, i.e., the cognition prediction and cortical thickness map development prediction, which are important in early brain development mapping. Both applications demonstrate the competitive performance of our Spherical Transformer in comparison with the state-of-the-art methods.

Fast Spherical Mapping of Cortical Surface Meshes Using Deep Unsupervised Learning

Spherical mapping of cortical surface meshes provides a more convenient and accurate space for cortical surface registration and analysis and thus has been widely adopted in neuroimaging field. Conventional approaches typically first inflate and project the original cortical surface mesh onto a sphere to generate an initial spherical mesh which contains large distortions. Then they iteratively reshape the spherical mesh to minimize the metric (distance), area or angle distortions. However, these methods suffer from two major issues: 1) the iterative optimization process is computationally expensive, making them not suitable for large-scale data processing; 2) when metric distortion cannot be further minimized, either area or angle distortion is minimized at the expense of the other, which is not flexible to generate application-specific meshes based on both of them. To address these issues, for the first time, we propose a deep learning-based algorithm to learn the mapping between the original cortical surface and spherical surface meshes. Specifically, we take advantage of the Spherical U-Net model to learn the spherical diffeomorphic deformation field for minimizing the distortions between the icosahedron-reparameterized original surface and spherical surface meshes. The end-to-end unsupervised learning scheme is very flexible to incorporate various optimization objectives. We further integrate it into a coarse-to-fine multi-resolution framework for better correcting fine-scaled distortions. We have validated our method on 800+ cortical surfaces, demonstrating reduced distortions than FreeSurfer (the most popularly used tool), while speeding up the process from 20 min to 5 s.

Harmonization of Multi-site Cortical Data Across the Human Lifespan

Neuroimaging data harmonization has become a prerequisite in integrative data analytics for standardizing a wide variety of data collected from multiple studies and enabling interdisciplinary research. The lack of standardized image acquisition and computational procedures introduces non-biological variability and inconsistency in multi-site data, complicating downstream statistical analyses. Here, we propose a novel statistical technique to retrospectively harmonize multi-site cortical data collected longitudinally and cross-sectionally between birth and 100 years. We demonstrate that our method can effectively eliminate non-biological disparities from cortical thickness and myelination measurements, while preserving biological variation across the entire lifespan. Our harmonization method will foster large-scale population studies by providing comparable data required for investigating developmental and aging processes.

Path Signature Neural Network of Cortical Features for Prediction of Infant Cognitive Scores

Studies have shown that there is a tight connection between cognition skills and brain morphology during infancy. Nonetheless, it is still a great challenge to predict individual cognitive scores using their brain morphological features, considering issues like the excessive feature dimension, small sample size and missing data. Due to the limited data, a compact but expressive feature set is desirable as it can reduce the dimension and avoid the potential overfitting issue. Therefore, we pioneer the path signature method to further explore the essential hidden dynamic patterns of longitudinal cortical features. To form a hierarchical and more informative temporal representation, in this work, a novel cortical feature based path signature neural network (CF-PSNet) is proposed with stacked differentiable temporal path signature layers for prediction of individual cognitive scores. By introducing the existence embedding in path generation, we can improve the robustness against the missing data. Benefiting from the global temporal receptive field of CF-PSNet, characteristics consisted in the existing data can be fully leveraged. Further, as there is no need for the whole brain to work for a certain cognitive ability, a top K selection module is used to select the most influential brain regions, decreasing the model size and the risk of overfitting. Extensive experiments are conducted on an in-house longitudinal infant dataset within 9 time points. By comparing with several recent algorithms, we illustrate the state-of-the-art performance of our CF-PSNet (i.e., root mean square error of 0.027 with the time latency of 518 milliseconds for each sample).

Quantitative Structural Brain Magnetic Resonance Imaging Analyses: Methodological Overview and Application to Rett Syndrome

Congenital genetic disorders often present with neurological manifestations such as neurodevelopmental disorders, motor developmental retardation, epilepsy, and involuntary movement. Through qualitative morphometric evaluation of neuroimaging studies, remarkable structural abnormalities, such as lissencephaly, polymicrogyria, white matter lesions, and cortical tubers, have been identified in these disorders, while no structural abnormalities were identified in clinical settings in a large population. Recent advances in data analysis programs have led to significant progress in the quantitative analysis of anatomical structural magnetic resonance imaging (MRI) and diffusion-weighted MRI tractography, and these approaches have been used to investigate psychological and congenital genetic disorders. Evaluation of morphometric brain characteristics may contribute to the identification of neuroimaging biomarkers for early diagnosis and response evaluation in patients with congenital genetic diseases. This mini-review focuses on the methodologies and attempts employed to study Rett syndrome using quantitative structural brain MRI analyses, including voxel- and surface-based morphometry and diffusion-weighted MRI tractography. The mini-review aims to deepen our understanding of how neuroimaging studies are used to examine congenital genetic disorders.

