Journals [1-97] (including Neuron, Nature Methods, Nature Biomedical Engineering, Nature Human Behaviour, Nature Neuroscience, Nature Communications, PNAS, NeuroImage, Cell Reports, IEEE TMI, etc.)
Conferences/Abstracts [98-140] (including ICCV, MICCAI, ISMRM, OHBM, ISBI, EMBC, BioMag, etc.)
Theses/Dissertations [141-142]
[1] “Each included structural scan had T1w and T2w images, which we processed with iBEAT V2.0.”
[2] “For each scan, structural MRI was processed with the infant Brain Extraction and Analysis Toolbox (iBEAT v2.0).”
[3] “For the BCP dataset, structural MRI images were preprocessed using the Infant Brain Extraction and Analysis Toolkit (iBEAT V2.0 Cloud), including N3 field inhomogeneity correction, skull stripping, T1-T2 alignment, and tissue segmentation.”
[4] “For participants aged less than 2 years, structural MRI data were processed using the iBEAT v2.0 pipeline, except for neonates from the developing HCP (dHCP) study, who were processed using the dHCP pipeline. The iBEAT pipeline mainly included intensity inhomogeneity correction of T1-images and, when available, T2-images; brain extraction; automatic cerebellar removal, followed by slice-by-slice manual correction when removal was incomplete; tissue segmentation; and cortical surface reconstruction, including topological correction and reconstruction of the inner and outer cortical surfaces.”
[5] “MR images were exported to the local PACS system to screen for incidental findings needing medical attention by one neuroradiologist, and then exported for further processing using iBEAT V2.0 software (Developing Brain Computing Lab and Baby Brain Mapping Lab) (Wang et al., 2023).”
[6] “T1- and T2-weighted images for each participant were rigidly aligned and tissue segmentation into gray and white matter was performed with iBEAT V2.0, followed by manual correction in ITKgray.”
[7] “The image resolution is isotropic 0.8 mm, and all images are bias-corrected and skull-stripped using the public infant brain extraction and analysis toolbox iBEAT V2.0 (Wang et al., 2023).”
[8] “All MR images were processed using an established structural computational pipeline (Wang et al., 2023), which includes motion and intensity inhomogeneity correction, skull stripping, tissue segmentation, reconstruction of left and right hemispheres, and inner and outer cortical surface reconstruction.”
[9] “Qualitychecked BCP images were then minimally preprocessed using iBEAT V2.0, a state-of-the-art pipeline specifically optimized for infant and toddler MRI data.”
[10] “All the scans were processed with the infant brain extraction and analysis toolbox (iBEAT V2.0) (http://www.ibeat.cloud/).”
[11] “Since Infant FreeSurfer, FreeSurfer, and iBEAT V2.0 are the encapsulated tools with fixed parameters or pretrained models specific to certain age groups, they are not retrained. We apply them directly to the testing data following their standard inference protocols.”
[12] “Rs-fMRI is a powerful non-invasive tool capable of characterizing the maturation of brain functional networks, and an infant-dedicated surface-based MRI processing was used to process structural MRI and rs-fMRI data (Hu et al., 2022; F. Wang et al., 2023; L. Wang et al., 2023).”
[13] “The structural MRIs were preprocessed via cortical surface-based processing pipelines, including skull stripping, tissue segmentation, cortical reconstruction, and cortical surface measurement calculation. Code availability: iBEAT pipeline v1.0.0 (https://github.com/iBEAT-V2/iBEAT-V2.0-Docker)”
[14] “3D T1-weighted images were processed using the Infant Brain Extraction and Analysis Toolkit toolbox (iBEAT), which has been specifically developed for anatomical segmentation of infant brain MRI during the first year of life.”
[15] “For comparison, we also present the average cortical thickness derived from the native pipeline of iBEAT V2.0...”
[16] “T1/T2 images were run through iBeat version 2.0 via the container available on GitHub (Wang et al., 2023), to produce segmentations for grey/white/CSF.”
[17] “This approach was complemented with segmentation obtained with iBEAT pipeline (version 2.0) (Wang et al., 2023). Tissue segmentation maps generated using iBEAT and DrawEM were systematically reviewed through visual quality control. Manual corrections were performed in about 25% of segmentations.”
[18] “For high-quality pseudo tissue labels during meta-training, we apply the automated iBEAT pipeline [19] to these pre-processed images. In the meta-test phase, iBEAT is similarly applied, followed by expert manual refinements to produce gold-standard annotations.”
[19] “Briefly, we used the iBEAT V2.0 toolbox to process brain structural images, reconstruct and parcellate cortical surfaces (Wang et al., 2023; Zhao et al., 2021) based on for cortical surface reconstruction, and then parcellated the cerebral cortex into 68 regions of interest following the FreeSurfer Desikan-Killiany atlas (Desikan et al., 2006).”
[20] “A second segmentation was done using both T1- and T2-weighted anatomical images and the brain extraction toolbox (Brain Extraction and Analysis Toolbox, iBEAT, v-2.0 cloud processing, https://ibeat.wildapricot.org/).”
[21] “An initial segmentation of gray and white matter was generated from the T1-weighted brain volume using infant FreeSurfer’s automatic segmentation code (infant-recon-all; version freesurfer-linux-centos7_x86_64-infant-dev- 4a14499-20210109; https://surfer.nmr.mgh.harvard.edu/fswiki/infantFS45). (2) A second segmentation was done using both the T1- and T2-weighted anatomical images and the brain extraction toolbox (Brain Extraction and Analysis Toolbox, iBEAT, v-2.0 cloud processing, https://ibeat.wildapricot.org/). iBEAT V2.0 was specifically designed for processing infant brain MRI data (0-2 years), using contrasts properties of both T1w and T2w images, and employs deep learning techniques trained on infant data to handle the unique challenges of low contrast between gray and white matter in developing brains. Through visual inspection, we determined that iBEAT provided a more accurate segmentation of the gray-white matter boundaries in our low-contrast infant images compared to the infant FreeSurfer approach.”
[22] “T1-weighted MPRAGE images of adults were segmented by the T1-multiatlas toolbox of MRICloud..., and those of infants were segmented by iBEAT V2.0 to generate gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) masks in T1 space.”
[23] “The resulting images were used to segment the different brain tissues and compartments by coupling two automatic tools dedicated to the neonatal brain: DrawEM (Developing brain Region Annotation With Expectation-Maximization) and iBEAT (infant Brain Extraction and Analysis Toolbox).”
[24] “Image processing for both datasets included the following: (a) skull stripping using the FMRIB Software Library brain extraction tool (ZJU) and iBEAT version 2 (25) (BCP) for optimal performance.”
[25] “Neonatal 3D-SPACE anatomical images underwent hippocampal extraction and tissue segmentation using the Infant Brain Extraction and Analysis Toolbox (iBEAT V2.0, http://www.ibeat.cloud).”
[26] “Due to the absence of ground-truth labels for the iSeg-19 validation set, we assess the performance of LODi through a qualitative comparison against the iBEAT V2.0 Cloud (Wang et al., 2023) model.”
