Can we predict subject-specific dynamic cortical thickness maps during infancy from birth?

Longitudinal Infant Functional Connectivity Prediction via Conditional Intensive Triplet Network

Longitudinal infant brain functional connectivity (FC) constructed from resting-state functional MRI (rs-fMRI) has increasingly become a pivotal tool in studying the dynamics of early brain development. However, due to various reasons including high acquisition cost, strong motion artifact, and subject dropout, there has been an extreme shortage of usable longitudinal infant rs-fMRI scans to construct longitudinal FCs, which hinders comprehensive understanding and modeling of brain functional development at early ages. To address this issue, in this paper, we propose a novel conditional intensive triplet network (CITN) for longitudinal prediction of the dynamic development of infant FC, which can traverse FCs within a long duration and predict the target FC at any specific age during infancy. Targeting at accurately modeling of the progression pattern of FC, while maintaining the individual functional uniqueness, our model effectively disentangles the intrinsically mixed age-related and identity-related information from the source FC and predicts the target FC by fusing well-disentangled identity-related information with the specific age-related information. Specifically, we introduce an intensive triplet auto-encoder for effective disentanglement of age-related and identity-related information and an identity conditional module to mix identity-related information with designated age-related information. We train the proposed model in a self-supervised way and design downstream tasks to help robustly disentangle age-related and identity-related features. Experiments on 464 longitudinal infant fMRI scans show the superior performance of the proposed method in longitudinal FC prediction in comparison with state-of-the-art approaches.

Infant and Child MRI: A Review of Scanning Procedures

Magnetic resonance imaging (MRI) is a safe method to examine human brain. However, a typical MR scan is very sensitive to motion, and it requires the subject to lie still during the acquisition, which is a major challenge for pediatric scans. Consequently, in a clinical setting, sedation or general anesthesia is often used. In the research setting including healthy subjects anesthetics are not recommended for ethical reasons and potential longer-term harm. Here we review the methods used to prepare a child for an MRI scan, but also on the techniques and tools used during the scanning to enable a successful scan. Additionally, we critically evaluate how studies have reported the scanning procedure and success of scanning. We searched articles based on special subject headings from PubMed and identified 86 studies using brain MRI in healthy subjects between 0 and 6 years of age. Scan preparations expectedly depended on subject's age; infants and young children were scanned asleep after feeding and swaddling and older children were scanned awake. Comparing the efficiency of different procedures was difficult because of the heterogeneous reporting of the used methods and the success rates. Based on this review, we recommend more detailed reporting of scanning procedure to help find out which are the factors affecting the success of scanning. In the long term, this could help the research field to get high quality data, but also the clinical field to reduce the use of anesthetics. Finally, we introduce the protocol used in scanning 2 to 5-week-old infants in the FinnBrain Birth Cohort Study, and tips for calming neonates during the scans.

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.

Longitudinal Prediction of Infant MR Images With Multi-Contrast Perceptual Adversarial Learning

The infant brain undergoes a remarkable period of neural development that is crucial for the development of cognitive and behavioral capacities (Hasegawa et al., 2018). Longitudinal magnetic resonance imaging (MRI) is able to characterize the developmental trajectories and is critical in neuroimaging studies of early brain development. However, missing data at different time points is an unavoidable occurrence in longitudinal studies owing to participant attrition and scan failure. Compared to dropping incomplete data, data imputation is considered a better solution to address such missing data in order to preserve all available samples. In this paper, we adapt generative adversarial networks (GAN) to a new application: longitudinal image prediction of structural MRI in the first year of life. In contrast to existing medical image-to-image translation applications of GANs, where inputs and outputs share a very close anatomical structure, our task is more challenging as brain size, shape and tissue contrast vary significantly between the input data and the predicted data. Several improvements over existing GAN approaches are proposed to address these challenges in our task. To enhance the realism, crispness, and accuracy of the predicted images, we incorporate both a traditional voxel-wise reconstruction loss as well as a perceptual loss term into the adversarial learning scheme. As the differing contrast changes in T1w and T2w MR images in the first year of life, we incorporate multi-contrast images leading to our proposed 3D multi-contrast perceptual adversarial network (MPGAN). Extensive evaluations are performed to assess the qualityand fidelity of the predicted images, including qualitative and quantitative assessments of the image appearance, as well as quantitative assessment on two segmentation tasks. Our experimental results show that our MPGAN is an effective solution for longitudinal MR image data imputation in the infant brain. We further apply our predicted/imputed images to two practical tasks, a regression task and a classification task, in order to highlight the enhanced task-related performance following image imputation. The results show that the model performance in both tasks is improved by including the additional imputed data, demonstrating the usability of the predicted images generated from our approach.