SPHERICAL TRANSFORMER FOR QUALITY ASSESSMENT OF PEDIATRIC CORTICAL SURFACES

Brain cortical surfaces, which have an intrinsic spherical topology, are typically represented by triangular meshes and mapped onto a spherical manifold in neuroimaging analysis. Inspired by the strong capability of feature learning in Convolutional Neural Networks (CNNs), spherical CNNs have been developed accordingly and achieved many successes in cortical surface analysis. Motivated by the recent success of the transformer, in this paper, for the first of time, we extend the transformer into the spherical space and propose the spherical transformer, which can better learn contextual and structural features than spherical CNNs. We applied the spherical transformer in the important task of automatic quality assessment of infant cortical surfaces, which is a necessary procedure to identify problematic cases due to extremely low tissue contrast and strong motion effects in pediatric brain MRI studies. Experiments on 1,860 infant cortical surfaces validated its superior effectiveness and efficiency in comparison with spherical CNNs.

White matter myelination during early infancy is linked to spatial gradients and myelin content at birth

Development of myelin, a fatty sheath that insulates nerve fibers, is critical for brain function. Myelination during infancy has been studied with histology, but postmortem data cannot evaluate the longitudinal trajectory of white matter development. Here, we obtained longitudinal diffusion MRI and quantitative MRI measures of longitudinal relaxation rate (R1) of white matter in 0, 3 and 6 months-old human infants, and developed an automated method to identify white matter bundles and quantify their properties in each infant's brain. We find that R1 increases from newborns to 6-months-olds in all bundles. R1 development is nonuniform: there is faster development in white matter that is less mature in newborns, and development rate increases along inferior-to-superior as well as anterior-to-posterior spatial gradients. As R1 is linearly related to myelin fraction in white matter bundles, these findings open new avenues to elucidate typical and atypical white matter myelination in early infancy.

Eye Gaze in Autism Spectrum Disorder: A Review of Neural Evidence for the Eye Avoidance Hypothesis

Reduced eye contact early in life may play a role in the developmental pathways that culminate in a diagnosis of autism spectrum disorder. However, there are contradictory theories regarding the neural mechanisms involved. According to the amygdala theory of autism, reduced eye contact results from a hypoactive amygdala that fails to flag eyes as salient. However, the eye avoidance hypothesis proposes the opposite-that amygdala hyperactivity causes eye avoidance. This review evaluated studies that measured the relationship between eye gaze and activity in the 'social brain' when viewing facial stimuli. Of the reviewed studies, eight of eleven supported the eye avoidance hypothesis. These results suggest eye avoidance may be used to reduce amygdala-related hyperarousal among people on the autism spectrum.

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.

Infants' cortex undergoes microstructural growth coupled with myelination during development

Development of cortical tissue during infancy is critical for the emergence of typical brain functions in cortex. However, how cortical microstructure develops during infancy remains unknown. We measured the longitudinal development of cortex from birth  to six months of age  using multimodal quantitative imaging of cortical microstructure. Here we show that infants' cortex undergoes profound microstructural tissue growth during the first six months of human life. Comparison of postnatal to prenatal transcriptomic gene expression data demonstrates that myelination and synaptic processes are dominant contributors to this postnatal microstructural tissue growth. Using visual cortex as a model system, we find hierarchical microstructural growth: higher-level visual areas have less mature tissue at birth than earlier visual areas but grow at faster rates. This overturns the prominent view that visual areas that are most mature at birth develop fastest. Together, in vivo, longitudinal, and quantitative measurements, which we validated with ex vivo transcriptomic data, shed light on the rate, sequence, and biological mechanisms of developing cortical systems during early infancy. Importantly, our findings propose a hypothesis that cortical myelination is a key factor in cortical development during early infancy, which has important implications for diagnosis of neurodevelopmental disorders and delays in infants.

Unified framework for early stage status prediction of autism based on infant structural magnetic resonance imaging

Autism, or autism spectrum disorder (ASD), is a developmental disability that is diagnosed at about 2 years of age based on abnormal behaviors. Existing neuroimaging‐based methods for the prediction of ASD typically focus on functional magnetic resonance imaging (fMRI); however, most of these fMRI‐based studies include subjects older than 5 years of age. Due to challenges in the application of fMRI for infants, structural magnetic resonance imaging (sMRI) has increasingly received attention in the field for early status prediction of ASD. In this study, we propose an automated prediction framework based on infant sMRI at about 24 months of age. Specifically, by leveraging an infant‐dedicated pipeline, iBEAT V2.0 Cloud, we derived segmentation and parcellation maps from infant sMRI. We employed a convolutional neural network to extract features from pairwise maps and a Siamese network to distinguish whether paired subjects were from the same or different classes. As compared to T1w imaging without segmentation and parcellation maps, our proposed approach with segmentation and parcellation maps yielded greater sensitivity, specificity, and accuracy of ASD prediction, which was validated using two datasets with different imaging protocols/scanners and was confirmed by receiver operating characteristic analysis. Furthermore, comparison with state‐of‐the‐art methods demonstrated the superior effectiveness and robustness of the proposed method. Finally, attention maps were generated to identify subject‐specific autism effects, supporting the reasonability of the predictive results. Collectively, these findings demonstrate the utility of our unified framework for the early‐stage status prediction of ASD by sMRI.