[27] “Source images were processed using the Infant Brain Extraction and Analysis Toolbox (iBEAT v2.0 Cloud; http://www.ibeat.cloud), which includes pipelines specifically designed for infant MRI and fully described in the original report.”
[28] “For participants aged 0–24 months, we used the iBEAT V2.0 pipelines. Compared with alternative approaches, this pipeline is optimized for preprocessing early-age neuroimaging data with advanced algorithms and shows superior performance in tissue segmentation and cortical reconstruction.”
[29] “We processed these images using iBEAT V2.0 Cloud, an infant-specific computational pipeline (available at http://www.ibeat.cloud) (Wang et al., 2023).”
[30] “Segmentation processing was performed using iBEAT2 (version 120 [28]). After bias correction, a first segmentation was carried out to generate the brain mask... Within this adjusted brain mask, brain tissues (grey and white matter, cerebrospinal fluid) were segmented (iBEAT2 version 205).”
[31] “To improve tissue classification accuracy, MPRAGE images were submitted in parallel to iBEATv2.0 Docker 1.1.0 [https://github.com/iBEAT-V2/iBEAT-V2.0-Docker], which has been validated for birth to age 6 y.”
[32] “Anatomical annotations for cerebrospinal fluid, gray matter, and white matter were provided by iBEAT V2.0 (Wang et al., 2023b).”
[33] “Structural MR images were processed by iBEAT V2.0 pipeline (http://www.ibeat.cloud).”
[34] “For each scan, brain structural images were processed using the infant Brain Extraction and Analysis Toolbox (iBEAT v.2.0, www.ibeat.cloud). This toolbox segments the brain into grey matter, white matter and cerebrospinal fluid (CSF), and reconstructs the topologically correct and geometrically accurate infant cortical surfaces.”
[35] “Furthermore, we used the officially recommended iBEAT V2.0 pipelines for participants aged from 0–2 years (all from the Baby Connectome Project (BCP)).”
[36] “Particularly, the segmentation task needs ground-truth segmentation maps of brain tissues for training data, and many established tools such as FSL, FreeSurfer, SPM and iBEAT can be used. In this work, we use iBEAT with careful manual verification to generate such ground-truth segmentation maps, aiming to provide more accurate segmentation.”
[37] “Then, we used iBEAT V2.0 to segment the white and gray matter.”
[38] “The final step common across analyses created a transformation into surface space. Surfaces were reconstructed from iBEAT v2.0.”
[39] “iBEATv2 is an integrated pipeline for infant brain analysis with comprehensive postprocessing for obtaining accurate anatomy. For a fair comparison, we only compare the brain tissue segmentation component from iBEATv2.”
[40] “All T1w and T2w MR images were processed using the iBEAT V2.0 infant-specific pipeline [41], which has been validated on over 17,000 infant MRI scans.”
[41] “Tissue volumes (WM, GM, CSF, ventricle and hippocampus) and mean cortical thickness were extracted by iBEAT V2.0.”
[42] “Segmentation of 0–24-month-old T2w brains was performed using iBEAT (http://www.ibeat.cloud/) followed by manual correction...”
[43] “All pediatric images were processed with an infant-dedicated pipeline (http://www.ibeat.cloud/) (Wang et al. (2023)). Destrieux parcellation (Destrieux et al. (2010)) was used to conduct ROI labeling for all the four age groups.”
[44] “CSF time-series was extracted using FSL FMRIB’s Automated Segmentation Tool (FAST), and white matter time-series was extracted following tissue segmentation with the Infant Brain Extraction and Analysis Toolbox (iBEAT; Li et al. 2014, 2015, 2019; Wang et al. 2023).”
[45] “To evaluate VINNA against state-of-the-art traditional segmentation methods, we further process the testing set with the docker version of the iBEAT V2.0 pipeline (Wang et al., 2023) and infantFS (Zöllei et al., 2020).”
[46] “All infant MR images are processed using an established infant-specific computational pipeline iBEAT V2.0 (www.ibeat.cloud) to reconstruct the cortical surfaces and generate the vertex-wise cortical features, including the surface area and the cortical thickness.”
[47] “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).”
[48] “The next best performing model (iBEATv2) yielded an average Dice of 0.949 ± 0.017.”
[49] “As a note, we also tested the iBEAT2 BE method. These limitations, therefore, precluded the use of this method and its comparison to others.”
[50] “The T1 and T2 scans were processed using Infant Brain Extraction and Analysis Toolbox (iBEAT V2.0 Cloud) for initial processing and brain segmentation.”
[51] “Based on evaluations by clinicians and professional researchers, segmentation labels of the OASIS-3 dataset (i.e. CSF, GM, and WM) were provided by Dr. Li Wang, using the iBEAT toolbox [47].”
[52] “Neonatal T1-weighted images underwent tissue segmentation using the Infant Brain Extraction and Analysis Toolbox (iBEAT) V2.0.”
[53] “Skull stripping and cerebellum extraction were performed using an infant cerebrum-dedicated pipeline (iBEAT V2.0, http://www.ibeat.cloud).”
[54] “Brain tissue segmentation was performed using iBEAT V2.0 (http://www.ibeat.cloud) to generate brain tissue labeling maps. Each voxel was labeled as gray matter, white matter, or cerebrospinal fluid.”
[55] “All T1-weighted and T2-weighted MR images were processed using an infant-dedicated computational pipeline (http://www.ibeat.cloud/) described previously.”
[56] “All images were then preprocessed using the infant brain extraction and analysis toolbox (iBEAT V2.0 Cloud) (http://www.ibeat.cloud/).”
[57] “The dataset was preprocessed using an infant-dedicated pipeline.”
[58] “We first preprocessed the MR images and extracted the cerebellum using the infant brain extraction and analysis toolbox (iBEAT V2.0 Cloud) (http://www.ibeat.cloud/).”
[59] “MR images were quality-controlled using an automated algorithm and then preprocessed using an infant-centric processing pipeline (iBEAT v.2.0; available at https://ibeat.wildapricot.org) consisting of the following steps:(i) rigid alignment of T1w and T2w images using FLIRT; (ii) skull stripping by a learning-based method; (iii) intensity inhomogeneity correction by N3; (iv) brain tissue segmentation by an infant dedicated learning-based method; (v) hemisphere separation and subcortical filling; and (vi) topologically-correct cortical surface reconstruction.”
[60] “To provide an approximation of the regional locations of significant correlations in the voxel-based analyses, the study-specific MPF group templates were parcellated. For gray matter, the MPF templates were skull stripped, tissue segmented and parcellated using an infant-dedicated processing pipeline, iBEAT V2.0 Cloud (http://www.ibeat.cloud).”
[61] “Specifically, the 3D T1-weighted images were post-processed by the iBEAT (Infant Brain Extraction and Analysis Toolbox) V2.0 software (developed by the Developing Brain Computing lab and Baby Brain Mapping lab at the University of North Carolina at Chapel Hill). iBEAT V2.0 is a newer version of the previous iBEAT software, utilizing advanced deep learning approaches to process pediatric brain structural MRI data such as 3D T1-weighted and/or 3D T2-weighted images.”