Neuroanatomical Differences Among Sexual Offenders: A Targeted Review with Limitations and Implications for Future Directions

As sexual assault and child sexual abuse continue to be worldwide public health concerns, research has continued to explore factors associated with sexual offending. Structural and functional neuroanatomical brain differences have been examined in an effort to differentiate sexual offenders and their behavior. This targeted review searched PubMed and Google Scholar for empirical studies using brain imaging techniques to examine possible structural or functional differences among control groups compared with at least one group of sexual offenders with contact offenses. This targeted review summarizes the structural and functional findings of 15 brain imaging studies (i.e., computed tomography, diffusion tensor imaging, magnetic resonance imaging, positron emission tomography, and functional magnetic resonance imaging), which suggest possible differences in brain size and gray matter volume, cortical thickness, white matter connectivity, and specific structural and functional differences among brain regions (fronto-temporal region, amygdala, prefrontal cortex, etc.). The methodological limitations of brain imaging studies and the associated findings with regard to sexual offenders are highlighted, as research indicates that many of the proposed differences in brain structure and function are not unique to this population. We further highlight several limitations to using neuroimaging studies to examine this population of interest, including publication bias, small sample size, underpowered studies, and all-male samples. As these results are mixed and findings are not seemingly unique to sexual offenders, we suggest future sexual offender research may benefit from focusing on more financially feasible options, such as neuropsychological assessment approaches, to assess for and attend to offenders' criminogenic and rehabilitative/therapeutic needs in alignment with the risk-need-responsivity model.

Longitudinal Prediction of Infant Diffusion MRI Data via Graph Convolutional Adversarial Networks

Missing data is a common problem in longitudinal studies due to subject dropouts and failed scans. We present a graph-based convolutional neural network to predict missing diffusion MRI data. In particular, we consider the relationships between sampling points in the spatial domain and the diffusion wave-vector domain to construct a graph. We then use a graph convolutional network to learn the non-linear mapping from available data to missing data. Our method harnesses a multi-scale residual architecture with adversarial learning for prediction with greater accuracy and perceptual quality. Experimental results show that our method is accurate and robust in the longitudinal prediction of infant brain diffusion MRI data.

Spherical U-Net on Cortical Surfaces: Methods and Applications

Convolutional Neural Networks (CNNs) have been providing the state-of-the-art performance for learning-related problems involving 2D/3D images in Euclidean space. However, unlike in the Euclidean space, the shapes of many structures in medical imaging have a spherical topology in a manifold space, e.g., brain cortical or subcortical surfaces represented by triangular meshes, with large inter-subject and intra-subject variations in vertex number and local connectivity. Hence, there is no consistent neighborhood definition and thus no straightforward convolution/transposed convolution operations for cortical/subcortical surface data. In this paper, by leveraging the regular and consistent geometric structure of the resampled cortical surface mapped onto the spherical space, we propose a novel convolution filter analogous to the standard convolution on the image grid. Accordingly, we develop corresponding operations for convolution, pooling, and transposed convolution for spherical surface data and thus construct spherical CNNs. Specifically, we propose the Spherical U-Net architecture by replacing all operations in the standard U-Net with their spherical operation counterparts. We then apply the Spherical U-Net to two challenging and neuroscientifically important tasks in infant brains: cortical surface parcellation and cortical attribute map development prediction. Both applications demonstrate the competitive performance in the accuracy, computational efficiency, and effectiveness of our proposed Spherical U-Net, in comparison with the state-of-the-art methods.