Maternal Obesity during Pregnancy is Associated with Lower Cortical Thickness in the Neonate Brain

BACKGROUND AND PURPOSE

Recent studies have suggested that maternal obesity during pregnancy is associated with differences in neurodevelopmental outcomes in children. In this study, we aimed to investigate the relationships between maternal obesity during pregnancy and neonatal brain cortical development.

MATERIALS AND METHODS

Forty-four healthy women (28 normal-weight, 16 obese) were prospectively recruited at <10 weeks' gestation, and their healthy full-term neonates (23 boys, 21 girls) underwent brain MR imaging. All pregnant women had their body composition (fat mass percentage) measured at ∼12 weeks of pregnancy. All neonates were scanned at ∼2 weeks of age during natural sleep without sedation, and their 3D T1-weighted images were postprocessed by the new iBEAT2.0 software. Brain MR imaging segmentation and cortical surface reconstruction and parcellation were completed using age-appropriate templates. Mean cortical thickness for 34 regions in each brain hemisphere defined by the UNC Neonatal Cortical Surface Atlas was measured, compared between groups, and correlated with maternal body fat mass percentage, controlled for neonate sex and race, postmenstrual age at MR imaging, maternal age at pregnancy, and the maternal intelligence quotient and education.

RESULTS

Neonates born to obese mothers showed significantly lower (P ≤ .05, false discovery rate-corrected) cortical thickness in the left pars opercularis gyrus, left pars triangularis gyrus, and left rostral middle frontal gyrus. Mean cortical thickness in these frontal lobe regions negatively correlated (R = -0.34, P = .04; R = -0.50, P = .001; and R = -0.42, P = .01; respectively) with the maternal body fat mass percentage measured at early pregnancy.

CONCLUSIONS

Maternal obesity during pregnancy is associated with lower neonate brain cortical thickness in several frontal lobe regions important for language and executive functions.

Multi-Scale Self-Supervised Learning for Multi-Site Pediatric Brain MR Image Segmentation with Motion/Gibbs Artifacts

Accurate tissue segmentation of large-scale pediatric brain MR images from multiple sites is essential to characterize early brain development. Due to imaging motion/Gibbs artifacts and multi-site issue (or domain shift issue), it remains a challenge to accurately segment brain tissues from multi-site pediatric MR images. In this paper, we present a multi-scale self-supervised learning (M-SSL) framework to accurately segment tissues for multi-site pediatric brain MR images with artifacts. Specifically, we first work on the downsampled images to estimate coarse tissue probabilities and build a global anatomic guidance. We then train another segmentation model based on the original images to estimate fine tissue probabilities, which are further integrated with the global anatomic guidance to refine the segmentation results. In the testing stage, to alleviate the multi-site issue, we propose an iterative self-supervised learning strategy to train a site-specific segmentation model based on a set of reliable training samples automatically generated for a to-be-segmented site. The experimental results on pediatric brain MR images with real artifacts and multi-site subjects from the iSeg2019 challenge demonstrate that our M-SSL method achieves better performance compared with several state-of-the-art methods.

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 Spatiotemporal Probabilistic Atlas of Fetal Brains with Anatomically Constrained Registration Network

Brain atlases are of fundamental importance for analyzing the dynamic neurodevelopment in fetal brain studies. Since the brain size, shape, and anatomical structures change rapidly during the prenatal period, it is essential to construct a spatiotemporal (4D) atlas equipped with tissue probability maps, which can preserve sharper early brain folding patterns for accurately characterizing dynamic changes in fetal brains and provide tissue prior informations for related tasks, e.g., segmentation, registration, and parcellation. In this work, we propose a novel unsupervised age-conditional learning framework to build temporally continuous fetal brain atlases by incorporating tissue segmentation maps, which outperforms previous traditional atlas construction methods in three aspects. First, our framework enables learning age-conditional deformable templates by leveraging the entire collection. Second, we leverage reliable brain tissue segmentation maps in addition to the low-contrast noisy intensity images to enhance the alignment of individual images. Third, a novel loss function is designed to enforce the similarity between the learned tissue probability map on the atlas and each subject tissue segmentation map after registration, thereby providing extra anatomical consistency supervision for atlas building. Our 4D temporally-continuous fetal brain atlases are constructed based on 82 healthy fetuses from 22 to 32 gestational weeks. Compared with the atlases built by the state-of-the-art algorithms, our atlases preserve more structural details and sharper folding patterns. Together with the learned tissue probability maps, our 4D fetal atlases provide a valuable reference for spatial normalization and analysis of fetal brain development.

