AdaPT: An adaptive preterm segmentation algorithm for neonatal brain MRI

Development of cortical folds in the human brain: An attempt to review biological hypotheses, early neuroimaging investigations and functional correlates

The folding of the human brain mostly takes place in utero, making it challenging to study. After a few pioneer studies looking into it in post-mortem foetal specimen, modern approaches based on neuroimaging have allowed the community to investigate the folding process in vivo, its normal progression, its early disturbances, and its relationship to later functional outcomes. In this review article, we aimed to first give an overview of the current hypotheses on the mechanisms governing cortical folding. After describing the methodological difficulties raised by its study in fetuses, neonates and infants with magnetic resonance imaging (MRI), we reported our current understanding of sulcal pattern emergence in the developing brain. We then highlighted the functional relevance of early sulcal development, through recent insights about hemispheric asymmetries and early factors influencing this dynamic such as prematurity. Finally, we outlined how longitudinal studies have started to relate early folding markers and the child's sensorimotor and cognitive outcome. Through this review, we hope to raise awareness on the potential of studying early sulcal patterns both from a fundamental and clinical perspective, as a window into early neurodevelopment and plasticity in relation to growth in utero and postnatal environment of the child.

ConvNets for automatic detection of polyglutamine SCAs from brain MRIs: state of the art applications

Polyglutamine spinocerebellar ataxias (polyQ SCAs) are a group of neurodegenerative diseases, clinically and genetically heterogeneous, characterized by loss of balance and motor coordination due to dysfunction of the cerebellum and its connections. The diagnosis of each type of polyQ SCA, alongside with genetic tests, includes medical images analysis, and its automation may help specialists to distinguish between each type. Convolutional neural networks (ConvNets or CNNs) have been recently used for medical image processing, with outstanding results. In this work, we present the main clinical and imaging features of polyglutamine SCAs, and the basics of CNNs. Finally, we review studies that have used this approach to automatically process brain medical images and may be applied to SCAs detection. We conclude by discussing the possible limitations and opportunities of using ConvNets for SCAs diagnose in the future.

Segmentation of Infant Brain Using Nonnegative Matrix Factorization

This study develops an atlas-based automated framework for segmenting infants’ brains from magnetic resonance imaging (MRI). For the accurate segmentation of different structures of an infant’s brain at the isointense age (6–12 months), our framework integrates features of diffusion tensor imaging (DTI) (e.g., the fractional anisotropy (FA)). A brain diffusion tensor (DT) image and its region map are considered samples of a Markov–Gibbs random field (MGRF) that jointly models visual appearance, shape, and spatial homogeneity of a goal structure. The visual appearance is modeled with an empirical distribution of the probability of the DTI features, fused by their nonnegative matrix factorization (NMF) and allocation to data clusters. Projecting an initial high-dimensional feature space onto a low-dimensional space of the significant fused features with the NMF allows for better separation of the goal structure and its background. The cluster centers in the latter space are determined at the training stage by the K-means clustering. In order to adapt to large infant brain inhomogeneities and segment the brain images more accurately, appearance descriptors of both the first-order and second-order are taken into account in the fused NMF feature space. Additionally, a second-order MGRF model is used to describe the appearance based on the voxel intensities and their pairwise spatial dependencies. An adaptive shape prior that is spatially variant is constructed from a training set of co-aligned images, forming an atlas database. Moreover, the spatial homogeneity of the shape is described with a spatially uniform 3D MGRF of the second-order for region labels. In vivo experiments on nine infant datasets showed promising results in terms of the accuracy, which was computed using three metrics: the 95-percentile modified Hausdorff distance (MHD), the Dice similarity coefficient (DSC), and the absolute volume difference (AVD). Both the quantitative and visual assessments confirm that integrating the proposed NMF-fused DTI feature and intensity MGRF models of visual appearance, the adaptive shape prior, and the shape homogeneity MGRF model is promising in segmenting the infant brain DTI.

Automated 2D Slice-Based Skull Stripping Multi-View Ensemble Model on NFBS and IBSR Datasets

This study proposed and evaluated a two-dimensional (2D) slice-based multi-view U-Net (MVU-Net) architecture for skull stripping. The proposed model fused all three TI-weighted brain magnetic resonance imaging (MRI) views, i.e., axial, coronal, and sagittal. This 2D method performed equally well as a three-dimensional (3D) model of skull stripping. while using fewer computational resources. The predictions of all three views were fused linearly, producing a final brain mask with better accuracy and efficiency. Meanwhile, two publicly available datasets-the Internet Brain Segmentation Repository (IBSR) and Neurofeedback Skull-stripped (NFBS) repository-were trained and tested. The MVU-Net, U-Net, and skip connection U-Net (SCU-Net) architectures were then compared. For the IBSR dataset, compared to U-Net and SC-UNet, the MVU-Net architecture attained better mean dice score coefficient (DSC), sensitivity, and specificity, at 0.9184, 0.9397, and 0.9908, respectively. Similarly, the MVU-Net architecture achieved better mean DSC, sensitivity, and specificity, at 0.9681, 0.9763, and 0.9954, respectively, than the U-Net and SC-UNet for the NFBS dataset.

Esophagus Segmentation in CT Images via Spatial Attention Network and STAPLE Algorithm

One essential step in radiotherapy treatment planning is the organ at risk of segmentation in Computed Tomography (CT). Many recent studies have focused on several organs such as the lung, heart, esophagus, trachea, liver, aorta, kidney, and prostate. However, among the above organs, the esophagus is one of the most difficult organs to segment because of its small size, ambiguous boundary, and very low contrast in CT images. To address these challenges, we propose a fully automated framework for the esophagus segmentation from CT images. The proposed method is based on the processing of slice images from the original three-dimensional (3D) image so that our method does not require large computational resources. We employ the spatial attention mechanism with the atrous spatial pyramid pooling module to locate the esophagus effectively, which enhances the segmentation performance. To optimize our model, we use group normalization because the computation is independent of batch sizes, and its performance is stable. We also used the simultaneous truth and performance level estimation (STAPLE) algorithm to reach robust results for segmentation. Firstly, our model was trained by k-fold cross-validation. And then, the candidate labels generated by each fold were combined by using the STAPLE algorithm. And as a result, Dice and Hausdorff Distance scores have an improvement when applying this algorithm to our segmentation results. Our method was evaluated on SegTHOR and StructSeg 2019 datasets, and the experiment shows that our method outperforms the state-of-the-art methods in esophagus segmentation. Our approach shows a promising result in esophagus segmentation, which is still challenging in medical analyses.

Impacts of skull stripping on construction of three-dimensional T1-weighted imaging-based brain structural network in full-term neonates

BACKGROUND

Skull stripping remains a challenge for neonatal brain MR image analysis. However, little is known about the accuracy of how skull stripping affects the neonatal brain tissue segmentation and subsequent network construction. This paper therefore aimed to clarify this issue by comparing two automatic (FMRIB Software Library's Brain Extraction Tool, BET; Infant Brain Extraction and Analysis Toolbox, iBEAT) and a semiautomatic (iBEAT with manual correction) processes in constructing 3D T1-weighted imaging (T1WI)-based brain structural network.