Construction of 4D infant cortical surface atlases with sharp folding patterns via spherical patch-based group-wise sparse representation

4D (spatial + temporal) infant cortical surface atlases covering dense time points are highly needed for understanding dynamic early brain development. In this article, we construct a set of 4D infant cortical surface atlases with longitudinally consistent and sharp cortical attribute patterns at 11 time points in the first six postnatal years, that is, at 1, 3, 6, 9, 12, 18, 24, 36, 48, 60, and 72 months of age, which is targeted for better normalization of the dynamic changing early brain cortical surfaces. To ensure longitudinal consistency and unbiasedness, we adopt a two-stage group-wise surface registration. To preserve sharp cortical attribute patterns on the atlas, instead of simply averaging over the coregistered cortical surfaces, we leverage a spherical patch-based sparse representation using the augmented dictionary to overcome the potential registration errors. Our atlases provide not only geometric attributes of the cortical folding, but also cortical thickness and myelin content. Therefore, to address the consistency across different cortical attributes on the atlas, instead of sparsely representing each attribute independently, we jointly represent all cortical attributes with a group-wise sparsity constraint. In addition, to further facilitate region-based analysis using our atlases, we have also provided two widely used parcellations, that is, FreeSurfer parcellation and multimodal parcellation, on our 4D infant cortical surface atlases. Compared to cortical surface atlases constructed with other methods, our cortical surface atlases preserve sharper cortical folding attribute patterns, thus leading to better accuracy in registration of individual infant cortical surfaces to the atlas.

Infant Brain Development Prediction With Latent Partial Multi-View Representation Learning

The early postnatal period witnesses rapid and dynamic brain development. However, the relationship between brain anatomical structure and cognitive ability is still unknown. Currently, there is no explicit model to characterize this relationship in the literature. In this paper, we explore this relationship by investigating the mapping between morphological features of the cerebral cortex and cognitive scores. To this end, we introduce a multi-view multi-task learning approach to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously. Accordingly, we establish a novel model, latent partial multi-view representation learning. Our approach regards data from different time-points as different views and constructs a latent representation to capture the complementary information from incomplete time-points. The latent representation explores the complementarity across different time-points and improves the accuracy of prediction. The minimization problem is solved by the alternating direction method of multipliers. Experimental results on both synthetic and real data validate the effectiveness of our proposed algorithm.

A computational method for longitudinal mapping of orientation-specific expansion of cortical surface in infants

The cortical surface of the human brain expands dynamically and regionally heterogeneously during the first postnatal year. As all primary and secondary cortical folds as well as many tertiary cortical folds are well established at term birth, the cortical surface area expansion during this stage is largely driven by the increase of surface area in two orthogonal orientations in the tangent plane: 1) the expansion parallel to the folding orientation (i.e., increasing the lengths of folds) and 2) the expansion perpendicular to the folding orientation (i.e., increasing the depths of folds). This information would help us better understand the mechanisms of cortical development and provide important insights into neurodevelopmental disorders, but still remains largely unknown due to lack of dedicated computational methods. To address this issue, we propose a novel method for longitudinal mapping of orientation-specific expansion of cortical surface area in these two orthogonal orientations during early infancy. First, to derive the two orientation fields perpendicular and parallel to cortical folds, we propose to adaptively and smoothly fuse the gradient field of sulcal depth and also the maximum principal direction field, by leveraging their region-specific reliability. Specifically, we formulate this task as a discrete labeling problem, in which each vertex is assigned to an orientation label, and solve it by graph cuts. Then, based on the computed longitudinal deformation of the cortical surface, we estimate the Jacobian matrix at each vertex by solving a least-squares problem and derive its corresponding stretch tensor. Finally, to obtain the orientation-specific cortical surface expansion, we project the stretch tensor into the two orthogonal orientations separately. We have applied the proposed method to 30 healthy infants, and for the first time we revealed the orientation-specific longitudinal cortical surface expansion maps during the first postnatal year.

Computational neuroanatomy of baby brains: A review

The first postnatal years are an exceptionally dynamic and critical period of structural, functional and connectivity development of the human brain. The increasing availability of non-invasive infant brain MR images provides unprecedented opportunities for accurate and reliable charting of dynamic early brain developmental trajectories in understanding normative and aberrant growth. However, infant brain MR images typically exhibit reduced tissue contrast (especially around 6 months of age), large within-tissue intensity variations, and regionally-heterogeneous, dynamic changes, in comparison with adult brain MR images. Consequently, the existing computational tools developed typically for adult brains are not suitable for infant brain MR image processing. To address these challenges, many infant-tailored computational methods have been proposed for computational neuroanatomy of infant brains. In this review paper, we provide a comprehensive review of the state-of-the-art computational methods for infant brain MRI processing and analysis, which have advanced our understanding of early postnatal brain development. We also summarize publically available infant-dedicated resources, including MRI datasets, computational tools, grand challenges, and brain atlases. Finally, we discuss the limitations in current research and suggest potential future research directions.