Fetal MRI: A Technical Update with Educational Aspirations

Advances in Fetal Brain Imaging

Over the last 20 years, there have been remarkable developments in fetal brain MR imaging analysis methods. This article delves into the specifics of structural imaging, diffusion imaging, functional MR imaging, and spectroscopy, highlighting the latest advancements in motion correction, fetal brain development atlases, and the challenges and innovations. Furthermore, this article explores the clinical applications of these advanced imaging techniques in comprehending and diagnosing fetal brain development and abnormalities.

How to Perform Fetal MR Imaging

This article provides the readers with practical guidance on how to perform fetal MR imaging, including technical considerations such as scanner field strength and use of appropriate radiofrequency receive coils, and summarizes the role, strengths, and limitations of the various MR imaging sequences. The authors review the various factors to consider in scan preparation, including study indication, timing, maternal preparation, and the creation of an institutional fetal imaging protocol. Additional factors that go into scan optimization during acquisition including prioritizing maternal comfort and ways to troubleshoot various artifacts that maybe encountered in fetal imaging are discussed.

FetMRQC: A robust quality control system for multi-centric fetal brain MRI

Fetal brain MRI is becoming an increasingly relevant complement to neurosonography for perinatal diagnosis, allowing fundamental insights into fetal brain development throughout gestation. However, uncontrolled fetal motion and heterogeneity in acquisition protocols lead to data of variable quality, potentially biasing the outcome of subsequent studies. We present FetMRQC, an open-source machine-learning framework for automated image quality assessment and quality control that is robust to domain shifts induced by the heterogeneity of clinical data. FetMRQC extracts an ensemble of quality metrics from unprocessed anatomical MRI and combines them to predict experts' ratings using random forests. We validate our framework on a pioneeringly large and diverse dataset of more than 1600 manually rated fetal brain T2-weighted images from four clinical centers and 13 different scanners. Our study shows that FetMRQC's predictions generalize well to unseen data while being interpretable. FetMRQC is a step towards more robust fetal brain neuroimaging, which has the potential to shed new insights on the developing human brain.

Efficient segmentation of fetal brain MRI based on the physical resolution

BACKGROUND

The image resolution of fetal brain magnetic resonance imaging (MRI) is a critical factor in brain development measures, which is mainly determined by the physical resolution configured in the MRI sequence. However, fetal brain MRI are commonly reconstructed to 3D images with a higher apparent resolution, compared to the original physical resolution.

PURPOSE

This work is to demonstrate that accurate segmentation can be achieved based on the MRI physical resolution, and the high apparent resolution segmentation can be achieved by a simple deep learning module.

METHODS

This retrospective study included 150 adult and 80 fetal brain MRIs. The adult brain MRIs were acquired at a high physical resolution, which were downsampled to visualize and quantify its impacts on the segmentation accuracy. The physical resolution of fetal images was estimated based on MRI acquisition settings and the images were downsampled accordingly before segmentation and restored using multiple upsampling strategies. Segmentation accuracy of ConvNet models were evaluated on the original and downsampled images. Dice coefficients were calculated, and compared to the original data.

RESULTS

When the apparent resolution was higher than the physical resolution, the accuracy of fetal brain segmentation had negligible degradation (accuracy reduced by 0.26%, 1.1%, and 1.8% with downsampling factors of 4/3, 2, and 4 in each dimension, without significant differences from the original data). Using a downsampling factor of 4 in each dimension, the proposed method provided 7× smaller and 10× faster models.

CONCLUSION

Efficient and accurate fetal brain segmentation models can be developed based on the physical resolution of MRI acquisitions.

Fetal-BET: Brain Extraction Tool for Fetal MRI

Goal: In this study, we address the critical challenge of fetal brain extraction from MRI sequences. Fetal MRI has played a crucial role in prenatal neurodevelopmental studies and in advancing our knowledge of fetal brain development in-utero. Fetal brain extraction is a necessary first step in most computational fetal brain MRI pipelines. However, it poses significant challenges due to 1) non-standard fetal head positioning, 2) fetal movements during examination, and 3) vastly heterogeneous appearance of the developing fetal brain and the neighboring fetal and maternal anatomy across gestation, and with various sequences and scanning conditions. Development of a machine learning method to effectively address this task requires a large and rich labeled dataset that has not been previously available. Currently, there is no method for accurate fetal brain extraction on various fetal MRI sequences. Methods: In this work, we first built a large annotated dataset of approximately 72,000 2D fetal brain MRI images. Our dataset covers the three common MRI sequences including T2-weighted, diffusion-weighted, and functional MRI acquired with different scanners. These data include images of normal and pathological brains. Using this dataset, we developed and validated deep learning methods, by exploiting the power of the U-Net style architectures, the attention mechanism, feature learning across multiple MRI modalities, and data augmentation for fast, accurate, and generalizable automatic fetal brain extraction. Results: Evaluations on independent test data, including data available from other centers, show that our method achieves accurate brain extraction on heterogeneous test data acquired with different scanners, on pathological brains, and at various gestational stages. Conclusions:By leveraging rich information from diverse multi-modality fetal MRI data, our proposed deep learning solution enables precise delineation of the fetal brain on various fetal MRI sequences. The robustness of our deep learning model underscores its potential utility for fetal brain imaging.

HAITCH: A Framework for Distortion and Motion Correction in Fetal Multi-Shell Diffusion-Weighted MRI

Diffusion magnetic resonance imaging (dMRI) is pivotal for probing the microstructure of the rapidly-developing fetal brain. However, fetal motion during scans and its interaction with magnetic field inhomogeneities result in artifacts and data scattering across spatial and angular domains. The effects of those artifacts are more pronounced in high-angular resolution fetal dMRI, where signal-to-noise ratio is very low. Those effects lead to biased estimates and compromise the consistency and reliability of dMRI analysis. This work presents HAITCH, the first and the only publicly available tool to correct and reconstruct multi-shell high-angular resolution fetal dMRI data. HAITCH offers several technical advances that include a blip-reversed dual-echo acquisition for dynamic distortion correction, advanced motion correction for model-free and robust reconstruction, optimized multi-shell design for enhanced information capture and increased tolerance to motion, and outlier detection for improved reconstruction fidelity. The framework is open-source, flexible, and can be used to process any type of fetal dMRI data including single-echo or single-shell acquisitions, but is most effective when used with multi-shell multi-echo fetal dMRI data that cannot be processed with any of the existing tools. Validation experiments on real fetal dMRI scans demonstrate significant improvements and accurate correction across diverse fetal ages and motion levels. HAITCH successfully removes artifacts and reconstructs high-fidelity fetal dMRI data suitable for advanced diffusion modeling, including fiber orientation distribution function estimation. These advancements pave the way for more reliable analysis of the fetal brain microstructure and tractography under challenging imaging conditions.