[62] “For processing the BCP dataset, we used an infant dedicated computational pipeline iBEAT V2.0 (http://www.ibeat.cloud/).”
[63] “Brain tissue segmentation was first conducted to generate tissue labelling maps (each voxel was assigned as grey matter, white matter, or cerebrospinal fluid) using a multi-site infant-dedicated computational toolbox, iBEAT V2.0 Cloud (http://www.ibeat.cloud).”
[64] “Preprocessing, including T1w/T2w alignment, intensity inhomogeneity correction, skull stripping, and histogram matching, was performed by an infant-dedicated pipeline, iBEAT V2.0 Cloud (http://www.ibeat.cloud).”
[65] “To improve the registration performance, we first applied the infant brain extraction and analysis toolbox (iBEAT V2.0 Cloud) to segment each scan into three tissue types and manually checked the achieved TPMs.”
[66] “A second segmentation was done using the T2-weighted anatomical images, which have a better contrast between gray and white matter in young infants, using the brain extraction toolbox (Brain Extraction and Analysis Toolbox, iBEAT, v-2.0 cloud processing, https://ibeat.wildapricot.org/).”
[67] “All images were processed by iBEAT V2.0 Cloud (http://www.ibeat.cloud/), an infant dedicated pipeline for tissue segmentation and cortical surface reconstruction.”
[68] “All functional MRI scans were preprocessed following an infant specific procedure, including the following major steps: (1) head motion and spatial distortion correction; (2) alignment of fMRI scans onto their structural MRI scans based on tissue boundary maps.”
[69] “These collected MR images were processed by an infant MRI computational pipeline to extract morphological measurements of the cerebral cortex.”
[70] “All T1-weighted and T2-weighted MRIs were processed by iBEAT V2.0 Cloud (https://www.ibeat.cloud/) with the following main steps: (1) skull stripping by a learning-based method; (2) cerebellum and brainstem removal by a deep-learning-based model (densely connected U-Net); (3) intensity inhomogeneity correction by the N3 framework; (4) tissue segmentation using an age-specific deep-learning-based framework, which was visually inspected to ensure sufficient accuracy; and (5) noncortical structures filling and left/right hemisphere separation.”
[71] “We used T2-weighted anatomical images, which have a better contrast between gray and white matter in infants, and an independent brain extraction toolbox (Brain Extraction and Analysis Toolbox, iBEAT, v-2.0 cloud processing, https://ibeat.wildapricot.org/) to generate more accurate white and gray matter segmentations.”
[72] “Intensity inhomogeneity correction, skull stripping, segmentation and parcellation were applied sequentially to original raw intensity images, leveraging the publicly available software iBEAT V2.0 Cloud (http://www.ibeat.cloud/).”
[73] “Specifically, DICOM images were converted to NIfTI format and were postprocessed by the new iBEAT V2.0 software (Developing Brain Computing Lab and Baby Brain Mapping Lab). iBEAT V2.0 is a toolbox using advanced approaches including deep learning for processing pediatric brain T1- and T2-weighted MR images.”
[74] “The tissue segmentation maps of dHCP dataset were acquired using iBEAT V2.0 Cloud (http://www.ibeat.cloud/), with segmentation method described in (Wang et al., 2018).”
[75] “Brain tissue segmentation was first conducted to generate tissue labeling maps (gray matter, white matter, or cerebrospinal fluid) using a multi-site infant-dedicated computational toolbox, iBEAT v2.0 Cloud (http://www.ibeat.cloud).”
[76] “To determine whether infants have retinotopic organization, we first created surface reconstructions using iBEAT v2.0. These surfaces were inflated and cut to make flatmaps. The contrast between horizontal and vertical meridians was projected onto each participant’s flatmap and used for tracing visual areas. Areas were traced based on the alternations in sensitivity to horizontal and vertical meridians using a suitable protocol for adults.”
[77] “Structural brain images were processed with the infant Brain Extraction and Analysis Toolbox (iBEAT) for volume-based and cortical surface-based analysis that was specifically developed for pediatric MRI scans matching the data acquisition parameters used in this study.”
[78] “First, each T1w MR image is segmented into WM, GM, and CSF tissues by iBEAT V2.0 Cloud (http://www.ibeat.cloud).”
[79] “We further validated our method on another dataset with 102 infants around 1 year of age. The cortical surfaces were reconstructed using an infant-specific pipeline, and further mapped onto the sphere.”
[80] “All structural images were preprocessed by a well-established infant-dedicated computational pipeline, including co-registration, intensity inhomogeneity correction, skull stripping, cerebellum removal, tissue segmentation, hemispheres separation, topological correction, and inner/middle/outer surface reconstruction.”
[81] “T2w anatomical images (hereafter referred to as T2w) were processed using iBEAT v1.”
[82] “To generate reliable manual segmentations, we first took advantage of the follow-up 24-month scans of the same subjects, with high tissue contrast, to generate an initial automatic segmentation for 6-month scans, by using a publicly available software iBEAT (www.nitrc.org/projects/ibeat/).”
[83] “To obtain the “ground truth” labels, we first conducted segmentation by iBEAT, then manually corrected and modified the labels using ITK-SNAP (www.itksnap.org) under the supervision of experienced neuroscientists.”
[84] “The data were analyzed in iBEAT, an open source toolbox for processing infant brain images.”
[85] “In this study, longitudinal MRI data from healthy infant subjects are acquired and processed using UNC Infant Pipeline.”
[86] “To generate manual segmentation for training, initial segmentation was first obtained with a publicly available infant brain segmentation software, iBEAT (http://www.nitrc.org/projects/ibeat).”
[87] “Since it is very difficult to segment infant images accurately, especially for the 6-month-old images, in the preprocessing stage, we use multimodal MR images (including T1-weighted MRI, T2-weighted MRI, and DTI) and longitudinal images for multimodal longitudinal infant image segmentation, thus obtaining reasonable tissue segmentation maps of each time-point for WM, GM, and CSF.”
[88] “All MR images at all the acquisition timepoints were preprocessed using a standard framework.”
[89] “Individual subject’s T1- and T2-weighted images were segmented into gray matter, white matter, and CSF tissue classes by using iBEAT software (https://www.med.unc.edu/bric/ideagroup/free-softwares/libra-longitudinal-infant-brain-processing-package), designed for neonatal and infant brain segmentation.”
[90] “All images were preprocessed with a standard pipeline in iBEAT software.”
[91] “We first pre-processed all images with a standard pipeline that included reorientation, resampling, intensity correction and brain extraction using iBeat developed for the neonate and infant brain.”
[92] “All MR images at all the acquisition timepoints were preprocessed using an infant-specific framework.”
[93] “To generate manual segmentation, an initial segmentation was obtained with publicly available infant brain segmentation software, iBEAT.”
[94] “To generate the manual segmentations, we first generated an initial reasonable segmentation by using a publicly available software iBEAT (http://www.nitrc.org/projects/ibeat/).”
[95] “All MR images were preprocessed using a standard procedure.”
[96] “For each set of aligned T1, T2, and FA images, non-cerebral tissues, such as skull, brain stem and cerebellum, were removed by using iBEAT.”