METHODS

Twenty-two full-term neonates (gestational age, 37-42 weeks; boys/girls, 13/9) without abnormalities on MRI who underwent brain 3D T1WI were retrospectively recruited. Two automatic (BET and iBEAT) and a semiautomatic preprocessing (iBEAT with manual correction) workflows were separately used to perform the skull stripping. Brain tissue segmentation and volume calculation were performed by a Johns Hopkins atlas-based method. Sixty-four gray matter regions were selected as nodes; volume covariance network and its properties (clustering coefficient, C_p; characteristic path length, L_p; local efficiency, E_local; global efficiency, E_global) were calculated by GRETNA. Analysis of variance (ANOVA) was used to compare the differences in the calculated volume between three workflows.

RESULTS

There were significant differences in volumes of 50 brain regions between the three workflows (P < 0.05). Three neonatal brain structural networks presented small-world topology. The semiautomatic workflow showed remarkably decreased C_p, increased L_p, decreased E_local, and decreased E_global, in contrast to the two automatic ones.

CONCLUSIONS

Imperfect skull stripping indeed affected the accuracy of brain structural network in full-term neonates.

SegSRGAN: Super-resolution and segmentation using generative adversarial networks - Application to neonatal brain MRI

BACKGROUND AND OBJECTIVE

One of the main issues in the analysis of clinical neonatal brain MRI is the low anisotropic resolution of the data. In most MRI analysis pipelines, data are first re-sampled using interpolation or single image super-resolution techniques and then segmented using (semi-)automated approaches. In other words, image reconstruction and segmentation are then performed separately. In this article, we propose a methodology and a software solution for carrying out simultaneously high-resolution reconstruction and segmentation of brain MRI data.

METHODS

Our strategy mainly relies on generative adversarial networks. The network architecture is described in detail. We provide information about its implementation, focusing on the most crucial technical points (whereas complementary details are given in a dedicated GitHub repository). We illustrate the behavior of the proposed method for cortex analysis from neonatal MR images.

RESULTS

The results of the method, evaluated quantitatively (Dice, peak signal-to-noise ratio, structural similarity, number of connected components) and qualitatively on a research dataset (dHCP) and a clinical one (Epirmex), emphasize the relevance of the approach, and its ability to take advantage of data-augmentation strategies.

CONCLUSIONS

Results emphasize the potential of our proposed method/software with respect to practical medical applications. The method is provided as a freely available software tool, which allows one to carry out his/her own experiments, and involve the method for the super-resolution reconstruction and segmentation of arbitrary cerebral structures from any MR image dataset.

Conventional and Deep Learning Methods for Skull Stripping in Brain MRI

Skull stripping in brain magnetic resonance volume has recently been attracting attention due to an increased demand to develop an efficient, accurate, and general algorithm for diverse datasets of the brain. Accurate skull stripping is a critical step for neuroimaging diagnostic systems because neither the inclusion of non-brain tissues nor removal of brain parts can be corrected in subsequent steps, which results in unfixed error through subsequent analysis. The objective of this review article is to give a comprehensive overview of skull stripping approaches, including recent deep learning-based approaches. In this paper, the current methods of skull stripping have been divided into two distinct groups—conventional or classical approaches, and convolutional neural networks or deep learning approaches. The potentials of several methods are emphasized because they can be applied to standard clinical imaging protocols. Finally, current trends and future developments are addressed giving special attention to recent deep learning algorithms.

Brain Morphological Dynamics of Procrastination: The Crucial Role of the Self-Control, Emotional, and Episodic Prospection Network

Globally, about 17% individuals are suffering from the maladaptive procrastination until now, which impacts individual's financial status, mental health, and even public policy. However, the comprehensive understanding of neuroanatomical understructure of procrastination still remains gap. 688 participants including 3 independent samples were recruited for this study. Brain morphological dynamics referred to the idiosyncrasies of both brain size and brain shape. Multilinear regression analysis was utilized to delineate brain morphological dynamics of procrastination in Sample 1. In the Sample 2, cross-validation was yielded. Finally, prediction models of machine learning were conducted in Sample 3. Procrastination had a significantly positive correlation with the gray matter volume (GMV) in the left insula, anterior cingulate gyrus (ACC), and parahippocampal gyrus (PHC) but was negatively correlated with GMV of dorsolateral prefrontal cortex (dlPFC) and gray matter density of ACC. Furthermore, procrastination was positively correlated to the cortical thickness and cortical complexity of bilateral orbital frontal cortex (OFC). In Sample 2, all the results were cross-validated highly. Predication analysis demonstrated that these brain morphological dynamic can predict procrastination with high accuracy. This study ascertained the brain morphological dynamics involving in self-control, emotion, and episodic prospection brain network for procrastination, which advanced promising aspects of the biomarkers for it.

Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation

Precise 3D segmentation of infant brain tissues is an essential step towards comprehensive volumetric studies and quantitative analysis of early brain development. However, computing such segmentations is very challenging, especially for 6-month infant brain, due to the poor image quality, among other difficulties inherent to infant brain MRI, e.g., the isointense contrast between white and gray matter and the severe partial volume effect due to small brain sizes. This study investigates the problem with an ensemble of semi-dense fully convolutional neural networks (CNNs), which employs T1-weighted and T2-weighted MR images as input. We demonstrate that the ensemble agreement is highly correlated with the segmentation errors. Therefore, our method provides measures that can guide local user corrections. To the best of our knowledge, this work is the first ensemble of 3D CNNs for suggesting annotations within images. Our quasi-dense architecture allows the efficient propagation of gradients during training, while limiting the number of parameters, requiring one order of magnitude less parameters than popular medical image segmentation networks such as 3D U-Net (Çiçek, et al.). We also investigated the impact that early or late fusions of multiple image modalities might have on the performances of deep architectures. We report evaluations of our method on the public data of the MICCAI iSEG-2017 Challenge on 6-month infant brain MRI segmentation, and show very competitive results among 21 teams, ranking first or second in most metrics.

Image Updating for Brain Shift Compensation During Resection

BACKGROUND

In open-cranial neurosurgery, preoperative magnetic resonance (pMR) images are typically coregistered for intraoperative guidance. Their accuracy can be significantly degraded by intraoperative brain deformation, especially when resection is involved.

OBJECTIVE

To produce model updated MR (uMR) images to compensate for brain shift that occurred during resection, and evaluate the performance of the image-updating process in terms of accuracy and computational efficiency.

METHODS

In 14 resection cases, intraoperative stereovision image pairs were acquired after dural opening and during resection to generate displacement maps of the surgical field. These data were assimilated by a biomechanical model to create uMR volumes of the evolving surgical field. A tracked stylus provided independent measurements of feature locations to quantify target registration errors (TREs) in the original coregistered pMR and uMR as surgery progressed.

RESULTS

Updated MR TREs were 1.66 ± 0.27 and 1.92 ± 0.49 mm in the 14 cases after dural opening and after partial resection, respectively, compared to 8.48 ± 3.74 and 8.77 ± 4.61 mm for pMR, respectively. The overall computational time for generating uMRs after partial resection was less than 10 min.

CONCLUSION

We have developed an image-updating system to compensate for brain deformation during resection using a computational model with data assimilation of displacements measured with intraoperative stereovision imaging that maintains TREs less than 2 mm on average.

Image Based Brain Segmentation: From Multi-Atlas Fusion to Deep Learning

Background:

This review aims to identify the development of the algorithms for brain tissue and structure segmentation in MRI images.

Discussion:

Starting from the results of the Grand Challenges on brain tissue and structure segmentation held in Medical Image Computing and Computer-Assisted Intervention (MICCAI), this review analyses the development of the algorithms and discusses the tendency from multi-atlas label fusion to deep learning. The intrinsic characteristics of the winners’ algorithms on the Grand Challenges from the year 2012 to 2018 are analyzed and the results are compared carefully.

