Transcription Factor MAZ Potentiates the Upregulated NEIL3-mediated Aerobic Glycolysis, Thereby Promoting Angiogenesis in Hepatocellular Carcinoma.

BACKGROUND: Hepatocellular carcinoma (HCC) is characterized by high vascularity and notable abnormality of blood vessels, where angiogenesis is a key process in tumorigenesis and metastasis. The main functions of Nei Like DNA Glycosylase 3 (NEIL3) include DNA alcoholization repair, immune response regulation, nervous system development and function, and DNA damage signal transduction. However, the underlying mechanism of high expression NEIL3 in the development and progression of HCC and whether the absence or silencing of NEIL3 inhibits the development of cancer remain unclear. Therefore, a deeper understanding of the mechanisms by which increased NEIL3 expression promotes cancer development is needed. METHODS: Expression of NEIL3 and its upstream transcription factor MAZ in HCC tumor tissues was analyzed in bioinformatics efforts, while validation was done by qRT-PCR and western blot in HCC cell lines. The migration and tube formation capacity of HUVEC cells were analyzed by Transwell and tube formation assays. Glycolytic capacity was analyzed by extracellular acidification rate, glucose uptake, and lactate production levels. Chromatin immunoprecipitation (ChIP) and dual-luciferase reporter gene assays were utilized to investigate specific interactions between MAZ and NEIL3. RESULTS: NEIL3 and MAZ were substantially upregulated in HCC tissues and cells. NEIL3 was involved in modulating the glycolysis pathway, suppression of which reversed the stimulative impact of NEIL3 overexpression on migration and angiogenesis in HUVEC cells. MAZ bound to the promoter of NEIL3 to facilitate NEIL3 transcription. Silencing MAZ reduced NEIL3 expression and suppressed the glycolysis pathway, HUVEC cell migration, and angiogenesis. CONCLUSION: MAZ potentiated the upregulated NEIL3-mediated glycolysis pathway and HCC angiogenesis. This study provided a rationale for the MAZ/NEIL3/glycolysis pathway as a possible option for anti-angiogenesis therapy in HCC.

Multivariate Time Series Forecasting Using Multiscale Recurrent Networks With Scale Attention and Cross-Scale Guidance.

Multivariate time series (MTS) forecasting is considered as a challenging task due to complex and nonlinear interdependencies between time steps and series. With the advance of deep learning, significant efforts have been made to model long-term and short-term temporal patterns hidden in historical information by recurrent neural networks (RNNs) with a temporal attention mechanism. Although various forecasting models have been developed, most of them are single-scale oriented, resulting in scale information loss. In this article, we seamlessly integrate multiscale analysis into deep learning frameworks to build scale-aware recurrent networks and propose two multiscale recurrent network (MRN) models for MTS forecasting. The first model called MRN-SA adopts a scale attention mechanism to dynamically select the most relevant information from different scales and simultaneously employs input attention and temporal attention to make predictions. The second one named as MRN-CSG introduces a novel cross-scale guidance mechanism to exploit the information from coarse scale to guide the decoding process at fine scale, which results in a lightweight and more easily trained model without obvious loss of accuracy. Extensive experimental results demonstrate that both MRN-SA and MRN-CSG can achieve state-of-the-art performance on five typical MTS datasets in different domains. The source codes will be publicly available at https://github.com/qguo2010/MRN.

Pact-Net: Parallel CNNs and Transformers for medical image segmentation.