[97] “To generate the ground-truth segmentations, we took a practical approach by first generating an initial reasonable segmentation by using a publicly available software iBEAT (http://www.nitrc.org/projects/ibeat/).”
[98] “The 3D T1w scans were first segmented with iBEAT [22] and then refined by three radiologists to form the ground-truth labels.”
[99] “All rs-fMRI data underwent rigorous preprocessing and quality control using state-of-the-art infant-specific pipelines [16-19].” (Reference [16] in the original paper is iBEAT V2.0, Wang et al., 2023.)
[100] “Preprocessing includes tissue segmentation with iBEAT [3] and skull stripping with SynthStrip [7]. Each scan is then processed by multiple segmentation tools (e.g., SynthSeg[5], FreeSurfer [8]), producing tissue and structure labels that serve as inputs to Medley later stage.”
[101] “All images were processed with the infant dedicated computational pipeline, iBEAT V2, to reconstruct high-quality cortical surfaces...”
[102] “The cortical surfaces of each hemisphere were reconstructed using iBEAT V2.0 [25].”
[103] “Ground-truth cortical surfaces were reconstructed using the FreeSurfer pipeline, except for BCP and NDAR infant datasets, which were processed with iBEAT v2.0.”
[104] “The segmentation labels were initially generated by iBEAT and subsequently refined by three radiologists.”
[105] “For participants aged 0–2 years, we employed the iBEAT v2.0 pipeline, which is optimized for early-age neuroimaging data and has demonstrated superior performance in tissue segmentation and cortical reconstruction for infants compared with alternative approaches.”
[106] “For infant structural and functional MRI processing, we follow the methodologies detailed in [10, 14, 15, 16] to extract the fMRI time-series for each vertex on middle cortical surfaces...”
[107] “The segmentation process begins with cortical surface reconstructions derived from MRI scans. These images are processed using a deep learning pipeline developed by the BRAIN lab at UNC Medical School [10].”
[108] “All T1- and T2-weighted magnetic resonance images underwent processing using an infant-specific pipeline [58]...”
[109] “All structural MR images were processed by a state-of-the-art infant-tailored pipeline (https://www.ibeat.cloud/) [14–17], including co-registration, intensity inhomogeneity correction, skull stripping, cerebellum removal, tissue segmentation, hemispheres separation, topological correction, and surface reconstruction.”
[110] “Moreover, we incorporated the segmentation outputs from Infant Brain Extraction and Analysis Toolbox (iBEAT) and another Attention U-Net to further enhance the performance and construct the end-to-end segmentation pipeline.”
[111] “Cortical property maps were derived from T1- and T2-weighted MRI images, processed and registered using an infant-dedicated pipeline.”
[112] “In addition, quantitative comparisons of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) segmented from the uLF and SF images were compared to segmentations from ground truth HF images obtained by iBeat, a state-of-the-art infant brain segmentation pipeline.”
[113] “All MR images were processed through an infant-dedicated computational pipeline, termed iBEAT V2.0.”
[114] “Second, we test the skull-stripping module of the Infant Brain Extraction and Analysis Toolbox (iBEAT) [10] developed for T1w and T2w MRI (version 2.0, release 120).”
[115] “Each image has a resolution of 0.8 × 0.8 × 0.8 mm³ and was bias-corrected, skull-stripped, and segmented by iBEAT V2.0 [18].”
[116] “Tissue segmentation and surface extraction using iBEAT v2.0.”
[117] “Pseudo-ground truth cortical surface meshes were generated using iBEAT v2.0 for both training and performance evaluation.”
[118] “We also tested various standard segmentation packages, including BrainSuite, Infant FreeSurfer, iBeat V2.0, and SynthSeg.”
[119] “All structural and functional MR images were preprocessed following state-of-the-art infant-tailored pipelines [11-15]. Cortical surfaces were reconstructed and aligned onto the public UNC 4D infant surface atlas [10, 11].”
[120] “Two neuroscientists manually labeled PWML areas and corrected tissue labels generated by iBeat.”
[121] “Ground truth cortical surfaces were generated with iBEAT v2.0.”
[122] “All images were preprocessed using the infant-dedicated pipeline iBEAT V2.0 (http://www.ibeat.cloud/).”
[123] “To provide accurate brain anatomy, we perform image preprocessing and brain tissue segmentation for these MRIs to generate ground-truth segmentation of three tissues, i.e., white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF), using an in-house toolbox iBEAT with manual verification.”
[124] “To obtain high-quality meta-training labels, we segmented the preprocessed T1w images automatically by using an advanced pipeline, i.e., iBEAT.”
[125] “Cortical surface maps were generated using an infant-dedicated pipeline (http://www.ibeat.cloud/) [5].”
[126] “MRI – T1 weighted images, averaged across right and left hemispheres, processed using the Infant Brain Extraction and Analysis Toolbox (iBEAT V2.0; Wang et al., 2023).”
[127] “We used minimally preprocessed data from dHCP, HCP-D, HCP-YA, and HCP-A and BCP data were preprocessed via iBEAT.”
[128] “These MR images were processed by the public infant dedicated MRI computational pipeline: iBEAT V2.0 Cloud to reconstruct cortical surfaces.”
[129] “We used an infant dataset with 864 cortical surfaces, which were reconstructed via iBEAT V2.0 Cloud (http://www.ibeat.cloud/).”
[130] “We used an infant dataset with 623 cortical surfaces, which were reconstructed via iBEAT V2.0 Cloud (http://www.ibeat.cloud/).”
[131] “Cortical surfaces were reconstructed via iBEAT V2.0 Cloud (http://www.ibeat.cloud/) and then mapped onto the sphere using FreeSurfer.”
[132] “All scans were segmented into the white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) using a learning-based method and then manually corrected by experts. All scans were firstly affinely-aligned together.”
[133] “3D T1-weighted images with resolution of 1mm 1mm 1mm were post-processed by iBEAT V2.0 software (developed by the Developing Brain Computing lab and Baby Brain Mapping lab at the University of North Carolina at Chapel Hill) to reconstruct for cortical surface and to measure cortical thickness.”
[134] “All structural and functional MR images were preprocessed following a state-of-the-art infant-tailored pipeline.”
[135] “We used a dataset with 102 pediatric subjects. The cortical surfaces were reconstructed with iBEAT V2.0 Cloud (http://www.ibeat.cloud/), an online infant-dedicated computational pipeline and then mapped onto the sphere using FreeSurfer.”
[136] “Besides T1w images and T2w images, we also employ the segmentation map and parcellation map for the diagnosis of ASD, which were generated by a publicly available software iBEAT V2.0 Cloud (http://www.ibeat.cloud).”
[137] “In preprocessing, FLIRT linear registration of other time point to 12-month-old was performed. The corresponding segmentation labels, i.e. WM, GM and hippocampus, were obtained by iBEAT toolbox and experts’ manual refinement.”
[138] “T1WI images were processed by using the UNC Infant Pipeline.”
[139] “Tissue segmentation was performed by using a deep learning method.”
[140] “Images were analyzed with iBEAT software that enables N3 bias correction, tissue segmentation and anatomical labelling (AAL atlas).”