Conclusion:

Although deep learning has got higher rankings in the challenge, it has not yet met the expectations in terms of accuracy. More effective and specialized work should be done in the future.

Processing of structural neuroimaging data in young children: Bridging the gap between current practice and state-of-the-art methods

The structure of the brain is subject to very rapid developmental changes during early childhood. Pediatric studies based on Magnetic Resonance Imaging (MRI) over this age range have recently become more frequent, with the advantage of providing in vivo and non-invasive high-resolution images of the developing brain, toward understanding typical and atypical trajectories. However, it has also been demonstrated that application of currently standard MRI processing methods that have been developed with datasets from adults may not be appropriate for use with pediatric datasets. In this review, we examine the approaches currently used in MRI studies involving young children, including an overview of the rationale for new MRI processing methods that have been designed specifically for pediatric investigations. These methods are mainly related to the use of age-specific or 4D brain atlases, improved methods for quantifying and optimizing image quality, and provision for registration of developmental data obtained with longitudinal designs. The overall goal is to raise awareness of the existence of these methods and the possibilities for implementing them in developmental neuroimaging studies.

An iterative multi-atlas patch-based approach for cortex segmentation from neonatal MRI

Brain structure analysis in the newborn is a major health issue. This is especially the case for preterm neonates, in order to obtain predictive information related to the child development. In particular, the cortex is a structure of interest, that can be observed in magnetic resonance imaging (MRI). However, neonatal MRI data present specific properties that make them challenging to process. In this context, multi-atlas approaches constitute an efficient strategy, taking advantage of images processed beforehand. The method proposed in this article relies on such a multi-atlas strategy. More precisely, it uses two paradigms: first, a non-local model based on patches; second, an iterative optimization scheme. Coupling both concepts allows us to consider patches related not only to the image information, but also to the current segmentation. This strategy is compared to other multi-atlas methods proposed in the literature. Experiments on dHCP datasets show that the proposed approach provides robust cortex segmentation results.

A Pilot Study Investigating a Novel Non-Linear Measure of Eyes Open versus Eyes Closed EEG Synchronization in People with Alzheimer’s Disease and Healthy Controls

Background: The incidence of Alzheimer disease (AD) is increasing with the ageing population. The development of low cost non-invasive diagnostic aids for AD is a research priority. This pilot study investigated whether an approach based on a novel dynamic quantitative parametric EEG method could detect abnormalities in people with AD. Methods: 20 patients with probable AD, 20 matched healthy controls (HC) and 4 patients with probable fronto temporal dementia (FTD) were included. All had detailed neuropsychology along with structural, resting state fMRI and EEG. EEG data were analyzed using the Error Reduction Ratio-causality (ERR-causality) test that can capture both linear and nonlinear interactions between different EEG recording areas. The 95% confidence intervals of EEG levels of bi-centroparietal synchronization were estimated for eyes open (EO) and eyes closed (EC) states. Results: In the EC state, AD patients and HC had very similar levels of bi-centro parietal synchronization; but in the EO resting state, patients with AD had significantly higher levels of synchronization (AD = 0.44; interquartile range (IQR) 0.41 vs. HC = 0.15; IQR 0.17, p < 0.0001). The EO/EC synchronization ratio, a measure of the dynamic changes between the two states, also showed significant differences between these two groups (AD ratio 0.78 versus HC ratio 0.37 p < 0.0001). EO synchronization was also significantly different between AD and FTD (FTD = 0.075; IQR 0.03, p < 0.0001). However, the EO/EC ratio was not informative in the FTD group due to very low levels of synchronization in both states (EO and EC). Conclusion: In this pilot work, resting state quantitative EEG shows significant differences between healthy controls and patients with AD. This approach has the potential to develop into a useful non-invasive and economical diagnostic aid in AD.

Evaluation of methods for volumetric analysis of pediatric brain data: The child pipeline versus adult-based approaches

Pediatric brain volumetric analysis based on Magnetic Resonance Imaging (MRI) is of particular interest in order to understand the typical brain development and to characterize neurodevelopmental disorders at an early age. However, it has been shown that the results can be biased due to head motion, inherent to pediatric data, and due to the use of methods based on adult brain data that are not able to accurately model the anatomical disparity of pediatric brains. To overcome these issues, we proposed childmetrix, a tool developed for the analysis of pediatric neuroimaging data that uses an age-specific atlas and a probabilistic model-based approach in order to segment the gray matter (GM) and white matter (WM). The tool was extensively validated on 55 scans of children between 5 and 6 years old (including 13 children with developmental dyslexia) and 10 pairs of test-retest scans of children between 6 and 8 years old and compared with two state-of-the-art methods using an adult atlas, namely icobrain (applying a probabilistic model-based segmentation) and Freesurfer (applying a surface model-based segmentation). The results obtained with childmetrix showed a better reproducibility of GM and WM segmentations and a better robustness to head motion in the estimation of GM volume compared to Freesurfer. Evaluated on two subjects, childmetrix showed good accuracy with 82-84% overlap with manual segmentation for both GM and WM, thereby outperforming the adult-based methods (icobrain and Freesurfer), especially for the subject with poor quality data. We also demonstrated that the adult-based methods needed double the number of subjects to detect significant morphological differences between dyslexics and typical readers. Once further developed and validated, we believe that childmetrix would provide appropriate and reliable measures for the examination of children's brain.

The challenge of cerebral magnetic resonance imaging in neonates: A new method using mathematical morphology for the segmentation of structures including diffuse excessive high signal intensities

Preterm birth is a multifactorial condition associated with increased morbidity and mortality. Diffuse excessive high signal intensity (DEHSI) has been recently described on T2-weighted MR sequences in this population and thought to be associated with neuropathologies. To date, no robust and reproducible method to assess the presence of white matter hyperintensities has been developed, perhaps explaining the current controversy over their prognostic value. The aim of this paper is to propose a new semi-automated framework to detect DEHSI on neonatal brain MR images having a particular pattern due to the physiological lack of complete myelination of the white matter. A novel method for semi- automatic segmentation of neonatal brain structures and DEHSI, based on mathematical morphology and on max-tree representations of the images is thus described. It is a mandatory first step to identify and clinically assess homogeneous cohorts of neonates for DEHSI and/or volume of any other segmented structures. Implemented in a user-friendly interface, the method makes it straightforward to select relevant markers of structures to be segmented, and if needed, apply eventually manual corrections. This method responds to the increasing need for providing medical experts with semi-automatic tools for image analysis, and overcomes the limitations of visual analysis alone, prone to subjectivity and variability. Experimental results demonstrate that the method is accurate, with excellent reproducibility and with very few manual corrections needed. Although the method was intended initially for images acquired at 1.5T, which corresponds to the usual clinical practice, preliminary results on images acquired at 3T suggest that the proposed approach can be generalized.

The developing human connectome project: A minimal processing pipeline for neonatal cortical surface reconstruction

The Developing Human Connectome Project (dHCP) seeks to create the first 4-dimensional connectome of early life. Understanding this connectome in detail may provide insights into normal as well as abnormal patterns of brain development. Following established best practices adopted by the WU-MINN Human Connectome Project (HCP), and pioneered by FreeSurfer, the project utilises cortical surface-based processing pipelines. In this paper, we propose a fully automated processing pipeline for the structural Magnetic Resonance Imaging (MRI) of the developing neonatal brain. This proposed pipeline consists of a refined framework for cortical and sub-cortical volume segmentation, cortical surface extraction, and cortical surface inflation, which has been specifically designed to address considerable differences between adult and neonatal brains, as imaged using MRI. Using the proposed pipeline our results demonstrate that images collected from 465 subjects ranging from 28 to 45 weeks post-menstrual age (PMA) can be processed fully automatically; generating cortical surface models that are topologically correct, and correspond well with manual evaluations of tissue boundaries in 85% of cases. Results improve on state-of-the-art neonatal tissue segmentation models and significant errors were found in only 2% of cases, where these corresponded to subjects with high motion. Downstream, these surfaces will enhance comparisons of functional and diffusion MRI datasets, supporting the modelling of emerging patterns of brain connectivity.

