Automated body organ segmentation, volumetry and population-averaged atlas for 3D motion-corrected T2-weighted fetal body MRI.

Structural fetal body MRI provides true 3D information required for volumetry of fetal organs. However, current clinical and research practice primarily relies on manual slice-wise segmentation of raw T2-weighted stacks, which is time consuming, subject to inter- and intra-observer bias and affected by motion-corruption. Furthermore, there are no existing standard guidelines defining a universal approach to parcellation of fetal organs. This work produces the first parcellation protocol of the fetal body organs for motion-corrected 3D fetal body MRI. It includes 10 organ ROIs relevant to fetal quantitative volumetry studies. We also introduce the first population-averaged T2w MRI atlas of the fetal body. The protocol was used as a basis for training of a neural network for automated organ segmentation. It showed robust performance for different gestational ages. This solution minimises the need for manual editing and significantly reduces time. The general feasibility of the proposed pipeline was also assessed by analysis of organ growth charts created from automated parcellations of 91 normal control 3T MRI datasets that showed expected increase in volumetry during 22-38 weeks gestational age range.

3D T2w fetal body MRI: automated organ volumetry, growth charts and population-averaged atlas.

Structural fetal body MRI provides true 3D information required for volumetry of fetal organs. However, current clinical and research practice primarily relies on manual slice-wise segmentation of raw T2-weighted stacks, which is time consuming, subject to inter- and intra-observer bias and affected by motion-corruption. Furthermore, there are no existing standard guidelines defining a universal approach to parcellation of fetal organs. This work produces the first parcellation protocol of the fetal body organs for motion-corrected 3D fetal body MRI. It includes 10 organ ROIs relevant to fetal quantitative volumetry studies. We also introduce the first population-averaged T2w MRI atlas of the fetal body. The protocol was used as a basis for training of a neural network for automated organ segmentation. It showed robust performance for different gestational ages. This solution minimises the need for manual editing and significantly reduces time. The general feasibility of the proposed pipeline was also assessed by analysis of organ growth charts created from automated parcellations of 91 normal control 3T MRI datasets that showed expected increase in volumetry during 22-38 weeks gestational age range. In addition, the results of comparison between 60 normal and 12 fetal growth restriction datasets revealed significant differences in organ volumes.

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.

BOUNTI: Brain vOlumetry and aUtomated parcellatioN for 3D feTal MRI.

Fetal MRI is widely used for quantitative brain volumetry studies. However, currently, there is a lack of universally accepted protocols for fetal brain parcellation and segmentation. Published clinical studies tend to use different segmentation approaches that also reportedly require significant amounts of time-consuming manual refinement. In this work, we propose to address this challenge by developing a new robust deep learning-based fetal brain segmentation pipeline for 3D T2w motion corrected brain images. At first, we defined a new refined brain tissue parcellation protocol with 19 regions-of-interest using the new fetal brain MRI atlas from the Developing Human Connectome Project. This protocol design was based on evidence from histological brain atlases, clear visibility of the structures in individual subject 3D T2w images and the clinical relevance to quantitative studies. It was then used as a basis for developing an automated deep learning brain tissue parcellation pipeline trained on 360 fetal MRI datasets with different acquisition parameters using semi-supervised approach with manually refined labels propagated from the atlas. The pipeline demonstrated robust performance for different acquisition protocols and GA ranges. Analysis of tissue volumetry for 390 normal participants (21-38 weeks gestational age range), scanned with three different acquisition protocols, did not reveal significant differences for major structures in the growth charts. Only minor errors were present in < 15% of cases thus significantly reducing the need for manual refinement. In addition, quantitative comparison between 65 fetuses with ventriculomegaly and 60 normal control cases were in agreement with the findings reported in our earlier work based on manual segmentations. These preliminary results support the feasibility of the proposed atlas-based deep learning approach for large-scale volumetric analysis. The created fetal brain volumetry centiles and a docker with the proposed pipeline are publicly available online at https://hub.docker.com/r/fetalsvrtk/segmentation (tag brain_bounti_tissue).

3D black blood cardiovascular magnetic resonance atlases of congenital aortic arch anomalies and the normal fetal heart: application to automated multi-label segmentation.