[141] “In this experiment, we fed real 6-month T1w and T2w images, along with brain masks, into iBEAT to obtain segmentation outputs for WM, GM and CSF.”
[142] “An ad hoc comparison of BIBSNet to iBeat, an existing deep learning model for infant brain segmentation, was also performed.”
[1] Li, T., Yang, Y., Cho, S.-H., et al., Microbes on the Mind: Multi-modal Neuroimaging Reveals Gut-Brain Axes in Infants. bioRxiv [Preprint], 2026. https://doi.org/10.64898/2026.09.23.753825
[2] Hu, D., Cheng, J., Han, K., et al., Division-Specific Organization of a Shared Functional Scaffold in the Early-Life Human Brain. bioRxiv, 2026. https://doi.org/10.64898/2026.09.14.751555
[3] Zhao, R., Li, M., Zhang, Y., et al., Brain structural and functional connectivity converge prenatally but diverge after birth. PLOS Biology, 2026. 24(9): p. e3003927. https://doi.org/10.1371/journal.pbio.3003927
[4] Yu, C., Lin, L., Sun, L., et al., Differential Lifespan Trajectories of Cerebral Asymmetry in Chinese and Western Populations. Research Square, 2026. https://doi.org/10.21203/rs.3.rs-10588519/v1
[5] Na, X., et al., Associations between maternal adiposity during pregnancy and neonatal brain cortical development. NeuroImage, 2026. 339: p. 122158. https://doi.org/10.1016/j.neuroimage.2026.122158
[6] Zika, S., et al., Cortical and white matter myelination proceed in concert during early infancy. Nature Communications, 2026. 17: p. 5353.
[7] Chen, L., et al., A longitudinally-consistent deep framework for joint subcortical segmentation and registration of infant brains. Computerized Medical Imaging and Graphics, 2026. 132: p. 102779.
[8] Ning, C., et al., Spatio-temporal reconstruction of early brain developmental trajectories via self-supervised learning. Medical Image Analysis, 2026. 112: p. 104132.
[9] Manoli, A., et al., Cerebellar growth is associated with domain-specific cerebral maturation and socio-linguistic behavior. Nature Communications, 2026. 17(1): p. 4338.
[10] Wang, Y., et al., Surface expansion regionalization of the hippocampus in early brain development. Developmental Cognitive Neuroscience, 2026. 79: p. 101733.
[11] Lian, Z., et al., UniSurf: Universal lifespan cortical surface reconstruction. Medical Image Analysis, 2026. 112: p. 104090.
[12] Pacyga, D.C., et al., Sex-specific associations of gestational age at birth and birth size with early life within-network brain connectivity: An exploratory study. Imaging Neuroscience, 2026. 4: p. IMAG.a.1204.
[13] Li, Q., et al., Spatiotemporal dynamics of the human cortical functional hierarchy across the lifespan. Nature Communications, 2026.
[14] Boisgontier, J., et al., Early neurodevelopmental brain perfusion abnormalities and functional connectivity findings in infants with Prader-Willi syndrome. Journal of Neurodevelopmental Disorders, 2026. 18: p. 28.
[15] Liu, J., et al., BrainParc: unified lifespan brain parcellation from structural magnetic resonance images. Nature Computational Science, 2026. 6: p. 588-602.
[16] Hendrickson, T.J., et al., BIBSNet: A deep learning baby image brain segmentation network for MRI scans. Developmental Cognitive Neuroscience, 2026. 79: p. 101706.
[17] Devisscher, L., et al., Impact of clinical risk factors on white matter microstructure in preterm-born infants: Investigation with diffusion MRI and tractography at term-equivalent age. medRxiv, 2026. https://doi.org/10.64898/2026.02.12.26346175
[18] Sun, Y., et al., DuMeta++: Spatiotemporal Dual Meta-Learning for Generalizable Few-Shot Brain Tissue Segmentation Across Diverse Ages. arXiv, 2026: p. 2602.07174.
[19] Engel, S.M., et al., Early life phthalate and replacement plasticizer exposures and changes in early childhood brain functional connectivity and structural morphology. Environment International, 2026. 208: p. 110119.
[20] Perez, K., et al., Hierarchical microstructural tissue growth of the gray and white matter of human visual cortex during the first year of life. Brain Structure and Function, 2026. 231: p. 15.
[21] Tung, S.S., et al., How do infant brains fold? Sulcal deepening is linked to development of sulcal span, thickness, curvature, and microstructure. Communications Biology, 2026.
[22] Wang, Y., et al., Automatic Quality Control for Resting-State BOLD-Based Cerebrovascular Reactivity Mapping. NMR in Biomedicine, 2025. 39: p. e70208.
[23] Elbaz, N., et al., Investigating Cerebral Anomalies in Preterm Infants and Associated Risk Factors With Magnetic Resonance Imaging at Term-Equivalent Age. Pediatric Neurology, 2026. 175: p. 156-164.
[24] Zhang, Y., et al., Spatiotemporal Development and Clinical Correlates of MRI-based Brain Myelination in Term- and Preterm-born Children. Radiology, 2025. 317(2): p. e251251.
[25] Xu, L., et al., Magnetic resonance imaging-based assessment of hippocampal glutamate and morphometric changes in preterm infants at term-equivalent age with low birth weight. Pediatric Radiology, 2026. 56(1): p. 140-149.
[26] Nigru, A.S., et al., Rewiring Development in Brain Segmentation: Leveraging Adult Brain Priors for Enhancing Infant MRI Segmentation. arXiv, 2025: p. 2510.09306.
[27] Pujol, J., et al., Unraveling the impact of prenatal air pollution for neonatal brain maturation. Environment International, 2025. 204: p. 109801.
[28] Liang, X., et al., Dissecting human cortical similarity networks across the lifespan. Neuron, 2025.
[29] Cheng, J., et al., STF: A spherical transformer for versatile cortical surfaces applications. NeuroImage, 2025. 318: p. 121370.
[30] Dornier, A., et al., On the Typical Development of the Central Sulcus in Infancy: A Longitudinal Evaluation of Its Morphology and Link to Behaviour. Developmental Neuroscience, 2025.
[31] Turesky, T.K., et al., Longitudinal trajectories of brain development from infancy to school age and their relationship with literacy development. Proceedings of the National Academy of Sciences, 2025. 122(24): p. e2414598122.
[32] Zhou, Y., et al., Efficient few-shot medical image segmentation via self-supervised variational autoencoder. Medical Image Analysis, 2025. 104: p. 103637.
[33] Werder, E.J., et al., Early life phthalate exposure impacts gray matter and white matter volume in infants and young children. Environmental Research, 2025. 279: p. 121826. https://doi.org/10.1016/j.envres.2025.121826
[34] Yin, W., et al., Charting brain functional development from birth to 6 years of age. Nature Human Behaviour, 2025. 9(6): p. 1246-1259. https://doi.org/10.1038/s41562-025-02160-2
[35] Sun, L., et al., Human lifespan changes in the brain’s functional connectome. Nature Neuroscience, 2025. 28(4): p. 891-901.