Fetal brain MRI atlases and datasets: A review

Fetal brain development is a complex process involving different stages of growth and organization which are crucial for the development of brain circuits and neural connections. Fetal atlases and labeled datasets are promising tools to investigate prenatal brain development. They support the identification of atypical brain patterns, providing insights into potential early signs of clinical conditions. In a nutshell, prenatal brain imaging and post-processing via modern tools are a cutting-edge field that will significantly contribute to the advancement of our understanding of fetal development. In this work, we first provide terminological clarification for specific terms (i.e., "brain template" and "brain atlas"), highlighting potentially misleading interpretations related to inconsistent use of terms in the literature. We discuss the major structures and neurodevelopmental milestones characterizing fetal brain ontogenesis. Our main contribution is the systematic review of 18 prenatal brain atlases and 3 datasets. We also tangentially focus on clinical, research, and ethical implications of prenatal neuroimaging.

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.

Assessment of fetal corpus callosum biometry by 3D super-resolution reconstructed T2-weighted magnetic resonance imaging

Objective

To assess the accuracy of corpus callosum (CC) biometry, including sub-segments, using 3D super-resolution fetal brain MRI (SR) compared to 2D or 3D ultrasound (US) and clinical low-resolution T2-weighted MRI (T2WS).

Method

Fetal brain biometry was conducted by two observers on 57 subjects [21-35 weeks of gestational age (GA)], including 11 cases of partial CC agenesis. Measures were performed by a junior observer (obs1) on US, T2WS and SR and by a senior neuroradiologist (obs2) on T2WS and SR. CC biometric regression with GA was established. Statistical analysis assessed agreement within and between modalities and observers.

Results

This study shows robust SR to US concordance across gestation, surpassing T2WS. In obs1, SR aligns with US, except for genu and CC length (CCL), enhancing splenium visibility. In obs2, SR closely corresponds to US, differing in rostrum and CCL. The anterior CC (rostrum and genu) exhibits higher variability. SR's regression aligns better with literature (US) for CCL, splenium and body than T2WS. SR is the method with the least missing values.

Conclusion

SR yields CC biometry akin to US (excluding anterior CC). Thanks to superior 3D visualization and better through plane spatial resolution, SR allows to perform CC biometry more frequently than T2WS.

Deep learning-based segmentation of whole-body fetal MRI and fetal weight estimation: assessing performance, repeatability, and reproducibility

OBJECTIVES

To develop a deep-learning method for whole-body fetal segmentation based on MRI; to assess the method's repeatability, reproducibility, and accuracy; to create an MRI-based normal fetal weight growth chart; and to assess the sensitivity to detect fetuses with growth restriction (FGR).

METHODS

Retrospective data of 348 fetuses with gestational age (GA) of 19-39 weeks were included: 249 normal appropriate for GA (AGA), 19 FGR, and 80 Other (having various imaging abnormalities). A fetal whole-body segmentation model with a quality estimation module was developed and evaluated in 169 cases. The method was evaluated for its repeatability (repeated scans within the same scanner, n = 22), reproducibility (different scanners, n = 6), and accuracy (compared with birth weight, n = 7). A normal MRI-based growth chart was derived.

RESULTS

The method achieved a Dice = 0.973, absolute volume difference ratio (VDR) = 1.8% and VDR mean difference = 0.75% ([Formula: see text]: - 3.95%, 5.46), and high agreement with the gold standard. The method achieved a repeatability coefficient = 4.01%, ICC = 0.99, high reproducibility with a mean difference = 2.21% ([Formula: see text]: - 1.92%, 6.35%), and high accuracy with a mean difference between estimated fetal weight (EFW) and birth weight of - 0.39% ([Formula: see text]: - 8.23%, 7.45%). A normal growth chart (n = 246) was consistent with four ultrasound charts. EFW based on MRI correctly predicted birth-weight percentiles for all 18 fetuses ≤ 10thpercentile and for 14 out of 17 FGR fetuses below the 3rd percentile. Six fetuses referred to MRI as AGA were found to be < 3rd percentile.

CONCLUSIONS

The proposed method for automatic MRI-based EFW demonstrated high performance and sensitivity to identify FGR fetuses.

CLINICAL RELEVANCE STATEMENT

Results from this study support the use of the automatic fetal weight estimation method based on MRI for the assessment of fetal development and to detect fetuses at risk for growth restriction.

KEY POINTS

• An AI-based segmentation method with a quality assessment module for fetal weight estimation based on MRI was developed, achieving high repeatability, reproducibility, and accuracy. • An MRI-based fetal weight growth chart constructed from a large cohort of normal and appropriate gestational-age fetuses is proposed. • The method showed a high sensitivity for the diagnosis of small fetuses suspected of growth restriction.

Stochastic-offset-enhanced restricted slice excitation and 180° refocusing designs with spatially non-linear ΔB0 shim array fields

PURPOSE

Developing a general framework with a novel stochastic offset strategy for the design of optimized RF pulses and time-varying spatially non-linear ΔB0 shim array fields for restricted slice excitation and refocusing with refined magnetization profiles within the intervals of the fixed voxels.

METHODS

Our framework uses the decomposition property of the Bloch equations to enable joint design of RF-pulses and shim array fields for restricted slice excitation and refocusing with auto-differentiation optimization. Bloch simulations are performed independently on orthogonal basis vectors, Mx, My, and Mz, which enables designs for arbitrary initial magnetizations. Requirements for refocusing pulse designs are derived from the extended phase graph formalism obviating time-consuming sub-voxel isochromatic simulations to model the effects of crusher gradients. To refine resultant slice-profiles because of voxelwise optimization functions, we propose an algorithm that stochastically offsets spatial points at which loss is computed during optimization.

