Automated fetal brain segmentation from 2D MRI slices for motion correction

A joint brain extraction and image quality assessment framework for fetal brain MRI slices

Brain extraction and image quality assessment are two fundamental steps in fetal brain magnetic resonance imaging (MRI) 3D reconstruction and quantification. However, the randomness of fetal position and orientation, the variability of fetal brain morphology, maternal organs around the fetus, and the scarcity of data samples, all add excessive noise and impose a great challenge to automated brain extraction and quality assessment of fetal MRI slices. Conventionally, brain extraction and quality assessment are typically performed independently. However, both of them focus on the brain image representation, so they can be jointly optimized to ensure the network learns more effective features and avoid overfitting. To this end, we propose a novel two-stage dual-task deep learning framework with a brain localization stage and a dual-task stage for joint brain extraction and quality assessment of fetal MRI slices. Specifically, the dual-task module compactly contains a feature extraction module, a quality assessment head and a segmentation head with feature fusion for simultaneous brain extraction and quality assessment. Besides, a transformer architecture is introduced into the feature extraction module and the segmentation head. We utilize a multi-step training strategy to guarantee a stable and successful training of all modules. Finally, we validate our method by a 5-fold cross-validation and ablation study on a dataset with fetal brain MRI slices in different qualities, and perform a cross-dataset validation in addition. Experiments show that the proposed framework achieves very promising performance.

One model, two brains: Automatic fetal brain extraction from MR images of twins

Fetal brain extraction from magnetic resonance (MR) images is of great importance for both clinical applications and neuroscience studies. However, it is a challenging task, especially when dealing with twins, which are commonly existing in pregnancy. Currently, there is no brain extraction method dedicated to twins, raising significant demand to develop an effective twin fetal brain extraction method. To this end, we propose the first twin fetal brain extraction framework, which possesses three novel features. First, to narrow down the region of interest and preserve structural information between the two brains in twin fetal MR images, we take advantage of an advanced object detector to locate all the brains in twin fetal MR images at once. Second, we propose a Twin Fetal Brain Extraction Network (TFBE-Net) to further suppress insignificant features for segmenting brain regions. Finally, we propose a Two-step Training Strategy (TTS) to learn correlation features of the single fetal brain for further improving the performance of TFBE-Net. We validate the proposed framework on a twin fetal brain dataset. The experiments show that our framework achieves promising performance on both quantitative and qualitative evaluations, and outperforms state-of-the-art methods for fetal brain extraction.

Image Recovery Matters: A Recovery-Extraction Framework for Robust Fetal Brain Extraction From MR Images

The extraction of the fetal brain from magnetic resonance (MR) images is a challenging task. In particular, fetal MR images suffer from different kinds of artifacts introduced during the image acquisition. Among those artifacts, intensity inhomogeneity is a common one affecting brain extraction. In this work, we propose a deep learning-based recovery-extraction framework for fetal brain extraction, which is particularly effective in handling fetal MR images with intensity inhomogeneity. Our framework involves two stages. First, the artifact-corrupted images are recovered with the proposed generative adversarial learning-based image recovery network with a novel region-of-darkness discriminator that enforces the network focusing on artifacts of the images. Second, we propose a brain extraction network for more effective fetal brain segmentation by strengthening the association between lower- and higher-level features as well as suppressing task-irrelevant features. Thanks to the proposed recovery-extraction strategy, our framework is able to accurately segment fetal brains from artifact-corrupted MR images. The experiments show that our framework achieves promising performance in both quantitative and qualitative evaluations, and outperforms state-of-the-art methods in both image recovery and fetal brain extraction.

Real-time fetal brain tracking for functional fetal MRI

PURPOSE

To improve motion robustness of functional fetal MRI scans by developing an intrinsic real-time motion correction method. MRI provides an ideal tool to characterize fetal brain development and growth. It is, however, a relatively slow imaging technique and therefore extremely susceptible to subject motion, particularly in functional MRI experiments acquiring multiple Echo-Planar-Imaging-based repetitions, for example, diffusion MRI or blood-oxygen-level-dependency MRI.

METHODS

A 3D UNet was trained on 125 fetal datasets to track the fetal brain position in each repetition of the scan in real time. This tracking, inserted into a Gadgetron pipeline on a clinical scanner, allows updating the position of the field of view in a modified echo-planar imaging sequence. The method was evaluated in real-time in controlled-motion phantom experiments and ten fetal MR studies (17 + 4-34 + 3 gestational weeks) at 3T. The localization network was additionally tested retrospectively on 29 low-field (0.55T) datasets.

RESULTS

Our method achieved real-time fetal head tracking and prospective correction of the acquisition geometry. Localization performance achieved Dice scores of 84.4% and 82.3%, respectively for both the unseen 1.5T/3T and 0.55T fetal data, with values higher for cephalic fetuses and increasing with gestational age.

CONCLUSIONS

Our technique was able to follow the fetal brain even for fetuses under 18 weeks GA in real-time at 3T and was successfully applied "offline" to new cohorts on 0.55T. Next, it will be deployed to other modalities such as fetal diffusion MRI and to cohorts of pregnant participants diagnosed with pregnancy complications, for example, pre-eclampsia and congenital heart disease.

An automatic pipeline for atlas-based fetal and neonatal brain segmentation and analysis

BACKGROUND AND OBJECTIVE

The automatic segmentation of perinatal brain structures in magnetic resonance imaging (MRI) is of utmost importance for the study of brain growth and related complications. While different methods exist for adult and pediatric MRI data, there is a lack for automatic tools for the analysis of perinatal imaging.

METHODS

In this work, a new pipeline for fetal and neonatal segmentation has been developed. We also report the creation of two new fetal atlases, and their use within the pipeline for atlas-based segmentation, based on novel registration methods. The pipeline is also able to extract cortical and pial surfaces and compute features, such as curvature, local gyrification index, sulcal depth, and thickness.

RESULTS

Results show that the introduction of the new templates together with our segmentation strategy leads to accurate results when compared to expert annotations, as well as better performances when compared to a reference pipeline (developing Human Connectome Project (dHCP)), for both early and late-onset fetal brains.

CONCLUSIONS

These findings show the potential of the presented atlases and the whole pipeline for application in both fetal, neonatal, and longitudinal studies, which could lead to dramatic improvements in the understanding of perinatal brain development.