BACKGROUND AND OBJECTIVE: The image segmentation of diseases can help clinical diagnosis and treatment in medical image analysis. Because medical images usually have low contrast and large changes in the size and shape of some structures, this will lead to over-segmentation and under-segmentation. These problems are particularly evident in the segmentation of skin damage. The blurring of the boundary in skin images and the specificity of patients will further increase the difficulty of skin lesion segmentation. Currently, most researchers use deep learning networks to solve these skin segmentation problems. However, traditional convolution methods often fail to obtain satisfactory segmentation performance due to their shortcomings in obtaining global features. Recently, Transformers with good global information extraction ability has achieved satisfactory results in computer vision, which brings new solutions to optimize the model of medical image segmentation further. METHODS: To extract more features related to medical image segmentation and effectively use features to further optimize the skin image segmentation model, we designed a network that combines CNNs and Transformers to improve local and global features, called Parallel CNNs and Transformers for Medical Image Segmentation (Pact-Net). Specifically, due to the advantages of Transformers in extracting global information, we create a novel fusion module CSMF, which uses channel and spatial attention mechanism and multi-scale mechanism to effectively fuse the global information extracted by Transformers into the local features extracted by CNNs. Therefore, our Pact-Net dual-branch runs in parallel to effectively capture global and local information. RESULTS: Our Pact-Net exceeds the models submitted on the three datasets ISIC 2016, ISIC 2017 and ISIC 2018, and the indicators required for the datasets reach 86.95%, 79.31% and 84.14%, respectively. We also conducted medical image segmentation experiments on cell and polyp datasets to evaluate the robustness, learning and generalization ability of the network. The ablation study of each part of Pact-Net proves the validity of each component, and the comparison with state-of-the-art methods on different indicators proves the predominance of the network. CONCLUSIONS: This paper uses the advantages of CNNs and Transformers in extracting local and global features, and further integrates features for skin lesion segmentation. Compared with the state-of-the-art methods, Pact-Net can achieve the most advanced segmentation ability on the skin lesion segmentation dataset, which can help doctors diagnose and treat diseases.

Shape-Aware Joint Distribution Alignment for Cross-Domain Image Segmentation.

We present an unsupervised domain adaptation method for image segmentation which aligns high-order statistics, computed for the source and target domains, encoding domain-invariant spatial relationships between segmentation classes. Our method first estimates the joint distribution of predictions for pairs of pixels whose relative position corresponds to a given spatial displacement. Domain adaptation is then achieved by aligning the joint distributions of source and target images, computed for a set of displacements. Two enhancements of this method are proposed. The first one uses an efficient multi-scale strategy that enables capturing long-range relationships in the statistics. The second one extends the joint distribution alignment loss to features in intermediate layers of the network by computing their cross-correlation. We test our method on the task of unpaired multi-modal cardiac segmentation using the Multi-Modality Whole Heart Segmentation Challenge dataset and prostate segmentation task where images from two datasets are taken as data in different domains. Our results show the advantages of our method compared to recent approaches for cross-domain image segmentation. Code is available at https://github.com/WangPing521/Domain_adaptation_shape_prior.

CAT: Constrained Adversarial Training for Anatomically-Plausible Semi-Supervised Segmentation.

Deep learning models for semi-supervised medical image segmentation have achieved unprecedented performance for a wide range of tasks. Despite their high accuracy, these models may however yield predictions that are considered anatomically impossible by clinicians. Moreover, incorporating complex anatomical constraints into standard deep learning frameworks remains challenging due to their non-differentiable nature. To address these limitations, we propose a Constrained Adversarial Training (CAT) method that learns how to produce anatomically plausible segmentations. Unlike approaches focusing solely on accuracy measures like Dice, our method considers complex anatomical constraints like connectivity, convexity, and symmetry which cannot be easily modeled in a loss function. The problem of non-differentiable constraints is solved using a Reinforce algorithm which enables to obtain a gradient for violated constraints. To generate constraint-violating examples on the fly, and thereby obtain useful gradients, our method adopts an adversarial training strategy which modifies training images to maximize the constraint loss, and then updates the network to be robust to these adversarial examples. The proposed method offers a generic and efficient way to add complex segmentation constraints on top of any segmentation network. Experiments on synthetic data and four clinically-relevant datasets demonstrate the effectiveness of our method in terms of segmentation accuracy and anatomical plausibility.