The developing human connectome project: A minimal processing pipeline for neonatal cortical surface reconstruction

The Developing Human Connectome Project (dHCP) seeks to create the first 4-dimensional connectome of early life. Understanding this connectome in detail may provide insights into normal as well as abnormal patterns of brain development. Following established best practices adopted by the WU-MINN Human Connectome Project (HCP), and pioneered by FreeSurfer, the project utilises cortical surface-based processing pipelines. In this paper, we propose a fully automated processing pipeline for the structural Magnetic Resonance Imaging (MRI) of the developing neonatal brain. This proposed pipeline consists of a refined framework for cortical and sub-cortical volume segmentation, cortical surface extraction, and cortical surface inflation, which has been specifically designed to address considerable differences between adult and neonatal brains, as imaged using MRI. Using the proposed pipeline our results demonstrate that images collected from 465 subjects ranging from 28 to 45 weeks post-menstrual age (PMA) can be processed fully automatically; generating cortical surface models that are topologically correct, and correspond well with manual evaluations of tissue boundaries in 85% of cases. Results improve on state-of-the-art neonatal tissue segmentation models and significant errors were found in only 2% of cases, where these corresponded to subjects with high motion. Downstream, these surfaces will enhance comparisons of functional and diffusion MRI datasets, supporting the modelling of emerging patterns of brain connectivity.

Differential Rates of Perinatal Maturation of Human Primary and Nonprimary Auditory Cortex

Primary and nonprimary cerebral cortex mature along different timescales; however, the differences between the rates of maturation of primary and nonprimary cortex are unclear. Cortical maturation can be measured through changes in tissue microstructure detectable by diffusion magnetic resonance imaging (MRI). In this study, diffusion tensor imaging (DTI) was used to characterize the maturation of Heschl's gyrus (HG), which contains both primary auditory cortex (pAC) and nonprimary auditory cortex (nAC), in 90 preterm infants between 26 and 42 weeks postmenstrual age (PMA). The preterm infants were in different acoustical environments during their hospitalization: 46 in open ward beds and 44 in single rooms. A control group consisted of 15 term-born infants. Diffusion parameters revealed that (1) changes in cortical microstructure that accompany cortical maturation had largely already occurred in pAC by 28 weeks PMA, and (2) rapid changes were taking place in nAC between 26 and 42 weeks PMA. At term equivalent PMA, diffusion parameters for auditory cortex were different between preterm infants and term control infants, reflecting either delayed maturation or injury. No effect of room type was observed. For the preterm group, disturbed maturation of nonprimary (but not primary) auditory cortex was associated with poorer language performance at age two years.

Investigating the maturation of microstructure and radial orientation in the preterm human cortex with diffusion MRI

Preterm birth disrupts and alters the complex developmental processes in the cerebral cortex. This disruption may be a contributing factor to widespread delay and cognitive difficulties in the preterm population. Diffusion-weighted magnetic resonance imaging (DW MRI) is a noninvasive imaging technique that makes inferences about cellular structures, at scales smaller than the imaging resolution. One established finding is that DW MRI shows a transient radial alignment in the preterm cortex. In this study, we quantify this maturational process with the "radiality index", a parameter that measures directional coherence, which we expect to change rapidly in the perinatal period. To measure this index, we used structural T²-weighted MRI to segment the cortex and generate cortical meshes. We obtained normal vectors for each face of the mesh and compared them to the principal diffusion direction, calculated by both the DTI and DIAMOND models, to generate the radiality index. The subjects included in this study were 89 infants born at fewer than 34 weeks completed gestation, each imaged at up to four timepoints between 27 and 42 weeks gestational age. In this manuscript, we quantify the longitudinal trajectory of radiality, fractional anisotropy and mean diffusivity from the DTI and DIAMOND models. For the radiality index and fractional anisotropy, the DIAMOND model offers improved sensitivity over the DTI model. The radiality index has a consistent progression across time, with the rate of change depending on the cortical lobe. The occipital lobe changes most rapidly, and the frontal and temporal least: this is commensurate with known developmental anatomy. Analysing the radiality index offers information complementary to other diffusion parameters.

Regional volumetric assessment of the brain in moderately preterm infants (30-35 gestational weeks) scanned at term-equivalent age on magnetic resonance imaging

BACKGROUND

Early volume analyses of the infantile brain may help predict neurodevelopmental outcome. However, brain volumes are not well understood in moderately preterm infants at term-equivalent age (TEA).

AIM

This study retrospectively investigated the relationship between regional brain volumes and infant gestational age (GA) at birth in moderately preterm infants (30-35weeks' GA) on magnetic resonance imaging (MRI) at TEA.

METHODS

Forty infants scanned at TEA were enrolled. Regional brain volumes were estimated by manual segmentation on MRI, and their relationship with GA at birth was assessed.

RESULTS

The regional volumes of the cerebral hemispheres and deep gray matter were larger (Spearman ρ=0.40, P=0.01, and Spearman ρ=0.48, P<0.01, respectively), and volumes of the lateral ventricles were smaller (Spearman ρ=-0.32, P=0.04) in infants born at a later GA. The volumes of the cerebral hemispheres of the infants born at 30weeks' GA were significantly smaller than those born at 33 and 35weeks' GA (P<0.05). No associations were found between the volume of the cerebellum and brainstem, and GA at birth (Spearman ρ=0.24, P=0.13, and Spearman ρ=0.24, P=0.14, respectively).

CONCLUSIONS

The volumes of the cerebral hemispheres at TEA may be smaller in infants born at 30weeks' GA, whereas those of the cerebellum and brainstem may not be correlated with GA among moderately preterm infants.

SEGMA: An Automatic SEGMentation Approach for Human Brain MRI Using Sliding Window and Random Forests

Quantitative volumes from brain magnetic resonance imaging (MRI) acquired across the life course may be useful for investigating long term effects of risk and resilience factors for brain development and healthy aging, and for understanding early life determinants of adult brain structure. Therefore, there is an increasing need for automated segmentation tools that can be applied to images acquired at different life stages. We developed an automatic segmentation method for human brain MRI, where a sliding window approach and a multi-class random forest classifier were applied to high-dimensional feature vectors for accurate segmentation. The method performed well on brain MRI data acquired from 179 individuals, analyzed in three age groups: newborns (38–42 weeks gestational age), children and adolescents (4–17 years) and adults (35–71 years). As the method can learn from partially labeled datasets, it can be used to segment large-scale datasets efficiently. It could also be applied to different populations and imaging modalities across the life course.