RESULTS

We first applied our proposed design framework to standard slice-selective excitation and refocusing pulses in the absence of non-linear ΔB0 shim array fields and compared them against pulses designed with Shinnar-Le Roux algorithm. Next, we demonstrated our technique in a simulated setup of fetal brain imaging in pregnancy for restricted-slice excitation and refocusing of the fetal brain.

CONCLUSIONS

Our proposed framework for optimizing RF pulse and time-varying spatially non-linear ΔB0 shim array fields achieve high fidelity restricted-slice excitation and refocusing for fetal MRI, which could enable zoomed fast-spin-echo-MRI and other applications.

Use of super resolution reconstruction MRI for surgical planning in Placenta accreta spectrum disorder: Case series

INTRODUCTION

Comprehensive imaging using ultrasound and MRI of placenta accreta spectrum (PAS) aims to prevent catastrophic haemorrhage and maternal death. Standard MRI of the placenta is limited by between-slice motion which can be mitigated by super-resolution reconstruction (SRR) MRI. We applied SRR in suspected PAS cases to determine its ability to enhance anatomical placental assessment and predict adverse maternal outcome.

METHODS

Suspected PAS patients (n = 22) underwent MRI at a gestational age (weeks + days) of (32+3±3+2, range (27+1-38+6)). SRR of the placental-myometrial-bladder interface involving rigid motion correction of acquired MRI slices combined with robust outlier detection to reconstruct an isotropic high-resolution volume, was achieved in twelve. 2D MRI or SRR images alone, and paired data were assessed by four radiologists in three review rounds. All radiologists were blinded to results of the ultrasound, original MR image reports, case outcomes, and PAS diagnosis. A Random Forest Classification model was used to highlight the most predictive pathological MRI markers for major obstetric haemorrhage (MOH), bladder adherence (BA), and placental attachment depth (PAD).

RESULTS

At delivery, four patients had placenta praevia with no abnormal attachment, two were clinically diagnosed with PAS, and six had histopathological PAS confirmation. Pathological MRI markers (T2-dark intraplacental bands, and loss of retroplacental T2-hypointense line) predicting MOH were more visible using SRR imaging (accuracy 0.73), in comparison to 2D MRI or paired imaging. Bladder wall interruption, predicting BA, was only easily detected by paired imaging (accuracy 0.72). Better detection of certain pathological markers predicting PAD was found using 2D MRI (placental bulge and myometrial thinning (accuracy 0.81)), and SRR (loss of retroplacental T2-hypointense line (accuracy 0.82)).

DISCUSSION

The addition of SRR to 2D MRI potentially improved anatomical assessment of certain pathological MRI markers of abnormal placentation that predict maternal morbidity which may benefit surgical planning.

Fetal neurosurgery

Among fetal surgical procedures, neurosurgery stands out due to the number of cases and the possibility of developing new procedures that can be performed in the fetal period. To perform fetal neurosurgical procedures, there is a need for specialized centers that have experts in the diagnosis of fetal pathologies and a highly complex obstetrics service with specialized maternal-fetal teams associated with a pediatric neurosurgery center with expertise in the diverse pathologies of the fetus and the central nervous system that offers multidisciplinary follow-up during postnatal life. Services that do not have these characteristics should refer their patients to these centers to obtain better treatment results. It is essential that the fetal neurosurgical procedure be performed by a pediatric neurosurgeon with extensive experience, as he will be responsible for monitoring these patients in the postnatal period and for several years. The objective of this manuscript is to demonstrate the diagnostic and treatment possibilities, in the fetal period, of some neurosurgical diseases such as hydrocephalus, tumors, occipital encephalocele, and myelomeningocele.

Review on deep learning fetal brain segmentation from Magnetic Resonance images

Brain segmentation is often the first and most critical step in quantitative analysis of the brain for many clinical applications, including fetal imaging. Different aspects challenge the segmentation of the fetal brain in magnetic resonance imaging (MRI), such as the non-standard position of the fetus owing to his/her movements during the examination, rapid brain development, and the limited availability of imaging data. In recent years, several segmentation methods have been proposed for automatically partitioning the fetal brain from MR images. These algorithms aim to define regions of interest with different shapes and intensities, encompassing the entire brain, or isolating specific structures. Deep learning techniques, particularly convolutional neural networks (CNNs), have become a state-of-the-art approach in the field because they can provide reliable segmentation results over heterogeneous datasets. Here, we review the deep learning algorithms developed in the field of fetal brain segmentation and categorize them according to their target structures. Finally, we discuss the perceived research gaps in the literature of the fetal domain, suggesting possible future research directions that could impact the management of fetal MR images.

Fetal brain tissue annotation and segmentation challenge results

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.

Geometric Reliability of Super-Resolution Reconstructed Images from Clinical Fetal MRI in the Second Trimester

Fetal Magnetic Resonance Imaging (MRI) is an important noninvasive diagnostic tool to characterize the central nervous system (CNS) development, significantly contributing to pregnancy management. In clinical practice, fetal MRI of the brain includes the acquisition of fast anatomical sequences over different planes on which several biometric measurements are manually extracted. Recently, modern toolkits use the acquired two-dimensional (2D) images to reconstruct a Super-Resolution (SR) isotropic volume of the brain, enabling three-dimensional (3D) analysis of the fetal CNS.We analyzed 17 fetal MR exams performed in the second trimester, including orthogonal T2-weighted (T2w) Turbo Spin Echo (TSE) and balanced Fast Field Echo (b-FFE) sequences. For each subject and type of sequence, three distinct high-resolution volumes were reconstructed via NiftyMIC, MIALSRTK, and SVRTK toolkits. Fifteen biometric measurements were assessed both on the acquired 2D images and SR reconstructed volumes, and compared using Passing-Bablok regression, Bland-Altman plot analysis, and statistical tests.Results indicate that NiftyMIC and MIALSRTK provide reliable SR reconstructed volumes, suitable for biometric assessments. NiftyMIC also improves the operator intraclass correlation coefficient on the quantitative biometric measures with respect to the acquired 2D images. In addition, TSE sequences lead to more robust fetal brain reconstructions against intensity artifacts compared to b-FFE sequences, despite the latter exhibiting more defined anatomical details.Our findings strengthen the adoption of automatic toolkits for fetal brain reconstructions to perform biometry evaluations of fetal brain development over common clinical MR at an early pregnancy stage.

