Simultaneous truth and performance level estimation through fusion of probabilistic segmentations

Topology-preserving contourwise shape fusion

The preservation of morphological features, such as protrusions and concavities, and of the topology of input shapes is important when establishing reference data for benchmarking segmentation algorithms or when constructing a mean or median shape. We present a contourwise topology-preserving fusion method, called shape-aware topology-preserving means (SATM), for merging complex simply connected shapes. The method is based on key point matching and piecewise contour averaging. Unlike existing pixelwise and contourwise fusion methods, SATM preserves topology and does not smooth morphological features. We also present a detailed comparison of SATM with state-of-the-art fusion techniques for the purpose of benchmarking and median shape construction. Our experiments show that SATM outperforms these techniques in terms of shape-related measures that reflect shape complexity, manifesting itself as a reliable method for both establishing a consensus of segmentation annotations and for computing mean shapes.

Extended Technical and Clinical Validation of Deep Learning-Based Brainstem Segmentation for Application in Neurodegenerative Diseases

Disorders of the central nervous system, including neurodegenerative diseases, frequently affect the brainstem and can present with focal atrophy. This study aimed to (1) optimize deep learning-based brainstem segmentation for a wide range of pathologies and T1-weighted image acquisition parameters, (2) conduct a systematic technical and clinical validation, (3) improve segmentation quality in the presence of brainstem lesions, and (4) make an optimized brainstem segmentation tool available for public use. An intentionally heterogeneous ground truth dataset (n = 257) was employed in the training of deep learning models based on multi-dimensional gated recurrent units (MD-GRU) or the nnU-Net method. Segmentation performance was evaluated against ground truth labels. FreeSurfer was used for benchmarking in subsequent validation. Technical validation, including scan-rescan repeatability (n = 46) and inter-scanner reproducibility (n = 20, 3 different scanners) in unseen data, was conducted in patients with cerebral small vessel disease. Clinical validation in unseen data was performed in 1-year follow-up data of 16 patients with multiple system atrophy, evaluating the annual percentage volume change. Two lesion filling algorithms were investigated to improve segmentation performance in 23 patients with multiple sclerosis. The MD-GRU and nnU-Net models demonstrated very good segmentation performance (median Dice coefficients ≥ 0.95 each) and outperformed a previously published model trained on a narrower dataset. Scan-rescan repeatability and inter-scanner reproducibility yielded similar Bland-Altman derived limits of agreement for longitudinal FreeSurfer (total brainstem volume repeatability/reproducibility 0.68/1.85), MD-GRU (0.72/1.46), and nnU-Net (0.48/1.52). All methods showed comparable performance in the detection of atrophy in the total brainstem (atrophy detected in 100% of patients) and its substructures. In patients with multiple sclerosis, lesion filling further improved the accuracy of brainstem segmentation. We enhanced and systematically validated two fully automated deep learning brainstem segmentation methods and released them publicly. This enables a broader evaluation of brainstem volume as a candidate biomarker for neurodegeneration.

Comparing automated subcortical volume estimation methods; amygdala volumes estimated by FSL and FreeSurfer have poor consistency

Subcortical volumes are a promising source of biomarkers and features in biosignatures, and automated methods facilitate extracting them in large, phenotypically rich datasets. However, while extensive research has verified that the automated methods produce volumes that are similar to those generated by expert annotation; the consistency of methods with each other is understudied. Using data from the UK Biobank, we compare the estimates of subcortical volumes produced by two popular software suites: FSL and FreeSurfer. Although most subcortical volumes exhibit good to excellent consistency across the methods, the tools produce diverging estimates of amygdalar volume. Through simulation, we show that this poor consistency can lead to conflicting results, where one but not the other tool suggests statistical significance, or where both tools suggest a significant relationship but in opposite directions. Considering these issues, we discuss several ways in which care should be taken when reporting on relationships involving amygdalar volume.

Artificial Intelligence Tools in Pediatric Urology: A Comprehensive Review of Recent Advances

Artificial intelligence (AI) is providing novel answers to long-standing clinical problems, and it is quickly changing pediatric urology. This thorough analysis focuses on current developments in AI technologies that improve pediatric urology diagnosis, treatment planning, and surgery results. Deep learning algorithms help detect problems with previously unheard-of precision in disorders including hydronephrosis, pyeloplasty, and vesicoureteral reflux, where AI-powered prediction models have demonstrated promising outcomes in boosting diagnostic accuracy. AI-enhanced image processing methods have significantly improved the quality and interpretation of medical images. Examples of these methods are deep-learning-based segmentation and contrast limited adaptive histogram equalization (CLAHE). These methods guarantee higher precision in the identification and classification of pediatric urological disorders, and AI-driven ground truth construction approaches aid in the standardization of and improvement in training data, resulting in more resilient and consistent segmentation models. AI is being used for surgical support as well. AI-assisted navigation devices help with difficult operations like pyeloplasty by decreasing complications and increasing surgical accuracy. AI also helps with long-term patient monitoring, predictive analytics, and customized treatment strategies, all of which improve results for younger patients. However, there are practical, ethical, and legal issues with AI integration in pediatric urology that need to be carefully navigated. To close knowledge gaps, more investigation is required, especially in the areas of AI-driven surgical methods and standardized ground truth datasets for pediatric radiologic image segmentation. In the end, AI has the potential to completely transform pediatric urology by enhancing patient care, increasing the effectiveness of treatments, and spurring more advancements in this exciting area.

Detailed delineation of the fetal brain in diffusion MRI via multi-task learning

Diffusion-weighted MRI is increasingly used to study the normal and abnormal development of fetal brain inutero. Recent studies have shown that dMRI can offer invaluable insights into the neurodevelopmental processes in the fetal stage. However, because of the low data quality and rapid brain development, reliable analysis of fetal dMRI data requires dedicated computational methods that are currently unavailable. The lack of automated methods for fast, accurate, and reproducible data analysis has seriously limited our ability to tap the potential of fetal brain dMRI for medical and scientific applications. In this work, we developed and validated a unified computational framework to (1) segment the brain tissue into white matter, cortical/subcortical gray matter, and cerebrospinal fluid, (2) segment 31 distinct white matter tracts, and (3) parcellate the brain's cortex and delineate the deep gray nuclei and white matter structures into 96 anatomically meaningful regions. We utilized a set of manual, semi-automatic, and automatic approaches to annotate 97 fetal brains. Using these labels, we developed and validated a multi-task deep learning method to perform the three computations. Our evaluations show that the new method can accurately carry out all three tasks, achieving a mean Dice similarity coefficient of 0.865 on tissue segmentation, 0.825 on white matter tract segmentation, and 0.819 on parcellation. The proposed method can greatly advance the field of fetal neuroimaging as it can lead to substantial improvements in fetal brain tractography, tract-specific analysis, and structural connectivity assessment.

Detailed delineation of the fetal brain in diffusion MRI via multi-task learning

Diffusion-weighted MRI is increasingly used to study the normal and abnormal development of fetal brain inutero. Recent studies have shown that dMRI can offer invaluable insights into the neurodevelopmental processes in the fetal stage. However, because of the low data quality and rapid brain development, reliable analysis of fetal dMRI data requires dedicated computational methods that are currently unavailable. The lack of automated methods for fast, accurate, and reproducible data analysis has seriously limited our ability to tap the potential of fetal brain dMRI for medical and scientific applications. In this work, we developed and validated a unified computational framework to (1) segment the brain tissue into white matter, cortical/subcortical gray matter, and cerebrospinal fluid, (2) segment 31 distinct white matter tracts, and (3) parcellate the brain's cortex and delineate the deep gray nuclei and white matter structures into 96 anatomically meaningful regions. We utilized a set of manual, semi-automatic, and automatic approaches to annotate 97 fetal brains. Using these labels, we developed and validated a multi-task deep learning method to perform the three computations. Our evaluations show that the new method can accurately carry out all three tasks, achieving a mean Dice similarity coefficient of 0.865 on tissue segmentation, 0.825 on white matter tract segmentation, and 0.819 on parcellation. The proposed method can greatly advance the field of fetal neuroimaging as it can lead to substantial improvements in fetal brain tractography, tract-specific analysis, and structural connectivity assessment.