Fully-Automated μMRI Morphometric Phenotyping of the Tc1 Mouse Model of Down Syndrome

We describe a fully automated pipeline for the morphometric phenotyping of mouse brains from μMRI data, and show its application to the Tc1 mouse model of Down syndrome, to identify new morphological phenotypes in the brain of this first transchromosomic animal carrying human chromosome 21. We incorporate an accessible approach for simultaneously scanning multiple ex vivo brains, requiring only a 3D-printed brain holder, and novel image processing steps for their separation and orientation. We employ clinically established multi-atlas techniques–superior to single-atlas methods–together with publicly-available atlas databases for automatic skull-stripping and tissue segmentation, providing high-quality, subject-specific tissue maps. We follow these steps with group-wise registration, structural parcellation and both Voxel- and Tensor-Based Morphometry–advantageous for their ability to highlight morphological differences without the laborious delineation of regions of interest. We show the application of freely available open-source software developed for clinical MRI analysis to mouse brain data: NiftySeg for segmentation and NiftyReg for registration, and discuss atlases and parameters suitable for the preclinical paradigm. We used this pipeline to compare 29 Tc1 brains with 26 wild-type littermate controls, imaged ex vivo at 9.4T. We show an unexpected increase in Tc1 total intracranial volume and, controlling for this, local volume and grey matter density reductions in the Tc1 brain compared to the wild-types, most prominently in the cerebellum, in agreement with human DS and previous histological findings.

Cortical folding of the preterm brain: a longitudinal analysis of extremely preterm born neonates using spectral matching

INTRODUCTION

Infants born extremely preterm (<28 weeks of gestation) are at risk of significant neurodevelopmental sequelae. In these infants birth coincides with a period of rapid brain growth and development, when the brain is also vulnerable to a range of insults. Mapping these changes is crucial for identifying potential biomarkers to predict early impairment.

METHODS

In this study we use surface-based spectral matching techniques to find an intrasubject longitudinal surface correspondence between the white-grey matter boundary at 30 and 40 weeks equivalent gestational age in nine extremely preterm born infants.

RESULTS

Using the resulting surface correspondence, we identified regions that undergo more cortical folding of the white-grey matter boundary during the preterm period by looking at changes in well-known curvature measures. We performed Hotelling T(2) statistics to evaluate the significance of our findings.

DISCUSSION

The prefrontal and temporal lobes exhibit most development during the preterm period, especially in the left hemisphere. Such correspondences are a promising result as longitudinal measurements of change in cortical folding could provide insightful information about the mechanical properties of the underlying tissue and may be useful in inferring changes during growth and development in this vulnerable period.

Automatic Segmentation of MR Brain Images With a Convolutional Neural Network

Automatic segmentation in MR brain images is important for quantitative analysis in large-scale studies with images acquired at all ages. This paper presents a method for the automatic segmentation of MR brain images into a number of tissue classes using a convolutional neural network. To ensure that the method obtains accurate segmentation details as well as spatial consistency, the network uses multiple patch sizes and multiple convolution kernel sizes to acquire multi-scale information about each voxel. The method is not dependent on explicit features, but learns to recognise the information that is important for the classification based on training data. The method requires a single anatomical MR image only. The segmentation method is applied to five different data sets: coronal T₂-weighted images of preterm infants acquired at 30 weeks postmenstrual age (PMA) and 40 weeks PMA, axial T₂-weighted images of preterm infants acquired at 40 weeks PMA, axial T₁-weighted images of ageing adults acquired at an average age of 70 years, and T₁-weighted images of young adults acquired at an average age of 23 years. The method obtained the following average Dice coefficients over all segmented tissue classes for each data set, respectively: 0.87, 0.82, 0.84, 0.86, and 0.91. The results demonstrate that the method obtains accurate segmentations in all five sets, and hence demonstrates its robustness to differences in age and acquisition protocol.

Neonatal Brain Tissue Classification with Morphological Adaptation and Unified Segmentation

Measuring the distribution of brain tissue types (tissue classification) in neonates is necessary for studying typical and atypical brain development, such as that associated with preterm birth, and may provide biomarkers for neurodevelopmental outcomes. Compared with magnetic resonance images of adults, neonatal images present specific challenges that require the development of specialized, population-specific methods. This paper introduces MANTiS (Morphologically Adaptive Neonatal Tissue Segmentation), which extends the unified segmentation approach to tissue classification implemented in Statistical Parametric Mapping (SPM) software to neonates. MANTiS utilizes a combination of unified segmentation, template adaptation via morphological segmentation tools and topological filtering, to segment the neonatal brain into eight tissue classes: cortical gray matter, white matter, deep nuclear gray matter, cerebellum, brainstem, cerebrospinal fluid (CSF), hippocampus and amygdala. We evaluated the performance of MANTiS using two independent datasets. The first dataset, provided by the NeoBrainS12 challenge, consisted of coronal T₂-weighted images of preterm infants (born ≤30 weeks' gestation) acquired at 30 weeks' corrected gestational age (n = 5), coronal T₂-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5) and axial T₂-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5). The second dataset, provided by the Washington University NeuroDevelopmental Research (WUNDeR) group, consisted of T₂-weighted images of preterm infants (born <30 weeks' gestation) acquired shortly after birth (n = 12), preterm infants acquired at term-equivalent age (n = 12), and healthy term-born infants (born ≥38 weeks' gestation) acquired within the first 9 days of life (n = 12). For the NeoBrainS12 dataset, mean Dice scores comparing MANTiS with manual segmentations were all above 0.7, except for the cortical gray matter for coronal images acquired at 30 weeks. This demonstrates that MANTiS' performance is competitive with existing techniques. For the WUNDeR dataset, mean Dice scores comparing MANTiS with manually edited segmentations demonstrated good agreement, where all scores were above 0.75, except for the hippocampus and amygdala. The results show that MANTiS is able to segment neonatal brain tissues well, even in images that have brain abnormalities common in preterm infants. MANTiS is available for download as an SPM toolbox from http://developmentalimagingmcri.github.io/mantis.

Accurate Learning with Few Atlases (ALFA): an algorithm for MRI neonatal brain extraction and comparison with 11 publicly available methods

Accurate whole-brain segmentation, or brain extraction, of magnetic resonance imaging (MRI) is a critical first step in most neuroimage analysis pipelines. The majority of brain extraction algorithms have been developed and evaluated for adult data and their validity for neonatal brain extraction, which presents age-specific challenges for this task, has not been established. We developed a novel method for brain extraction of multi-modal neonatal brain MR images, named ALFA (Accurate Learning with Few Atlases). The method uses a new sparsity-based atlas selection strategy that requires a very limited number of atlases 'uniformly' distributed in the low-dimensional data space, combined with a machine learning based label fusion technique. The performance of the method for brain extraction from multi-modal data of 50 newborns is evaluated and compared with results obtained using eleven publicly available brain extraction methods. ALFA outperformed the eleven compared methods providing robust and accurate brain extraction results across different modalities. As ALFA can learn from partially labelled datasets, it can be used to segment large-scale datasets efficiently. ALFA could also be applied to other imaging modalities and other stages across the life course.

Longitudinal development in the preterm thalamus and posterior white matter: MRI correlations between diffusion weighted imaging and T2 relaxometry

Infants born prematurely are at increased risk of adverse neurodevelopmental outcome. The measurement of white matter tissue composition and structure can help predict functional performance. Specifically, measurements of myelination and indicators of myelination status in the preterm brain could be predictive of later neurological outcome. Quantitative imaging of myelin could thus serve to develop biomarkers for prognosis or therapeutic intervention; however, accurate estimation of myelin content is difficult. This work combines diffusion MRI and multi-component T2 relaxation measurements in a group of 37 infants born very preterm and scanned between 27 and 58 weeks equivalent gestational age. Seven infants have longitudinal data at two time points that we analyze in detail. Our aim is to show that measurement of the myelin water fraction is achievable using widely available pulse sequences and state-of-the-art algorithmic modeling of the MR imaging procedure and that a multi-component fitting routine to multi-shell diffusion weighted data can show differences in neurite density and local spatial arrangement in grey and white matter. Inference on the myelin water fraction allows us to demonstrate that the change in diffusion properties of the preterm thalamus is not solely due to myelination (that increase in myelin content accounts for about a third of the observed changes) whilst the decrease in the posterior white matter T2 has no significant component that is due to myelin water content. This work applies multi-modal advanced quantitative neuroimaging to investigate changing tissue properties in the longitudinal setting. Hum Brain Mapp 37:2479-2492, 2016. © 2016 Wiley Periodicals, Inc.