Fetal cardiovascular blood flow MRI: techniques and applications

Fetal cardiac MRI is challenging due to fetal and maternal movements as well as the need for a reliable cardiac gating signal and high spatiotemporal resolution. Ongoing research and recent technical developments to address these challenges show the potential of MRI as an adjunct to ultrasound for the assessment of the fetal heart and great vessels. MRI measurements of blood flow have enabled the assessment of normal fetal circulation as well as conditions with disrupted circulations, such as congenital heart disease, along with associated organ underdevelopment and hemodynamic instability. This review provides details of the techniques used in fetal cardiovascular blood flow MRI, including single slice and volumetric imaging sequences, post-processing and analysis, along with a summary of applications in human studies and animal models.

Fetal lung MRI and features predicting post-natal outcome: a scoping review of the current literature

The outcome for infants with fetal lung pathologies not only depends on the nature of the pathology, but the impact it has on the developing lungs. The main prognostic factor is the degree of pulmonary hypoplasia, but this is not detectable pre-natally. Imaging techniques aim to simulate these features with a variety of surrogate measurements, including lung volume and MRI signal intensity. Despite the complexity of the various research studies and lack of consistent methodology, this scoping review aims to summarise current applications, and promising techniques requiring further investigation.

No Meta-analytic Evidence for Risks due to Prenatal Magnetic Resonance Imaging in Animal Models

BACKGROUND

Magnetic resonance imaging (MRI) is a powerful, noninvasive tool for both clinical practice and research. Though the safety of MRI has been endorsed by many professional societies and government bodies, some concerns have remained about potential risk from prenatal MRI. Case-control animal studies of MRI scanning during gestation and effects on offspring are the most direct test available for potential risks. We performed a meta-analysis of extant animal studies of prenatal MRI examining reproductive and offspring outcomes.

METHODS

Relevant articles were identified through PubMed search and citation searching of known articles and review papers. Eighteen relevant studies were identified with case-control designs of prenatal scanning conducted in vivo with mammalian species using MRI-relevant field strength. Standardized mean difference effect sizes were analyzed across k = 81 outcomes assessed across 649 unexposed dams, 622 exposed dams, 3024 unexposed offspring, and 3328 exposed offspring using a multilevel meta-analytic approach that clustered effect sizes within publications.

RESULTS

The meta-analysis indicated no significant evidence for a deleterious effects of prenatal MRI (standardized mean difference = 0.17, 95% CI [-0.19, 0.54], t80 = 0.94, p = .35) across outcomes. Similarly, no effects were observed when separately examining the 4 most commonly assessed outcomes: birth weight, litter size, fetal viability, and physical malformations (p > .05).

CONCLUSIONS

Case-control mammalian animal studies indicate no significant known risks of prenatal MRI to reproductive outcomes or offspring development. This finding is largely mirrored in human research, though the lack of randomized case-control designs limits direct comparison. The current findings provide additional support to the prevailing consensus that prenatal MRI poses no known risk to offspring.

Cardiovascular Magnetic Resonance from Fetal to Adult Life-Indications and Challenges: A State-of-the-Art Review

Cardiovascular magnetic resonance (CMR) imaging offers a comprehensive, non-invasive, and radiation-free imaging modality, which provides a highly accurate and reproducible assessment of cardiac morphology and functions across a wide spectrum of cardiac conditions spanning from fetal to adult life. It minimises risks to the patient, particularly the risks associated with exposure to ionising radiation and the risk of complications from more invasive haemodynamic assessments. CMR utilises high spatial resolution and provides a detailed assessment of intracardiac and extracardiac anatomy, ventricular and valvular function, and flow haemodynamic and tissue characterisation, which aid in the diagnosis, and, hence, with the management of patients with cardiac disease. This article aims to discuss the role of CMR and the indications for its use throughout the different stages of life, from fetal to adult life.

Quantitative measurements and morphological evaluation of fetal cardiovascular structures with fetal cardiac MRI

PURPOSE

Fetal cardiac magnetic resonance imaging (FCMR) can be used as an imaging modality in fetal cardiovascular evaluation as studied in recent years. We aimed to evaluate cardiovascular morphology using FCMR and to observe the development of cardiovascular structures according to gestational age (GA) in pregnant women.

METHOD

In our prospective study, 120 pregnant women between 19 and 37 weeks of gestation in whom absence of cardiac anomaly could not be excluded by ultrasonography (US) or, who were referred to us for magnetic resonance imaging (MRI) for suspected non-cardiovascular system pathology, were included. According to the axis of the fetal heart, axial, coronal, and sagittal multiplanar steady-state free precession (SSFP) and 'real time' untriggered SSFP sequence, respectively, were obtained. The morphology of the cardiovascular structures and their relationships with each other were evaluated, and their sizes were measured.

RESULTS

Seven cases (6.3%) contained motion artefacts that did not allow the assessment and measurement of cardiovascular morphology, and three (2.9%) cases with cardiac pathology in the analysed images were excluded from the study. The study included a total of 100 cases. Cardiac chamber diameter, heart diameter, heart length, heart area, thoracic diameter, and thoracic area were measured in all fetuses. The diameters of the aorta ascendens (Aa), aortic isthmus (Ai), aorta descendens (Ad), main pulmonary artery (MPA), ductus arteriosus (DA, superior vena cava (SVC), and inferior vena cava (IVC) were measured in all fetuses. The left pulmonary artery (LPA) was visualised in 89 patients (89%). The right PA (RPA) was visualised in 99 (99%) cases. Four pulmonary veins (PVs) were seen in 49 (49%) cases, three in 33 (33%), and two in 18 (18%). High correlation values were found for all diameter measurements performed with GW.

CONCLUSION

In cases where US cannot achieve adequate image quality, FCMR can contribute to diagnosis. The very short acquisition time and parallel imaging technique with the SSFP sequence allow for adequate image quality without maternal or fetal sedation.

Fetal MRI at 3 T: Principles to Optimize Success

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.