AFFIRM: Affinity Fusion-Based Framework for Iteratively Random Motion Correction of Multi-Slice Fetal Brain MRI

Multi-slice magnetic resonance images of the fetal brain are usually contaminated by severe and arbitrary fetal and maternal motion. Hence, stable and robust motion correction is necessary to reconstruct high-resolution 3D fetal brain volume for clinical diagnosis and quantitative analysis. However, the conventional registration-based correction has a limited capture range and is insufficient for detecting relatively large motions. Here, we present a novel Affinity Fusion-based Framework for Iteratively Random Motion (AFFIRM) correction of the multi-slice fetal brain MRI. It learns the sequential motion from multiple stacks of slices and integrates the features between 2D slices and reconstructed 3D volume using affinity fusion, which resembles the iterations between slice-to-volume registration and volumetric reconstruction in the regular pipeline. The method accurately estimates the motion regardless of brain orientations and outperforms other state-of-the-art learning-based methods on the simulated motion-corrupted data, with a 48.4% reduction of mean absolute error for rotation and 61.3% for displacement. We then incorporated AFFIRM into the multi-resolution slice-to-volume registration and tested it on the real-world fetal MRI scans at different gestation stages. The results indicated that adding AFFIRM to the conventional pipeline improved the success rate of fetal brain super-resolution reconstruction from 77.2% to 91.9%.

BEAN: Brain Extraction and Alignment Network for 3D Fetal Neurosonography

Brain extraction (masking of extra-cerebral tissues) and alignment are fundamental first steps of most neuroimage analysis pipelines. The lack of automated solutions for 3D ultrasound (US) has therefore limited its potential as a neuroimaging modality for studying fetal brain development using routinely acquired scans. In this work, we propose a convolutional neural network (CNN) that accurately and consistently aligns and extracts the fetal brain from minimally pre-processed 3D US scans. Our multi-task CNN, Brain Extraction and Alignment Network (BEAN), consists of two independent branches: 1) a fully-convolutional encoder-decoder branch for brain extraction of unaligned scans, and 2) a two-step regression-based branch for similarity alignment of the brain to a common coordinate space. BEAN was tested on 356 fetal head 3D scans spanning the gestational range of 14 to 30 weeks, significantly outperforming all current alternatives for fetal brain extraction and alignment. BEAN achieved state-of-the-art performance for both tasks, with a mean Dice Similarity Coefficient (DSC) of 0.94 for the brain extraction masks, and a mean DSC of 0.93 for the alignment of the target brain masks. The presented experimental results show that brain structures such as the thalamus, choroid plexus, cavum septum pellucidum, and Sylvian fissure, are consistently aligned throughout the dataset and remain clearly visible when the scans are averaged together. The BEAN implementation and related code can be found under www.github.com/felipemoser/kelluwen.

An ode to fetal, infant, and toddler neuroimaging: Chronicling early clinical to research applications with MRI, and an introduction to an academic society connecting the field

Fetal, infant, and toddler neuroimaging is commonly thought of as a development of modern times (last two decades). Yet, this field mobilized shortly after the discovery and implementation of MRI technology. Here, we provide a review of the parallel advancements in the fields of fetal, infant, and toddler neuroimaging, noting the shifts from clinical to research use, and the ongoing challenges in this fast-growing field. We chronicle the pioneering science of fetal, infant, and toddler neuroimaging, highlighting the early studies that set the stage for modern advances in imaging during this developmental period, and the large-scale multi-site efforts which ultimately led to the explosion of interest in the field today. Lastly, we consider the growing pains of the community and the need for an academic society that bridges expertise in developmental neuroscience, clinical science, as well as computational and biomedical engineering, to ensure special consideration of the vulnerable mother-offspring dyad (especially during pregnancy), data quality, and image processing tools that are created, rather than adapted, for the young brain.

Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images

In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively.

Rapid head-pose detection for automated slice prescription of fetal-brain MRI

In fetal-brain MRI, head-pose changes between prescription and acquisition present a challenge to obtaining the standard sagittal, coronal and axial views essential to clinical assessment. As motion limits acquisitions to thick slices that preclude retrospective resampling, technologists repeat ~55-second stack-of-slices scans (HASTE) with incrementally reoriented field of view numerous times, deducing the head pose from previous stacks. To address this inefficient workflow, we propose a robust head-pose detection algorithm using full-uterus scout scans (EPI) which take ~5 seconds to acquire. Our ~2-second procedure automatically locates the fetal brain and eyes, which we derive from maximally stable extremal regions (MSERs). The success rate of the method exceeds 94% in the third trimester, outperforming a trained technologist by up to 20%. The pipeline may be used to automatically orient the anatomical sequence, removing the need to estimate the head pose from 2D views and reducing delays during which motion can occur.

Data Quality Assessment for Super-Resolution Fetal Brain MR Imaging: A Retrospective 1.5 T Study

BACKGROUND

Super-resolution is a promising technique to create isotropic image volumes from stacks of two-dimensional (2D) motion-corrupted images in fetal magnetic resonance imaging (MRI).

PURPOSE

To determine an acquisition quality metric and correlate that metric with radiologist perception of three-dimensional (3D) image quality.

STUDY TYPE

Retrospective.

SUBJECTS

Eighty-seven patients, mean gestational age 29 ± 6 weeks.

FIELD STRENGTH/SEQUENCE

1.5 T/2D fast spin-echo.

ASSESSMENT

Four radiologists (L.G., D.M.E.B., P.C., and J.V.; 31, 21, 7, and 7 years' experience, respectively) graded reconstructions on a 0 to 4 scale for overall appearance and visibility of specific anatomy. During reconstruction, slices were labeled as inliers based on correlation between a simulated vs. actual acquisition. The fraction of brain voxels in inlier slicers vs. total brain voxels was measured for each acquisition.

STATISTICAL TESTS

Paired sample t test, Pearson's correlation, intra-class correlation.

RESULTS

The average brain mask inlier fraction for all acquisitions was 0.8. There was a statistically significant correlation (0.71) between overall reconstruction appearance and number of acquisitions with inlier fraction above 0.73. There was low correlation (0.21, P = 0.05) between the number of acquisitions used in the reconstruction and overall score when no data quality measure was considered. Similar results were found for ratings of specific anatomy. Statistically significant differences in overall perception of image quality were found when using three vs. four, four vs. five, and three vs. five high-quality acquisitions in the reconstruction. Five high-quality acquisitions were sufficient to yield an average radiologist rating of 3.59 out of 4.0 for overall image quality.

DATA CONCLUSION

Reconstruction quality can be reliably predicted using the brain mask inlier fraction. Real-time super-resolution protocols could exploit this to terminate acquisition when enough high-quality acquisitions have been collected. To achieve consistent 3D image quality it may be necessary to acquire more than five scans to compensate for severely motion-corrupted acquisitions.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: 1.

