The UNC/UMN Baby Connectome Project (BCP): An overview of the study design and protocol development

Howell, Brittany R.; Styner, Martin; Gao, Wei; Yap, Pew-Thian; Wang, Li; Baluyot, Kristine; Yacoub, Essa; Chen, Geng; Potts, Taylor; Salzwedel, Andrew P.; Li, Gang; Gilmore, John H.; Piven, Joseph; Smith, Jeffrey K.; Shen, Dinggang; Uğurbil, Kâmil; Zhu, Hongtu; Lin, Weili; Elison, Jed T.

doi:10.1016/j.neuroimage.2018.03.049

Cited by 300 publications

(222 citation statements)

References 132 publications

(126 reference statements)

Supporting

Mentioning

220

Contrasting

Unclassified

Order By: Relevance

“…The rapid growth and changes in brain morphology during the neonatal period, as well as fast alterations in tissue composition that alter imaging contrast over time , render it challenging to ensure correspondence between template-driven ROIs and tractography protocols at different stages of development (Serag et al, 2012). Manual delineation on a subject-by-subject basis could be an alternative, but it is time-consuming, assumes very detailed knowledge of how neonatal neuroanatomy is depicted in MRI at various early development stages, and becomes prohibitive for large cohorts, such as the developing human connectome projects (Howell et al, 2019;Hughes et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Non-Negative Data-Driven Mapping of Structural Connections in the Neonatal Brain

Thompson

Mohammadi‐Nejad

Glasser³

et al. 2020

Preprint

View full text Add to dashboard Cite

Mapping connections in the neonatal brain can provide insight into the crucial early stages of neurodevelopment that shape brain organisation and lay the foundations for cognition and behaviour. Diffusion MRI and tractography provide unique opportunities for such explorations, through estimation of white matter bundles and brain connectivity. Atlas-based tractography protocols, i.e. a priori defined sets of masks and logical operations in a template space, have been commonly used in the adult brain to drive such explorations. However, rapid growth and maturation of the brain during early development make it challenging to ensure correspondence and validity of such atlas-based tractography approaches in the developing brain. An alternative can be provided by data-driven methods, which do not depend on predefined regions of interest. Here, we develop a novel data-driven framework to extract white matter bundles and their associated grey matter networks from neonatal tractography data, based on non-negative matrix factorisation that is inherently suited to the non-negative nature of structural connectivity data. We also develop a non-negative dual regression framework to map group-level components to individual subjects. Using in-silico simulations, we evaluate the accuracy of our approach in extracting connectivity components and compare with an alternative data-driven method, independent component analysis. We apply non-negative matrix factorisation to whole-brain connectivity obtained from publicly available datasets from the Developing Human Connectome Project, yielding grey matter components and their corresponding white matter bundles. We assess the validity and interpretability of these components against traditional tractography results and grey matter networks obtained from resting-state fMRI in the same subjects. We subsequently use them to generate a parcellation of the neonatal cortex using data from 323 new-born babies and we assess the robustness and reproducibility of this connectivity-driven parcellation.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-Negative Data-Driven Mapping of Structural Connections in the Neonatal Brain

Thompson

Mohammadi‐Nejad

Glasser³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…While the baby connectome project (BCP) and the developing human connectome project (http://www.developing http://connectome.org/project/) have begun to collect pediatric MR images, including 3D T1w, T2w, resting‐state functional MRI and diffusion‐weighted images, to construct a public database, but BCP database has been distributed for the limited purpose, such as iSeg‐2017 (http://iseg2017.web.unc.edu/) and the amount of available data with segmentation mask is still not sufficient. As an alternative, pretraining of the proposed network was conducted with the HCP dataset in this study using 50 T2w 3D MR volumes from different subjects.…”