Reference-Relation Guided Autoencoder with Deep CCA Restriction for Awake-to-Sleep Brain Functional Connectome Prediction

The difficulty of acquiring resting-state fMRI of early developing children under the same condition leads to a dedicated protocol, i.e., scanning younger infants during sleep and older children during being awake, respectively. However, the obviously different brain activities of sleep and awake states arouse a new challenge of awake-to-sleep connectome prediction/translation, which remains unexplored despite its importance in the longitudinally-consistent delineation of brain functional development. Due to the data scarcity and huge differences between natural images and geometric data (e.g., brain connectome), existing methods tailored for image translation generally fail in predicting functional connectome from awake to sleep. To fill this critical gap, we unprecedentedly propose a novel reference-relation guided autoencoder with deep CCA restriction (R²AE-dCCA) for awake-to-sleep connectome prediction. Specifically, 1) A reference-autoencoder (RAE) is proposed to realize a guided generation from the source domain to the target domain. The limited paired data are thus greatly augmented by including the combinations of all the age-restricted neighboring subjects as the references, while the target-specific pattern is fully learned; 2) A relation network is then designed and embedded into RAE, which utilizes the similarity in the source domain to determine the belief-strength of the reference during prediction; 3) To ensure that the learned relation in the source domain can effectively guide the generation in the target domain, a deep CCA restriction is further employed to maintain the neighboring relation during translation; 4) New validation metrics dedicated for connectome prediction are also proposed. Experimental results showed that our proposed R²AE-dCCA produces better prediction accuracy and well maintains the modular structure of brain functional connectome in comparison with state-of-the-art methods.

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.

ABCnet: Adversarial bias correction network for infant brain MR images

Automatic correction of intensity nonuniformity (also termed as the bias correction) is an essential step in brain MR image analysis. Existing methods are typically developed for adult brain MR images based on the assumption that the image intensities within the same brain tissue are relatively uniform. However, this assumption is not valid in infant brain MR images, due to the dynamic and regionally-heterogeneous image contrast and appearance changes, which are caused by the underlying spatiotemporally-nonuniform myelination process. Therefore, it is not appropriate to directly use existing methods to correct the infant brain MR images. In this paper, we propose an end-to-end 3D adversarial bias correction network (ABCnet), tailored for direct prediction of bias fields from the input infant brain MR images for bias correction. The "ground-truth" bias fields for training our network are carefully defined by an improved N4 method, which integrates manually-corrected tissue segmentation maps as anatomical prior knowledge. The whole network is trained alternatively by minimizing generative and adversarial losses. To handle the heterogeneous intensity changes, our generative loss includes a tissue-aware local intensity uniformity term to reduce the local intensity variation in the corrected image. Besides, it also integrates two additional terms to enhance the smoothness of the estimated bias field and to improve the robustness of the proposed method, respectively. Comprehensive experiments with different sizes of training datasets have been carried out on a total of 1492 T1w and T2w MR images from neonates, infants, and adults, respectively. Both qualitative and quantitative evaluations on simulated and real datasets consistently demonstrate the superior performance of our ABCnet in both accuracy and efficiency, compared with popularly available methods.

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.

Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge

To better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; h owever, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. T raining/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.

MhURI:A Supervised Segmentation Approach to Leverage Salient Brain Tissues in Magnetic Resonance Images

BACKGROUND AND OBJECTIVES

Accurate segmentation of critical tissues from a brain MRI is pivotal for characterization and quantitative pattern analysis of the human brain and thereby, identifies the earliest signs of various neurodegenerative diseases. To date, in most cases, it is done manually by the radiologists. The overwhelming workload in some of the thickly populated nations may cause exhaustion leading to interruption for the doctors, which may pose a continuing threat to patient safety. A novel fusion method called U-Net inception based on 3D convolutions and transition layers is proposed to address this issue.

METHODS

A 3D deep learning method called Multi headed U-Net with Residual Inception (MhURI) accompanied by Morphological Gradient channel for brain tissue segmentation is proposed, which incorporates Residual Inception 2-Residual (RI2R) module as the basic building block. The model exploits the benefits of morphological pre-processing for structural enhancement of MR images. A multi-path data encoding pipeline is introduced on top of the U-Net backbone, which encapsulates initial global features and captures the information from each MRI modality.

RESULTS

The proposed model has accomplished encouraging outcomes, which appreciates the adequacy in terms of some of the established quality metrices when compared with some of the state-of-the-art methods while evaluating with respect to two popular publicly available data sets.