Automatic brain extraction from 3D fetal MR image with deep learning-based multi-step framework

Brain extraction is a fundamental prerequisite step in neuroimage analysis for fetus. Due to surrounding maternal tissues and unpredictable movement, brain extraction from fetal Magnetic Resonance (MR) images is a challenging task. In this paper, we propose a novel deep learning-based multi-step framework for brain extraction from 3D fetal MR images. In the first step, a global localization network is applied to estimate probability maps for brain candidates. Connected-component labeling algorithm is applied to eliminate small erroneous components and accurately locate the candidate brain area. In the second step, a local refinement network is implemented in the brain candidate area to obtain fine-grained probability maps. Final extraction results are derived by a fusion network with the two cascaded probability maps obtained from previous two steps. Experimental results demonstrate that our proposed method has superior performance compared with existing deep learning-based methods.

Global and Regional Changes in Cortical Development Assessed by MRI in Fetuses with Isolated Nonsevere Ventriculomegaly Correlate with Neonatal Neurobehavior

BACKGROUND AND PURPOSE

Fetuses with isolated nonsevere ventriculomegaly (INSVM) are at risk of presenting neurodevelopmental delay. However, the currently used clinical parameters are insufficient to select cases with high risk and determine whether subtle changes in brain development are present and might be a risk factor. The aim of this study was to perform a comprehensive evaluation of cortical development in INSVM by magnetic resonance (MR) imaging and assess its association with neonatal neurobehavior.

MATERIALS AND METHODS

Thirty-two INSVM fetuses and 29 healthy controls between 26-28 weeks of gestation were evaluated using MR imaging. We compared sulci and fissure depth, cortical maturation grading of specific areas and sulci and volumes of different brain regions obtained from 3D brain reconstruction of cases and controls. Neonatal outcome was assessed by using the Neonatal Behavioral Assessment Scale at a mean of 4 ± 2 weeks after birth.

RESULTS

Fetuses with INSVM showed less profound and underdeveloped sulcation, including the Sylvian fissure (mean depth: controls 16.8 ± 1.9 mm, versus INSVM 16.0 ± 1.6 mm; P = .01), and reduced global cortical grading (mean score: controls 42.9 ± 10.2 mm, versus INSVM: 37.8 ± 9.9 mm; P = .01). Fetuses with isolated nonsevere ventriculomegaly showed a mean global increase of gray matter volume (controls, 276.8 ± 46.0 ×10 mm³, versus INSVM 277.5 ± 49.3 ×10 mm³, P = .01), but decreased mean cortical volume in the frontal lobe (left: controls, 53.2 ± 8.8 ×10 mm³, versus INSVM 52.4 ± 5.4 ×10 mm³; P = < .01). Sulcal depth and brain volumes were significantly associated with the Neonatal Behavioral Assessment Scale severity (P = .005, Nagelkerke R² = 0.732).

CONCLUSIONS

INSVM fetuses showed differences in cortical development, including regions far from the lateral ventricles, that are associated with neonatal neurobehavior. These results suggest the possible use of these parameters to identify cases at higher risk of altered neurodevelopment.

A novel approach to multiple anatomical shape analysis: Application to fetal ventriculomegaly

Fetal ventriculomegaly (VM) is a condition in which one or both lateral ventricles are enlarged, and is diagnosed as an atrial diameter larger than 10 mm. Evidence of altered cortical folding associated with VM has been shown in the literature. However, existing works use a single scalar value such as diagnosis or lateral ventricular volume to characterize VM and study its relationship with alterations in cortical folding, thus failing to reveal the spatially-heterogeneous associations. In this work, we propose a novel approach to identify fine-grained associations between cortical folding and ventricular enlargement by leveraging the vertex-wise correlations between their growth patterns in terms of area expansion and curvature. Our approach comprises three steps. In the first step, we define a joint graph Laplacian matrix using cortex-to-ventricle correlations. The joint Laplacian is built based on multiple cortical features. Next, we propose a spectral embedding of the cortex-to-ventricle graph into a common underlying space where its nodes are projected according to the joint ventricle-cortex growth patterns. In this low-dimensional joint ventricle-cortex space, associated growth patterns lie close to each other. In the final step, we perform hierarchical clustering in the joint embedded space to identify associated sub-regions between cortex and ventricle. Using a dataset of 25 healthy fetuses and 23 fetuses with isolated non-severe VM within the age range of 26-29 gestational weeks, our approach reveals clinically relevant and heterogeneous regional associations. Cortical regions forming these associations are further validated using statistical analysis, revealing regions with altered folding that are significantly associated with ventricular dilation.

An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI

High-resolution volume reconstruction from multiple motion-corrupted stacks of 2D slices plays an increasing role for fetal brain Magnetic Resonance Imaging (MRI) studies. Currently existing reconstruction methods are time-consuming and often require user interactions to localize and extract the brain from several stacks of 2D slices. We propose a fully automatic framework for fetal brain reconstruction that consists of four stages: 1) fetal brain localization based on a coarse segmentation by a Convolutional Neural Network (CNN), 2) fine segmentation by another CNN trained with a multi-scale loss function, 3) novel, single-parameter outlier-robust super-resolution reconstruction, and 4) fast and automatic high-resolution visualization in standard anatomical space suitable for pathological brains. We validated our framework with images from fetuses with normal brains and with variable degrees of ventriculomegaly associated with open spina bifida, a congenital malformation affecting also the brain. Experiments show that each step of our proposed pipeline outperforms state-of-the-art methods in both segmentation and reconstruction comparisons including expert-reader quality assessments. The reconstruction results of our proposed method compare favorably with those obtained by manual, labor-intensive brain segmentation, which unlocks the potential use of automatic fetal brain reconstruction studies in clinical practice.

Automatic extraction of the intracranial volume in fetal and neonatal MR scans using convolutional neural networks

•

Automatic intracranial volume segmentation.

•

Fetal and neonatal MRI.

•

Deep learning.

MR images of infants and fetuses allow non-invasive analysis of the brain. Quantitative analysis of brain development requires automatic brain tissue segmentation that is typically preceded by segmentation of the intracranial volume (ICV). Fast changes in the size and morphology of the developing brain, motion artifacts, and large variation in the field of view make ICV segmentation a challenging task.