Streamline tractography of the fetal brain in utero with machine learning

Diffusion-weighted magnetic resonance imaging (dMRI) is the only non-invasive tool for studying white matter tracts and structural connectivity of the brain. These assessments rely heavily on tractography techniques, which reconstruct virtual streamlines representing white matter fibers. Much effort has been devoted to improving tractography methodology for adult brains, while tractography of the fetal brain has been largely neglected. Fetal tractography faces unique difficulties due to low dMRI signal quality, immature and rapidly developing brain structures, and paucity of reference data. To address these challenges, this work presents the first machine learning model, based on a deep neural network, for fetal tractography. The model input consists of five different sources of information: (1) Voxel-wise fiber orientation, inferred from a diffusion tensor fit to the dMRI signal; (2) Directions of recent propagation steps; (3) Global spatial information, encoded as normalized distances to keypoints in the brain cortex; (4) Tissue segmentation information; and (5) Prior information about the expected local fiber orientations supplied with an atlas. In order to mitigate the local tensor estimation error, a large spatial context around the current point in the diffusion tensor image is encoded using convolutional and attention neural network modules. Moreover, the diffusion tensor information at a hypothetical next point is included in the model input. Filtering rules based on anatomically constrained tractography are applied to prune implausible streamlines. We trained the model on manually-refined whole-brain fetal tractograms and validated the trained model on an independent set of 11 test scans with gestational ages between 23 and 36 weeks. Results show that our proposed method achieves superior performance across all evaluated tracts. The new method can significantly advance the capabilities of dMRI for studying normal and abnormal brain development in utero.

Anatomically constrained tractography of the fetal brain

Diffusion-weighted Magnetic Resonance Imaging (dMRI) is increasingly used to study the fetal brain in utero. An important computation enabled by dMRI is streamline tractography, which has unique applications such as tract-specific analysis of the brain white matter and structural connectivity assessment. However, due to the low fetal dMRI data quality and the challenging nature of tractography, existing methods tend to produce highly inaccurate results. They generate many false streamlines while failing to reconstruct the streamlines that constitute the major white matter tracts. In this paper, we advocate for anatomically constrained tractography based on an accurate segmentation of the fetal brain tissue directly in the dMRI space. We develop a deep learning method to compute the segmentation automatically. Experiments on independent test data show that this method can accurately segment the fetal brain tissue and drastically improve the tractography results. It enables the reconstruction of highly curved tracts such as optic radiations. Importantly, our method infers the tissue segmentation and streamline propagation direction from a diffusion tensor fit to the dMRI data, making it applicable to routine fetal dMRI scans. The proposed method can facilitate the study of fetal brain white matter tracts with dMRI.

Comparing Automated Subcortical Volume Estimation Methods; Amygdala Volumes Estimated by FSL and FreeSurfer Have Poor Consistency

Subcortical volumes are a promising source of biomarkers and features in biosignatures, and automated methods facilitate extracting them in large, phenotypically rich datasets. However, while extensive research has verified that the automated methods produce volumes that are similar to those generated by expert annotation, the consistency of methods with each other is understudied. Using data from the UK Biobank, we compare the estimates of subcortical volumes produced by two popular software suites: FSL and FreeSurfer. Although most subcortical volumes exhibit good to excellent consistency across the methods, the tools produce diverging estimates of amygdalar volume. Through simulation, we show that this poor consistency can lead to conflicting results, where one but not the other tool suggests statistical significance, or where both tools suggest a significant relationship but in opposite directions. Considering these issues, we discuss several ways in which care should be taken when reporting on relationships involving amygdalar volume.

Divergent growth of the transient brain compartments in fetuses with nonsyndromic isolated clefts involving the primary and secondary palate

Cleft lip/palate is a common orofacial malformation that often leads to speech/language difficulties as well as developmental delays in affected children, despite surgical repair. Our understanding of brain development in these children is limited. This study aimed to analyze prenatal brain development in fetuses with cleft lip/palate and controls. We examined in utero MRIs of 30 controls and 42 cleft lip/palate fetal cases and measured regional brain volumes. Cleft lip/palate was categorized into groups A (cleft lip or alveolus) and B (any combination of clefts involving the primary and secondary palates). Using a repeated-measures regression model with relative brain hemisphere volumes (%), and after adjusting for multiple comparisons, we did not identify significant differences in regional brain growth between group A and controls. Group B clefts had significantly slower weekly cerebellar growth compared with controls. We also observed divergent brain growth in transient brain structures (cortical plate, subplate, ganglionic eminence) within group B clefts, depending on severity (unilateral or bilateral) and defect location (hemisphere ipsilateral or contralateral to the defect). Further research is needed to explore the association between regional fetal brain growth and cleft lip/palate severity, with the potential to inform early neurodevelopmental biomarkers and personalized diagnostics.

Characterizing microstructural development in the fetal brain using diffusion MRI from 23 to 36 weeks of gestation

We utilized motion-corrected diffusion tensor imaging (DTI) to evaluate microstructural changes in healthy fetal brains during the late second and third trimesters. Data were derived from fetal magnetic resonance imaging scans conducted as part of a prospective study spanning from 2013 March to 2019 May. The study included 44 fetuses between the gestational ages (GAs) of 23 and 36 weeks. We reconstructed fetal brain DTI using a motion-tracked slice-to-volume registration framework. Images were segmented into 14 regions of interest (ROIs) through label propagation using a fetal DTI atlas, with expert refinement. Statistical analysis involved assessing changes in fractional anisotropy (FA) and mean diffusivity (MD) throughout gestation using mixed-effects models, and identifying points of change in trajectory for ROIs with nonlinear trends. Results showed significant GA-related changes in FA and MD in all ROIs except in the thalamus' FA and corpus callosum's MD. Hemispheric asymmetries were found in the FA of the periventricular white matter (pvWM), intermediate zone, and subplate and in the MD of the ganglionic eminence and pvWM. This study provides valuable insight into the normal patterns of development of MD and FA in the fetal brain. These changes are closely linked with cytoarchitectonic changes and display indications of early functional specialization.

Atypical fetal brain development in fetuses with non-syndromic isolated musculoskeletal birth defects (niMSBDs)

Non-syndromic, isolated musculoskeletal birth defects (niMSBDs) are among the leading causes of pediatric hospitalization. However, little is known about brain development in niMSBDs. Our study aimed to characterize prenatal brain development in fetuses with niMSBDs and identify altered brain regions compared to controls. We retrospectively analyzed in vivo structural T2-weighted MRIs of 99 fetuses (48 controls and 51 niMSBDs cases). For each group (19-31 and >31 gestational weeks (GW)), we conducted repeated-measures regression analysis with relative regional volume (% brain hemisphere) as a dependent variable (adjusted for age, side, and interactions). Between 19 and 31GW, fetuses with niMSBDs had a significantly (P < 0.001) smaller relative volume of the intermediate zone (-22.9 ± 3.2%) and cerebellum (-16.1 ± 3.5%,) and a larger relative volume of proliferative zones (38.3 ± 7.2%), the ganglionic eminence (34.8 ± 7.3%), and the ventricles (35.8 ± 8.0%). Between 32 and 37 GW, compared to the controls, niMSBDs showed significantly smaller volumes of central regions (-9.1 ± 2.1%) and larger volumes of the cortical plate. Our results suggest there is altered brain development in fetuses with niMSBDs compared to controls (13.1 ± 4.2%). Further basic and translational neuroscience research is needed to better visualize these differences and to characterize the altered development in fetuses with specific niMSBDs.

Brain growth in fetuses with congenital diaphragmatic hernia

BACKGROUND AND PURPOSE

To perform a volumetric evaluation of the brain in fetuses with right or left congenital diaphragmatic hernia (CDH), and to compare brain growth trajectories to normal fetuses.

METHODS

We identified fetal MRIs performed between 2015 and 2020 in fetuses with a diagnosis of CDH. Gestational age (GA) range was 19-40 weeks. Control subjects consisted of normally developing fetuses between 19 and 40 weeks recruited for a separate prospective study. All images were acquired at 3 Tesla and were processed with retrospective motion correction and slice-to-volume reconstruction to generate super-resolution 3-dimensional volumes. These volumes were registered to a common atlas space and segmented in 29 anatomic parcellations.

RESULTS

A total of 174 fetal MRIs in 149 fetuses were analyzed (99 controls [mean GA: 29.2 ± 5.2 weeks], 34 fetuses left-sided CDH [mean GA: 28.4 ± 5.3 weeks], and 16 fetuses right-sided CDH [mean GA: 27 ± 5.4 weeks]). In fetuses with left-sided CDH, brain parenchymal volume was -8.0% (95% confidence interval [CI] [-13.1, -2.5]; p = .005) lower than normal controls. Differences ranged from -11.4% (95% CI [-18, -4.3]; p < .001) in the corpus callosum to -4.6% (95% CI [-8.9, -0.1]; p = .044) in the hippocampus. In fetuses with right-sided CDH, brain parenchymal volume was -10.1% (95% CI [-16.8, -2.7]; p = .008) lower than controls. Differences ranged from -14.1% (95% CI [-21, -6.5]; p < .001) in the ventricular zone to -5.6% (95% CI [-9.3, -1.8]; p = .025) in the brainstem.