BACKGROUND: Image-domain motion correction of black-blood contrast T2-weighted fetal cardiovascular magnetic resonance imaging (CMR) using slice-to-volume registration (SVR) provides high-resolution three-dimensional (3D) images of the fetal heart providing excellent 3D visualisation of vascular anomalies [1]. However, 3D segmentation of these datasets, important for both clinical reporting and the application of advanced analysis techniques is currently a time-consuming process requiring manual input with potential for inter-user variability. METHODS: In this work, we present novel 3D fetal CMR population-averaged atlases of normal and abnormal fetal cardiovascular anatomy. The atlases are created using motion-corrected 3D reconstructed volumes of 86 third trimester fetuses (gestational age range 29-34 weeks) including: 28 healthy controls, 20 cases with postnatally confirmed neonatal coarctation of the aorta (CoA) and 38 vascular rings (21 right aortic arch (RAA), 17 double aortic arch (DAA)). We used only high image quality datasets with isolated anomalies and without any other deviations in the cardiovascular anatomy.In addition, we implemented and evaluated atlas-guided registration and deep learning (UNETR) methods for automated 3D multi-label segmentation of fetal cardiac vessels. We used images from CoA, RAA and DAA cohorts including: 42 cases for training (14 from each cohort), 3 for validation and 6 for testing. In addition, the potential limitations of the network were investigated on unseen datasets including 3 early gestational age (22 weeks) and 3 low SNR cases. RESULTS: We created four atlases representing the average anatomy of the normal fetal heart, postnatally confirmed neonatal CoA, RAA and DAA. Visual inspection was undertaken to verify expected anatomy per subgroup. The results of the multi-label cardiac vessel UNETR segmentation showed 100[Formula: see text] per-vessel detection rate for both normal and abnormal aortic arch anatomy. CONCLUSIONS: This work introduces the first set of 3D black-blood T2-weighted CMR atlases of normal and abnormal fetal cardiovascular anatomy including detailed segmentation of the major cardiovascular structures. Additionally, we demonstrated the general feasibility of using deep learning for multi-label vessel segmentation of 3D fetal CMR images.

Automated 3D reconstruction of the fetal thorax in the standard atlas space from motion-corrupted MRI stacks for 21-36 weeks GA range.

Slice-to-volume registration (SVR) methods allow reconstruction of high-resolution 3D images from multiple motion-corrupted stacks. SVR-based pipelines have been increasingly used for motion correction for T2-weighted structural fetal MRI since they allow more informed and detailed diagnosis of brain and body anomalies including congenital heart defects (Lloyd et al., 2019). Recently, fully automated rigid SVR reconstruction of the fetal brain in the atlas space was achieved in Salehi et al. (2019) that used convolutional neural networks (CNNs) for segmentation and pose estimation. However, these CNN-based methods have not yet been applied to the fetal trunk region. Meanwhile, the existing rigid and deformable SVR (DSVR) solutions (Uus et al., 2020) for the fetal trunk region are limited by the requirement of manual input as well the narrow capture range of the classical gradient descent based registration methods that cannot resolve severe fetal motion frequently occurring at the early gestational age (GA). Furthermore, in our experience, the conventional 2D slice-wise CNN-based brain masking solutions are reportedly prone to errors that require manual corrections when applied on a wide range of acquisition protocols or abnormal cases in clinical setting. In this work, we propose a fully automated pipeline for reconstruction of the fetal thorax region for 21-36 weeks GA range T2-weighted MRI datasets. It includes 3D CNN-based intra-uterine localisation of the fetal trunk and landmark-guided pose estimation steps that allow automated DSVR reconstruction in the standard radiological space irrespective of the fetal trunk position or the regional stack coverage. The additional step for generation of the common template space and rejection of outliers provides the means for automated exclusion of stacks affected by low image quality or extreme motion. The pipeline was quantitatively evaluated on a series of experiments including fetal MRI datasets and simulated rotation motion. Furthermore, we performed a qualitative assessment of the image reconstruction quality in terms of the definition of vascular structures on 100 early (median 23.14 weeks) and late (median 31.79 weeks) GA group MRI datasets covering 21 to 36 weeks GA range.