Section: Methodsmentioning

confidence: 99%

“…Over the past decades, the introduction of MR image processing software (eg, SPM, Freesurfer, and FSL) and in vivo MR image databases (eg, human connectome project [HCP] database) has encouraged cross‐sectional studies and the use of quantitative measurements as diagnostic biomarkers. While these software provide robust brain extraction results for adult brains, it is rather difficult to perform neuroimaging studies with a pediatric brain due to smaller sizes and lower tissue contrast values of developing brains, not to mention the lack of public databases . In addition, existing brain extraction algorithms focus on identifying the brain tissues from T1‐weighted (T1w) images, although there are many occasions that benefit from the characteristics of T2‐weighted (T2w) images: estimation of cerebrospinal fluid in quantitative evaluation of brain atrophy, pathologic studies of pediatric brains (pediatric MRI brain: normal or abnormal, that is the question), etc.…”

Section: Introductionmentioning

confidence: 99%

“…While these software provide robust brain extraction results for adult brains, it is rather difficult to perform neuroimaging studies with a pediatric brain due to smaller sizes and lower tissue contrast values of developing brains, not to mention the lack of public databases. 7 In addition, existing brain extraction algorithms focus on identifying the brain tissues from T1-weighted (T1w) images, although there are many occasions that benefit from the characteristics of T2-weighted (T2w) images: estimation of cerebrospinal fluid in quantitative evaluation of brain atrophy, 4 pathologic studies of pediatric brains (pediatric MRI brain: normal or abnormal, that is the question), etc. More recently, deep learning-based pediatric brain segmentation techniques have been proposed for brain extraction and segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…However, the performance of iBEAT can be reduced for 2D MR images, because 3D volumetric pediatric MR images were utilized during the learning stage of iBEAT. In addition, the acquisition of 3D MR images require 5 to 6 minutes of imaging time depending on its contrast, 7 which may be difficult in many clinical settings due to the limitation in available imaging time for pediatric patients, but the 2D MR imaging sequence requires less than 3 minutes. 12,13 Thus, a brain extraction method for multislice T2w pediatric brain MR images is proposed in this study, based on the deep convolutional neural networks used for segmentation of medical images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pediatric brain extraction from T2‐weighted MR images using 3D dual frame U‐net and human connectome database

Kim

Chae

Han

2019

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Accurate extraction of brain tissues from magnetic resonance (MR) images is important in neuroradiology. However, brain extraction is more difficult for pediatric brains than for adult brains due to several factors including smaller brain sizes and lower tissue contrasts. In this work, we propose a brain extraction technique that utilizes dual frame (DF) 3D U‐net deep learning architecture and the human connectome project (HCP) database for multislice 2D pediatric T2‐weighted MR images with diseases. To improve segmentation accuracy in small pediatric brains with detailed boundary regions, DF 3D U‐net architecture was used. We pretrained networks with the HCP database to compensate for the limited amount of MR images and manual segmentation masks of pediatric patients. For quantitative analysis, we compared the brain extraction results of brain extraction tool, DF, and conventional 3D U‐net using the dice similarity coefficient (DSC), intersection of union (IoU), and boundary F1 (BF) scores; each deep learning architecture was evaluated with and without pretraining using the HCP. This study included 10 patients with diseases and all images were acquired using a PROPELLER MR sequence. Pretraining using the HCP database enhanced segmentation performance of the network, and the skip connections in the DF 3D U‐net could enhance the contour similarity of segmentation results. Experimental results showed that the proposed method increased the DSC, IoU, and BF scores by 0.8%, 1.6%, and 1.5%, respectively, compared with those of the conventional 3D U‐net without pretraining.

show abstract

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

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

show abstract

The UNC/UMN Baby Connectome Project (BCP): An overview of the study design and protocol development

Cited by 300 publications

References 132 publications

Non-Negative Data-Driven Mapping of Structural Connections in the Neonatal Brain

Non-Negative Data-Driven Mapping of Structural Connections in the Neonatal Brain

Pediatric brain extraction from T2‐weighted MR images using 3D dual frame U‐net and human connectome database

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

Contact Info

Product

Resources

About