CONCLUSION

Left and right CDH are associated with lower fetal brain volumes.

Abnormal prenatal brain development in Chiari II malformation

Introduction

The Chiari II is a relatively common birth defect that is associated with open spinal abnormalities and is characterized by caudal migration of the posterior fossa contents through the foramen magnum. The pathophysiology of Chiari II is not entirely known, and the neurobiological substrate beyond posterior fossa findings remains unexplored. We aimed to identify brain regions altered in Chiari II fetuses between 17 and 26 GW.

Methods

We used in vivo structural T2-weighted MRIs of 31 fetuses (6 controls and 25 cases with Chiari II).

Results

The results of our study indicated altered development of diencephalon and proliferative zones (ventricular and subventricular zones) in fetuses with a Chiari II malformation compared to controls. Specifically, fetuses with Chiari II showed significantly smaller volumes of the diencephalon and significantly larger volumes of lateral ventricles and proliferative zones.

Discussion

We conclude that regional brain development should be taken into consideration when evaluating prenatal brain development in fetuses with Chiari II.

Learning to segment fetal brain tissue from noisy annotations

Automatic fetal brain tissue segmentation can enhance the quantitative assessment of brain development at this critical stage. Deep learning methods represent the state of the art in medical image segmentation and have also achieved impressive results in brain segmentation. However, effective training of a deep learning model to perform this task requires a large number of training images to represent the rapid development of the transient fetal brain structures. On the other hand, manual multi-label segmentation of a large number of 3D images is prohibitive. To address this challenge, we segmented 272 training images, covering 19-39 gestational weeks, using an automatic multi-atlas segmentation strategy based on deformable registration and probabilistic atlas fusion, and manually corrected large errors in those segmentations. Since this process generated a large training dataset with noisy segmentations, we developed a novel label smoothing procedure and a loss function to train a deep learning model with smoothed noisy segmentations. Our proposed methods properly account for the uncertainty in tissue boundaries. We evaluated our method on 23 manually-segmented test images of a separate set of fetuses. Results show that our method achieves an average Dice similarity coefficient of 0.893 and 0.916 for the transient structures of younger and older fetuses, respectively. Our method generated results that were significantly more accurate than several state-of-the-art methods including nnU-Net that achieved the closest results to our method. Our trained model can serve as a valuable tool to enhance the accuracy and reproducibility of fetal brain analysis in MRI.

Detailed anatomic segmentations of a fetal brain diffusion tensor imaging atlas between 23 and 30 weeks of gestation

This work presents detailed anatomic labels for a spatiotemporal atlas of fetal brain Diffusion Tensor Imaging (DTI) between 23 and 30 weeks of post-conceptional age. Additionally, we examined developmental trajectories in fractional anisotropy (FA) and mean diffusivity (MD) across gestational ages (GA). We performed manual segmentations on a fetal brain DTI atlas. We labeled 14 regions of interest (ROIs): cortical plate (CP), subplate (SP), Intermediate zone-subventricular zone-ventricular zone (IZ/SVZ/VZ), Ganglionic Eminence (GE), anterior and posterior limbs of the internal capsule (ALIC, PLIC), genu (GCC), body (BCC), and splenium (SCC) of the corpus callosum (CC), hippocampus, lentiform Nucleus, thalamus, brainstem, and cerebellum. A series of linear regressions were used to assess GA as a predictor of FA and MD for each ROI. The combination of MD and FA allowed the identification of all ROIs. Increasing GA was significantly associated with decreasing FA in the CP, SP, IZ/SVZ/IZ, GE, ALIC, hippocampus, and BCC (p < .03, for all), and with increasing FA in the PLIC and SCC (p < .002, for both). Increasing GA was significantly associated with increasing MD in the CP, SP, IZ/SVZ/IZ, GE, ALIC, and CC (p < .03, for all). We developed a set of expert-annotated labels for a DTI spatiotemporal atlas of the fetal brain and presented a pilot analysis of developmental changes in cerebral microstructure between 23 and 30 weeks of GA.

Abnormal development of transient fetal zones in mild isolated fetal ventriculomegaly

Mild isolated fetal ventriculomegaly (iFVM) is the most common abnormality of the fetal central nervous system. It is characterized by enlargement of one or both of the lateral ventricles (defined as ventricular width greater than 10 mm, but less than 12 mm). Despite its high prevalence, the pathophysiology of iFVM during fetal brain development and the neurobiological substrate beyond ventricular enlargement remain unexplored. In this work, we aimed to establish the relationships between the structural development of transient fetal brain zones/compartments and increased cerebrospinal fluid volume. For this purpose, we used in vivo structural T2-weighted magnetic resonance imaging of 89 fetuses (48 controls and 41 cases with iFVM). Our results indicate abnormal development of transient zones/compartments belonging to both hemispheres (i.e. on the side with and also on the contralateral side without a dilated ventricle) in fetuses with iFVM. Specifically, compared to controls, we observed enlargement of proliferative zones and overgrowth of the cortical plate in iFVM with associated reduction of volumes of central structures, subplate, and fetal white matter. These results indicate that enlarged lateral ventricles might be linked to the development of transient fetal zones and that global brain development should be taken into consideration when evaluating iFVM.

Growth of prefrontal and limbic brain regions and anxiety disorders in children born very preterm

BACKGROUND

Children born very preterm (VP) display altered growth in corticolimbic structures compared with full-term peers. Given the association between the cortiocolimbic system and anxiety, this study aimed to compare developmental trajectories of corticolimbic regions in VP children with and without anxiety diagnosis at 13 years.

METHODS

MRI data from 124 VP children were used to calculate whole brain and corticolimbic region volumes at term-equivalent age (TEA), 7 and 13 years. The presence of an anxiety disorder was assessed at 13 years using a structured clinical interview.

RESULTS

VP children who met criteria for an anxiety disorder at 13 years (n = 16) displayed altered trajectories for intracranial volume (ICV, p < 0.0001), total brain volume (TBV, p = 0.029), the right amygdala (p = 0.0009) and left hippocampus (p = 0.029) compared with VP children without anxiety (n = 108), with trends in the right hippocampus (p = 0.062) and left medial orbitofrontal cortex (p = 0.079). Altered trajectories predominantly reflected slower growth in early childhood (0-7 years) for ICV (β = -0.461, p = 0.020), TBV (β = -0.503, p = 0.021), left (β = -0.518, p = 0.020) and right hippocampi (β = -0.469, p = 0.020) and left medial orbitofrontal cortex (β = -0.761, p = 0.020) and did not persist after adjusting for TBV and social risk.

CONCLUSIONS

Region- and time-specific alterations in the development of the corticolimbic system in children born VP may help to explain an increase in anxiety disorders observed in this population.

Triplanar U-Net with lesion-wise voting for the segmentation of new lesions on longitudinal MRI studies

We present a deep learning method for the segmentation of new lesions in longitudinal FLAIR MRI sequences acquired at two different time points. In our approach, the 3D volumes are processed slice-wise across the coronal, axial, and sagittal planes and the predictions from the three orientations are merged using an optimized voting strategy. Our method achieved best F1 score (0.541) among all participating methods in the MICCAI 2021 challenge Multiple sclerosis new lesions segmentation (MSSEG-2). Moreover, we show that our method is on par with the challenge's expert neuroradiologists: on an unbiased ground truth, our method achieves results comparable to those of the four experts in terms of detection (F1 score) and segmentation accuracy (Dice score).

