Mary A. Rutherford

While slice‐to‐volume registration and super‐resolution reconstruction laid the foundation for motion‐corrected 3D T2‐weighted fetal brain magnetic resonance imaging (MRI) more than two decades ago, advances in deep learning are now enabling automation across acquisition planning, segmentation, biometry, and image quality control. In this narrative review, we highlight these emerging techniques and analyse their strengths and limitations in the context of clinical translation. We examine the major barriers to widespread clinical adoption of artificial intelligence tools and outline future directions at the clinical interface that may further transform the diagnostic role of fetal MRI. Together, these developments underscore a shifting landscape towards more comprehensive, quantitative in‐utero assessment, with the potential to enhance diagnostic accuracy and workflow efficiency, and broaden the clinical applications of fetal MRI in prenatal care.

Purpose: To develop and evaluate a real‐time framework for targeted slice‐level reacquisition in fetal diffusion MRI. Methods: A DW‐SE‐EPI sequence was modified to support independent diffusion preparation per slice. A pathology‐robust nnU‐Net segmentation network, updated from a previously published baseline (V1) using pathological fetal cases and physics‐inspired augmentation (V2), and intensity‐based artifact detection drive automated reacquisition prioritization. Retrospective validation was performed on 60 cases across three cohorts at two field strengths and prospective deployment in 14 cases at two clinical sites. Results: Segmentation V2 significantly outperformed V1 across all cohorts (), with largest gains at b0 s mm (median DSC gain 0.87 at 1.5 T). Blackout detection achieved F1 = 0.81 0.29 at T = 0.35. Prospective real‐time deployment confirmed clinical feasibility at both field strengths. Conclusion: Real‐time slice‐level fetal diffusion reacquisition is demonstrated for the first time, opening a pathway toward routine quantitative fetal diffusion MRI in research and clinical settings.

Preterm birth is associated with significant mortality and a risk for lifelong morbidity. The complex multifactorial aetiology hampers accurate prediction and thus optimal care. A pipeline consisting of bespoke machine learning methods for data imputation, feature selection, and regression models to predict gestational age (GA) at birth was developed and evaluated from comprehensive multi-modal morphological and functional fetal MRI data from 333 control cases and 93 preterm birth cases. The GA at birth predictions were classified into term and preterm categories and their accuracy, sensitivity, and speci- ficity were reported. An ablation study was performed to further validate the design of the pipeline. Performance was evaluated using stratified 10-fold cross-validation. The pipeline achieves an R2 score of 0.13 and a mean absolute error of 2.74 weeks. It also achieves a 0.77 accuracy, 0.59 sensitivity, and 0.82 specificity across folds. The predom- inant features selected by the pipeline include cervical length and statistics derived from placental T2* values. The confluence of fast, motion-robust and multi-modal fetal MRI techniques and machine learning prediction allowed the prediction of the gestation at birth. This information is essential for any pregnancy. To the best of our knowledge, preterm birth had only been addressed as a classification problem in the literature. There- fore, this work provides a proof of concept. Future work will increase the cohort size to allow for finer stratification within the preterm birth cohort. Our code is available at https://github.com/dfajardorojas/ml-for-preterm-birth-

Background: Brain development is altered in neonates with congenital heart disease (CHD). However, development in the perioperative period remains incompletely understood. Purpose: This study used Structural Covariance Component (SCC) analysis to identify brain regions showing spatial patterns of coordinated expansion and contraction that differ between neonates with CHD after cardiac intervention and healthy controls, as well as pre-to postoperative changes and effects of perioperative risk factors. Study type: Prospective. Population: The cohort included 41 neonates with CHD who underwent cardiac surgery or catheterization and 359 healthy neonates. Field strength and sequence: 3 Tesla T2-weighted turbo-spin-echo sequence. Assessment: Brain MRI were motion-corrected and reconstructed using an established neonatal algorithm. Jacobian determinants calculated from non-linear registration of MRI to a neonatal template were input into an Independent Component Analysis to identify SCCs (N=40). SCC weightings were extracted, reflecting the degree to which the pattern of covariance is expressed in each neonate. Statistical tests: Postoperative SCC weightings were compared to healthy neonates using a general linear model or robust regression. Pre- and postoperative SCC weightings were compared using a linear mixed effect model. Pre- to postoperative differences were calculated and associations with age at surgery, cardiopulmonary bypass duration, and postoperative paediatric intensive care unit stay were assessed using partial spearman’s rank correlation. Analyses were adjusted for covariates and corrected for multiple comparisons using False Discovery Rate. Results: 16/40 SCCs showed significant differences between neonates with CHD after surgery and controls, including white matter, cortical- and deep grey matter, brainstem, and CSF regions, with seven also showing significant perioperative change. A further nine SCCs only showed significant perioperative change. Perioperative risk factors were not associated with perioperative change. Data conclusion: This data-driven approach highlights region-specific postoperative alterations and perioperative changes in brain morphology of neonates with CHD. Evidence level. 1. Technical Efficacy: Stage 3.