Magnetic resonance imaging of the monkey fetal brain in utero

Non-human primates (NHPs) are the closest living relatives of the human and play a critical role in investigating the effects of maternal viral infection and consumption of medicines, drugs, and alcohol on fetal development. With the advance of contemporary fast MRI techniques with parallel imaging, fetal MRI is becoming a robust tool increasingly used in clinical practice and preclinical studies to examine congenital abnormalities including placental dysfunction, congenital heart disease (CHD), and brain abnormalities non-invasively. Because NHPs are usually scanned under anesthesia, the motion artifact is reduced substantially, allowing multi-parameter MRI techniques to be used intensively to examine the fetal development in a single scanning session or longitudinal studies. In this paper, the MRI techniques for scanning monkey fetal brains in utero in biomedical research are summarized. Also, a fast imaging protocol including T2-weighted imaging, diffusion MRI, resting-state functional MRI (rsfMRI) to examine rhesus monkey fetal brains in utero on a clinical 3T scanner is introduced.

microRNA Biology on Brain Development and Neuroimaging Approach

Proper brain development requires the precise coordination and orchestration of various molecular and cellular processes and dysregulation of these processes can lead to neurological diseases. In the past decades, post-transcriptional regulation of gene expression has been shown to contribute to various aspects of brain development and function in the central nervous system. MicroRNAs (miRNAs), short non-coding RNAs, are emerging as crucial players in post-transcriptional gene regulation in a variety of tissues, such as the nervous system. In recent years, miRNAs have been implicated in multiple aspects of brain development, including neurogenesis, migration, axon and dendrite formation, and synaptogenesis. Moreover, altered expression and dysregulation of miRNAs have been linked to neurodevelopmental and psychiatric disorders. Magnetic resonance imaging (MRI) is a powerful imaging technology to obtain high-quality, detailed structural and functional information from the brains of human and animal models in a non-invasive manner. Because the spatial expression patterns of miRNAs in the brain, unlike those of DNA and RNA, remain largely unknown, a whole-brain imaging approach using MRI may be useful in revealing biological and pathological information about the brain affected by miRNAs. In this review, we highlight recent advancements in the research of miRNA-mediated modulation of neuronal processes that are important for brain development and their involvement in disease pathogenesis. Also, we overview each MRI technique, and its technological considerations, and discuss the applications of MRI techniques in miRNA research. This review aims to link miRNA biological study with MRI analytical technology and deepen our understanding of how miRNAs impact brain development and pathology of neurological diseases.

A Fetal Brain magnetic resonance Acquisition Numerical phantom (FaBiAN)

Accurate characterization of in utero human brain maturation is critical as it involves complex and interconnected structural and functional processes that may influence health later in life. Magnetic resonance imaging is a powerful tool to investigate equivocal neurological patterns during fetal development. However, the number of acquisitions of satisfactory quality available in this cohort of sensitive subjects remains scarce, thus hindering the validation of advanced image processing techniques. Numerical phantoms can mitigate these limitations by providing a controlled environment with a known ground truth. In this work, we present FaBiAN, an open-source Fetal Brain magnetic resonance Acquisition Numerical phantom that simulates clinical T2-weighted fast spin echo sequences of the fetal brain. This unique tool is based on a general, flexible and realistic setup that includes stochastic fetal movements, thus providing images of the fetal brain throughout maturation comparable to clinical acquisitions. We demonstrate its value to evaluate the robustness and optimize the accuracy of an algorithm for super-resolution fetal brain magnetic resonance imaging from simulated motion-corrupted 2D low-resolution series compared to a synthetic high-resolution reference volume. We also show that the images generated can complement clinical datasets to support data-intensive deep learning methods for fetal brain tissue segmentation.

Automated detection and reacquisition of motion-degraded images in fetal HASTE imaging at 3 T

PURPOSE

Fetal brain Magnetic Resonance Imaging suffers from unpredictable and unconstrained fetal motion that causes severe image artifacts even with half-Fourier single-shot fast spin echo (HASTE) readouts. This work presents the implementation of a closed-loop pipeline that automatically detects and reacquires HASTE images that were degraded by fetal motion without any human interaction.

METHODS

A convolutional neural network that performs automatic image quality assessment (IQA) was run on an external GPU-equipped computer that was connected to the internal network of the MRI scanner. The modified HASTE pulse sequence sent each image to the external computer, where the IQA convolutional neural network evaluated it, and then the IQA score was sent back to the sequence. At the end of the HASTE stack, the IQA scores from all the slices were sorted, and only slices with the lowest scores (corresponding to the slices with worst image quality) were reacquired.

RESULTS

The closed-loop HASTE acquisition framework was tested on 10 pregnant mothers, for a total of 73 acquisitions of our modified HASTE sequence. The IQA convolutional neural network, which was successfully employed by our modified sequence in real time, achieved an accuracy of 85.2% and area under the receiver operator characteristic of 0.899.

CONCLUSION

The proposed acquisition/reconstruction pipeline was shown to successfully identify and automatically reacquire only the motion degraded fetal brain HASTE slices in the prescribed stack. This minimizes the overall time spent on HASTE acquisitions by avoiding the need to repeat the entire stack if only few slices in the stack are motion-degraded.

Attention-guided deep learning for gestational age prediction using fetal brain MRI

Magnetic resonance imaging offers unrivaled visualization of the fetal brain, forming the basis for establishing age-specific morphologic milestones. However, gauging age-appropriate neural development remains a difficult task due to the constantly changing appearance of the fetal brain, variable image quality, and frequent motion artifacts. Here we present an end-to-end, attention-guided deep learning model that predicts gestational age with R² score of 0.945, mean absolute error of 6.7 days, and concordance correlation coefficient of 0.970. The convolutional neural network was trained on a heterogeneous dataset of 741 developmentally normal fetal brain images ranging from 19 to 39 weeks in gestational age. We also demonstrate model performance and generalizability using independent datasets from four academic institutions across the U.S. and Turkey with R² scores of 0.81–0.90 after minimal fine-tuning. The proposed regression algorithm provides an automated machine-enabled tool with the potential to better characterize in utero neurodevelopment and guide real-time gestational age estimation after the first trimester.

Optimization of the image contrast for the developing fetal brain using 3D radial VIBE sequence in 3 T magnetic resonance imaging

BACKGROUND

Faster and motion robust magnetic resonance imaging (MRI) sequences are desirable in fetal brain MRI. T1-weighted images are essential for evaluating fetal brain development. We optimized the radial volumetric interpolated breath-hold examination (VIBE) sequence for qualitative T1-weighted images of the fetal brain with improved image contrast and reduced motion sensitivity.