Normal Growth, Sexual Dimorphism, and Lateral Asymmetries at Fetal Brain MRI

Background Tools in image reconstruction, motion correction, and segmentation have enabled the accurate volumetric characterization of fetal brain growth at MRI. Purpose To evaluate the volumetric growth of intracranial structures in healthy fetuses, accounting for gestational age (GA), sex, and laterality with use of a spatiotemporal MRI atlas of fetal brain development. Materials and Methods T2-weighted 3.0-T half-Fourier acquired single-shot turbo spin-echo sequence MRI was performed in healthy fetuses from prospectively recruited pregnant volunteers from March 2013 to May 2019. A previously validated section-to-volume reconstruction algorithm was used to generate intensity-normalized superresolution three-dimensional volumes that were registered to a fetal brain MRI atlas with 28 anatomic regions of interest. Atlas-based segmentation was performed and manually refined. Labels included the bilateral hippocampus, amygdala, caudate nucleus, lentiform nucleus, thalamus, lateral ventricle, cerebellum, cortical plate, hemispheric white matter, internal capsule, ganglionic eminence, ventricular zone, corpus callosum, brainstem, hippocampal commissure, and extra-axial cerebrospinal fluid. For fetuses younger than 31 weeks of GA, the subplate and intermediate zones were delineated. A linear regression analysis was used to determine weekly age-related change adjusted for sex and laterality. Results The final analytic sample consisted of 122 MRI scans in 98 fetuses (mean GA, 29 weeks ± 5 [range, 20-38 weeks]). All structures had significant volume growth with increasing GA (P < .001). Weekly age-related change for individual structures in the brain parenchyma ranged from 2.0% (95% CI: 0.9, 3.1; P < .001) in the hippocampal commissure to 19.4% (95% CI: 18.7, 20.1; P < .001) in the cerebellum. The largest sex-related differences were 22.1% higher volume in male fetuses for the lateral ventricles (95% CI: 10.9, 34.4; P < .001). There was rightward volumetric asymmetry of 15.6% for the hippocampus (95% CI: 14.2, 17.2; P < .001) and leftward volumetric asymmetry of 8.1% for the lateral ventricles (95% CI: 3.7, 12.2; P < .001). Conclusion With use of a spatiotemporal MRI atlas, volumetric growth of the fetal brain showed complex trajectories dependent on structure, gestational age, sex, and laterality. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Rollins in this issue.

Robust Bayesian fusion of continuous segmentation maps

The fusion of probability maps is required when trying to analyse a collection of image labels or probability maps produced by several segmentation algorithms or human raters. The challenge is to weight the combination of maps correctly, in order to reflect the agreement among raters, the presence of outliers and the spatial uncertainty in the consensus. In this paper, we address several shortcomings of prior work in continuous label fusion. We introduce a novel approach to jointly estimate a reliable consensus map and to assess the presence of outliers and the confidence in each rater. Our robust approach is based on heavy-tailed distributions allowing local estimates of raters performances. In particular, we investigate the Laplace, the Student's t and the generalized double Pareto distributions, and compare them with respect to the classical Gaussian likelihood used in prior works. We unify these distributions into a common tractable inference scheme based on variational calculus and scale mixture representations. Moreover, the introduction of bias and spatial priors leads to proper rater bias estimates and control over the smoothness of the consensus map. Finally, we propose an approach that clusters raters based on variational boosting, and thus may produce several alternative consensus maps. Our approach was successfully tested on MR prostate delineations and on lung nodule segmentations from the LIDC-IDRI dataset.

The Connectivity Fingerprint of the Fusiform Gyrus Captures the Risk of Developing Autism in Infants with Tuberous Sclerosis Complex

Tuberous sclerosis complex (TSC) is a rare genetic disorder characterized by benign tumors throughout the body; it is generally diagnosed early in life and has a high prevalence of autism spectrum disorder (ASD), making it uniquely valuable in studying the early development of autism, before neuropsychiatric symptoms become apparent. One well-documented deficit in ASD is an impairment in face processing. In this work, we assessed whether anatomical connectivity patterns of the fusiform gyrus, a central structure in face processing, capture the risk of developing autism early in life. We longitudinally imaged TSC patients at 1, 2, and 3 years of age with diffusion compartment imaging. We evaluated whether the anatomical connectivity fingerprint of the fusiform gyrus was associated with the risk of developing autism measured by the Autism Observation Scale for Infants (AOSI). Our findings suggest that the fusiform gyrus connectivity captures the risk of developing autism as early as 1 year of age and provides evidence that abnormal fusiform gyrus connectivity increases with age. Moreover, the identified connections that best capture the risk of developing autism involved the fusiform gyrus and limbic and paralimbic regions that were consistent with the ASD phenotype, involving an increased number of left-lateralized structures with increasing age.

A structural brain network of genetic vulnerability to psychiatric illness

Psychiatry is undergoing a paradigm shift from the acceptance of distinct diagnoses to a representation of psychiatric illness that crosses diagnostic boundaries. How this transition is supported by a shared neurobiology remains largely unknown. In this study, we first identify single nucleotide polymorphisms (SNPs) associated with psychiatric disorders based on 136 genome-wide association studies. We then conduct a joint analysis of these SNPs and brain structural connectomes in 678 healthy children in the PING study. We discovered a strong, robust, and transdiagnostic mode of genome-connectome covariation which is positively and specifically correlated with genetic risk for psychiatric illness at the level of individual SNPs. Similarly, this mode is also significantly positively correlated with polygenic risk scores for schizophrenia, alcohol use disorder, major depressive disorder, a combined bipolar disorder-schizophrenia phenotype, and a broader cross-disorder phenotype, and significantly negatively correlated with a polygenic risk score for educational attainment. The resulting "vulnerability network" is shown to mediate the influence of genetic risks onto behaviors related to psychiatric vulnerability (e.g., marijuana, alcohol, and caffeine misuse, perceived stress, and impulsive behavior). Its anatomy overlaps with the default-mode network, with a network of cognitive control, and with the occipital cortex. These findings suggest that the brain vulnerability network represents an endophenotype funneling genetic risks for various psychiatric illnesses through a common neurobiological root. It may form part of the neural underpinning of the well-recognized but poorly explained overlap and comorbidity between psychiatric disorders.

A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI

Fetal cortical plate segmentation is essential in quantitative analysis of fetal brain maturation and cortical folding. Manual segmentation of the cortical plate, or manual refinement of automatic segmentations is tedious and time-consuming. Automatic segmentation of the cortical plate, on the other hand, is challenged by the relatively low resolution of the reconstructed fetal brain MRI scans compared to the thin structure of the cortical plate, partial voluming, and the wide range of variations in the morphology of the cortical plate as the brain matures during gestation. To reduce the burden of manual refinement of segmentations, we have developed a new and powerful deep learning segmentation method. Our method exploits new deep attentive modules with mixed kernel convolutions within a fully convolutional neural network architecture that utilizes deep supervision and residual connections. We evaluated our method quantitatively based on several performance measures and expert evaluations. Results show that our method outperforms several state-of-the-art deep models for segmentation, as well as a state-of-the-art multi-atlas segmentation technique. We achieved average Dice similarity coefficient of 0.87, average Hausdorff distance of 0.96 mm, and average symmetric surface difference of 0.28 mm on reconstructed fetal brain MRI scans of fetuses scanned in the gestational age range of 16 to 39 weeks (28.6± 5.3). With a computation time of less than 1 minute per fetal brain, our method can facilitate and accelerate large-scale studies on normal and altered fetal brain cortical maturation and folding.

Automated contour propagation of the prostate from pCT to CBCT images via deep unsupervised learning

PURPOSE

To develop and evaluate a deep unsupervised learning (DUL) framework based on a regional deformable model for automated prostate contour propagation from planning computed tomography (pCT) to cone-beam CT (CBCT).

METHODS

We introduce a DUL model to map the prostate contour from pCT to on-treatment CBCT. The DUL framework used a regional deformable model via narrow-band mapping to augment the conventional strategy. Two hundred and fifty-one anonymized CBCT images from prostate cancer patients were retrospectively selected and divided into three sets: 180 were used for training, 12 for validation, and 59 for testing. The testing dataset was divided into two groups. Group 1 contained 50 CBCT volumes, with one physician-generated prostate contour on CBCT image. Group 2 contained nine CBCT images, each including prostate contours delineated by four independent physicians and a consensus contour generated using the STAPLE method. Results were compared between the proposed DUL and physician-generated contours through the Dice similarity coefficients (DSCs), the Hausdorff distances, and the distances of the center-of-mass.

RESULTS

The average DSCs between DUL-based prostate contours and reference contours for test data in group 1 and group 2 consensus were 0.83 ± 0.04, and 0.85 ± 0.04, respectively. Correspondingly, the mean center-of-mass distances were 3.52 mm ± 1.15 mm, and 2.98 mm ± 1.42 mm, respectively.

CONCLUSIONS

This novel DUL technique can automatically propagate the contour of the prostate from pCT to CBCT. The proposed method shows that highly accurate contour propagation for CBCT-guided adaptive radiotherapy is achievable via the deep learning technique.