Predicting age and clinical risk from the neonatal connectome.

The development of perinatal brain connectivity underpins motor, cognitive and behavioural abilities in later life. Diffusion MRI allows the characterisation of subtle inter-individual differences in structural brain connectivity. Individual brain connectivity maps (connectomes) are by nature high in dimensionality and complex to interpret. Machine learning methods are a powerful tool to uncover properties of the connectome which are not readily visible and can give us clues as to how and why individual developmental trajectories differ. In this manuscript we used Deep Neural Networks and Random Forests to predict demographic and neurodevelopmental characteristics from neonatal structural connectomes in a large sample of babies (n = 524) from the developing Human Connectome Project. We achieved an accurate prediction of post menstrual age (PMA) at scan in term-born infants (mean absolute error (MAE) = 0.72 weeks, r = 0.83 and p < 0.001). We also achieved good accuracy when predicting gestational age at birth in a cohort of term and preterm babies scanned at term equivalent age (MAE = 2.21 weeks, r = 0.82, p < 0.001). We subsequently used sensitivity analysis to obtain feature relevance from our prediction models, with the most important connections for prediction of PMA and GA found to predominantly involve frontal and temporal regions, thalami, and basal ganglia. From our models of PMA at scan for infants born at term, we computed a brain maturation index (predicted age minus actual age) of individual preterm neonates and found a significant correlation between this index and motor outcome at 18 months corrected age. Our results demonstrate the applicability of machine learning techniques in analyses of the neonatal connectome and suggest that a neural substrate of brain maturation with implications for future neurodevelopment is detectable at term equivalent age from the neonatal connectome.

Multi-Channel 4D Parametrized Atlas of Macro- and Microstructural Neonatal Brain Development.

Structural (also known as anatomical) and diffusion MRI provide complimentary anatomical and microstructural characterization of early brain maturation. However, the existing models of the developing brain in time include only either structural or diffusion MRI channels. Furthermore, there is a lack of tools for combined analysis of structural and diffusion MRI in the same reference space. In this work, we propose a methodology to generate a multi-channel (MC) continuous spatio-temporal parametrized atlas of the brain development that combines multiple MRI-derived parameters in the same anatomical space during 37-44 weeks of postmenstrual age range. We co-align structural and diffusion MRI of 170 normal term subjects from the developing Human Connectomme Project using MC registration driven by both T2-weighted and orientation distribution functions channels and fit the Gompertz model to the signals and spatial transformations in time. The resulting atlas consists of 14 spatio-temporal microstructural indices and two parcellation maps delineating white matter tracts and neonatal transient structures. In order to demonstrate applicability of the atlas for quantitative region-specific studies, a comparison analysis of 140 term and 40 preterm subjects scanned at the term-equivalent age is performed using different MRI-derived microstructural indices in the atlas reference space for multiple white matter regions, including the transient compartments. The atlas and software will be available after publication of the article.

Harmonized Segmentation of Neonatal Brain MRI.

Deep learning based medical image segmentation has shown great potential in becoming a key part of the clinical analysis pipeline. However, many of these models rely on the assumption that the train and test data come from the same distribution. This means that such methods cannot guarantee high quality predictions when the source and target domains are dissimilar due to different acquisition protocols, or biases in patient cohorts. Recently, unsupervised domain adaptation techniques have shown great potential in alleviating this problem by minimizing the shift between the source and target distributions, without requiring the use of labeled data in the target domain. In this work, we aim to predict tissue segmentation maps on T 2-weighted magnetic resonance imaging data of an unseen preterm-born neonatal population, which has both different acquisition parameters and population bias when compared to our training data. We achieve this by investigating two unsupervised domain adaptation techniques with the objective of finding the best solution for our problem. We compare the two methods with a baseline fully-supervised segmentation network and report our results in terms of Dice scores obtained on our source test dataset. Moreover, we analyse tissue volumes and cortical thickness measures of the harmonized data on a subset of the population matched for gestational age at birth and postmenstrual age at scan. Finally, we demonstrate the applicability of the harmonized cortical gray matter maps with an analysis comparing term and preterm-born neonates and a proof-of-principle investigation of the association between cortical thickness and a language outcome measure.