MATERIALS AND METHODS

This was an institutional review board-approved prospective study. Thirty-five pregnant subjects underwent fetal brain scan at 3 Tesla MRI. T1-weighted images were acquired using a 3D radial VIBE sequence with flip angles of 6º, 9º, 12º, and 15º. T1-weighted images of Cartesian VIBE sequence were acquired in three of the subjects. Qualitative assessments including image quality and motion artifact severity were evaluated. The image contrast ratio between gray and white matter were measured. Interobserver reliability and intraobserver repeatability were assessed using intraclass correlation coefficient (ICC).

RESULTS

Interobserver reliability and intraobserver repeatability universally revealed almost perfect agreement (ICC > 0.800). Significant differences in image quality were detected in basal ganglia (P = 0.023), central sulcus (P = 0.028), myelination (P = 0.007) and gray matter (P = 0.023) among radial VIBE with flip angles 6º, 9º, 12º, 15º. Image quality at the 9º flip angle in radial VIBE was generally better than flip angle of 15º. Radial VIBE sequence with 9º flip angle of gray matter was significantly different by gestational age (GA) before and after 28 weeks (P = 0.036). Quantified image contrast was significantly different among different flip angles, consistent with qualitative analysis of image quality.

CONCLUSIONS

Three-dimensional radial VIBE with 9º flip angle provides optimal, stable T1-weighted images of the fetal brain. Fetal brain structure and development can be evaluated using high-quality images obtained using this angle. However, different scanners will achieve different TRs and so the FA should be re-optimized each time a new protocol is employed.

Selective RF excitation designs enabled by time-varying spatially non-linear ΔB0 fields with applications in fetal MRI

PURPOSE

To demonstrate, through numerical simulations, novel designs of spatially selective radiofrequency (RF) excitations of the fetal brain by both a restricted 2D slice and 3D inner-volume selection. These designs exploit a single-channel RF pulse, conventional gradient fields, and the spatially non-linear ΔB₀ fields of a multi-coil shim array, using an auto-differentiation optimization algorithm.

METHODS

The design algorithm jointly optimizes the RF pulse and the time-varying ΔB₀ fields, which is produced by a 64-channel multi-coil ΔB₀ body array to augment the RF and the linear gradient fields, using an auto-differentiation approach. Two design targets were specified, one a 4-mm thick slice with a limited in-slice extent in one dimension ("restricted slice"), and the other a 3D inner-volume selection encompassing the fetal brain ("inner volume"). The RF duration was limited to 2 ms for the restricted slice excitation and 6 ms for the inner-volume excitation.

RESULTS

Excitation profiles were achieved for both the restricted slice excitation task (one-minus-minimum magnitude, 8%) within the region of interest (ROI) and (maximum-minus-zero magnitude, 8%) in the suppressed regions and the fetal brain volume excitation task (13% and 9%, respectively).

CONCLUSIONS

The proposed joint design of RF and time-varying, spatially non-linear ΔB₀ fields achieves the target excitation profiles with short RF pulse durations and demonstrates the potential to enhance fetal MRI with multi-channel body shim arrays.

Super-resolution Reconstruction MRI Application in Fetal Neck Masses and Congenital High Airway Obstruction Syndrome

Objective

Reliable airway patency diagnosis in fetal tracheolaryngeal obstruction is crucial to select and plan ex utero intrapartum treatment (EXIT) surgery. We compared the clinical utility of magnetic resonance imaging (MRI) super-resolution reconstruction (SRR) of the trachea, which can mitigate unpredictable fetal motion effects, with standard 2-dimensional (2D) MRI for airway patency diagnosis and assessment of fetal neck mass anatomy.

Study Design

A single-center case series of 7 consecutive singleton pregnancies with complex upper airway obstruction (2013-2019).

Setting

A tertiary fetal medicine unit performing EXIT surgery.

Methods

MRI SRR of the trachea was performed involving rigid motion correction of acquired 2D MRI slices combined with robust outlier detection to reconstruct an isotropic high-resolution volume. SRR, 2D MRI, and paired data were blindly assessed by 3 radiologists in 3 experimental rounds.

Results

Airway patency was correctly diagnosed in 4 of 7 cases (57%) with 2D MRI as compared with 2 of 7 cases (29%) with SRR alone or paired 2D MRI and SRR. Radiologists were more confident (P = .026) in airway patency diagnosis when using 2D MRI than SRR. Anatomic clarity was higher with SRR (P = .027) or paired data (P = .041) in comparison with 2D MRI alone. Radiologists detected further anatomic details by using paired images versus 2D MRI alone (P < .001). Cognitive load, as assessed by the NASA Task Load Index, was increased with paired or SRR data in comparison with 2D MRI.

Conclusion

The addition of SRR to 2D MRI does not increase fetal airway patency diagnostic accuracy but does provide improved anatomic information, which may benefit surgical planning of EXIT procedures.

Deep learning-based parameter estimation in fetal diffusion-weighted MRI

Diffusion-weighted magnetic resonance imaging (DW-MRI) of fetal brain is challenged by frequent fetal motion and signal to noise ratio that is much lower than non-fetal imaging. As a result, accurate and robust parameter estimation in fetal DW-MRI remains an open problem. Recently, deep learning techniques have been successfully used for DW-MRI parameter estimation in non-fetal subjects. However, none of those prior works has addressed the fetal brain because obtaining reliable fetal training data is challenging. To address this problem, in this work we propose a novel methodology that utilizes fetal scans as well as scans from prematurely-born infants. High-quality newborn scans are used to estimate accurate maps of the parameter of interest. These parameter maps are then used to generate DW-MRI data that match the measurement scheme and noise distribution that are characteristic of fetal data. In order to demonstrate the effectiveness and reliability of the proposed data generation pipeline, we used the generated data to train a convolutional neural network (CNN) to estimate color fractional anisotropy (CFA). We evaluated the trained CNN on independent sets of fetal data in terms of reconstruction accuracy, precision, and expert assessment of reconstruction quality. Results showed significantly lower reconstruction error (n=100,p<0.001) and higher reconstruction precision (n=20,p<0.001) for the proposed machine learning pipeline compared with standard estimation methods. Expert assessments on 20 fetal test scans showed significantly better overall reconstruction quality (p<0.001) and more accurate reconstruction of 11 regions of interest (p<0.001) with the proposed method.