SEVs-mediated miR-6750 transfer inhibits pre-metastatic niche formation in nasopharyngeal carcinoma by targeting M6PR.

Reliable detection of circulating small extracellular vesicles (SEVs) and their miRNA cargo has been needed to develop potential specific non-invasive diagnostic and therapeutic marker for cancer metastasis. Here, we detected miR-6750, the precise molecular function of which was largely unknown, was significantly enriched in serum-SEVs from normal volunteers vs. patients with nasopharyngeal carcinoma (NPC). And we determined that miR-6750-SEVs attenuated NPC metastasis. Subsequently, miR-6750-SEVs was proven to inhibit angiogenesis and activate macrophage toward to M1 phenotype to inhibit pre-metastatic niche formation. After analyzing the expression level of miR-6750 in NPC cells, HUVECs and macrophage, we found that once miR-6750 level in NPC cells was close to or higher than normal nasopharyngeal epithelial cells (NP69), miR-6750-SEVs would be transferred from NPC cells to macrophage and then to HUVECs to modulate metastatic niche. Moreover, in vitro assays and BALB/c mouse tumor models revealed that miR-6750 directly targeted mannose 6-phosphate receptor (M6PR). Taken together, our findings revealed that miR-6750-M6PR axis can mediate NPC metastasis by remodeling tumor microenvironment (TME) via SEVs, which give novel sights to pathogenesis of NPC.

COVID19-MLSF: A multi-task learning-based stock market forecasting framework during the COVID-19 pandemic.

The sudden outbreak of COVID-19 has dramatically altered the state of the global economy, and the stock market has become more volatile and even fallen sharply as a result of its negative impact, heightening investors' apprehension regarding the correlation between unexpected events and stock market volatility. Additionally, internal and external characteristics coexist in the stock market. Existing research has struggled to extract more effective stock market features during the COVID-19 outbreak using a single time-series neural network model. This paper presents a framework for multitasking learning-based stock market forecasting (COVID-19-MLSF), which can extract the internal and external features of the stock market and their relationships effectively during COVID-19.The innovation comprises three components: designing a new market sentiment index (NMSI) and COVID-19 index to represent the external characteristics of the stock market during the COVID-19 pandemic. Besides, it introduces a multi-task learning framework to extract global and local features of the stock market. Moreover, a temporal convolutional neural network with a multi-scale attention mechanism is designed (MA-TCN) alongside a Multi-View Convolutional-Bidirectional Recurrent Neural Network with Temporal Attention (MVCNN-BiLSTM-Att), adjusting the model to account for the changing status of COVID-19 and its impact on the stock market. Experiments indicate that our model achieves superior performance both in terms of predicting the accuracy of the China CSI 300 Index during the COVID-19 period and in terms of sing market trading.

Neural Modeling of Portrait Bas-Relief From a Single Photograph.

In this paper, we present an end-to-end neural solution to model portrait bas-relief from a single photograph, which is cast as a problem of image-to-depth translation. The main challenge is the lack of bas-relief data for network training. To solve this problem, we propose a semi-automatic pipeline to synthesize bas-relief samples. The main idea is to first construct normal maps from photos, and then generate bas-relief samples by reconstructing pixel-wise depths. In total, our synthetic dataset contains 23 k pixel-wise photo/bas-relief pairs. Since the process of bas-relief synthesis requires a certain amount of user interactions, we propose end-to-end solutions with various network architectures, and train them on the synthetic data. We select the one that gave the best results through qualitative and quantitative comparisons. Experiments on numerous portrait photos, comparisons with state-of-the-art methods and evaluations by artists have proven the effectiveness and efficiency of the selected network.

SNHG3 regulates NEIL3 via transcription factor E2F1 to mediate malignant proliferation of hepatocellular carcinoma.