CONCLUSION

The model is entirely automatic and able to segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from brain MRI effectively with sufficient accuracy. Hence, it may be considered to be a potential computer-aided diagnostic (CAD) tool for radiologists and other medical practitioners in their clinical diagnosis workflow.

Disentangled-Multimodal Adversarial Autoencoder: Application to Infant Age Prediction With Incomplete Multimodal Neuroimages

Effective fusion of structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) data has the potential to boost the accuracy of infant age prediction thanks to the complementary information provided by different imaging modalities. However, functional connectivity measured by fMRI during infancy is largely immature and noisy compared to the morphological features from sMRI, thus making the sMRI and fMRI fusion for infant brain analysis extremely challenging. With the conventional multimodal fusion strategies, adding fMRI data for age prediction has a high risk of introducing more noises than useful features, which would lead to reduced accuracy than that merely using sMRI data. To address this issue, we develop a novel model termed as disentangled-multimodal adversarial autoencoder (DMM-AAE) for infant age prediction based on multimodal brain MRI. Specifically, we disentangle the latent variables of autoencoder into common and specific codes to represent the shared and complementary information among modalities, respectively. Then, cross-reconstruction requirement and common-specific distance ratio loss are designed as regularizations to ensure the effectiveness and thoroughness of the disentanglement. By arranging relatively independent autoencoders to separate the modalities and employing disentanglement under cross-reconstruction requirement to integrate them, our DMM-AAE method effectively restrains the possible interference cross modalities, while realizing effective information fusion. Taking advantage of the latent variable disentanglement, a new strategy is further proposed and embedded into DMM-AAE to address the issue of incompleteness of the multimodal neuroimages, which can also be used as an independent algorithm for missing modality imputation. By taking six types of cortical morphometric features from sMRI and brain functional connectivity from fMRI as predictors, the superiority of the proposed DMM-AAE is validated on infant age (35 to 848 days after birth) prediction using incomplete multimodal neuroimages. The mean absolute error of the prediction based on DMM-AAE reaches 37.6 days, outperforming state-of-the-art methods. Generally, our proposed DMM-AAE can serve as a promising model for prediction with multimodal data.

Automatic segmentation of true color sectioned images using FMRIB Software Library: First trial in brain, gray matter, and white matter

Three-dimensional (3D) models of the brain made from magnetic resonance images (MRI) are used in various medical fields. 3D models assembled from grayscale color and low-resolution can be complemented with true color sectioned images of the Visible Korean. The purpose of this study is to apply the MRI automatic segmentation technique to the sectioned images. 3D models of the sectioned images, which have true color and high resolution, can be produced without manual segmentation. The Brain Extraction Tool and the Automated Segmentation Tool of the FMRIB Software Library (FSL) were chosen for automatic segmentation. Using those tools, true color sectioned images were reconstructed from gray 3D models of brain, gray matter, and white matter. Color 3D models of those structures were generated from the gray 3D models using MRIcroGL. The color 3D models made from the sectioned images revealed details of brain anatomy that could not be observed on the 3D models from MRI. This trial suggests that convergence of the MRI segmentation technique with color sectioned images is a time-efficient method for producing color 3D models of various structures. In future, the method of this study will be used for various sectioned images of cadavers. The resulting color sectioned images and 3D models will be made available to other researchers.

Infant Cognitive Scores Prediction with Multi-stream Attention-Based Temporal Path Signature Features

There is stunning rapid development of human brains in the first year of life. Some studies have revealed the tight connection between cognition skills and cortical morphology in this period. Nonetheless, it is still a great challenge to predict cognitive scores using brain morphological features, given issues like small sample size and missing data in longitudinal studies. In this work, for the first time, we introduce the path signature method to explore hidden analytical and geometric properties of longitudinal cortical morphology features. A novel BrainPSNet is proposed with a differentiable temporal path signature layer to produce informative representations of different time points and various temporal granules. Further, a two-stream neural network is included to combine groups of raw features and path signature features for predicting the cognitive score. More importantly, considering different influences of each brain region on the cognitive function, we design a learning-based attention mask generator to automatically weight regions correspondingly. Experiments are conducted on an in-house longitudinal dataset. By comparing with several recent algorithms, the proposed method achieves the state-of-the-art performance. The relationship between morphological features and cognitive abilities is also analyzed.

Semi-supervised Transfer Learning for Infant Cerebellum Tissue Segmentation

To characterize early cerebellum development, accurate segmentation of the cerebellum into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) tissues is one of the most pivotal steps. However, due to the weak tissue contrast, extremely folded tiny structures, and severe partial volume effect, infant cerebellum tissue segmentation is especially challenging, and the manual labels are hard to obtain and correct for learning-based methods. To the best of our knowledge, there is no work on the cerebellum segmentation for infant subjects less than 24 months of age. In this work, we develop a semi-supervised transfer learning framework guided by a confidence map for tissue segmentation of cerebellum MR images from 24-month-old to 6-month-old infants. Note that only 24-month-old subjects have reliable manual labels for training, due to their high tissue contrast. Through the proposed semi-supervised transfer learning, the labels from 24-month-old subjects are gradually propagated to the 18-, 12-, and 6-month-old subjects, which have a low tissue contrast. Comparison with the state-of-the-art methods demonstrates the superior performance of the proposed method, especially for 6-month-old subjects.