We propose an automatic method for segmentation of the ICV in fetal and neonatal MRI scans. The method was developed and tested with a diverse set of scans regarding image acquisition parameters (i.e. field strength, image acquisition plane, image resolution), infant age (23–45 weeks post menstrual age), and pathology (posthaemorrhagic ventricular dilatation, stroke, asphyxia, and Down syndrome). The results demonstrate that the method achieves accurate segmentation with a Dice coefficient (DC) ranging from 0.98 to 0.99 in neonatal and fetal scans regardless of image acquisition parameters or patient characteristics. Hence, the algorithm provides a generic tool for segmentation of the ICV that may be used as a preprocessing step for brain tissue segmentation in fetal and neonatal brain MR scans.

A new approach to automatic fetal brain extraction from MRI using a variational level set method

BACKGROUND AND PURPOSE

Appropriate images extracted from the MRI of mothers' wombs can be of great help in the medical diagnosis of fetal abnormalities. As maternal tissue may appear in such images, affecting visualization of myelination of the fetal brain, it is not possible to use methods routinely used for extraction of adult brains for fetal brains. The aim of the present study was to use a variational level set approach to extract fetal brain from T2-weighted MR images of the womb.

METHODS

Coronal T2-weighted images were acquired using fast MRI protocols (to avoid artifacts). The database includes 105 MR images from eight subjects. After correcting the inhomogeneity of the images, the fetal eyes were located, and from that information, the location of the fetus brain was automatically determined. Then, the variational level set was used for fetus brain extraction. The results were analyzed by a clinical specialist (radiologist) and the similarity (Dice and Jaccard coefficients), sensitivity and specificity were calculated.

RESULTS AND CONCLUSIONS

The means of the statistical analysis for the Dice and Jaccard coefficients, sensitivity and specificity, were 99.56%, 96.89%, 95.71%, and 97.96%, respectively. Thus, extraction of fetal brain from MR images was confirmed, both statistically and visually through cross-validation.

Quantitative analysis of fetal magnetic resonance phantoms and recommendations for an anthropomorphic motion phantom

OBJECTIVE

To provide a review and quantitative analysis of the available fetal MR imaging phantoms.

MATERIALS AND METHODS

A literature search was conducted across Pubmed, Google Scholar, and Ryerson University Library databases to identify fetal MR imaging phantoms. Phantoms were graded on a semi-quantitative scale in regards to four evaluation categories: (1) anatomical accuracy in size and shape, (2) dielectric conductivity similar to the simulated tissue, (3) relaxation times similar to simulated tissue, and (4) physiological motion similar to fetal gross body, cardiovascular, and breathing motion. This was followed by statistical analysis to identify significant findings.

RESULTS

Seventeen fetal phantoms were identified and had an average overall percentage accuracy of 26%, with anatomical accuracy being satisfied the most (56%) and physiological motion the least (7%). Phantoms constructed using 3D printing were significantly more accurate than conventionally constructed phantoms.

DISCUSSION

Currently available fetal phantoms lack accuracy and motion simulation. 3D printing may lead to higher accuracy compared with traditional manufacturing. Future research needs to focus on properly simulating both fetal anatomy and physiological motion to produce a phantom that is appropriate for fetal MRI sequence development and optimization.

Evaluation of a motion-robust 2D chemical shift-encoded technique for R2* and field map quantification in ferumoxytol-enhanced MRI of the placenta in pregnant rhesus macaques

BACKGROUND

3D chemical shift-encoded (CSE)-MRI techniques enable assessment of ferumoxytol concentration but are unreliable in the presence of motion.

PURPOSE

To evaluate a motion-robust 2D-sequential CSE-MRI for R2* and B0 mapping in ferumoxytol-enhanced MRI of the placenta.

STUDY TYPE

Prospective.

ANIMAL MODEL

Pregnant rhesus macaques.

FIELD STRENGTH/SEQUENCE

3.0T/CSE-MRI.

ASSESSMENT

2D-sequential CSE-MRI was compared with 3D respiratory-gated CSE-MRI in placental imaging of 11 anesthetized animals at multiple timepoints before and after ferumoxytol administration, and in ferumoxytol phantoms (0 μg/mL-440 μg/mL). Motion artifacts of CSE-MRI in 10 pregnant women without ferumoxytol administration were assessed retrospectively by three blinded readers (4-point Likert scale). The repeatability of CSE-MRI in seven pregnant women was also prospectively studied.

STATISTICAL TESTS

Placental R2* and boundary B0 field measurements (ΔB0) were compared between 2D-sequential and 3D respiratory-gated CSE-MRI using linear regression and Bland-Altman analysis.

RESULTS

In phantoms, a slope of 0.94 (r² = 0.99, concordance correlation coefficient ρ = 0.99), and bias of -4.8 s^-1 (limit of agreement [LOA], -41.4 s^-1 , +31.8 s^-1 ) in R2*, and a slope of 1.07 (r² = 1.00, ρ = 0.99) and bias of 11.4 Hz (LOA -12.0 Hz, +34.8 Hz) in ΔB0 were obtained in 2D CSE-MRI compared with 3D CSE-MRI for reference R2* ≤390 s^-1 . In animals, a slope of 0.92 (r² = 0.97, ρ = 0.98) and bias of -2.2 s^-1 (LOA -55.6 s^-1 , +51.3 s^-1 ) in R2*, and a slope of 1.05 (r² = 0.95, ρ = 0.97) and bias of 0.4 Hz (LOA -9.0 Hz, +9.7 Hz) in ΔB0 were obtained. In humans, motion-impaired R2* maps in 3D CSE-MRI (Reader 1: 1.8 ± 0.6, Reader 2: 1.3 ± 0.7, Reader 3: 1.9 ± 0.6), while 2D CSE-MRI was motion-free (Reader 1: 2.9 ± 0.3, Reader 2: 3.0 ± 0, Reader 3: 3.0 ± 0). A mean difference of 0.66 s^-1 and coefficient of repeatability of 9.48 s^-1 for placental R2* were observed in the repeated 2D CSE-MRI.

DATA CONCLUSION

2D-sequential CSE-MRI provides accurate R2* and B0 measurements in ferumoxytol-enhanced placental MRI of animals in the presence of respiratory motion, and motion-robustness in human placental imaging.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2020;51:580-592.

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation

Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.

Fetal cortical surface atlas parcellation based on growth patterns

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

Normative volume measurements of the fetal intra-cranial compartments using 3D volume in utero MR imaging

PURPOSE

To describe the normal linear measurements of the skull (bi-parietal diameter and occipito-frontal diameter) and intracranial volumes (ventricular volume, brain parenchymal volume, extra-axial volume and total intra-cranial volume) in normal fetuses.