The involvement of small nucleolar RNA host gene 3 (SNHG3) in cancer regulation has been reported. This study attempted to deeply investigate the molecular regulatory mechanism of SNHG3 on malignant progression of hepatocellular carcinoma (HCC). According to TCGA analysis, high SNHG3 expression was a risk factor for poor prognosis of HCC patients. Therefore, we further detected the mRNA level of SNHG3 in HCC tissue and cells. It was found that SNHG3 was upregulated in HCC tissue and cells. Afterwards, CCK-8 and flow cytometry assays further proved that silencing SNHG3 inhibited HCC cell proliferation while inducing cell apoptosis and G0/G1 phase arrest. It was also attested in vivo experiments that silencing SNHG3 could reduce the volume and weight of tumors and downregulate the Ki-67 expression to suppress HCC tumor growth. Next, it was discovered that SNHG3 increased the binding of E2F1 and NEIL3 promoter region, thereby activating the transcription feature of NEIL3. Lastly, rescue assays indicated that NEIL3 participated in SNHG3-mediated HCC cell cycle, apoptosis and proliferation. All in all, this study revealed the specific regulatory mechanism of SNHG3 in HCC to enable SNHG3 a hopeful marker for HCC diagnosis and treatment.

Fast Generation of Superpixels With Lattice Topology.

Serving as an essential step for many applications of image processing, superpixel generation has attracted a lot of attentions. Most existing superpixel generation algorithms focus on the boundary adherence and compactness of the superpixels, but ignore the topological consistency between the superpixels, which severely limites their applications in the subsequent tasks, especially in the CNN based image processing tasks. In this paper, we present a fast lattice superpixel generation algorithm, which can generate superpixels with lattice topology like the original pixels. We also propose a local similarity loss function to improve the segmentation accuracy of the generated lattice superpixels. The whole algorithm is parallelly implemented on GPU. We perform extensive experiments on three datasets (i.e., BSDS500, NYUv2 and VOC) to verify the efficacy of our algorithm. The experimental results show that our method achieves competitive results compared to the state-of-the-art methods.

Mechanism of RNA circHIPK3 Involved in Resistance of Lung Cancer Cells to Gefitinib.

To study the mechanism of circular ribonucleic acid (RNA) circHIPK3 involved in the resistance of lung cancer cells to gefitinib, 110 patients with lung cancer were recruited as the research objects, and the tumor tissue and para-cancerous tissue of each patient's surgical specimens were collected and paraffinized to detect the expression of circHIPK3 in different tissues. Gefitinib drug-resistant cell line of lung cancer was constructed with gefitinib to detect cell apoptosis under different conditions. As a result, the relative expression of circHIPK3 in patients with tumor diameter no less than 3 cm was dramatically inferior to that in patients with tumor diameter less than 3 cm (P < 0.05). The relative expression of circHIPK3 in patients with TNM stage II/III was dramatically inferior to that in patients with tumor, node, and metastasis (TNM) stage I (P < 0.05). Expression of circHIPK3 in patients with lymph node metastasis was dramatically inferior to that in patients without lymph node metastasis (P < 0.05). Of the lung cancer tissues of patients with different TNM stages, only six patients had high expression, and the remaining 104 patients had low expression. Moreover, electrophoresis revealed that circHIPK3 can only be amplified in cDNA, but not in gDNA. Gefitinib-mediated apoptosis rate of lung cancer drug-resistant cell lines decreased notably. In summary, the circular RNA circHIPK3 may have a notably low expression in lung cancer tissues, whose low expression had a certain enhancement effect on the drug resistance of lung adenocarcinoma cells to gefitinib.

Self-paced and self-consistent co-training for semi-supervised image segmentation.

Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent co-training method. To help distillate information from unlabeled images, we first design a self-paced learning strategy for co-training that lets jointly-trained neural networks focus on easier-to-segment regions first, and then gradually consider harder ones. This is achieved via an end-to-end differentiable loss in the form of a generalized Jensen Shannon Divergence (JSD). Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy. The robustness of individual models is further improved using a self-ensembling loss that enforces their prediction to be consistent across different training iterations. We demonstrate the potential of our method on three challenging image segmentation problems with different image modalities, using a small fraction of labeled data. Results show clear advantages in terms of performance compared to the standard co-training baselines and recently proposed state-of-the-art approaches for semi-supervised segmentation.

Developing univariate neurodegeneration biomarkers with low-rank and sparse subspace decomposition.

Cognitive decline due to Alzheimer's disease (AD) is closely associated with brain structure alterations captured by structural magnetic resonance imaging (sMRI). It supports the validity to develop sMRI-based univariate neurodegeneration biomarkers (UNB). However, existing UNB work either fails to model large group variances or does not capture AD dementia (ADD) induced changes. We propose a novel low-rank and sparse subspace decomposition method capable of stably quantifying the morphological changes induced by ADD. Specifically, we propose a numerically efficient rank minimization mechanism to extract group common structure and impose regularization constraints to encode the original 3D morphometry connectivity. Further, we generate regions-of-interest (ROI) with group difference study between common subspaces of Aß+AD and Aß-cognitively unimpaired (CU) groups. A univariate morphometry index (UMI) is constructed from these ROIs by summarizing individual morphological characteristics weighted by normalized difference between Aß+AD and Aß-CU groups. We use hippocampal surface radial distance feature to compute the UMIs and validate our work in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25% reduction in the mean annual change with 80% power and two-tailed P=0.05are 116, 279 and 387 for the longitudinal Aß+AD, Aß+mild cognitive impairment (MCI) and Aß+CU groups, respectively. Additionally, for MCI patients, UMIs well correlate with hazard ratio of conversion to AD (4.3, 95% CI = 2.3-8.2) within 18 months. Our experimental results outperform traditional hippocampal volume measures and suggest the application of UMI as a potential UNB.

Automated coronary artery tree segmentation in coronary CTA using a multiobjective clustering and toroidal model-guided tracking method.

BACKGROUND AND OBJECTIVE: Accurate coronary artery tree segmentation can now be developed to assist radiologists in detecting coronary artery disease. In clinical medicine, the noise, low contrast, and uneven intensity of medical images along with complex shapes and vessel bifurcation structures make coronary artery segmentation challenging. In this work, we propose a multiobjective clustering and toroidal model-guided tracking method that can accurately extract coronary arteries from computed tomography angiography (CTA) imagery. METHODS: Utilizing integrated noise reduction, candidate region detection, geometric feature extraction, and coronary artery tracking techniques, a new segmentation framework for 3D coronary artery trees is presented. The candidate regions are extracted using a multiobjective clustering method, and the coronary arteries are tracked by a toroidal model-guided tracking method. RESULTS: The qualitative and quantitative results demonstrate the effectiveness of the presented framework, which achieves better performance than the compared segmentation methods in three widely used evaluation indices: the Dice similarity coefficient (DSC), Jaccard index and Recall across the CTA data. The proposed method can accurately identify the coronary artery tree with a mean DSC of 84%, a Jaccard index of 74%, and a Recall of 93%. CONCLUSIONS: The proposed segmentation framework effectively segments the coronary tree from the CTA volume, which improves the accuracy of 3D vascular tree segmentation.

Chromatin 3D structure reconstruction with consideration of adjacency relationship among genomic loci.