Patch-based augmentation of Expectation-Maximization for brain MRI tissue segmentation at arbitrary age after premature birth

Accurate automated tissue segmentation of premature neonatal magnetic resonance images is a crucial task for quantification of brain injury and its impact on early postnatal growth and later cognitive development. In such studies it is common for scans to be acquired shortly after birth or later during the hospital stay and therefore occur at arbitrary gestational ages during a period of rapid developmental change. It is important to be able to segment any of these scans with comparable accuracy. Previous work on brain tissue segmentation in premature neonates has focused on segmentation at specific ages. Here we look at solving the more general problem using adaptations of age specific atlas based methods and evaluate this using a unique manually traced database of high resolution images spanning 20 gestational weeks of development. We examine the complimentary strengths of age specific atlas-based Expectation-Maximization approaches and patch-based methods for this problem and explore the development of two new hybrid techniques, patch-based augmentation of Expectation-Maximization with weighted fusion and a spatial variability constrained patch search. The former approach seeks to combine the advantages of both atlas- and patch-based methods by learning from the performance of the two techniques across the brain anatomy at different developmental ages, while the latter technique aims to use anatomical variability maps learnt from atlas training data to locally constrain the patch-based search range. The proposed approaches were evaluated using leave-one-out cross-validation. Compared with the conventional age specific atlas-based segmentation and direct patch based segmentation, both new approaches demonstrate improved accuracy in the automated labeling of cortical gray matter, white matter, ventricles and sulcal cortical-spinal fluid regions, while maintaining comparable results in deep gray matter.

Regional growth and atlasing of the developing human brain

Detailed morphometric analysis of the neonatal brain is required to characterise brain development and define neuroimaging biomarkers related to impaired brain growth. Accurate automatic segmentation of neonatal brain MRI is a prerequisite to analyse large datasets. We have previously presented an accurate and robust automatic segmentation technique for parcellating the neonatal brain into multiple cortical and subcortical regions. In this study, we further extend our segmentation method to detect cortical sulci and provide a detailed delineation of the cortical ribbon. These detailed segmentations are used to build a 4-dimensional spatio-temporal structural atlas of the brain for 82 cortical and subcortical structures throughout this developmental period. We employ the algorithm to segment an extensive database of 420 MR images of the developing brain, from 27 to 45 weeks post-menstrual age at imaging. Regional volumetric and cortical surface measurements are derived and used to investigate brain growth and development during this critical period and to assess the impact of immaturity at birth. Whole brain volume, the absolute volume of all structures studied, cortical curvature and cortical surface area increased with increasing age at scan. Relative volumes of cortical grey matter, cerebellum and cerebrospinal fluid increased with age at scan, while relative volumes of white matter, ventricles, brainstem and basal ganglia and thalami decreased. Preterm infants at term had smaller whole brain volumes, reduced regional white matter and cortical and subcortical grey matter volumes, and reduced cortical surface area compared with term born controls, while ventricular volume was greater in the preterm group. Increasing prematurity at birth was associated with a reduction in total and regional white matter, cortical and subcortical grey matter volume, an increase in ventricular volume, and reduced cortical surface area.

•

A novel methodology is proposed for delineating the cortical ribbon.

•

Regional brain growth is assessed in the developing preterm brain.

•

We investigate the effect of prematurity on brain growth and cortical development.

•

A spatio-temporal neonatal atlas is constructed with 82 brain structures.

Bayesian model selection for pathological neuroimaging data applied to white matter lesion segmentation

In neuroimaging studies, pathologies can present themselves as abnormal intensity patterns. Thus, solutions for detecting abnormal intensities are currently under investigation. As each patient is unique, an unbiased and biologically plausible model of pathological data would have to be able to adapt to the subject's individual presentation. Such a model would provide the means for a better understanding of the underlying biological processes and improve one's ability to define pathologically meaningful imaging biomarkers. With this aim in mind, this work proposes a hierarchical fully unsupervised model selection framework for neuroimaging data which enables the distinction between different types of abnormal image patterns without pathological a priori knowledge. Its application on simulated and clinical data demonstrated the ability to detect abnormal intensity clusters, resulting in a competitive to improved behavior in white matter lesion segmentation when compared to three other freely-available automated methods.

Automatic segmentation of the hippocampus for preterm neonates from early-in-life to term-equivalent age

Introduction

The hippocampus, a medial temporal lobe structure central to learning and memory, is particularly vulnerable in preterm-born neonates. To date, segmentation of the hippocampus for preterm-born neonates has not yet been performed early-in-life (shortly after birth when clinically stable). The present study focuses on the development and validation of an automatic segmentation protocol that is based on the MAGeT-Brain (Multiple Automatically Generated Templates) algorithm to delineate the hippocampi of preterm neonates on their brain MRIs acquired at not only term-equivalent age but also early-in-life.

Methods

First, we present a three-step manual segmentation protocol to delineate the hippocampus for preterm neonates and apply this protocol on 22 early-in-life and 22 term images. These manual segmentations are considered the gold standard in assessing the automatic segmentations. MAGeT-Brain, automatic hippocampal segmentation pipeline, requires only a small number of input atlases and reduces the registration and resampling errors by employing an intermediate template library. We assess the segmentation accuracy of MAGeT-Brain in three validation studies, evaluate the hippocampal growth from early-in-life to term-equivalent age, and study the effect of preterm birth on the hippocampal volume. The first experiment thoroughly validates MAGeT-Brain segmentation in three sets of 10-fold Monte Carlo cross-validation (MCCV) analyses with 187 different groups of input atlases and templates. The second experiment segments the neonatal hippocampi on 168 early-in-life and 154 term images and evaluates the hippocampal growth rate of 125 infants from early-in-life to term-equivalent age. The third experiment analyzes the effect of gestational age (GA) at birth on the average hippocampal volume at early-in-life and term-equivalent age using linear regression.

Results

The final segmentations demonstrate that MAGeT-Brain consistently provides accurate segmentations in comparison to manually derived gold standards (mean Dice's Kappa > 0.79 and Euclidean distance <1.3 mm between centroids). Using this method, we demonstrate that the average volume of the hippocampus is significantly different (p < 0.0001) in early-in-life (621.8 mm³) and term-equivalent age (958.8 mm³). Using these differences, we generalize the hippocampal growth rate to 38.3 ± 11.7 mm³/week and 40.5 ± 12.9 mm³/week for the left and right hippocampi respectively. Not surprisingly, younger gestational age at birth is associated with smaller volumes of the hippocampi (p = 0.001).

Conclusions

MAGeT-Brain is capable of segmenting hippocampi accurately in preterm neonates, even at early-in-life. Hippocampal asymmetry with a larger right side is demonstrated on early-in-life images, suggesting that this phenomenon has its onset in the 3rd trimester of gestation. Hippocampal volume assessed at the time of early-in-life and term-equivalent age is linearly associated with GA at birth, whereby smaller volumes are associated with earlier birth.