[36] Zhang, L., et al., Brain Anatomy Prior Modeling to Forecast Clinical Progression of Cognitive Impairment with Structural MRI. Pattern Recognition, 2025. 165: p. 111603. https://doi.org/10.1016/j.patcog.2025.111603
[37] Kubota, E., et al., White matter connections of human ventral temporal cortex are organized by cytoarchitecture, eccentricity and category-selectivity from birth. Nature Human Behaviour, 2025. 9(5): p. 955-970.
[38] Ellis, C.T., et al., Movies reveal the fine-grained organization of infant visual cortex. eLife, 2025. 12: p. RP92119.
[39] Liu, J., et al., Structure-Aware Brain Tissue Segmentation for Isointense Infant MRI Data Using Multi-Phase Multi-Scale Assistance Network. IEEE Journal of Biomedical and Health Informatics, 2025. 29(2): p. 1297-1307.
[40] Yuan, X., et al., Flexible Individualized Developmental Prediction of Infant Cortical Surface Maps via Intensive Triplet Autoencoder. IEEE Transactions on Medical Imaging, 2025. 44(7): p. 3110-3122.
[41] Sun, Y., et al., A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks. Nature Biomedical Engineering, 2025. 9: p. 521-538. https://doi.org/10.1038/s41551-024-01283-7
[42] Wu, J., et al., Age-specific optimization of the T2-weighted MRI contrast in infant and toddler brain. Magnetic Resonance in Medicine, 2025. 93: p. 1014-1025.
[43] Zhang, L., et al., Learning lifespan brain anatomical correspondence via cortical developmental continuity transfer. Medical Image Analysis, 2025. 99: p. 103328. https://doi.org/10.1016/j.media.2024.103328
[44] Guha, A., et al., Intrinsic Infant Hippocampal Function Supports Inhibitory Processing. Developmental Psychobiology, 2024. 66: p. e22529.
[45] Henschel, L., et al., VINNA for neonates: Orientation independence through latent augmentations. Imaging Neuroscience, 2024. 2: p. 1-26.
[46] Yin, Z., et al., Early autism diagnosis based on path signature and Siamese unsupervised feature compressor. Cerebral Cortex, 2024. 34(13): p. 72-83. https://doi.org/10.1093/cercor/bhae069
[47] Shimotsuma, T., et al., Severe Bronchopulmonary Dysplasia Adversely Affects Brain Growth in Preterm Infants. Neonatology, 2024: p. 1-9.
[48] Chen, J.V., et al., Automated neonatal nnU-Net brain MRI extractor trained on a large multi-institutional dataset. Scientific Reports, 2024. 14(1): p. 4583.
[49] Vaz, T.F., et al., Brain Extraction Methods in Neonatal Brain MRI and Their Effects on Intracranial Volumes. Applied Sciences, 2024. 14(4): p. 1339. https://doi.org/10.3390/app14041339
[50] Muñoz, J.S., et al., Parenting Influences on Frontal Lobe Gray Matter and Preterm Toddlers’ Problem-Solving Skills. Children, 2024. 11(2): p. 206.
[51] Wu, L., et al., RClaNet: An Explainable Alzheimer’s Disease Diagnosis Framework by Joint Registration and Classification. IEEE Journal of Biomedical and Health Informatics, 2024. 28(4): p. 2338-2349.
[52] Kelly, C.E., et al., Cortical growth from infancy to adolescence in preterm and term-born children. Brain, 2024. 147(4): p. 1526-1538.
[53] Sun, Y., et al., Self-supervised learning with application for infant cerebellum segmentation and analysis. Nature Communications, 2023. 14(1): p. 4717.
[54] Jiang, W., et al., Mapping the evolution of regional brain network efficiency and its association with cognitive abilities during the first twenty-eight months of life. Developmental Cognitive Neuroscience, 2023. 63: p. 101284.
[55] Huang, Y., et al., Mapping Genetic Topography of Cortical Thickness and Surface Area in Neonatal Brains. The Journal of Neuroscience, 2023. 43(34): p. 6010-6020.
[56] Chen, L., et al., Four-dimensional mapping of dynamic longitudinal brain subcortical development and early learning functions in infants. Nature Communications, 2023. 14(1): p. 3727.
[57] Huang, Y., et al., Longitudinal Prediction of Postnatal Brain Magnetic Resonance Images via a Metamorphic Generative Adversarial Network. Pattern Recognition, 2023: p. 109715.
[58] Wang, Y., et al., Longitudinal development of the cerebellum in human infants during the first 800 days. Cell Rep, 2023. 42(4): p. 112281.
[59] Ahmad, S., et al., Multifaceted atlases of the human brain in its infancy. Nature Methods, 2023. 20(1): p. 55-64.
[60] Corrigan, N.M., et al., Brain myelination at 7 months of age predicts later language development. NeuroImage, 2022. 263: p. 119641.
[61] Na, X., et al., Mother’s physical activity during pregnancy and newborn’s brain cortical development. Frontiers in Human Neuroscience, 2022. 16: p. 943341.
[62] Huang, Y., et al., Mapping developmental regionalization and patterns of cortical surface area from 29 post-menstrual weeks to 2 years of age. Proc Natl Acad Sci U S A, 2022. 119(33): p. e2121748119.
[63] Jiang, W., et al., Neural alterations in opioid-exposed infants revealed by edge-centric brain functional networks. Brain Communications, 2022. 4(3): p. fcac112.
[64] Li, G., et al., Volumetric Analysis of Amygdala and Hippocampal Subfields for Infants with Autism. Journal of Autism and Developmental Disorders, 2023. 53(6): p. 2475-2489.
[65] Chen, L., et al., A 4D infant brain volumetric atlas based on the UNC/UMN baby connectome project (BCP) cohort. NeuroImage, 2022. 253: p. 119097.
[66] Grotheer, M., et al., White matter myelination during early infancy is linked to spatial gradients and myelin content at birth. Nature Communications, 2022. 13(1): p. 997.
[67] Wang, Y., et al., Developmental abnormalities of structural covariance networks of cortical thickness and surface area in autistic infants within the first 2 years. Cerebral Cortex, 2022. 32(17): p. 3786-3798.
[68] Li, Y., et al., Brain Connectivity Based Graph Convolutional Networks and Its Application to Infant Age Prediction. IEEE Transactions on Medical Imaging, 2022. 41(10): p. 2764-2776.
[69] Cheng, J., et al., Path Signature Neural Network of Cortical Features for Prediction of Infant Cognitive Scores. IEEE Trans Med Imaging, 2022. 41(7): p. 1665-1676.
[70] Hu, D., et al., Existence of Functional Connectome Fingerprint during Infancy and Its Stability over Months. The Journal of Neuroscience, 2022. 42(3): p. 377-389.
[71] Natu, V.S., et al., Infants’ cortex undergoes microstructural growth coupled with myelination during development. Communications Biology, 2021. 4(1): p. 1191.
[72] Gao, K., et al., Unified framework for early stage status prediction of autism based on infant structural magnetic resonance imaging. Autism Research, 2021. 14(12): p. 2512-2523.