BACKGROUND: Chromatin 3D conformation plays important roles in regulating gene or protein functions. High-throughout chromosome conformation capture (3C)-based technologies, such as Hi-C, have been exploited to acquire the contact frequencies among genomic loci at genome-scale. Various computational tools have been proposed to recover the underlying chromatin 3D structures from in situ Hi-C contact map data. As connected residuals in a polymer, neighboring genomic loci have intrinsic mutual dependencies in building a 3D conformation. However, current methods seldom take this feature into account. RESULTS: We present a method called ShNeigh, which combines the classical MDS technique with local dependence of neighboring loci modeled by a Gaussian formula, to infer the best 3D structure from noisy and incomplete contact frequency matrices. We validated ShNeigh by comparing it to two typical distance-based algorithms, ShRec3D and ChromSDE. The comparison results on simulated Hi-C dataset showed that, while keeping the high-speed nature of classical MDS, ShNeigh can recover the true structure better than ShRec3D and ChromSDE. Meanwhile, ShNeigh is more robust to data noise. On the publicly available human GM06990 Hi-C data, we demonstrated that the structures reconstructed by ShNeigh are more reproducible between different restriction enzymes than by ShRec3D and ChromSDE, especially at high resolutions manifested by sparse contact maps, which means ShNeigh is more robust to signal coverage. CONCLUSIONS: Our method can recover stable structures in high noise and sparse signal settings. It can also reconstruct similar structures from Hi-C data obtained using different restriction enzymes. Therefore, our method provides a new direction for enhancing the reconstruction quality of chromatin 3D structures.

Cortical thickness computation by solving tetrahedron-based harmonic field.

Cortical thickness computation in magnetic resonance imaging (MRI) is an important method to study the brain morphological changes induced by neurodegenerative diseases. This paper presents an algorithm of thickness measurement based on a volumetric Laplacian operator (VLO), which is able to capture accurately the geometric information of brain images. The proposed algorithm is a novel three-step method: 1) The rule of parity and the shrinkage strategy are combined to detect and fix the intersection error regions between the cortical surface meshes separated by FreeSurfer software and the tetrahedral mesh is constructed which reflects the original morphological features of the cerebral cortex, 2) VLO and finite element method are combined to compute the temperature distribution in the cerebral cortex under the Dirichlet boundary conditions, and 3) the thermal gradient line is determined based on the constructed local isothermal surfaces and linear geometric interpolation results. Combined with half-face data storage structure, the cortical thickness can be computed accurately and effectively from the length of each gradient line. With the obtained thickness, we set experiments to study the group differences among groups of Alzheimer's disease (AD, N = 110), mild cognitive impairment (MCI, N = 101) and healthy control people (CTL, N = 128) by statistical analysis. The results show that the q-value associated with the group differences is 0.0458 between AD and CTL, 0.0371 between MCI and CTL, and 0.0044 between AD and MCI. Practical tests demonstrate that the algorithm of thickness measurement has high efficiency and is generic to be applied to various biological structures that have internal and external surfaces.

Portrait Relief Modeling from a Single Image.

We present a novel solution to enable portrait relief modeling from a single image. The main challenges are geometry reconstruction, facial details recovery and depth structure preservation. Previous image-based methods are developed for portrait bas-relief modeling in 2.5D form, but not adequate for 3D-like high relief modeling with undercut features. In this paper, we propose a template-based framework to generate portrait reliefs of various forms. Our method benefits from Shape-from-Shading (SFS). Specifically, we use bi-Laplacian mesh deformation to guide the relief modeling. Given a portrait image, we first use a template face to fit the portrait. We then apply bi-Laplacian mesh deformation to align the facial features. Afterwards, SFS-based reconstruction with a few user interactions is used to optimize the face depth, and create a relief with similar appearance to the input. Both depth structures and geometric details can be well constructed in the final relief. Experiments and comparisons to other methods demonstrate the effectiveness of the proposed method.

Mapping hemispheric asymmetries of the macaque cerebral cortex during early brain development.

