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.

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.

Fetal MRI has emerged as a cornerstone of prenatal imaging, helping to establish the correct diagnosis in pregnancies affected by congenital anomalies. In the past decade, 3 T imaging was introduced as an alternative to increase the signal-to-noise ratio (SNR) of the pulse sequences and improve anatomic detail. However, imaging at a higher field strength is not without challenges. Many artifacts that are barely appreciable at 1.5 T are amplified at 3 T. A systematic approach to imaging at 3 T that incorporates appropriate patient positioning, a thoughtful protocol design, and sequence optimization minimizes the impact of these artifacts and allows radiologists to reap the benefits of the increased SNR. The sequences used are the same at both field strengths and include single-shot T2-weighted, balanced steady-state free-precession, three-dimensional T1-weighted spoiled gradient-echo, and echo-planar imaging. Synergistic use of these acquisitions to sample various tissue contrasts and in various planes provides valuable information about fetal anatomy and pathologic conditions. In the authors' experience, fetal imaging at 3 T outperforms imaging at 1.5 T for most indications when performed under optimal circumstances. The authors condense the cumulative experience of fetal imaging specialists and MRI technologists who practice at a large referral center into a guideline covering all major aspects of fetal MRI at 3 T, from patient preparation to image interpretation. © RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Quantitative assessment of the brain’s structural connectivity in the perinatal stage is useful for studying normal and abnormal neurodevelopment. However, estimation of the structural connectome from diffusion MRI data involves a series of complex and ill-posed computations. For the perinatal period, this analysis is further challenged by the rapid brain development and difficulties of imaging subjects at this stage. These factors, along with high inter-subject variability, have made it difficult to chart the normative development of the structural connectome. Hence, there is a lack of baseline trends in connectivity metrics that can be used as reliable references for assessing normal and abnormal brain development at this critical stage. In this paper we propose a computational framework, based on spatio-temporal atlases, for determining such baselines. We apply the framework on data from 169 subjects between 33 and 45 postmenstrual weeks. We show that this framework can unveil clear and strong trends in the development of structural connectivity in the perinatal stage. Some of our interesting findings include that connection weighting based on neurite density produces more consistent trends and that the trends in global efficiency, local efficiency, and characteristic path length are more consistent than in other metrics.

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.

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.

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

The human cerebrum consists of a precise and stereotyped arrangement of lobes, primary gyri, and connectivity that underlies human cognition [P. Rakic, Nat. Rev. Neurosci. 10, 724-735 (2009)]. The development of this arrangement is less clear. Current models explain individual primary gyrification but largely do not account for the global configuration of the cerebral lobes [T. Tallinen, J. Y. Chung, J. S. Biggins, L. Mahadevan, Proc. Natl. Acad. Sci. U.S.A. 111, 12667-12672 (2014) and D. C. Van Essen, Nature 385, 313-318 (1997)]. The insula, buried in the depths of the Sylvian fissure, is unique in terms of gyral anatomy and size. Here, we quantitatively show that the insula has unique morphology and location in the cerebrum and that these key differences emerge during fetal development. Finally, we identify quantitative differences in developmental migration patterns to the insula that may underlie these differences. We calculated morphologic data in the insula and other lobes in adults (N = 107) and in an in utero fetal brain atlas (N = 81 healthy fetuses). In utero, the insula grows an order of magnitude slower than the other lobes and demonstrates shallower sulci, less curvature, and less surface complexity both in adults and progressively throughout fetal development. Spherical projection analysis demonstrates that the lenticular nuclei obstruct 60 to 70% of radial pathways from the ventricular zone (VZ) to the insula, forcing a curved migration to the insula in contrast to a direct radial pathway. Using fetal diffusion tractography, we identify radial glial fascicles that originate from the VZ and curve around the lenticular nuclei to form the insula. These results confirm existing models of radial migration to the cortex and illustrate findings that suggest differential insular and cerebral development, laying the groundwork to understand cerebral malformations and insular function and pathologies.