[73] Na, X., et al., Maternal Obesity during Pregnancy is Associated with Lower Cortical Thickness in the Neonate Brain. American Journal of Neuroradiology, 2021. 42(12): p. 2238-2244.
[74] Chen, L., et al., ABCnet: Adversarial bias correction network for infant brain MR images. Medical image analysis, 2021. 72: p. 102133.
[75] Merhar, S.L., et al., Effects of prenatal opioid exposure on functional networks in infancy. Developmental Cognitive Neuroscience, 2021. 51: p. 100996.
[76] Ellis, C.T., et al., Retinotopic organization of visual cortex in human infants. Neuron, 2021. 109(16): p. 2616-2626. e6.
[77] Woodburn, M., et al., The maturation and cognitive relevance of structural brain network organization from early infancy to childhood. NeuroImage, 2021. 238: p. 118232.
[78] Sun, Y., et al., Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge. IEEE Transactions on Medical Imaging, 2021. 40(5): p. 1363-1376.
[79] Zhao, F., et al., S3Reg: Superfast Spherical Surface Registration Based on Deep Learning. IEEE Transactions on Medical Imaging, 2021. 40(8): p. 1964-1976.
[80] Hu, D., et al., Disentangled-Multimodal Adversarial Autoencoder: Application to Infant Age Prediction With Incomplete Multimodal Neuroimages. IEEE Transactions on Medical Imaging, 2020. 39(12): p. 4137-4149.
[81] Catalina Camacho, M., et al., Cerebral blood flow in 5‐to 8‐month‐olds: Regional tissue maturity is associated with infant affect. Developmental Science, 2020. 23(5): p. e12928.
[82] Wang, L., et al., Benchmark on Automatic Six-Month-Old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge. IEEE Transactions on Medical Imaging, 2019. 38(9): p. 2219-2230.
[83] Hu, S., et al., Brain deformable registration using global and local label-driven deep regression learning in the first year of life. IEEE Access, 2019. 8: p. 25691-25705.
[84] Lehtola, S.J., et al., Associations of age and sex with brain volumes and asymmetry in 2–5-week-old infants. Brain Structure and Function, 2019. 224(1): p. 501-513.
[85] Adeli, E., et al., Multi-task prediction of infant cognitive scores from longitudinal incomplete neuroimaging data. NeuroImage, 2019. 185: p. 783-792.
[86] Nie, D., et al., 3-D fully convolutional networks for multimodal isointense infant brain image segmentation. IEEE transactions on cybernetics, 2018. 49(3): p. 1123-1136.
[87] Wei, L., et al., Learning‐based deformable registration for infant MRI by integrating random forest with auto‐context model. Medical physics, 2017. 44(12): p. 6289-6303.
[88] Rekik, I., et al., Joint prediction of longitudinal development of cortical surfaces and white matter fibers from neonatal MRI. NeuroImage, 2017. 152: p. 411-424.
[89] Peyton, C., et al., White Matter Injury and General Movements in High-Risk Preterm Infants. American Journal of Neuroradiology, 2017. 38(1): p. 162-169.
[90] Zhang, Y., et al., Consistent spatial-temporal longitudinal atlas construction for developing infant brains. IEEE transactions on medical imaging, 2016. 35(12): p. 2568-2577.
[91] Yamada, Y., et al., An Embodied Brain Model of the Human Foetus. Scientific Reports, 2016. 6(1): p. 27893.
[92] Rekik, I., et al., Predicting infant cortical surface development using a 4D varifold-based learning framework and local topography-based shape morphing. Medical image analysis, 2016. 28: p. 1-12.
[93] Zhang, W., et al., Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage, 2015. 108: p. 214-224.
[94] Wang, L., et al., LINKS: learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images. Neuroimage, 2015. 108: p. 160-72.
[95] Gang, L., et al., Mapping Longitudinal Development of Local Cortical Gyrification in Infants from Birth to 2 Years of Age. The Journal of Neuroscience, 2014. 34(12): p. 4228.
[96] Li, G., et al., Measuring the dynamic longitudinal cortex development in infants by reconstruction of temporally consistent cortical surfaces. Neuroimage, 2014. 90: p. 266-279.
[97] Wang, L., et al., Integration of sparse multi-modality representation and anatomical constraint for isointense infant brain MR image segmentation. NeuroImage, 2014. 89: p. 152-164.
[98] Ren, Z., et al., SynHydro: Biomechanics-Driven Domain Randomization for Hydrocephalus-Agnostic, Generalizable Tissue-Ventricle Segmentation Across Age, Modality, and Resolution, in Medical Image Computing and Computer Assisted Intervention – MICCAI 2026. Lecture Notes in Computer Science, 16881: p. 534–544. Springer, Cham, 2027 (first online: 26 September 2026). https://doi.org/10.1007/978-3-032-38072-2_51 (Full text).
[99] Hu, D., et al., The Neuro-Developing Engine: A Surrogate Longitudinal Model for Infant Brain Dynamics via Causal Distillation, in Medical Image Computing and Computer Assisted Intervention – MICCAI 2026. Lecture Notes in Computer Science, 16887: p. 631–641. Springer, Cham, 2027 (first online: 24 September 2026). https://doi.org/10.1007/978-3-032-38172-9_60 (Full text).
[100] Le, I.A.T., et al., MEDLEY: Orchestrating Imperfect Segmentation Through Physics-Aware Multi-Tool Curation for Infant Brain MRI, in IEEE 23rd International Symposium on Biomedical Imaging (ISBI). 2026.
[101] Wang, X., et al., Biophysical modeling of anatomically realistic prenatal cortical folding development. Research Square, 2026.
[102] Tang, K., et al., Surface-Guided Construction of 4D Volumetric Atlases of Fetal Brains, in Machine Learning in Medical Imaging: 16th International Workshop, MLMI 2025, Held in Conjunction with MICCAI 2025. 2026. Cham: Springer Nature Switzerland.
[103] Dong, X., et al., Lifespan Cortical Surface Reconstruction from Thick-Slice Clinical MRI, in Medical Image Computing and Computer Assisted Intervention - MICCAI 2025. Lecture Notes in Computer Science, 2025. 15961: p. 303-313. https://doi.org/10.1007/978-3-032-04937-7_29
[104] Wang, H., et al., Flexibly Distilled 3D Rectified Flow with Anatomical Constraints for Developmental Infant Brain MRI Prediction, in Medical Image Computing and Computer Assisted Intervention - MICCAI 2025. Lecture Notes in Computer Science, 2025. 15974: p. 228-237. https://doi.org/10.1007/978-3-032-05182-0_23
[105] Sun, L., et al., Population-specific brain charts reveal Chinese-Western differences in neurodevelopmental trajectories. bioRxiv, 2025.
[106] Xia, W., et al., Individualized Trajectory Prediction of Early Developing Functional Connectivity, in 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI). 2025.
[107] Godin, C., and Holland, M., Cortical Curvedness Patterns Alter with Volumetric Expansion During Infancy: A Longitudinal Analysis, in Summer Bioengineering Conference (SBC). 2025.
[108] Yuan, X., et al., Local Gradients of Functional Connectivity Enable Precise Fingerprinting of Infant Brains During Dynamic Development. bioRxiv, 2024.