Studying cortical hemispheric asymmetries during the dynamic early postnatal stages in macaque monkeys (with close phylogenetic relationship to humans) would increase our limited understanding on the possible origins, developmental trajectories, and evolutional mechanisms of brain asymmetries in nonhuman primates, but remains a blind spot to the community. Via cortical surface-based morphometry, we comprehensively analyze hemispheric structural asymmetries in 134 longitudinal MRI scans from birth to 20 months of age from 32 healthy macaque monkeys. We reveal that most clusters of hemispheric asymmetries of cortical properties, such as surface area, cortical thickness, sulcal depth, and vertex positions, expand in the first 4 months of life, and evolve only moderately thereafter. Prominent hemispheric asymmetries are found at the inferior frontal gyrus, precentral gyrus, posterior temporal cortex, superior temporal gyrus (STG), superior temporal sulcus (STS), and cingulate cortex. Specifically, the left planum temporale and left STG consistently have larger area and thicker cortices than those on the right hemisphere, while the right STS, right cingulate cortex, and right anterior insula are consistently deeper than the left ones, partially consistent with the findings in human infants and adults. Our results thus provide a valuable reference in studying early brain development and evolution.

CHARTING DEVELOPMENT-BASED JOINT PARCELLATION MAPS OF HUMAN AND MACAQUE BRAINS DURING INFANCY.

Comparative characterization of early brain development between human and macaque using neuroimaging data is crucial to understand the mechanisms of brain development and evolution. To this end, joint cortical parcellation maps of human and macaque infant brains with corresponding regions are highly desirable, since they provide basic cortical parcels for both region-based and network-based studies of two closely-related species. To address this issue, we propose to leverage developmental patterns of cortical properties of both human and macaque infants for creating joint parcellation maps with inter-species comparability. The motivation is that the developmental patterns of cortical properties indicate underlying rapid changes of microstructures, which determine the molecular and functional principles of the cortex. Thus, developmental patterns are well suitable for defining distinct cortical regions in both structures and functions. To comprehensively capture the similarities of developmental patterns of vertices on cortical surfaces, for each species, we first construct two complementary similarity matrices: a low-order matrix and a high-order matrix. Then, we non-linearly fuse these four matrices together as a single matrix in a hierarchical manner, thus capturing the common and complementary information of both human and macaque infants. Finally, based on the fused similarity matrix, we apply the spectral clustering to derive the joint parcellation maps. By applying our method to 210 longitudinal human infant MRI scans and 140 longitudinal macaque infant MRI scans, we generate the first biologically-meaningful joint parcellation maps of human and macaque infants.

Fetal cortical surface atlas parcellation based on growth patterns.

Defining anatomically and functionally meaningful parcellation maps on cortical surface atlases is of great importance in surface-based neuroimaging analysis. The conventional cortical parcellation maps are typically defined based on anatomical cortical folding landmarks in adult surface atlases. However, they are not suitable for fetal brain studies, due to dramatic differences in brain size, shape, and properties between adults and fetuses. To address this issue, we propose a novel data-driven method for parcellation of fetal cortical surface atlases into distinct regions based on the dynamic "growth patterns" of cortical properties (e.g., surface area) from a population of fetuses. Our motivation is that the growth patterns of cortical properties indicate the underlying rapid changes of microstructures, which determine the molecular and functional principles of the cortex. Thus, growth patterns are well suitable for defining distinct cortical regions in development, structure, and function. To comprehensively capture the similarities of cortical growth patterns among vertices, we construct two complementary similarity matrices. One is directly based on the growth trajectories of vertices, and the other is based on the correlation profiles of vertices' growth trajectories in relation to a set of reference points. Then, we nonlinearly fuse these two similarity matrices into a single one, which can better capture both their common and complementary information than by simply averaging them. Finally, based on this fused similarity matrix, we perform spectral clustering to divide the fetal cortical surface atlases into distinct regions. By applying our method on 25 normal fetuses from 26 to 29 gestational weeks, we construct age-specific fetal cortical surface atlases equipped with biologically meaningful parcellation maps based on cortical growth patterns. Importantly, our generated parcellation maps reveal spatially contiguous, hierarchical and bilaterally relatively symmetric patterns of fetal cortical surface development.