MATERIALS AND METHODS

We recruited pregnant women from low-risk pregnancies whose fetuses had normal ultrasound and in utero MR studies. All volunteers had in utero MR imaging on the same 1.5T MR scanner with a protocol consisting of routine and 3D steady-state volume imaging of the fetal brain. Linear measurements of the skull were made using the volume imaging. The 3D volume imaging also was manually segmented to delineate the intracranial compartments described above to determine quantitative values for each.

RESULTS

Two hundred normal fetuses were studied with gestational ages between 18 and 37 weeks. The linear skull measurements made on in utero MR imaging closely correlate with published data from ultrasonography. The intracranial volume data is presented as graphs and as tabular summaries of 3rd, 10th, 50th, 90th and 97th centiles.

CONCLUSION

It is now possible to measure the volumes of the intracranial compartments in individual fetuses using ultrafast in utero MR techniques.

KEY POINTS

• There are limitations in using the skull size of the fetus to comment on the state of the fetal brain. • Volumes for the intracranial compartments are presented, based on in utero MR imaging of the fetal brain between 18 and 37 weeks gestational age. • Those normative values can be used to assess fetuses with known or suspected structural brain abnormalities and may assist the differential diagnosis provided by visual assessment of routine iuMR studies.

Patch spaces and fusion strategies in patch-based label fusion

In the field of multi-atlas segmentation, patch-based approaches have shown promising results in the segmentation of biomedical images. In the most common approach, registration is used to warp the atlases to the target space and then the warped atlas labelmaps are fused into a consensus segmentation based on local appearance information encoded in form of patches. The registration step establishes spatial correspondence, which is important to obtain anatomical priors. Patch-based label fusion in the target space has shown to produce very accurate segmentations although at the expense of registering all atlases to each target image. Moreover, appearance (i.e., patches) and label information used by label fusion is extracted from the warped atlases, which are subject to interpolation errors. In this work, we revisit and extend the patch-based label fusion framework, exploring the role of extracting this information from the native space of both atlases and target images, thus avoiding interpolation artifacts, but at the same time, we do it in a way that it does not sacrifice the anatomical priors derived by registration. We further propose a common formulation for two widely-used label fusion strategies, i.e., similarity-based and a particular type of learning-based label fusion. The proposed framework is evaluated on subcortical structure segmentation in adult brains and tissue segmentation in fetal brain MRI. Our results indicate that using atlas patches in their native space yields superior performance than warping the atlases to the target image. The learning-based approach tends to outperform the similarity-based approach, with the particularity that using patches in native space lessens the computational requirements of learning. As conclusion, the combination of learning-based label fusion and native atlas patches yields the best performance with reduced test times than conventional similarity-based approaches.

Fetal MRI, lower acceptance by women in research vs. clinical setting

AIM

To determine acceptance of pregnant women to undergo fetal magnetic resonance imaging (MRI) examination in research and clinical setting.

METHODS

A prospective study included a research group [part of a study comparing brain ultrasound (US) to MRI in fetuses at risk for acquired brain damage] and a clinical group [fetuses with suspected (brain) anomalies after structural US examination] from 2011 to 2014. All women were advised to use sedatives. MRI declinations, use of sedation, MRI duration and imaging quality were compared between both groups.

RESULTS

Study participation was accepted in 57/104 (55%) research cases. Fetal MRI was performed in 34/104 (33%) research and 43/44 (98%) clinical cases. Reasons to decline study participation were MRI related in 41%, and participation was too burdensome in 46%. Acceptance was highest for indication infection and lowest in alloimmune thrombocytopenia and monochorionic twin pregnancy. Sedatives were used in 14/34 research and 43/43 clinical cases. Scan duration and quality were comparable (21 and 20 min in research and clinical cases, respectively, moderate/good quality in both groups).

CONCLUSIONS

Pregnant women consider MRI more burdensome than professionals realize. Two-third of women at risk for fetal brain damage decline MRI examination. Future studies should evaluate which information about fetal MRI is supportive.

Segmentation and classification in MRI and US fetal imaging: Recent trends and future prospects

Fetal imaging is a burgeoning topic. New advancements in both magnetic resonance imaging and (3D) ultrasound currently allow doctors to diagnose fetal structural abnormalities such as those involved in twin-to-twin transfusion syndrome, gestational diabetes mellitus, pulmonary sequestration and hypoplasia, congenital heart disease, diaphragmatic hernia, ventriculomegaly, etc. Considering the continued breakthroughs in utero image analysis and (3D) reconstruction models, it is now possible to gain more insight into the ongoing development of the fetus. Best prenatal diagnosis performances rely on the conscious preparation of the clinicians in terms of fetal anatomy knowledge. Therefore, fetal imaging will likely span and increase its prevalence in the forthcoming years. This review covers state-of-the-art segmentation and classification methodologies for the whole fetus and, more specifically, the fetal brain, lungs, liver, heart and placenta in magnetic resonance imaging and (3D) ultrasound for the first time. Potential applications of the aforementioned methods into clinical settings are also inspected. Finally, improvements in existing approaches as well as most promising avenues to new areas of research are briefly outlined.

Learning to combine complementary segmentation methods for fetal and 6-month infant brain MRI segmentation

Segmentation of brain structures during the pre-natal and early post-natal periods is the first step for subsequent analysis of brain development. Segmentation techniques can be roughly divided into two families. The first, which we denote as registration-based techniques, rely on initial estimates derived by registration to one (or several) templates. The second family, denoted as learning-based techniques, relate imaging (and spatial) features to their corresponding anatomical labels. Each approach has its own qualities and both are complementary to each other. In this paper, we explore two ensembling strategies, namely, stacking and cascading to combine the strengths of both families. We present experiments on segmentation of 6-month infant brains and a cohort of fetuses with isolated non-severe ventriculomegaly (INSVM). INSVM is diagnosed when ventricles are mildly enlarged and no other anomalies are apparent. Prognosis is difficult based solely on the degree of ventricular enlargement. In order to find markers for a more reliable prognosis, we use the resulting segmentations to find abnormalities in the cortical folding of INSVM fetuses. Segmentation results show that either combination strategy outperform all of the individual methods, thus demonstrating the capability of learning systematic combinations that lead to an overall improvement. In particular, the cascading strategy outperforms the ensembling one, the former one obtaining top 5, 7 and 13 results (out of 21 teams) in the segmentation of white matter, gray matter and cerebro-spinal fluid in the iSeg2017 MICCAI Segmentation Challenge. The resulting segmentations reveal that INSVM fetuses have a less convoluted cortex. This points to cortical folding abnormalities as potential markers of later neurodevelopmental outcomes.