Parcellation of the neonatal cortex using Surface-based Melbourne Children's Regional Infant Brain atlases (M-CRIB-S)

Longitudinal studies measuring changes in cortical morphology over time are best facilitated by parcellation schemes compatible across all life stages. The Melbourne Children’s Regional Infant Brain (M-CRIB) and M-CRIB 2.0 atlases provide voxel-based parcellations of the cerebral cortex compatible with the Desikan-Killiany (DK) and the Desikan-Killiany-Tourville (DKT) cortical labelling schemes. This study introduces surface-based versions of the M-CRIB and M-CRIB 2.0 atlases, termed M-CRIB-S(DK) and M-CRIB-S(DKT), with a pipeline for automated parcellation utilizing FreeSurfer and developing Human Connectome Project (dHCP) tools. Using T₂-weighted magnetic resonance images of healthy neonates (n = 58), we created average spherical templates of cortical curvature and sulcal depth. Manually labelled regions in a subset (n = 10) were encoded into the spherical template space to construct M-CRIB-S(DK) and M-CRIB-S(DKT) atlases. Labelling accuracy was assessed using Dice overlap and boundary discrepancy measures with leave-one-out cross-validation. Cross-validated labelling accuracy was high for both atlases (average regional Dice = 0.79–0.83). Worst-case boundary discrepancy instances ranged from 9.96–10.22 mm, which appeared to be driven by variability in anatomy for some cases. The M-CRIB-S atlas data and automatic pipeline allow extraction of neonatal cortical surfaces labelled according to the DK or DKT parcellation schemes.

White matter extension of the Melbourne Children's Regional Infant Brain atlas: M-CRIB-WM

Brain atlases providing standardised identification of neonatal brain regions are key in investigating neurological disorders of early childhood. Our previously developed Melbourne Children's Regional Infant Brain (M-CRIB) and M-CRIB 2.0 neonatal brain atlases provide standardised parcellation of 100 brain regions including cortical, subcortical, and cerebellar regions. The aim of this study was to extend M-CRIB atlas coverage to include 54 white matter (WM) regions. Participants were 10 healthy term-born neonates that were used to create the initial M-CRIB atlas. WM regions were manually segmented based on T₂ images and co-registered diffusion tensor imaging-based, direction-encoded colour maps. Our labelled regions imitate the Johns Hopkins University neonatal atlas, with minor anatomical modifications. All segmentations were reviewed and approved by a paediatric radiologist and a neurosurgery research fellow for anatomical accuracy. The resulting neonatal WM atlas comprises 54 WM regions: 24 paired regions, and six unpaired regions comprising five corpus callosum subdivisions, and one pontine crossing tract. Detailed protocols for manual WM parcellations are provided, and the M-CRIB-WM atlas is presented together with the existing M-CRIB cortical, subcortical, and cerebellar parcellations in 10 individual neonatal MRI data sets. The novel M-CRIB-WM atlas, along with the M-CRIB cortical and subcortical atlases, provide neonatal whole brain MRI coverage in the first multi-subject manually parcellated neonatal atlas compatible with atlases commonly used at older time points. The M-CRIB-WM atlas is publicly available, providing a valuable tool that will help facilitate neuroimaging research into neonatal brain development in both healthy and diseased states.

Tracking regional brain growth up to age 13 in children born term and very preterm

Serial regional brain growth from the newborn period to adolescence has not been described. Here, we measured regional brain growth in 216 very preterm (VP) and 45 full-term (FT) children. Brain MRI was performed at term-equivalent age, 7 and 13 years in 82 regions. Brain volumes increased between term-equivalent and 7 years, with faster growth in the FT than VP group. Perinatal brain abnormality was associated with less increase in brain volume between term-equivalent and 7 years in the VP group. Between 7 and 13 years, volumes were relatively stable, with some subcortical and cortical regions increasing while others reduced. Notably, VP infants continued to lag, with overall brain size generally less than that of FT peers at 13 years. Parieto–frontal growth, mainly between 7 and 13 years in FT children, was associated with higher intelligence at 13 years. This study improves understanding of typical and atypical regional brain growth.

In this longitudinal study, the authors tracked the course of brain development from birth to adolescence (age 13 years) and examined the effects of very preterm birth. Very preterm children showed slower brain growth from age 0 (term equivalent) to age 7.

Multi-Resolution Graph Based Volumetric Cortical Basis Functions From Local Anatomic Features

OBJECTIVE

Modern clinical MRI collects millimeter scale anatomic information, but scalp electroencephalography source localization is ill posed, and cannot resolve individual sources at that resolution. Dimensionality reduction in the space of cortical sources is needed to improve computational and storage complexity, yet volumetric methods still employ simplistic grid coarsening that eliminates fine scale anatomic structure. We present an approach to extend near-arbitrary spatial scaling to volumetric localization.

METHODS

Starting from a voxelwise brain parcellation, sub-parcels are identified from local cortical connectivity with an iterated graph cut approach. Spatial basis functions in each parcel are constructed using either a decomposition of the local leadfield matrix or spectral basis functions of local cortical connectivity graphs.

RESULTS

We present quantitative evaluation with extensive simulations and use multiple sets of real data to highlight how parameter changes impact computed reconstructions. Our results show that volumetric basis functions can improve accuracy by as much as 30%, while reducing computational complexity by over two orders of magnitude. In real data from epilepsy surgical candidates, accurate localization of seizure onset regions is demonstrated.

CONCLUSION

Spatial dimensionality reduction with volumetric basis functions improves reconstruction accuracy while reducing computational complexity.

SIGNIFICANCE

Near-arbitrary spatial dimensionality reduction will enable volumetric reconstruction with modern computationally intensive algorithms and anatomically driven multi-resolution methods.

Biomechanical modeling and computer simulation of the brain during neurosurgery

Computational biomechanics of the brain for neurosurgery is an emerging area of research recently gaining in importance and practical applications. This review paper presents the contributions of the Intelligent Systems for Medicine Laboratory and its collaborators to this field, discussing the modeling approaches adopted and the methods developed for obtaining the numerical solutions. We adopt a physics-based modeling approach and describe the brain deformation in mechanical terms (such as displacements, strains, and stresses), which can be computed using a biomechanical model, by solving a continuum mechanics problem. We present our modeling approaches related to geometry creation, boundary conditions, loading, and material properties. From the point of view of solution methods, we advocate the use of fully nonlinear modeling approaches, capable of capturing very large deformations and nonlinear material behavior. We discuss finite element and meshless domain discretization, the use of the total Lagrangian formulation of continuum mechanics, and explicit time integration for solving both time-accurate and steady-state problems. We present the methods developed for handling contacts and for warping 3D medical images using the results of our simulations. We present two examples to showcase these methods: brain shift estimation for image registration and brain deformation computation for neuronavigation in epilepsy treatment.

Reproducibility of Structural and Diffusion Tensor Imaging in the TACERN Multi-Center Study

BACKGROUND

Multi-site MRI studies are often necessary for recruiting sufficiently sized samples when studying rare conditions. However, they require pooling data from multiple scanners into a single data set, and therefore it is critical to evaluate the variability of quantitative MRI measures within and across scanners used in multi-site studies. The aim of this study was to evaluate the reproducibility of structural and diffusion weighted (DW) MRI measurements acquired on seven scanners at five medical centers as part of the Tuberous Sclerosis Complex Autism Center of Excellence Research Network (TACERN) multisite study.

METHODS

The American College of Radiology (ACR) phantom was imaged monthly to measure reproducibility of signal intensity and uniformity within and across seven 3T scanners from General Electric, Philips, and Siemens vendors. One healthy adult male volunteer was imaged repeatedly on all seven scanners under the TACERN structural and DW protocol (5 b = 0 s/mm2 and 30 b = 1000 s/mm2) over a period of 5 years (age 22-27 years). Reproducibility of inter- and intra-scanner brain segmentation volumes and diffusion tensor imaging metrics fractional anisotropy (FA) and mean diffusivity (MD) within white matter regions was quantified with coefficient of variation.

RESULTS

The American College of Radiology Phantom signal intensity and uniformity were similar across scanners and changed little over time, with a mean intra-scanner coefficient of variation of 3.6 and 1.8%, respectively. The mean inter- and intra-scanner coefficients of variation of brain structure volumes derived from T1-weighted (T1w) images of the human phantom were 3.3 and 1.1%, respectively. The mean inter- and intra-scanner coefficients of variation of FA in white matter regions were 4.5 and 2.5%, while the mean inter- and intra-scanner coefficients of variation of MD in white matter regions were 5.4 and 1.5%.

CONCLUSION

Our results suggest that volumetric and diffusion tensor imaging (DTI) measurements are highly reproducible between and within scanners and provide typical variation amplitudes that can be used as references to interpret future findings in the TACERN network.