•

We develop a MAGeT-Brain based automatic protocol to segment hippocampus in preterm neonates.

•

MAGeT-Brain can accurately segment hippocampus in preterm neonates, even at early-in-life.

•

Hippocampal asymmetry with a larger right side is demonstrated on early-in-life images.

•

Smaller hippocampal volumes are associated with earlier birth in preterm neonates.

Longitudinal measurement of the developing grey matter in preterm subjects using multi-modal MRI

Preterm birth is a major public health concern, with the severity and occurrence of adverse outcome increasing with earlier delivery. Being born preterm disrupts a time of rapid brain development: in addition to volumetric growth, the cortex folds, myelination is occurring and there are changes on the cellular level. These neurological events have been imaged non-invasively using diffusion-weighted (DW) MRI. In this population, there has been a focus on examining diffusion in the white matter, but the grey matter is also critically important for neurological health. We acquired multi-shell high-resolution diffusion data on 12 infants born at ≤ 28 weeks of gestational age at two time-points: once when stable after birth, and again at term-equivalent age. We used the Neurite Orientation Dispersion and Density Imaging model (NODDI) (Zhang et al., 2012) to analyse the changes in the cerebral cortex and the thalamus, both grey matter regions. We showed region-dependent changes in NODDI parameters over the preterm period, highlighting underlying changes specific to the microstructure. This work is the first time that NODDI parameters have been evaluated in both the cortical and the thalamic grey matter as a function of age in preterm infants, offering a unique insight into neuro-development in this at-risk population.

Deep convolutional neural networks for multi-modality isointense infant brain image segmentation

The segmentation of infant brain tissue images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) plays an important role in studying early brain development in health and disease. In the isointense stage (approximately 6-8 months of age), WM and GM exhibit similar levels of intensity in both T1 and T2 MR images, making the tissue segmentation very challenging. Only a small number of existing methods have been designed for tissue segmentation in this isointense stage; however, they only used a single T1 or T2 images, or the combination of T1 and T2 images. In this paper, we propose to use deep convolutional neural networks (CNNs) for segmenting isointense stage brain tissues using multi-modality MR images. CNNs are a type of deep models in which trainable filters and local neighborhood pooling operations are applied alternatingly on the raw input images, resulting in a hierarchy of increasingly complex features. Specifically, we used multi-modality information from T1, T2, and fractional anisotropy (FA) images as inputs and then generated the segmentation maps as outputs. The multiple intermediate layers applied convolution, pooling, normalization, and other operations to capture the highly nonlinear mappings between inputs and outputs. We compared the performance of our approach with that of the commonly used segmentation methods on a set of manually segmented isointense stage brain images. Results showed that our proposed model significantly outperformed prior methods on infant brain tissue segmentation. In addition, our results indicated that integration of multi-modality images led to significant performance improvement.

Template-Based Multimodal Joint Generative Model of Brain Data

The advent of large of multi-modal imaging databases opens up the opportunity to learn how local intensity patterns covariate between multiple modalities. These models can then be used to describe expected intensities in an unseen image modalities given one or multiple observations, or to detect deviations (e.g. pathology) from the expected intensity patterns. In this work, we propose a template-based multi-modal generative mixture-model of imaging data and apply it to the problems of inlier/outlier pattern classification and image synthesis. Results on synthetic and patient data demonstrate that the proposed method is able to synthesise unseen data and accurately localise pathological regions, even in the presence of large abnormalities. It also demonstrates that the proposed model can provide accurate and uncertainty-aware intensity estimates of expected imaging patterns.

Robust whole-brain segmentation: application to traumatic brain injury

We propose a framework for the robust and fully-automatic segmentation of magnetic resonance (MR) brain images called "Multi-Atlas Label Propagation with Expectation-Maximisation based refinement" (MALP-EM). The presented approach is based on a robust registration approach (MAPER), highly performant label fusion (joint label fusion) and intensity-based label refinement using EM. We further adapt this framework to be applicable for the segmentation of brain images with gross changes in anatomy. We propose to account for consistent registration errors by relaxing anatomical priors obtained by multi-atlas propagation and a weighting scheme to locally combine anatomical atlas priors and intensity-refined posterior probabilities. The method is evaluated on a benchmark dataset used in a recent MICCAI segmentation challenge. In this context we show that MALP-EM is competitive for the segmentation of MR brain scans of healthy adults when compared to state-of-the-art automatic labelling techniques. To demonstrate the versatility of the proposed approach, we employed MALP-EM to segment 125 MR brain images into 134 regions from subjects who had sustained traumatic brain injury (TBI). We employ a protocol to assess segmentation quality if no manual reference labels are available. Based on this protocol, three independent, blinded raters confirmed on 13 MR brain scans with pathology that MALP-EM is superior to established label fusion techniques. We visually confirm the robustness of our segmentation approach on the full cohort and investigate the potential of derived symmetry-based imaging biomarkers that correlate with and predict clinically relevant variables in TBI such as the Marshall Classification (MC) or Glasgow Outcome Score (GOS). Specifically, we show that we are able to stratify TBI patients with favourable outcomes from non-favourable outcomes with 64.7% accuracy using acute-phase MR images and 66.8% accuracy using follow-up MR images. Furthermore, we are able to differentiate subjects with the presence of a mass lesion or midline shift from those with diffuse brain injury with 76.0% accuracy. The thalamus, putamen, pallidum and hippocampus are particularly affected. Their involvement predicts TBI disease progression.

Brain volume estimation from post-mortem newborn and fetal MRI

Objective

Minimally invasive autopsy using post-mortem magnetic resonance imaging (MRI) is a valid alternative to conventional autopsy in fetuses and infants. Estimation of brain weight is an integral part of autopsy, but manual segmentation of organ volumes on MRI is labor intensive and prone to errors, therefore unsuitable for routine clinical practice. In this paper we aim to show that volumetric measurements of the post-mortem fetal and neonatal brain can be accurately estimated using semi-automatic techniques and a high correlation can be found with the weights measured from conventional autopsy results.

Methods

The brains of 17 newborn subjects, part of Magnetic Resonance Imaging Autopsy Study (MaRIAS), were segmented from post-mortem MR images into cerebrum, cerebellum and brainstem using a publicly available neonate brain atlas and semi-automatic segmentation algorithm. The results of the segmentation were averaged to create a new atlas, which was then used for the automated atlas-based segmentation of 17 MaRIAS fetus subjects. As validation, we manually segmented the MR images from 8 subjects of each cohort and compared them with the automatic ones. The semi-automatic estimation of cerebrum weight was compared with the results of the conventional autopsy.

Results

The Dice overlaps between the manual and automatic segmentations are 0.991 and 0.992 for cerebrum, 0.873 and 0.888 for cerebellum and 0.819 and 0.815 for brainstem, for newborns and fetuses, respectively. Excellent agreement was obtained between the estimated MR weights and autopsy gold standard ones: mean absolute difference of 5 g and 2% maximum error for the fetus cohort and mean absolute difference of 20 g and 11% maximum error for the newborn one.

Conclusions

The high correlation between the obtained segmentation and autopsy weights strengthens the idea of using post-mortem MRI as an alternative for conventional autopsy of the brain.

•

We segment the cerebrum of 17 newborns and 17 fetuses from postmortem MR.

•

There is high correlation between the autopsy and MR segmentation brain volumes.

•

Postmortem MR can be a non-invasive alternative to conventional autopsy of infants.