3-D Reconstruction in Canonical Co-Ordinate Space From Arbitrarily Oriented 2-D Images

Limited capture range, and the requirement to provide high quality initialization for optimization-based 2-D/3-D image registration methods, can significantly degrade the performance of 3-D image reconstruction and motion compensation pipelines. Challenging clinical imaging scenarios, which contain significant subject motion, such as fetal in-utero imaging, complicate the 3-D image and volume reconstruction process. In this paper, we present a learning-based image registration method capable of predicting 3-D rigid transformations of arbitrarily oriented 2-D image slices, with respect to a learned canonical atlas co-ordinate system. Only image slice intensity information is used to perform registration and canonical alignment, no spatial transform initialization is required. To find image transformations, we utilize a convolutional neural network architecture to learn the regression function capable of mapping 2-D image slices to a 3-D canonical atlas space. We extensively evaluate the effectiveness of our approach quantitatively on simulated magnetic resonance imaging (MRI), fetal brain imagery with synthetic motion and further demonstrate qualitative results on real fetal MRI data where our method is integrated into a full reconstruction and motion compensation pipeline. Our learning based registration achieves an average spatial prediction error of 7 mm on simulated data and produces qualitatively improved reconstructions for heavily moving fetuses with gestational ages of approximately 20 weeks. Our model provides a general and computationally efficient solution to the 2-D/3-D registration initialization problem and is suitable for real-time scenarios.

A fast segmentation-free fully automated approach to white matter injury detection in preterm infants

White matter injury (WMI) is the most prevalent brain injury in the preterm neonate leading to developmental deficits. However, detecting WMI in magnetic resonance (MR) images of preterm neonate brains using traditional WM segmentation-based methods is difficult mainly due to lack of reliable preterm neonate brain atlases to guide segmentation. Hence, we propose a segmentation-free, fast, unsupervised, atlas-free WMI detection method. We detect the ventricles as blobs using a fast linear maximally stable extremal regions algorithm. A reference contour equidistant from the blobs and the brain-background boundary is used to identify tissue adjacent to the blobs. Assuming normal distribution of the gray-value intensity of this tissue, the outlier intensities in the entire brain region are identified as potential WMI candidates. Thereafter, false positives are discriminated using appropriate heuristics. Experiments using an expert-annotated dataset show that the proposed method runs 20 times faster than our earlier work which relied on time-consuming segmentation of the WM region, without compromising WMI detection accuracy. Graphical Abstract Key Steps of Segmentation-free WMI Detection.

Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning

Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes (a.k.a. zero-shot learning). To address these problems, we propose a novel deep learning-based interactive segmentation framework by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine tuning. We applied this framework to two applications: 2-D segmentation of multiple organs from fetal magnetic resonance (MR) slices, where only two types of these organs were annotated for training and 3-D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only the tumor core in one MR sequence was annotated for training. Experimental results show that: 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.

Fetal neuroimaging: an update on technical advances and clinical findings

This paper is based on a literature review from 2011 to 2016. The paper is divided into two main sections. The first section relates to technical advances in fetal imaging techniques, including fetal motion compensation, imaging at 3.0 T, 3-D T2-weighted MRI, susceptibility-weighted imaging, computed tomography, morphometric analysis, diffusion tensor imaging, spectroscopy and fetal behavioral assessment. The second section relates to clinical updates, including cerebral lamination, migrational anomalies, midline anomalies, neural tube defects, posterior fossa anomalies, sulcation/gyration and hypoxic-ischemic insults.

Sulcal pits and patterns in developing human brains

Spatial distribution and specific geometric and topological patterning of early sulcal folds have been hypothesized to be under stronger genetic control and are more associated with optimal organization of cortical functional areas and their white matter connections, compared to later developing sulci. Several previous studies of sulcal pit (putative first sulcal fold) distribution and sulcal pattern analyses using graph structures have provided evidence of the importance of sulcal pits and patterns as remarkable anatomical features closely related to human brain function, suggesting additional insights concerning the anatomical and functional development of the human brain. Recently, early sulcal folding patterns have been observed in healthy fetuses and fetuses with brain abnormalities such as polymicrogyria and agenesis of corpus callosum. Graph-based quantitative sulcal pattern analysis has shown high sensitivity in detecting emerging subtle abnormalities in cerebral cortical growth in early fetal stages that are difficult to detect via qualitative visual assessment or using traditional cortical measures such as gyrification index and curvature. It has proven effective for characterizing genetically influenced early cortical folding development. Future studies will be aimed at better understanding a comprehensive map of spatio-temporal dynamics of fetal cortical folding in a large longitudinal cohort in order to examine individual clinical fetal MRIs and predict postnatal neurodevelopmental outcomes from early fetal life.

A comparison of ultrasound with magnetic resonance imaging in the assessment of fetal biometry and weight in the second trimester of pregnancy: An observer agreement and variability study

Objective

To compare the intra and interobserver variability of ultrasound and magnetic resonance imaging in the assessment of common fetal biometry and estimated fetal weight in the second trimester.

Methods

Retrospective measurements on preselected image planes were performed independently by two pairs of observers for contemporaneous ultrasound and magnetic resonance imaging studies of the same fetus. Four common fetal measurements (biparietal diameter, head circumference, abdominal circumference and femur length) and an estimated fetal weight were analysed for 44 'low risk' cases. Comparisons included, intra-class correlation coefficients, systematic error in the mean differences and the random error.

Results

The ultrasound inter- and intraobserver agreements for ultrasound were good, except intraobserver abdominal circumference (intra-class correlation coefficient = 0.880, poor), significant increases in error was seen with larger abdominal circumference sizes. Magnetic resonance imaging produced good/excellent intraobserver agreement with higher intra-class correlation coefficients than ultrasound. Good interobserver agreement was found for both modalities except for the biparietal diameter (magnetic resonance imaging intra-class correlation coefficient = 0.942, moderate). Systematic errors between modalities were seen for the biparietal diameter, femur length and estimated fetal weight (mean percentage error = +2.5%, -5.4% and -8.7%, respectively, p < 0.05). Random error was above 5% for ultrasound intraobserver abdominal circumference, femur length and estimated fetal weight and magnetic resonance imaging interobserver biparietal diameter, abdominal circumference, femur length and estimated fetal weight (magnetic resonance imaging estimated fetal weight error >10%).