STRESS: Super-Resolution for Dynamic Fetal MRI using Self-Supervised Learning

Fetal motion is unpredictable and rapid on the scale of conventional MR scan times. Therefore, dynamic fetal MRI, which aims at capturing fetal motion and dynamics of fetal function, is limited to fast imaging techniques with compromises in image quality and resolution. Super-resolution for dynamic fetal MRI is still a challenge, especially when multi-oriented stacks of image slices for oversampling are not available and high temporal resolution for recording the dynamics of the fetus or placenta is desired. Further, fetal motion makes it difficult to acquire high-resolution images for supervised learning methods. To address this problem, in this work, we propose STRESS (Spatio-Temporal Resolution Enhancement with Simulated Scans), a self-supervised super-resolution framework for dynamic fetal MRI with interleaved slice acquisitions. Our proposed method simulates an interleaved slice acquisition along the high-resolution axis on the originally acquired data to generate pairs of low- and high-resolution images. Then, it trains a super-resolution network by exploiting both spatial and temporal correlations in the MR time series, which is used to enhance the resolution of the original data. Evaluations on both simulated and in utero data show that our proposed method outperforms other self-supervised super-resolution methods and improves image quality, which is beneficial to other downstream tasks and evaluations.

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.

An automatic multi-tissue human fetal brain segmentation benchmark using the Fetal Tissue Annotation Dataset

It is critical to quantitatively analyse the developing human fetal brain in order to fully understand neurodevelopment in both normal fetuses and those with congenital disorders. To facilitate this analysis, automatic multi-tissue fetal brain segmentation algorithms are needed, which in turn requires open datasets of segmented fetal brains. Here we introduce a publicly available dataset of 50 manually segmented pathological and non-pathological fetal magnetic resonance brain volume reconstructions across a range of gestational ages (20 to 33 weeks) into 7 different tissue categories (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, deep grey matter, brainstem/spinal cord). In addition, we quantitatively evaluate the accuracy of several automatic multi-tissue segmentation algorithms of the developing human fetal brain. Four research groups participated, submitting a total of 10 algorithms, demonstrating the benefits the dataset for the development of automatic algorithms.

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.

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

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

Update on fetal cardiovascular magnetic resonance and utility in congenital heart disease

Background

Congenital heart disease (CHD) is the most common birth defect, affecting approximately eight per thousand newborns. Between one and two neonates per thousand have congenital cardiac lesions that require immediate post-natal treatment to stabilize the circulation, and the management of these patients in particular has been greatly enhanced by prenatal detection. The antenatal diagnosis of CHD has been made possible through the development of fetal echocardiography, which provides excellent visualization of cardiac anatomy and physiology and is widely available. However, late gestational fetal echocardiographic imaging can be hampered by suboptimal sonographic windows, particularly in the setting of oligohydramnios or adverse maternal body habitus.

Main body

Recent advances in fetal cardiovascular magnetic resonance (CMR) technology now provide a feasible alternative that could be helpful when echocardiography is inconclusive or limited. Fetal CMR has also been used to study fetal circulatory physiology in human fetuses with CHD, providing new insights into how these common anatomical abnormalities impact the distribution of blood flow and oxygen across the fetal circulation. In combination with conventional fetal and neonatal magnetic resonance imaging (MRI) techniques, fetal CMR can be used to explore the relationship between abnormal cardiovascular physiology and fetal development. Similarly, fetal CMR has been successfully applied in large animal models of the human fetal circulation, aiding in the evaluation of experimental interventions aimed at improving in utero development. With the advent of accelerated image acquisition techniques, post-processing approaches to correcting motion artifacts and commercial MRI compatible cardiotocography units for acquiring gated fetal cardiac imaging, an increasing number of CMR methods including angiography, ventricular volumetry, and the quantification of vessel blood flow and oxygen content are now possible.

Conclusion

Fetal CMR has reached an exciting stage whereby it may now be used to enhance the assessment of cardiac morphology and fetal hemodynamics in the setting of prenatal CHD.

Fetal head and neck tumors

Imaging plays a leading role in detection and diagnosis of fetal head and neck lesions. These lesions comprise a heterogeneous group of congenital tumors and malformations. Complementary imaging modalities that can be used in prenatal medicine are ultrasound and MRI. The authors discuss imaging characteristics of fetal lesions, assessment of potential complications and pregnancy management options for the most common pathology of the fetal head and neck.

Fetal cardiovascular magnetic resonance imaging

Fetal cardiovascular MRI is showing promise as a clinical diagnostic tool in the setting of congenital heart disease when the cardiac anatomy is unresolved by US or when complementary quantitative data on blood flow, oxygen saturation and hematocrit are required to aid in management. Compared with postnatal cardiovascular MRI, prenatal cardiovascular MRI still has some technical limitations. However, ongoing technical advances continue to improve the robustness and usability of fetal cardiovascular MRI. In this review, we provide an overview of the state of the art of fetal cardiovascular MRI and summarize the current focus of clinical application for this versatile technique.

Image-quality optimization and artifact reduction in fetal magnetic resonance imaging

Fetal MRI allows for earlier and better detection of complex congenital anomalies. However, its diagnostic utility is often limited by technical barriers that introduce artifacts and reduce image quality. The main determinants of fetal MR image quality are speed of acquisition, spatial resolution and signal-to-noise ratio (SNR). Imaging optimization is a challenge because a change to improve one scan parameter often leads to worsening of another. Moreover, the recent introduction of fetal MRI on 3-tesla (T) scanners to achieve better SNR can amplify some technical issues. Motion, banding artifacts and aliasing artifacts impact the quality of fetal acquisitions at any field strength. High specific absorption rate (SAR) and artifacts from inhomogeneities in the radiofrequency field are important limitations of high-field-strength imaging. We discuss technical barriers that impact image quality and are important limitations to prenatal MRI diagnosis, and propose solutions to improve image quality and reduce artifacts.

Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging

Fetal magnetic resonance imaging (MRI) is challenged by uncontrollable, large, and irregular fetal movements. It is, therefore, performed through visual monitoring of fetal motion and repeated acquisitions to ensure diagnostic-quality images are acquired. Nevertheless, visual monitoring of fetal motion based on displayed slices, and navigation at the level of stacks-of-slices is inefficient. The current process is highly operator-dependent, increases scanner usage and cost, and significantly increases the length of fetal MRI scans which makes them hard to tolerate for pregnant women. To help build automatic MRI motion tracking and navigation systems to overcome the limitations of the current process and improve fetal imaging, we have developed a new real-time image-based motion tracking method based on deep learning that learns to predict fetal motion directly from acquired images. Our method is based on a recurrent neural network, composed of spatial and temporal encoder-decoders, that infers motion parameters from anatomical features extracted from sequences of acquired slices. We compared our trained network on held-out test sets (including data with different characteristics, e.g. different fetuses scanned at different ages, and motion trajectories recorded from volunteer subjects) with networks designed for estimation as well as methods adopted to make predictions. The results show that our method outperformed alternative techniques, and achieved real-time performance with average errors of 3.5 and 8 degrees for the estimation and prediction tasks, respectively. Our real-time deep predictive motion tracking technique can be used to assess fetal movements, to guide slice acquisitions, and to build navigation systems for fetal MRI.

Combination of volume-rendering 3D surface modeling and medical illustration to capture the living fetus

OBJECTIVE

A good medical illustration renders essential aspects of a procedure or condition faithfully, yet idealizes it enough to make it widely applicable. Unfortunately, the live fetus is generally hidden from sight, and illustrating it relies either on autopsy material or manipulated newborn images. High-definition volume rendering of diagnostic imaging data can represent hidden conditions with an almost lifelike realism but is limited by the resolution and artifacts of the data capture. We have combined both approaches to enhance the accuracy and didactic value of illustrations of fetal conditions.

METHODS

Three examples, of increasing complexity, are presented to demonstrate the creation of medical illustrations of the fetus based on semiautomatic computerized posthoc manipulation of diagnostic images.

RESULTS

The end product utilizes the diagnostic accuracy of ultrasound and magnetic resonance imaging of the fetuses and the spatial manipulation of 3D models to create a lifelike, accurate and informative image of the fetal anomalies.

CONCLUSION

Volume-rendering and 3D surface modeling can be combined with medical illustration to create realistic and informative images of the developing fetus, using a level of detail that is tailored to the intended audience.

Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistency

Fetal brain MRI is useful for diagnosing brain abnormalities but is challenged by fetal motion. The current protocol for T2-weighted fetal brain MRI is not robust to motion so image volumes are degraded by inter- and intra-slice motion artifacts. Besides, manual annotation for fetal MR image quality assessment are usually time-consuming. Therefore, in this work, a semi-supervised deep learning method that detects slices with artifacts during the brain volume scan is proposed. Our method is based on the mean teacher model, where we not only enforce consistency between student and teacher models on the whole image, but also adopt an ROI consistency loss to guide the network to focus on the brain region. The proposed method is evaluated on a fetal brain MR dataset with 11,223 labeled images and more than 200,000 unlabeled images. Results show that compared with supervised learning, the proposed method can improve model accuracy by about 6% and outperform other state-of-the-art semi-supervised learning methods. The proposed method is also implemented and evaluated on an MR scanner, which demonstrates the feasibility of online image quality assessment and image reacquisition during fetal MR scans.

Spatiotemporal Differences in the Regional Cortical Plate and Subplate Volume Growth during Fetal Development

The regional specification of the cerebral cortex can be described by protomap and protocortex hypotheses. The protomap hypothesis suggests that the regional destiny of cortical neurons and the relative size of the cortical area are genetically determined early during embryonic development. The protocortex hypothesis suggests that the regional growth rate is predominantly shaped by external influences. In order to determine regional volumes of cortical compartments (cortical plate (CP) or subplate (SP)) and estimate their growth rates, we acquired T2-weighted in utero MRIs of 40 healthy fetuses and grouped them into early (<25.5 GW), mid- (25.5-31.6 GW), and late (>31.6 GW) prenatal periods. MRIs were segmented into CP and SP and further parcellated into 22 gyral regions. No significant difference was found between periods in regional volume fractions of the CP or SP. However, during the early and mid-prenatal periods, we found significant differences in relative growth rates (% increase per GW) between regions of cortical compartments. Thus, the relative size of these regions are most likely conserved and determined early during development whereas more subtle growth differences between regions are fine-tuned later, during periods of peak thalamocortical growth. This is in agreement with both the protomap and protocortex hypothesis.

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.

Fetal Cardiac MRI: A Review of Technical Advancements

Magnetic resonance imaging (MRI) is an appealing technology for fetal cardiovascular assessment. It can be used to visualize fetal cardiac and vascular anatomy, to quantify fetal blood flow, and to quantify fetal blood oxygen saturation and hematocrit. However, there are practical limitations to the use of conventional MRI for fetal cardiovascular assessment, including the small size and high heart rate of the human fetus, the lack of conventional cardiac gating methods to synchronize data acquisition, and the potential corruption of MRI data due to maternal respiration and unpredictable fetal movements. In this review, we discuss recent technical advances in accelerated imaging, image reconstruction, cardiac gating, and motion compensation that have enabled dynamic MRI of the fetal heart.

Fetal Echoplanar Imaging: Promises and Challenges

Fetal magnetic resonance imaging (MRI) has been gaining increasing interest in both clinical radiology and research. Echoplanar imaging (EPI) offers a unique potential, as it can be used to acquire images very fast. It can be used to freeze motion, or to get multiple images with various contrast mechanisms that allow studying the microstructure and function of the fetal brain and body organs. In this article, we discuss the current clinical and research applications of fetal EPI. This includes T2*-weighted imaging to better identify blood products and vessels, using diffusion-weighted MRI to investigate connections of the developing brain and using functional MRI (fMRI) to identify the functional networks of the developing brain. EPI can also be used as an alternative structural sequence when banding or standing wave artifacts adversely affect the mainstream sequences used routinely in structural fetal MRI. We also discuss the challenges with EPI acquisitions, and potential solutions. As EPI acquisitions are inherently sensitive to susceptibility artifacts, geometric distortions limit the use of high-resolution EPI acquisitions. Also, interslice motion and transmit and receive field inhomogeneities may create significant artifacts in fetal EPI. We conclude by discussing promising research directions to overcome these challenges to improve the use of EPI in clinical and research applications.