Automatic whole brain MRI segmentation of the developing neonatal brain

Magnetic resonance (MR) imaging is increasingly being used to assess brain growth and development in infants. Such studies are often based on quantitative analysis of anatomical segmentations of brain MR images. However, the large changes in brain shape and appearance associated with development, the lower signal to noise ratio and partial volume effects in the neonatal brain present challenges for automatic segmentation of neonatal MR imaging data. In this study, we propose a framework for accurate intensity-based segmentation of the developing neonatal brain, from the early preterm period to term-equivalent age, into 50 brain regions. We present a novel segmentation algorithm that models the intensities across the whole brain by introducing a structural hierarchy and anatomical constraints. The proposed method is compared to standard atlas-based techniques and improves label overlaps with respect to manual reference segmentations. We demonstrate that the proposed technique achieves highly accurate results and is very robust across a wide range of gestational ages, from 24 weeks gestational age to term-equivalent age.

[Recent advances in newborn MRI]

The accurate morphological exploration of the brain is a major challenge in neonatology that advances in magnetic resonance imaging (MRI) can now provide. MRI is the gold standard if an hypoxic ischemic pathology is suspected in a full term neonate. In prematures, the specific role of MRI remains to be defined, secondary to US in any case. We present a state of the art of hardware and software technical developments in MRI. The increase in magnetic field strength (3 tesla) and the emergence of new MRI sequences provide access to new information. They both have positive and negative consequences on the daily clinical data acquisition use. The semiology of brain imaging in full term newborns and prematures is more extensive and complex and thereby more difficult to interpret. The segmentation of different brain structures in the newborn, even very premature, is now available. It is now possible to dissociate the cortex and basal ganglia from the cerebral white matter, to calculate the volume of anatomical structures, which improves the morphometric quantification and the understanding of the normal and abnormal brain development. MRI is a powerful tool to analyze the neonatal brain. The relevance of the diagnostic contribution requires an adaptation of the parameters of the sequences to acquire and of the image processing methods.

Measurement of myelin in the preterm brain: multi-compartment diffusion imaging and multi-component T2 relaxometry

Measurements of myelination and indicators of myelination status in the preterm brain could be predictive of later neurological outcome. Quantitative imaging of myelin could thus serve to develop predictive biomarkers; however, accurate estimation of myelin content is difficult. In this work we show that measurement of the myelin water fraction (MWF) is achievable using widely available pulse sequences and state-of-the-art algorithmic modelling of the MR imaging. We show results of myelin water fraction measurement at both 30 (4 infants) and 40 (2 infants) weeks equivalent gestational age (EGA) and show that the spatial pattern of myelin is different between these ages. Furthermore we apply a multi-component fitting routine to multi-shell diffusion weighted data to show differences in neurite density and local spatial arrangement in grey and white matter. Finally we combine these results to investigate the relationships between the diffusion and myelin measurements to show that MWF in the preterm brain may be measured alongside multi-component diffusion characteristics using clinically feasible MR sequences.

Integration of sparse multi-modality representation and anatomical constraint for isointense infant brain MR image segmentation

Segmentation of infant brain MR images is challenging due to poor spatial resolution, severe partial volume effect, and the ongoing maturation and myelination processes. During the first year of life, the brain image contrast between white and gray matters undergoes dramatic changes. In particular, the image contrast inverses around 6-8months of age, where the white and gray matter tissues are isointense in T1 and T2 weighted images and hence exhibit the extremely low tissue contrast, posing significant challenges for automated segmentation. In this paper, we propose a general framework that adopts sparse representation to fuse the multi-modality image information and further incorporate the anatomical constraints for brain tissue segmentation. Specifically, we first derive an initial segmentation from a library of aligned images with ground-truth segmentations by using sparse representation in a patch-based fashion for the multi-modality T1, T2 and FA images. The segmentation result is further iteratively refined by integration of the anatomical constraint. The proposed method was evaluated on 22 infant brain MR images acquired at around 6months of age by using a leave-one-out cross-validation, as well as other 10 unseen testing subjects. Our method achieved a high accuracy for the Dice ratios that measure the volume overlap between automated and manual segmentations, i.e., 0.889±0.008 for white matter and 0.870±0.006 for gray matter.

Automatic segmentation of eight tissue classes in neonatal brain MRI

Purpose

Volumetric measurements of neonatal brain tissues may be used as a biomarker for later neurodevelopmental outcome. We propose an automatic method for probabilistic brain segmentation in neonatal MRIs.

Materials and Methods

In an IRB-approved study axial T1- and T2-weighted MR images were acquired at term-equivalent age for a preterm cohort of 108 neonates. A method for automatic probabilistic segmentation of the images into eight cerebral tissue classes was developed: cortical and central grey matter, unmyelinated and myelinated white matter, cerebrospinal fluid in the ventricles and in the extra cerebral space, brainstem and cerebellum. Segmentation is based on supervised pixel classification using intensity values and spatial positions of the image voxels. The method was trained and evaluated using leave-one-out experiments on seven images, for which an expert had set a reference standard manually. Subsequently, the method was applied to the remaining 101 scans, and the resulting segmentations were evaluated visually by three experts. Finally, volumes of the eight segmented tissue classes were determined for each patient.

Results

The Dice similarity coefficients of the segmented tissue classes, except myelinated white matter, ranged from 0.75 to 0.92. Myelinated white matter was difficult to segment and the achieved Dice coefficient was 0.47. Visual analysis of the results demonstrated accurate segmentations of the eight tissue classes. The probabilistic segmentation method produced volumes that compared favorably with the reference standard.

Conclusion

The proposed method provides accurate segmentation of neonatal brain MR images into all given tissue classes, except myelinated white matter. This is the one of the first methods that distinguishes cerebrospinal fluid in the ventricles from cerebrospinal fluid in the extracerebral space. This method might be helpful in predicting neurodevelopmental outcome and useful for evaluating neuroprotective clinical trials in neonates.

Preterm birth affects the developmental synergy between cortical folding and cortical connectivity observed on multimodal MRI

The survival rates of infants born prematurely have improved as a result of advances in neonatal care, although there remains an increased risk of subsequent disability. Accurate measurement of the shape and appearance of the very preterm brain at term-equivalent age may guide the development of predictive biomarkers of neurological outcome. We demonstrate in 92 preterm infants (born at an average gestational age of 27.0±2.7weeks) scanned at term equivalent age (scanned at 40.4±1.74weeks) that the cortical sulcation ratio varies spatially over the cortical surface at term equivalent age and correlates significantly with gestational age at birth (r=0.49,p<0.0001). In the underlying white matter, fractional anisotropy of local white matter regions correlated significantly with gestational age at birth at term equivalent age (for the genu of the corpus callosum r=0.26,p=0.02 and for the splenium r=0.52,p<0.001) and in addition the fractional anisotropy in these local regions varies according to location. Finally, we demonstrate that connectivity measurements from tractography correlate significantly and specifically with the sulcation ratio of the overlying cortical surface at term equivalent age in a subgroup of 20 infants (r={0.67,0.61,0.86}, p={0.004,0.01,0.00002}) for tract systems emanating from the left and right corticospinal tracts and the corpus callosum respectively). Combined, these results suggest a close relationship between the cortical surface phenotype and underlying white matter structure assessed by diffusion weighted MRI. The spatial surface pattern may allow inference on the connectivity and developmental trajectory of the underlying white matter complementary to diffusion imaging and this result may guide the development of biomarkers of functional outcome.