Conclusion

Ultrasound remains the modality of choice when estimating fetal weight, however with increasing application of fetal magnetic resonance imaging a method of assessing fetal weight is desirable. Both methods are subject to random error and operator dependence. Assessment of calliper placement variations may be an objective method detecting larger than expected errors in fetal measurements.

Cortical folding alterations in fetuses with isolated non-severe ventriculomegaly

Neuroimaging of brain diseases plays a crucial role in understanding brain abnormalities and early diagnosis. Of great importance is the study of brain abnormalities in utero and the assessment of deviations in case of maldevelopment. In this work, brain magnetic resonance images from 23 isolated non-severe ventriculomegaly (INSVM) fetuses and 25 healthy controls between 26 and 29 gestational weeks were used to identify INSVM-related cortical folding deviations from normative development. Since these alterations may reflect abnormal neurodevelopment, our working hypothesis is that markers of cortical folding can provide cues to improve the prediction of later neurodevelopmental problems in INSVM subjects. We analyzed the relationship of ventricular enlargement with cortical folding alterations in a regional basis using several curvature-based measures describing the folding of each cortical region. Statistical analysis (global and hemispheric) and sparse linear regression approaches were then used to find the cortical regions whose folding is associated with ventricular dilation. Results from both approaches were in great accordance, showing a significant cortical folding decrease in the insula, posterior part of the temporal lobe and occipital lobe. Moreover, compared to the global analysis, stronger ipsilateral associations of ventricular enlargement with reduced cortical folding were encountered by the hemispheric analysis. Our findings confirm and extend previous studies by identifying various cortical regions and emphasizing ipsilateral effects of ventricular enlargement in altered folding. This suggests that INSVM is an indicator of altered cortical development, and moreover, cortical regions with reduced folding constitute potential prognostic biomarkers to be used in follow-up studies to decipher the outcome of INSVM fetuses.

Volume of Structures in the Fetal Brain Measured with a New Semiautomated Method

BACKGROUND AND PURPOSE

Measuring the volume of fetal brain structures is challenging due to fetal motion, low resolution, and artifacts caused by maternal tissue. Our aim was to introduce a new, simple, Matlab-based semiautomated method to measure the volume of structures in the fetal brain and present normal volumetric curves of the structures measured.

MATERIALS AND METHODS

The volume of the supratentorial brain, left and right hemispheres, cerebellum, and left and right eyeballs was measured retrospectively by the new semiautomated method in MR imaging examinations of 94 healthy fetuses. Four volume ratios were calculated. Interobserver agreement was calculated with the intraclass correlation coefficient, and a Bland-Altman plot was drawn for comparison of manual and semiautomated method measurements of the supratentorial brain.

RESULTS

We present normal volumetric curves and normal percentile values of the structures measured according to gestational age and of the ratios between the cerebellum and the supratentorial brain volume and the total eyeball and the supratentorial brain volume. Interobserver agreement was good or excellent for all structures measured. The Bland-Altman plot between manual and semiautomated measurements showed a maximal relative difference of 7.84%.

CONCLUSIONS

We present a technologically simple, reproducible method that can be applied prospectively and retrospectively on any MR imaging protocol, and we present normal volumetric curves measured. The method shows results like manual measurements while being less time-consuming and user-dependent. By applying this method on different cranial and extracranial structures, anatomic and pathologic, we believe that fetal volumetry can turn from a research tool into a practical clinical one.

Auto-Context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging

Brain extraction or whole brain segmentation is an important first step in many of the neuroimage analysis pipelines. The accuracy and the robustness of brain extraction, therefore, are crucial for the accuracy of the entire brain analysis process. The state-of-the-art brain extraction techniques rely heavily on the accuracy of alignment or registration between brain atlases and query brain anatomy, and/or make assumptions about the image geometry, and therefore have limited success when these assumptions do not hold or image registration fails. With the aim of designing an accurate, learning-based, geometry-independent, and registration-free brain extraction tool, in this paper, we present a technique based on an auto-context convolutional neural network (CNN), in which intrinsic local and global image features are learned through 2-D patches of different window sizes. We consider two different architectures: 1) a voxelwise approach based on three parallel 2-D convolutional pathways for three different directions (axial, coronal, and sagittal) that implicitly learn 3-D image information without the need for computationally expensive 3-D convolutions and 2) a fully convolutional network based on the U-net architecture. Posterior probability maps generated by the networks are used iteratively as context information along with the original image patches to learn the local shape and connectedness of the brain to extract it from non-brain tissue. The brain extraction results we have obtained from our CNNs are superior to the recently reported results in the literature on two publicly available benchmark data sets, namely, LPBA40 and OASIS, in which we obtained the Dice overlap coefficients of 97.73% and 97.62%, respectively. Significant improvement was achieved via our auto-context algorithm. Furthermore, we evaluated the performance of our algorithm in the challenging problem of extracting arbitrarily oriented fetal brains in reconstructed fetal brain magnetic resonance imaging (MRI) data sets. In this application, our voxelwise auto-context CNN performed much better than the other methods (Dice coefficient: 95.97%), where the other methods performed poorly due to the non-standard orientation and geometry of the fetal brain in MRI. Through training, our method can provide accurate brain extraction in challenging applications. This, in turn, may reduce the problems associated with image registration in segmentation tasks.

PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI

In this paper, we present a novel method for the correction of motion artifacts that are present in fetal magnetic resonance imaging (MRI) scans of the whole uterus. Contrary to current slice-to-volume registration (SVR) methods, requiring an inflexible anatomical enclosure of a single investigated organ, the proposed patch-to-volume reconstruction (PVR) approach is able to reconstruct a large field of view of non-rigidly deforming structures. It relaxes rigid motion assumptions by introducing a specific amount of redundant information that is exploited with parallelized patchwise optimization, super-resolution, and automatic outlier rejection. We further describe and provide an efficient parallel implementation of PVR allowing its execution within reasonable time on commercially available graphics processing units, enabling its use in the clinical practice. We evaluate PVR's computational overhead compared with standard methods and observe improved reconstruction accuracy in the presence of affine motion artifacts compared with conventional SVR in synthetic experiments. Furthermore, we have evaluated our method qualitatively and quantitatively on real fetal MRI data subject to maternal breathing and sudden fetal movements. We evaluate peak-signal-to-noise ratio, structural similarity index, and cross correlation with respect to the originally acquired data and provide a method for visual inspection of reconstruction uncertainty. We further evaluate the distance error for selected anatomical landmarks in the fetal head, as well as calculating the mean and maximum displacements resulting from automatic non-rigid registration to a motion-free ground truth image. These experiments demonstrate a successful application of PVR motion compensation to the whole fetal body, uterus, and placenta.