[109] Cheng, J., et al., Disentangled Hybrid Transformer for Identification of Infants with Prenatal Drug Exposure, in Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. 2024. Cham: Springer Nature Switzerland.
[110] Dong, Y., et al., Automatic 8-Tissue Segmentation for 6-Month Infant Brains. Lecture Notes in Computer Science, 2025. 14747: p. 59-69. https://doi.org/10.1007/978-3-031-73260-7_6
[111] Yuan, X., et al. Longitudinally Consistent Individualized Prediction of Infant Cortical Morphological Development. in Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. 2024. Cham: Springer Nature Switzerland.
[112] Tapp, A., et al. Super-Field MRI Synthesis for Infant Brains Enhanced by Dual Channel Latent Diffusion. in Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. 2024. Cham: Springer Nature Switzerland.
[113] Huang, Y., et al., Revealing Fine-grained Genetically Informed Cortical Parcellation Maps of Neonates Based on Multi-view Spectral Clustering, in 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2024.
[114] Kelley, W., et al., Boosting Skull-Stripping Performance for Pediatric Brain Images, in IEEE International Symposium on Biomedical Imaging (ISBI). 2024.
[115] Tang, K., et al., Generation of Anatomy-Realistic 4D Infant Brain Atlases with Tissue Maps Using Generative Adversarial Networks, in 2024 IEEE International Symposium on Biomedical Imaging (ISBI). 2024.
[116] Rayson, H., et al., Laminar resolution in infant MEG: Simulating event-related fields for non-invasive cortical layer inference, in BioMag. 2024.
[117] Chen, X., et al. Reconstruction of Cortical Surfaces with Spherical Topology from Infant Brain MRI via Recurrent Deformation Learning. 2023. arXiv:2312.05986 DOI: 10.48550/arXiv.2312.05986.
[118] Rouhi, R., et al., Automated Segmentation of the Hippocampus in Pediatric Imaging, in 2023 19th International Symposium on Medical Information Processing and Analysis (SIPAIM). 2023.
[119] Cheng, J., et al., Prediction of Infant Cognitive Development with Cortical Surface-Based Multimodal Learning, in Medical Image Computing and Computer Assisted Intervention - MICCAI 2023. Lecture Notes in Computer Science, 2023. 14221: p. 618-627. https://doi.org/10.1007/978-3-031-43895-0_58
[120] Ren, Z., et al. Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning. in Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. 2023. Cham: Springer Nature Switzerland.
[121] Chen, X., et al. SurfFlow: A Flow-Based Approach for Rapid and Accurate Cortical Surface Reconstruction from Infant Brain MRI. in Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. 2023. Cham: Springer Nature Switzerland.
[122] Zhao, F., et al. Disentangling Site Effects with Cycle-Consistent Adversarial Autoencoder for Multi-site Cortical Data Harmonization. in Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. 2023. Cham: Springer Nature Switzerland.
[123] Zhang, L., et al., Brain Anatomy-Guided MRI Analysis for Assessing Clinical Progression of Cognitive Impairment with Structural MRI. Med Image Comput Comput Assist Interv, 2023. 14227: p. 109-119.
[124] Sun, Y., et al., Dual Meta-Learning with Longitudinally Consistent Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan, in International Conference on Computer Vision (ICCV). 2023: Paris, France.
[125] Yuan, X., et al., Multi-task Joint Prediction of Infant Cortical Morphological and Cognitive Development, in Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. 2023. Cham: Springer Nature Switzerland.
[126] Barry, K., Laughlin, H., Merrill, L., and Bick, J., Integrating Dimensional Models of Early Adversity: Relative Contributions of Caregiver and Environmental Risks on Frontal-Limbic Development in Early Childhood. FLUX, 2023.
[127] Ahmad, S., et al. Harmonization of Multi-site Cortical Data Across the Human Lifespan. 2022. Cham: Springer Nature Switzerland.
[128] Cheng, J., et al. Spherical Transformer on Cortical Surfaces. in Machine Learning in Medical Imaging. 2022. Cham: Springer Nature Switzerland.
[129] Zhao, F., et al. Fast Spherical Mapping of Cortical Surface Meshes Using Deep Unsupervised Learning. in Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. 2022. Cham: Springer Nature Switzerland.
[130] Zhao, F., et al., A Deep Network for Joint Registration and Parcellation of Cortical Surfaces. Med Image Comput Comput Assist Interv, 2021. 12904: p. 171-181.
[131] Zhao, F., et al., Learning 4D Infant Cortical Surface Atlas with Unsupervised Spherical Networks. Med Image Comput Comput Assist Interv, 2021. 12902: p. 262-272.
[132] Pei, Y., et al., Learning Spatiotemporal Probabilistic Atlas of Fetal Brains with Anatomically Constrained Registration Network. Med Image Comput Comput Assist Interv, 2021. 12907: p. 239-248.
[133] Na, X., et al., Maternal Obesity during Pregnancy is Associated with Lower Cortical Thickness in the Newborn Brain, in International Society for Magnetic Resonance in Medicine. 2021: Online.
[134] Hu, D., et al., Disentangled Intensive Triplet Autoencoder for Infant Functional Connectome Fingerprinting. Med Image Comput Comput Assist Interv, 2020. 12267: p. 72-82.
[135] Zhao, F., et al. Unsupervised Learning for Spherical Surface Registration. in Machine Learning in Medical Imaging. 2020. Cham: Springer International Publishing.
[136] Gao, K., et al. Informative Feature-Guided Siamese Network for Early Diagnosis of Autism. in Machine Learning in Medical Imaging. 2020. Cham: Springer International Publishing.
[137] Hu, S., et al. Infant brain deformable registration using global and local label-driven deep regression learning. in Machine Learning in Medical Imaging: 10th International Workshop, MLMI 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedings 10. 2019. Springer.
[138] Li, X., et al., Surfaces Area and Cortical Volume Development of Infant Transverse Temporal Cortex Influenced by Preterm Birth, in International Society for Magnetic Resonance in Medicine. 2019: QC, Canada.
[139] Wang, M., et al., Cortical thickness is a sensitive biomarker for characterizing the gray matter abnormities in neonates with mild white matter injury, in International Society for Magnetic Resonance in Medicine. 2019: QC, Canada.
[140] Rajasilta, O., et al., A structural volumetric connectome in infants – An MRI study within the FinnBrain Birth Cohort study, in Organization for Human Brain Mapping (OHBM). 2016: Geneva, Switzerland.
[141] Dong, Y., Machine Learning to Uncover Neuroimaging Features of Autism. PhD thesis, King’s College London, 2025.
[142] Hendrickson, T.J., Deep Learning and State of the Art Infant Brain MRI Processing Methods. PhD dissertation, University of Minnesota, 2025.
iBEAT V2.0 is a toolbox for processing pediatric brain MR images, using multimodality (including T1w and T2w) or single-modality. The software is developed by the Developing Brain Computing Lab, and the Brain Research through Analysis and Informatics of Neuroimaging (BRAIN) Lab in the University of North Carolina at Chapel Hill. | ContactsDr. Li Wang: li_wang@med.unc.edu |