Accurate, rapid and reliable, fully automated MRI brainstem segmentation for application in multiple sclerosis and neurodegenerative diseases

Neurodegenerative disorders, such as Alzheimer's disease (AD) and progressive forms of multiple sclerosis (MS), can affect the brainstem and are associated with atrophy that can be visualized by MRI. Anatomically accurate, large-scale assessments of brainstem atrophy are challenging due to lack of automated, accurate segmentation methods. We present a novel method for brainstem volumetry using a fully-automated segmentation approach based on multi-dimensional gated recurrent units (MD-GRU), a deep learning based semantic segmentation approach employing a convolutional adaptation of gated recurrent units. The neural network was trained on 67 3D-high resolution T1-weighted MRI scans from MS patients and healthy controls (HC) and refined using segmentations of 20 independent MS patients' scans. Reproducibility was assessed in MR test-retest experiments in 33 HC. Accuracy and robustness were examined by Dice scores comparing MD-GRU to FreeSurfer and manual brainstem segmentations in independent MS and AD datasets. The mean %-change/SD between test-retest brainstem volumes were 0.45%/0.005 (MD-GRU), 0.95%/0.009 (FreeSurfer), 0.86%/0.007 (manually edited segmentations). Comparing MD-GRU to manually edited segmentations the mean Dice scores/SD were: 0.97/0.005 (brainstem), 0.95/0.013 (mesencephalon), 0.98/0.006 (pons), 0.95/0.015 (medulla oblongata). Compared to the manual gold standard, MD-GRU brainstem segmentations were more accurate than FreeSurfer segmentations (p < .001). In the multi-centric acquired AD data, the mean Dice score/SD for the MD-GRU-manual segmentation comparison was 0.97/0.006. The fully automated brainstem segmentation method MD-GRU provides accurate, highly reproducible, and robust segmentations in HC and patients with MS and AD in 200 s/scan on an Nvidia GeForce GTX 1080 GPU and shows potential for application in large and longitudinal datasets.

Novel stochastic framework for automatic segmentation of human thigh MRI volumes and its applications in spinal cord injured individuals

Severe spinal cord injury (SCI) leads to skeletal muscle atrophy and adipose tissue infiltration in the skeletal muscle, which can result in compromised muscle mechanical output and lead to health-related complications. In this study, we developed a novel automatic 3-D approach for volumetric segmentation and quantitative assessment of thigh Magnetic Resonance Imaging (MRI) volumes in individuals with chronic SCI as well as non-disabled individuals. In this framework, subcutaneous adipose tissue, inter-muscular adipose tissue and total muscle tissue are segmented using linear combination of discrete Gaussians algorithm. Also, three thigh muscle groups were segmented utilizing the proposed 3-D Joint Markov Gibbs Random Field model that integrates first order appearance model, spatial information, and shape model to localize the muscle groups. The accuracy of the automatic segmentation method was tested both on SCI (N = 16) and on non-disabled (N = 14) individuals, showing an overall 0.93±0.06 accuracy for adipose tissue and muscle compartments segmentation based on Dice Similarity Coefficient. The proposed framework for muscle compartment segmentation showed an overall higher accuracy compared to ANTs and STAPLE, two previously validated atlas-based segmentation methods. Also, the framework proposed in this study showed similar Dice accuracy and better Hausdorff distance measure to that obtained using DeepMedic Convolutional Neural Network structure, a well-known deep learning network for 3-D medical image segmentation. The automatic segmentation method proposed in this study can provide fast and accurate quantification of adipose and muscle tissues, which have important health and functional implications in the SCI population.

Feasibility of multi-atlas cardiac segmentation from thoracic planning CT in a probabilistic framework

Toxicity to cardiac and coronary structures is an important late morbidity for patients undergoing left-sided breast radiotherapy. Many current studies have relied on estimates of cardiac doses assuming standardised anatomy, with a calculated increase in relative risk of 7.4% per Gy (mean heart dose). To provide individualised estimates for dose, delineation of various cardiac structures on patient images is required. Automatic multi-atlas based segmentation can provide a consistent, robust solution, however there are challenges to this method. We are aiming to develop and validate a cardiac atlas and segmentation framework, with a focus on the limitations and uncertainties in the process. We present a probabilistic approach to segmentation, which provides a simple method to incorporate inter-observer variation, as well as a useful tool for evaluating the accuracy and sources of error in segmentation. A dataset consisting of 20 planning computed tomography (CT) images of Australian breast cancer patients with delineations of 17 structures (including whole heart, four chambers, coronary arteries and valves) was manually contoured by three independent observers, following a protocol based on a published reference atlas, with verification by a cardiologist. To develop and validate the segmentation framework a leave-one-out cross-validation strategy was implemented. Performance of the automatic segmentations was evaluated relative to inter-observer variability in manually-derived contours; measures of volume and surface accuracy (Dice similarity coefficient (DSC) and mean absolute surface distance (MASD), respectively) were used to compare automatic segmentation to the consensus segmentation from manual contours. For the whole heart, the resulting segmentation achieved a DSC of [Formula: see text], with a MASD of [Formula: see text] mm. Quantitative results, together with the analysis of probabilistic labelling, indicate the feasibility of accurate and consistent segmentation of larger structures, whereas this is not the case for many smaller structures, where a major limitation in segmentation accuracy is the inter-observer variability in manual contouring.

Brain structure segmentation in the presence of multiple sclerosis lesions

Intensity-based multi-atlas segmentation strategies have shown to be particularly successful in segmenting brain images of healthy subjects. However, in the same way as most of the methods in the state of the art, their performance tends to be affected by the presence of MRI visible lesions, such as those found in multiple sclerosis (MS) patients. Here, we present an approach to minimize the effect of the abnormal lesion intensities on multi-atlas segmentation. We propose a new voxel/patch correspondence model for intensity-based multi-atlas label fusion strategies that leads to more accurate similarity measures, having a key role in the final brain segmentation. We present the theory of this model and integrate it into two well-known fusion strategies: Non-local Spatial STAPLE (NLSS) and Joint Label Fusion (JLF). The experiments performed show that our proposal improves the segmentation performance of the lesion areas. The results indicate a mean Dice Similarity Coefficient (DSC) improvement of 1.96% for NLSS (3.29% inside and 0.79% around the lesion masks) and, an improvement of 2.06% for JLF (2.31% inside and 1.42% around lesions). Furthermore, we show that, with the proposed strategy, the well-established preprocessing step of lesion filling can be disregarded, obtaining similar or even more accurate segmentation results.

•

We present an approach to improve multi-atlas brain parcellation of MS patients.

•

We integrate our model into 2 well-known segmentation strategies.

•

Our model improves the segmentation on the lesion areas.

•

The improvement on the lesion areas is also reflected in the global performance.

•

With our model, lesion filling can be omitted, obtaining at least similar results.

Desikan-Killiany-Tourville Atlas Compatible Version of M-CRIB Neonatal Parcellated Whole Brain Atlas: The M-CRIB 2.0

Our recently published M-CRIB atlas comprises 100 neonatal brain regions including 68 compatible with the widely-used Desikan-Killiany adult cortical atlas. A successor to the Desikan-Killiany atlas is the Desikan-Killiany-Tourville atlas, in which some regions with unclear boundaries were removed, and many existing boundaries were revised to conform to clearer landmarks in sulcal fundi. Our first aim here was to modify cortical M-CRIB regions to comply with the Desikan-Killiany-Tourville protocol, in order to offer: (a) compatibility with this adult cortical atlas, (b) greater labeling accuracy due to clearer landmarks, and (c) optimisation of cortical regions for integration with surface-based infant parcellation pipelines. Secondly, we aimed to update subcortical regions in order to offer greater compatibility with subcortical segmentations produced in FreeSurfer. Data utilized were the T2-weighted MRI scans in our M-CRIB atlas, for 10 healthy neonates (post-menstrual age at MRI 40–43 weeks, four female), and corresponding parcellated images. Edits were performed on the parcellated images in volume space using ITK-SNAP. Cortical updates included deletion of frontal and temporal poles and ‘Banks STS,’ and modification of boundaries of many other regions. Changes to subcortical regions included the addition of ‘ventral diencephalon,’ and deletion of ‘subcortical matter’ labels. A detailed updated parcellation protocol was produced. The resulting whole-brain M-CRIB 2.0 atlas comprises 94 regions altogether. This atlas provides comparability with adult Desikan-Killiany-Tourville-labeled cortical data and FreeSurfer-labeed subcortical data, and is more readily adaptable for incorporation into surface-based neonatal parcellation pipelines. As such, it offers the ability to help facilitate a broad range of investigations into brain structure and function both at the neonatal time point and developmentally across the lifespan.