Anatomy-Guided Convolutional Neural Network for Motion Correction in Fetal Brain MRI

Fetal Magnetic Resonance Imaging (MRI) is challenged by the fetal movements and maternal breathing. Although fast MRI sequences allow artifact free acquisition of individual 2D slices, motion commonly occurs in between slices acquisitions. Motion correction for each slice is thus very important for reconstruction of 3D fetal brain MRI, but is highly operator-dependent and time-consuming. Approaches based on convolutional neural networks (CNNs) have achieved encouraging performance on prediction of 3D motion parameters of arbitrarily oriented 2D slices, which, however, does not capitalize on important brain structural information. To address this problem, we propose a new multi-task learning framework to jointly learn the transformation parameters and tissue segmentation map of each slice, for providing brain anatomical information to guide the mapping from 2D slices to 3D volumetric space in a coarse to fine manner. In the coarse stage, the first network learns the features shared for both regression and segmentation tasks. In the refinement stage, to fully utilize the anatomical information, distance maps constructed based on the coarse segmentation are introduced to the second network. Finally, incorporation of the signed distance maps to guide the regression and segmentation together improves the performance in both tasks. Experimental results indicate that the proposed method achieves superior performance in reducing the motion prediction error and obtaining satisfactory tissue segmentation results simultaneously, compared with state-of-the-art methods.

A Deep Spatial Context Guided Framework for Infant Brain Subcortical Segmentation

Accurate subcortical segmentation of infant brain magnetic resonance (MR) images is crucial for studying early subcortical structural growth patterns and related diseases diagnosis. However, dynamic intensity changes, low tissue contrast, and small subcortical size of infant brain MR images make subcortical segmentation a challenging task. In this paper, we propose a spatial context guided, coarse-to-fine deep convolutional neural network (CNN) based framework for accurate infant subcortical segmentation. At the coarse stage, we propose a signed distance map (SDM) learning UNet (SDM-UNet) to predict SDMs from the original multi-modal images, including T1w, T2w, and T1w/T2w images. By doing this, the spatial context information, including the relative position information across different structures and the shape information of the segmented structures contained in the ground-truth SDMs, is used for supervising the SDM-UNet to remedy the bad influence from the low tissue contrast in infant brain MR images and generate high-quality SDMs. To improve the robustness to outliers, a Correntropy based loss is introduced in SDM-UNet to penalize the difference between the ground-truth SDMs and predicted SDMs in training. At the fine stage, the predicted SDMs, which contains spatial context information of subcortical structures, are combined with the multi-modal images, and then fed into a multi-source and multi-path UNet (M2-UNet) for delivering refined segmentation. We validate our method on an infant brain MR image dataset with 24 scans by evaluating the Dice ratio between our segmentation and the manual delineation. Compared to four state-of-the-art methods, our method consistently achieves better performances in both qualitative and quantitative evaluations.

Informative Feature-Guided Siamese Network for Early Diagnosis of Autism

Autism, or autism spectrum disorder (ASD), is a complex developmental disability, and usually diagnosed with observations at around 3-4 years old based on behaviors. Studies have indicated that the early treatment, especially during early brain development in the first two years of life, can significantly improve the symptoms, therefore, it is important to identify ASD as early as possible. Most previous works employed imaging-based biomarkers for the early diagnosis of ASD. However, they only focused on extracting features from the intensity images, ignoring the more informative guidance from segmentation and parcellation maps. Moreover, since the number of autistic subjects is always much smaller than that of normal subjects, this class-imbalance issue makes the ASD diagnosis more challenging. In this work, we propose an end-to-end informative feature-guided Siamese network for the early ASD diagnosis. Specifically, besides T1w and T2w images, the discriminative features from segmentation and parcellation maps are also employed to train the model. To alleviate the class-imbalance issue, the Siamese network is utilized to effectively learn what makes the pair of inputs belong to the same class or different classes. Furthermore, the subject-specific attention module is incorporated to identify the ASD-related regions in an end-to-end fully automatic learning manner. Both ablation study and comparisons demonstrate the effectiveness of the proposed method, achieving an overall accuracy of 85.4%, sensitivity of 80.8%, and specificity of 86.7%.