In utero diffusion tensor imaging of the fetal brain: A reproducibility study

Our purpose was to evaluate the within-subject reproducibility of in utero diffusion tensor imaging (DTI) metrics and the visibility of major white matter structures. Images for 30 fetuses (20-33. postmenstrual weeks, normal neurodevelopment: 6 cases, cerebral pathology: 24 cases) were acquired on 1.5 T or 3.0 T MRI. DTI with 15 diffusion-weighting directions was repeated three times for each case, TR/TE: 2200/63 ms, voxel size: 1 ∗ 1 mm, slice thickness: 3-5 mm, b-factor: 700 s/mm². Reproducibility was evaluated from structure detectability, variability of DTI measures using the coefficient of variation (CV), image correlation and structural similarity across repeated scans for six selected structures. The effect of age, scanner type, presence of pathology was determined using Wilcoxon rank sum test. White matter structures were detectable in the following percentage of fetuses in at least two of the three repeated scans: corpus callosum genu 76%, splenium 64%, internal capsule, posterior limb 60%, brainstem fibers 40% and temporooccipital association pathways 60%. The mean CV of DTI metrics ranged between 3% and 14.6% and we measured higher reproducibility in fetuses with normal brain development. Head motion was negatively correlated with reproducibility, this effect was partially ameliorated by motion-correction algorithm using image registration. Structures on 3.0 T had higher variability both with- and without motion correction. Fetal DTI is reproducible for projection and commissural bundles during mid-gestation, however, in 16-30% of the cases, data were corrupted by artifacts, resulting in impaired detection of white matter structures. To achieve robust results for the quantitative analysis of diffusivity and anisotropy values, fetal-specific image processing is recommended and repeated DTI is needed to ensure the detectability of fiber pathways.

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.

Motion compensated cine CMR of the fetal heart using radial undersampling and compressed sensing

BACKGROUND

To develop and evaluate a reconstruction framework for high resolution time-resolved CMR of the fetal heart in the presence of motion.

METHODS

Data were acquired using a golden angle radial trajectory in seven fetal subjects and reconstructed as real-time images to detect fetal movement. Data acquired during through-plane motion were discarded whereas in-plane motion was corrected. A fetal cardiac gating signal was extracted to sort the corrected data by cardiac phase, allowing reconstruction of cine images. The quality of motion corrected images and the effect of data undersampling were quantified using separate expressions for spatial blur and image error.

RESULTS

Motion corrected reordered cine reconstructions (127 slices) showed improved image quality relative to both uncorrected cines and corresponding real-time images across a range of root-mean-squared (RMS) displacements (0.3-3.7 mm) and fetal heart rates (119-176 bpm). The relative spatial blur between cines with and without motion correction increased with in-plane RMS displacement leading to an effective decrease in the effective spatial resolution for images without motion correction. Image error between undersampled and reference images was less than 10% for reconstructions using 750 or more spokes, yielding a minimum acceptable scan time of approximately 4 s/slice during quiescent through plane motion.

CONCLUSIONS

By rejecting data corrupted by through-plane motion, and correcting data corrupted by in-plane translation, the proposed reconstruction framework accounts for common sources of motion artifact (gross fetal movement, maternal respiration, fetal cardiac contraction) to produce high quality images of the fetal heart.

Toward the automatic quantification of in utero brain development in 3D structural MRI: A review

Investigating the human brain in utero is important for researchers and clinicians seeking to understand early neurodevelopmental processes. With the advent of fast magnetic resonance imaging (MRI) techniques and the development of motion correction algorithms to obtain high-quality 3D images of the fetal brain, it is now possible to gain more insight into the ongoing maturational processes in the brain. In this article, we present a review of the major building blocks of the pipeline toward performing quantitative analysis of in vivo MRI of the developing brain and its potential applications in clinical settings. The review focuses on T1- and T2-weighted modalities, and covers state of the art methodologies involved in each step of the pipeline, in particular, 3D volume reconstruction, spatio-temporal modeling of the developing brain, segmentation, quantification techniques, and clinical applications. Hum Brain Mapp 38:2772-2787, 2017. © 2017 Wiley Periodicals, Inc.

DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks

In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in our case bounding boxes. It extends the approach of the well-known GrabCut [1] method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naïve approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.

A Multi-Atlas Labeling Approach for Identifying Subject-Specific Functional Regions of Interest

The functional region of interest (fROI) approach has increasingly become a favored methodology in functional magnetic resonance imaging (fMRI) because it can circumvent inter-subject anatomical and functional variability, and thus increase the sensitivity and functional resolution of fMRI analyses. The standard fROI method requires human experts to meticulously examine and identify subject-specific fROIs within activation clusters. This process is time-consuming and heavily dependent on experts’ knowledge. Several algorithmic approaches have been proposed for identifying subject-specific fROIs; however, these approaches cannot easily incorporate prior knowledge of inter-subject variability. In the present study, we improved the multi-atlas labeling approach for defining subject-specific fROIs. In particular, we used a classifier-based atlas-encoding scheme and an atlas selection procedure to account for the large spatial variability across subjects. Using a functional atlas database for face recognition, we showed that with these two features, our approach efficiently circumvented inter-subject anatomical and functional variability and thus improved labeling accuracy. Moreover, in comparison with a single-atlas approach, our multi-atlas labeling approach showed better performance in identifying subject-specific fROIs.

Multivariate Analyses Applied to Healthy Neurodevelopment in Fetal, Neonatal, and Pediatric MRI

Multivariate analysis (MVA) is a class of statistical and pattern recognition techniques that involve the processing of data that contains multiple measurements per sample. MVA can be used to address a wide variety of neurological medical imaging related challenges including the evaluation of healthy brain development, the automated analysis of brain tissues and structures through image segmentation, evaluating the effects of genetic and environmental factors on brain development, evaluating sensory stimulation's relationship with functional brain activity and much more. Compared to adult imaging, pediatric, neonatal and fetal imaging have attracted less attention from MVA researchers, however, recent years have seen remarkable MVA research growth in pre-adult populations. This paper presents the results of a systematic review of the literature focusing on MVA applied to healthy subjects in fetal, neonatal and pediatric magnetic resonance imaging (MRI) of the brain. While the results of this review demonstrate considerable interest from the scientific community in applications of MVA technologies in brain MRI, the field is still young and significant research growth will continue into the future.