Volumetric Analysis of the Basal Ganglia and Cerebellar Structures in Patients with Phelan-McDermid Syndrome

OBJECTIVE

Phelan-McDermid syndrome is caused by haploinsufficiency of SHANK3 on terminal chromosome 22. Knowledge about altered neuroanatomic circuitry in Phelan-McDermid syndrome comes from mouse models showing striatal hypertrophy in the basal ganglia, and from humans with evidence of cerebellar atrophy. To date, no studies have performed volumetric analysis on Phelan-McDermid syndrome patients.

METHODS

We performed volumetric analysis of baseline brain MRIs of Phelan-McDermid syndrome patients (ages three to 21 years) enrolled in a prospective natural history study (ClinicalTrials.gov NCT02461420). Using MRI segmentations carried out with PSTAPLE algorithm, we measured relative volumes (volume of the structure divided by the volume of the brain parenchyma) of basal ganglia and cerebellar structures. We compared these measurements to those of age- and sex-matched healthy controls part of another study. Among the patients, we performed linear regression of each relative volume using Repetitive Behavior Scale-Revised total score and Aberrant Behavior Checklist stereotypy score. Eleven patients with Phelan-McDermid syndrome (six females, five males) and 11 healthy controls were in this analysis.

RESULTS

At time of MRI, the mean age of the patients and controls was 9.24 (5.29) years and 9.00 (4.49) years, respectively (P = 0.66). Compared to controls, patients had decreased caudate (P ≤ 0.013), putamen (P ≤ 0.026), and left pallidum (P = 0.033) relative volumes. Relative volume of cerebellar vermal lobules I to V (beta coefficient = -17119, P = 0.017) decreased with increasing Repetitive Behavior Scale-Revised total score.

CONCLUSIONS

The volumes of the striatum and left pallidum are decreased in individuals with Phelan-McDermid syndrome. Cerebellar vermis volume may predict repetitive behavior severity in Phelan-McDermid syndrome. These findings warrant further investigation in larger samples.

Multidimensional co-segmentation of longitudinal brain MRI ensembles in the presence of a neurodegenerative process

MRI Segmentation of a pathological brain poses a significant challenge, as the available anatomical priors that provide top-down information to aid segmentation are inadequate in the presence of abnormalities. This problem is further complicated for longitudinal data capturing impaired brain development or neurodegenerative conditions, since the dynamic of brain atrophies has to be considered as well. For these cases, the absence of compatible annotated training examples renders the commonly used multi-atlas or machine-learning approaches impractical. We present a novel segmentation approach that accounts for the lack of labeled data via multi-region multi-subject co-segmentation (MMCoSeg) of longitudinal MRI sequences. The underlying, unknown anatomy is learned throughout an iterative process, in which the segmentation of a region is supported both by the segmentation of the neighboring regions, which share common boundaries, and by the segmentation of corresponding regions, in the other jointly segmented images. A 4D multi-region atlas that models the spatio-temporal deformations and can be adapted to different subjects undergoing similar degeneration processes is reconstructed concurrently. An inducible mouse model of p25 accumulation (the CK-p25 mouse) that displays key pathological hallmarks of Alzheimer disease (AD) is used as a gold-standard to test the proposed algorithm by providing a conditional control of rapid neurodegeneration. Applying the MMCoSeg to a cohort of CK-p25 mice and littermate controls yields promising segmentation results that demonstrate high compatibility with expertise manual annotations. An extensive comparative analysis with respect to current well-established, atlas-based segmentation methods highlights the advantage of the proposed approach, which provides accurate segmentation of longitudinal brain MRIs in pathological conditions, where only very few annotated examples are available.

Cerebellar volume as an imaging marker of development in infants with tuberous sclerosis complex

OBJECTIVE

In this cohort analysis, we studied 1-year-old infants with tuberous sclerosis complex (TSC), correlating volumes of cerebellar structures with neurodevelopmental measures.

METHODS

We analyzed data from a prospective biomarker study in infants with TSC (ClinicalTrials.gov NCT01780441). We included participants aged 12 months with an identified mutation of TSC1 or TSC2. Using MRI segmentation performed with the PSTAPLE algorithm, we measured relative volumes (structure volume divided by intracranial contents volume) of the following structures: right/left cerebellar white matter, right/left cerebellar exterior, vermal lobules I-V, vermal lobules VI-VII, and vermal lobules VIII-X. We correlated relative volumes to Mullen Scales of Early Learning (MSEL) scores.

RESULTS

There were 70 participants (mean age 1.03 [0.11] years): n = 11 had a TSC1 mutation; n = 59 had a TSC2 mutation. For patients with TSC2 mutation, for every percentage increase in total cerebellar volume, there was an approximate 10-point increase in MSEL composite score (β = 10.47 [95% confidence interval 5.67, 15.27], p < 0.001). For patients with TSC1 mutation, the relationship between cerebellar volume and MSEL composite score was not statistically significant (β = -10.88 [95% confidence interval -22.16, 0.41], p = 0.06). For patients with TSC2 mutation, there were positive slopes when regressing expressive language and visual reception skills with volumes of nearly all cerebellar structures (p ≤ 0.29); there were also positive slopes when regressing receptive language skills, gross motor skills, and fine motor skills with volumes of cerebellar right/left exterior (p ≤ 0.014).

CONCLUSIONS

Cerebellar volume loss-perhaps reflecting Purkinje cell degeneration-may predict neurodevelopmental severity in patients with TSC2 mutations.

Supervoxel based method for multi-atlas segmentation of brain MR images

Multi-atlas segmentation has been widely applied to the analysis of brain MR images. However, the state-of-the-art techniques in multi-atlas segmentation, including both patch-based and learning-based methods, are strongly dependent on the pairwise registration or exhibit huge spatial inconsistency. The paper proposes a new segmentation framework based on supervoxels to solve the existing challenges of previous methods. The supervoxel is an aggregation of voxels with similar attributes, which can be used to replace the voxel grid. By formulating the segmentation as a tissue labeling problem associated with a maximum-a-posteriori inference in Markov random field, the problem is solved via a graphical model with supervoxels being considered as the nodes. In addition, a dense labeling scheme is developed to refine the supervoxel labeling results, and the spatial consistency is incorporated in the proposed method. The proposed approach is robust to the pairwise registration errors and of high computational efficiency. Extensive experimental evaluations on three publically available brain MR datasets demonstrate the effectiveness and superior performance of the proposed approach.

Reproducibility of Brain MRI Segmentation Algorithms: Empirical Comparison of Local MAP PSTAPLE, FreeSurfer, and FSL-FIRST

BACKGROUND AND PURPOSE

Segmentation of human brain structures is crucial for the volumetric quantification of brain disease. Advances in algorithmic approaches have led to automated techniques that save time compared to interactive methods. Recently, the utility and accuracy of template library fusion algorithms, such as Local MAP PSTAPLE (PSTAPLE), have been demonstrated but there is little guidance regarding its reproducibility compared to single template-based algorithms such as FreeSurfer and FSL-FIRST.

METHODS

Eight repeated magnetic resonance imagings of 20 subjects were segmented using FreeSurfer, FSL-FIRST, and PSTAPLE. We reported the reproducibility of segmentation-derived volume measurements for brain structures and calculated sample size estimates for detecting hypothetical rates of tissue atrophy given the observed variances.

RESULTS

PSTAPLE had the most reproducible volume measurements for hippocampus, putamen, thalamus, caudate, pallidum, amygdala, Accumbens area, and cortical regions. FreeSurfer was most reproducible for brainstem. PSTAPLE was the most accurate algorithm in terms of several metrics include Dice's coefficient. The sample size estimates showed that a study utilizing PSTAPLE would require tens to hundreds less subjects than the other algorithms for detecting atrophy rates typically observed in brain disease.

CONCLUSIONS

PSTAPLE is a useful tool for automatic human brain segmentation due to its precision and accuracy, which enable the detection of the size of the effect typically reported for neurological disorders with a substantially reduced sample size, in comparison to the other tools we assessed. This enables randomized controlled trials to be executed with reduced cost and duration, in turn, facilitating the assessment of new therapeutic interventions.