Unsupervised Learning for Spherical Surface Registration

Current spherical surface registration methods achieve good performance on alignment and spatial normalization of cortical surfaces across individuals in neuroimaging analysis. However, they are computationally intensive, since they have to optimize an objective function independently for each pair of surfaces. In this paper, we present a fast learning-based algorithm that makes use of the recent development in spherical Convolutional Neural Networks (CNNs) for spherical cortical surface registration. Given a set of surface pairs without supervised information such as ground truth deformation fields or anatomical landmarks, we formulate the registration as a parametric function and learn its parameters by enforcing the feature similarity between one surface and the other one warped by the estimated deformation field using the function. Then, given a new pair of surfaces, we can quickly infer the spherical deformation field registering one surface to the other one. We model this parametric function using three orthogonal Spherical U-Nets and use spherical transform layers to warp the spherical surfaces, while imposing smoothness constraints on the deformation field. All the layers in the network are well-defined and differentiable, thus the parameters can be effectively learned. We show that our method achieves accurate cortical alignment results on 102 subjects, comparable to two state-of-the-art methods: Spherical Demons and MSM, while runs much faster.

Automatic Identification of High-Risk Autism Spectrum Disorder: A Feasibility Study Using Video and Audio Data Under the Still-Face Paradigm

It is reported that the symptoms of autism spectrum disorder (ASD) could be improved by effective early interventions, which arouses an urgent need for large-scale early identification of ASD. Until now, the screening of ASD has relied on the child psychiatrist to collect medical history and conduct behavioral observations with the help of psychological assessment tools. Such screening measures inevitably have some disadvantages, including strong subjectivity, relying on experts and low-efficiency. With the development of computer science, it is possible to realize a computer-aided screening for ASD and alleviate the disadvantages of manual evaluation. In this study, we propose a behavior-based automated screening method to identify high-risk ASD (HR-ASD) for babies aged 8-24 months. The still-face paradigm (SFP) was used to elicit baby's spontaneous social behavior through a face-to-face interaction, in which a mother was required to maintain a normal interaction to amuse her baby for 2 minutes (a baseline episode) and then suddenly change to the no-reaction and no-expression status with 1 minute (a still-face episode). Here, multiple cues derived from baby's social stress response behavior during the latter episode, including head-movements, facial expressions and vocal characteristics, were statistically analyzed between HR-ASD and typical developmental (TD) groups. An automated identification model of HR-ASD was constructed based on these multi-cue features and the support vector machine (SVM) classifier; moreover, its screening performance was satisfied, for all the accuracy, specificity and sensitivity exceeded 90% on the cases included in this study. The experimental results suggest its feasibility in the early screening of HR-ASD.

Disentangled Intensive Triplet Autoencoder for Infant Functional Connectome Fingerprinting

Functional connectome "fingerprint" is a highly characterized brain pattern that distinguishes one individual from others. Although its existence has been demonstrated in adults, an unanswered but fundamental question is whether such individualized pattern emerges since infancy. This problem is barely investigated despites its importance in identifying the origin of the intrinsic connectome patterns that mirror distinct behavioral phenotypes. However, addressing this knowledge gap is challenging because the conventional methods are only applicable to developed brains with subtle longitudinal changes and typically fail on the dramatically developing infant brains. To tackle this challenge, we invent a novel model, namely, disentangled intensive triplet autoencoder (DI-TAE). First, we introduce the triplet autoencoder to embed the original connectivity into a latent space with higher discriminative capability among infant individuals. Then, a disentanglement strategy is proposed to separate the latent variables into identity-code, age-code, and noise-code, which not only restrains the interference from age-related developmental variance, but also captures the identity-related invariance. Next, a cross-reconstruction loss and an intensive triplet loss are designed to guarantee the effectiveness of the disentanglement and enhance the inter-subject dissimilarity for better discrimination. Finally, a variance-guided bootstrap aggregating is developed for DI-TAE to further improve the performance of identification. DI-TAE is validated on three longitudinal resting-state fMRI datasets with 394 infant scans aged 16 to 874 days. Our proposed model outperforms other state-of-the-art methods by increasing the identification rate by more than 50%, and for the first time suggests the plausible existence of brain functional connectome "fingerprint" since early infancy.

SIAMESE VERIFICATION FRAMEWORK FOR AUTISM IDENTIFICATION DURING INFANCY USING CORTICAL PATH SIGNATURE FEATURES

Autism spectrum disorder (ASD) is a complex neurodevelopmental disability, which is lack of biologic diagnostic markers. Therefore, exploring the ASD Identification directly from brain imaging data has been an important topic. In this work, we propose the Siamese verification model to identify ASD using 6 and 12 months cortical features. Rather than directly classifying a testing subject is ASD or not, we determine whether it has the same or different label with the reference subject who has been successfully diagnosed. Then, based on the comparison to all the reference subjects, we can predict the label of the testing subject. The advantage of modeling the classification problem as a verification framework is that it can greatly enlarge the training data size and enable us to train a more accurate and reliable model in an end-to-end manner. In addition, to further improve the classification performance, we introduce the path signature (PS) features, which can capture the dynamic longitudinal information of the brain development for the ASD Identification. Experiments showed that our proposed method reaches the best result, i.e., 87% accuracy, 83% sensitivity and 90% specificity comparing to the state-of-the-art methods.