Temporal slice registration and robust diffusion-tensor reconstruction for improved fetal brain structural connectivity analysis

Diffusion weighted magnetic resonance imaging, or DWI, is one of the most promising tools for the analysis of neural microstructure and the structural connectome of the human brain. The application of DWI to map early development of the human connectome in-utero, however, is challenged by intermittent fetal and maternal motion that disrupts the spatial correspondence of data acquired in the relatively long DWI acquisitions. Fetuses move continuously during DWI scans. Reliable and accurate analysis of the fetal brain structural connectome requires careful compensation of motion effects and robust reconstruction to avoid introducing bias based on the degree of fetal motion. In this paper we introduce a novel robust algorithm to reconstruct in-vivo diffusion-tensor MRI (DTI) of the moving fetal brain and show its effect on structural connectivity analysis. The proposed algorithm involves multiple steps of image registration incorporating a dynamic registration-based motion tracking algorithm to restore the spatial correspondence of DWI data at the slice level and reconstruct DTI of the fetal brain in the standard (atlas) coordinate space. A weighted linear least squares approach is adapted to remove the effect of intra-slice motion and reconstruct DTI from motion-corrected data. The proposed algorithm was tested on data obtained from 21 healthy fetuses scanned in-utero at 22-38 weeks gestation. Significantly higher fractional anisotropy values in fiber-rich regions, and the analysis of whole-brain tractography and group structural connectivity, showed the efficacy of the proposed method compared to the analyses based on original data and previously proposed methods. The results of this study show that slice-level motion correction and robust reconstruction is necessary for reliable in-vivo structural connectivity analysis of the fetal brain. Connectivity analysis based on graph theoretic measures show high degree of modularity and clustering, and short average characteristic path lengths indicative of small-worldness property of the fetal brain network. These findings comply with previous findings in newborns and a recent study on fetuses. The proposed algorithm can provide valuable information from DWI of the fetal brain not available in the assessment of the original 2D slices and may be used to more reliably study the developing fetal brain connectome.

Automated template-based brain localization and extraction for fetal brain MRI reconstruction

Most fetal brain MRI reconstruction algorithms rely only on brain tissue-relevant voxels of low-resolution (LR) images to enhance the quality of inter-slice motion correction and image reconstruction. Consequently the fetal brain needs to be localized and extracted as a first step, which is usually a laborious and time consuming manual or semi-automatic task. We have proposed in this work to use age-matched template images as prior knowledge to automatize brain localization and extraction. This has been achieved through a novel automatic brain localization and extraction method based on robust template-to-slice block matching and deformable slice-to-template registration. Our template-based approach has also enabled the reconstruction of fetal brain images in standard radiological anatomical planes in a common coordinate space. We have integrated this approach into our new reconstruction pipeline that involves intensity normalization, inter-slice motion correction, and super-resolution (SR) reconstruction. To this end we have adopted a novel approach based on projection of every slice of the LR brain masks into the template space using a fusion strategy. This has enabled the refinement of brain masks in the LR images at each motion correction iteration. The overall brain localization and extraction algorithm has shown to produce brain masks that are very close to manually drawn brain masks, showing an average Dice overlap measure of 94.5%. We have also demonstrated that adopting a slice-to-template registration and propagation of the brain mask slice-by-slice leads to a significant improvement in brain extraction performance compared to global rigid brain extraction and consequently in the quality of the final reconstructed images. Ratings performed by two expert observers show that the proposed pipeline can achieve similar reconstruction quality to reference reconstruction based on manual slice-by-slice brain extraction. The proposed brain mask refinement and reconstruction method has shown to provide promising results in automatic fetal brain MRI segmentation and volumetry in 26 fetuses with gestational age range of 23 to 38 weeks.

A normative spatiotemporal MRI atlas of the fetal brain for automatic segmentation and analysis of early brain growth

Longitudinal characterization of early brain growth in-utero has been limited by a number of challenges in fetal imaging, the rapid change in size, shape and volume of the developing brain, and the consequent lack of suitable algorithms for fetal brain image analysis. There is a need for an improved digital brain atlas of the spatiotemporal maturation of the fetal brain extending over the key developmental periods. We have developed an algorithm for construction of an unbiased four-dimensional atlas of the developing fetal brain by integrating symmetric diffeomorphic deformable registration in space with kernel regression in age. We applied this new algorithm to construct a spatiotemporal atlas from MRI of 81 normal fetuses scanned between 19 and 39 weeks of gestation and labeled the structures of the developing brain. We evaluated the use of this atlas and additional individual fetal brain MRI atlases for completely automatic multi-atlas segmentation of fetal brain MRI. The atlas is available online as a reference for anatomy and for registration and segmentation, to aid in connectivity analysis, and for groupwise and longitudinal analysis of early brain growth.

Reduced thalamic volume in patients with Electrical Status Epilepticus in Sleep

PURPOSE

To test whether patients with Electrical Status Epilepticus in Sleep (ESES) and normal neuroimaging have a smaller thalamic volume than expected for age and for total brain volume.

METHODS

Case-control study comparing three groups of subjects of 4-14 years of age and normal magnetic resonance imaging: 1) ESES patients, 2) patients with refractory epilepsy control group, and 3) healthy controls. Thalamic and total brain volumes were calculated using an algorithm for automatic segmentation and parcellation of magnetic resonance imaging.

RESULTS

Eighteen ESES patients, 29 refractory epilepsy controls and 51 healthy controls were included. The median (p25-p75) age was 8.8 (7.5-10.3) years for ESES patients, 11 (7-12) years for healthy controls, and 9 (6.3-11.2) years for refractory epilepsy controls. After correcting for total brain volume and age, the left thalamus was not statistically significantly smaller in ESES patients than in healthy controls (p=0.077), in ESES patients than in refractory epilepsy controls (p=0.056); but the right thalamus was smaller in ESES patients than in healthy controls (p=0.044), and in ESES patients than in refractory epilepsy controls (p=0.033).

CONCLUSION

Patients with ESES and normal magnetic resonance imaging have smaller relative thalamic volume controlling for age and total brain volume.

White Matter Volume Predicts Language Development in Congenital Heart Disease

OBJECTIVE

To determine whether brain volume is reduced at 1 year of age and whether these volumes are associated with neurodevelopment in biventricular congenital heart disease (CHD) repaired in infancy.

STUDY DESIGN

Infants with biventricular CHD (n = 48) underwent brain magnetic resonance imaging (MRI) and neurodevelopmental testing with the Bayley Scales of Infant Development-II and the MacArthur-Bates Communicative Development Inventories at 1 year of age. A multitemplate based probabilistic segmentation algorithm was applied to volumetric MRI data. We compared volumes with those of 13 healthy control infants of comparable ages. In the group with CHD, we measured Spearman correlations between neurodevelopmental outcomes and the residuals from linear regression of the volumes on corrected chronological age at MRI and sex.

RESULTS

Compared with controls, infants with CHD had reductions of 54 mL in total brain (P = .009), 40 mL in cerebral white matter (P <.001), and 1.2 mL in brainstem (P = .003) volumes. Within the group with CHD, brain volumes were not correlated with Bayley Scales of Infant Development-II scores but did correlate positively with MacArthur-Bates Communicative Development Inventory language development.

CONCLUSIONS

Infants with biventricular CHD show total brain volume reductions at 1 year of age, driven by differences in cerebral white matter. White matter volume correlates with language development, but not broader developmental indices. These findings suggest that abnormalities in white matter development detected months after corrective heart surgery may contribute to language impairment.

TRIAL REGISTRATION

ClinicalTrials.gov: NCT00006183.

Characterizing brain tissue by assessment of the distribution of anisotropic microstructural environments in diffusion-compartment imaging (DIAMOND)

PURPOSE

To develop a statistical model for the tridimensional diffusion MRI signal at each voxel that describes the signal arising from each tissue compartment in each voxel.

THEORY AND METHODS

In prior work, a statistical model of the apparent diffusion coefficient was shown to well-characterize the diffusivity and heterogeneity of the mono-directional diffusion MRI signal. However, this model was unable to characterize the three-dimensional anisotropic diffusion observed in the brain. We introduce a new model that extends the statistical distribution representation to be fully tridimensional, in which apparent diffusion coefficients are extended to be diffusion tensors. The set of compartments present at a voxel is modeled by a finite sum of unimodal continuous distributions of diffusion tensors. Each distribution provides measures of each compartment microstructural diffusivity and heterogeneity.

RESULTS

The ability to estimate the tridimensional diffusivity and heterogeneity of multiple fascicles and of free diffusion is demonstrated.

CONCLUSION

Our novel tissue model allows for the characterization of the intra-voxel orientational heterogeneity, a prerequisite for accurate tractography while also characterizing the overall tridimensional diffusivity and heterogeneity of each tissue compartment. The model parameters can be estimated from short duration acquisitions. The diffusivity and heterogeneity microstructural parameters may provide novel indicator of the presence of disease or injury. Magn Reson Med 76:963-977, 2016. © 2015 Wiley Periodicals, Inc.