Multi-task Learning for Neonatal Brain Segmentation Using 3D Dense-Unet with Dense Attention Guided by Geodesic Distance

The deep convolutional neural network has achieved outstanding performance on neonatal brain MRI tissue segmentation. However, it may fail to produce reasonable results on unseen datasets that have different imaging appearance distributions with the training data. The main reason is that deep learning models tend to have a good fitting to the training dataset, but do not lead to a good generalization on the unseen datasets. To address this problem, we propose a multi-task learning method, which simultaneously learns both tissue segmentation and geodesic distance regression to regularize a shared encoder network. Furthermore, a dense attention gate is explored to force the network to learn rich contextual information. By using three neonatal brain datasets with different imaging protocols from different scanners, our experimental results demonstrate superior performance of our proposed method over the existing deep learning-based methods on the unseen datasets.

A Longitudinal MRI Study of Amygdala and Hippocampal Subfields for Infants with Risk of Autism

Currently, there are still no early biomarkers to detect infants with risk of autism spectrum disorder (ASD), which is mainly diagnosed based on behavioral observations at three or four years of age. Since intervention efforts may miss a critical developmental window after 2 years old, it is clinically significant to identify imaging-based biomarkers at an early stage for better intervention, before behavioral diagnostic signs of ASD typically arising. Previous studies on older children and young adults with ASD demonstrate altered developmental trajectories of the amygdala and hippocampus. However, our knowledge on their developmental trajectories in early postnatal stages remains very limited. In this paper, for the first time, we propose a volume-based analysis of the amygdala and hippocampal subfields of the infant subjects with risk of ASD at 6, 12, and 24 months of age. To address the challenge of low tissue contrast and small structural size of infant amygdala and hippocampal subfields, we propose a novel deep-learning approach, dilated-dense U-Net, to digitally segment the amygdala and hippocampal subfields in a longitudinal dataset, the National Database for Autism Research (NDAR). A volume-based analysis is then performed based on the segmentation results. Our study shows that the overgrowth of amygdala and cornu ammonis sectors (CA) 1-3 May start from 6 months of age, which may be related to the emergence of autistic spectrum disorder.

A PRELIMINARY VOLUMETRIC MRI STUDY OF AMYGDALA AND HIPPOCAMPAL SUBFIELDS IN AUTISM DURING INFANCY

Currently, autism spectrum disorder (ASD) is mainly diagnosed by the observation of core behavioral symptoms. Consequently, the window of opportunity for effective intervention may have passed, when the disorder is detected until 3 years of age. Thus, it is of great importance to identify imaging-based biomarkers for early diagnosis of ASD. Previous findings indicate that an abnormal pattern of the amygdala and hippocampal development in autism persists through childhood and adolescence. However, due to the low tissue contrast and small structural size of amygdala and hippocampal subfields, our knowledge on their growth in autistics in early stage still remains very limited. In this paper, for the first time, we propose a volume-based analysis of the amygdala and hippocampal subfields of the infant subjects with risk of ASD at around 24 months of age. Specifically, to address the challenge of low tissue contrast, we propose a novel deep-learning approach, i.e., dilated-dense U-Net, to automatically segment the amygdala and hippocampal subfields. Experimental results on National Database for Autism Research (NDAR) show the advantages of our proposed method in terms of segmentation accuracy. Our volume-based analysis shows the overgrowths of amygdala and CA1-3 of hippocampus, which may link to the emergence of autism spectrum disorder.

Benchmark on Automatic 6-month-old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge

Accurate segmentation of infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is an indispensable foundation for early studying of brain growth patterns and morphological changes in neurodevelopmental disorders. Nevertheless, in the isointense phase (approximately 6-9 months of age), due to inherent myelination and maturation process, WM and GM exhibit similar levels of intensity in both T1-weighted (T1w) and T2-weighted (T2w) MR images, making tissue segmentation very challenging. Despite many efforts were devoted to brain segmentation, only few studies have focused on the segmentation of 6-month infant brain images. With the idea of boosting methodological development in the community, iSeg-2017 challenge (http://iseg2017.web.unc.edu) provides a set of 6-month infant subjects with manual labels for training and testing the participating methods. Among the 21 automatic segmentation methods participating in iSeg-2017, we review the 8 top-ranked teams, in terms of Dice ratio, modified Hausdorff distance and average surface distance, and introduce their pipelines, implementations, as well as source codes. We further discuss limitations and possible future directions. We hope the dataset in iSeg-2017 and this review article could provide insights into methodological development for the community.