Background: The role of MRI pelvimetry and fetal size estimation in predicting mode of birth and risk of operative birth have been studied. However, there are no complete MRI studies that assess the maternal pelvis, fetal dimensions, and the placenta in a single protocol, in order to better inform the likelihood of operative vaginal birth or emergency caesarean section. Therefore, the aim of this pilot study was to assess the feasibility of obtaining a comprehensive prelabour assessment of maternal pelvimetry and fetal biometry using 3D MRI reconstructions, in addition to measures of placental function, in one MR examination. Methods: This was a retrospective cohort study of 29 women in late third trimester. Maternal pelvimetry and fetal measurements were performed using structural motion corrected T2 weighted MR images, placental T2* values (an indirect measure of placental oxygenation), and birth outcomes were also collected. Intra and inter-rater variability were calculated for the first 10 patients using the intraclass correlation coefficient. The correlation between manual (measuring the contour area) and calculated circumferences of maternal and fetal structures were also assessed to compare the practicability of performing the two alternative approaches. Results: People were imaged between 36 + 1 to 38 + 4 weeks’ gestation. It was possible to obtain comprehensive maternal and fetal measurements. Intra-rater variability was generally excellent, and inter-rater reliability was moderate to excellent. There was a strong correlation between manually obtained and calculated circumferences; Spearman’s ranged from 0.75 to 0.95. Placental volume, mean T2* and kurtosis were available for 23 datasets. The median placental volume was 569.7, the median T2* mean was 44.2, and the median kurtosis was 1.4. Conclusions: It is possible to perform maternal pelvimetry, fetal biometry and assess placental oxygenation from one late gestation MRI examination. The approach could be employed in a large, prospective study to ascertain whether we can predict the likelihood of assisted birth or caesarean section, with automation of image analysis to minimise inter-rater variability.

Background: The detailed assessment of fetal brain maturation and development involves morphological evaluation, gyration analysis, and reliable biometric measurements. Manual measurements on conventional 2-D magnetic resonance imaging (MRI) are affected by fetal motion, and there is no clear consensus regarding definitions for brain biometric parameters and anatomical landmark placements, making consistent reference plane and slice selection challenging. Automated biometry with 3-D slice-to-volume reconstruction (SVR) has the potential to improve the reliability of derived measurements, allowing precise quantification of fetal brain development. Previous published works have primarily focused on the technical feasibility of automated fetal brain biometry methods for T2-weighted (T2W) MRI. However, none have proposed solutions for automating the reporting of biometry results, which could enhance clinical utility and support real-time integration into routine clinical workflows. Furthermore, there is no consensus on a universal fetal biometry protocol for 3-D fetal MRI. Objective: To implement and validate a fully automated biometry reporting pipeline for 3-D T2W fetal brain MRI, based on deep learning biometry measurements and computation of z -scores and centiles, by comparison to normative growth charts. Materials and methods: Automated extraction of 13 routinely reported linear fetal biometry measurements using deep learning localization of anatomical landmarks in 3-D reconstructed T2W brain images based on 3-D UNet and presentation of the results in an .html report with centile calculation. The automated biometry method was quantitatively evaluated on 90 retrospective cases against expert manual measurements. Additionally, the fully automated, end-to-end biometry reporting pipeline was prospectively evaluated on 111 cases across a wide range of gestational ages, field strengths, and scanning parameters. We also generated normal centile ranges for 19-40 weeks GA range from 406 normal control datasets. Results: The retrospective quantitative evaluation demonstrated good agreement with manual measurements, with the maximum absolute difference between automated vs. manual measurement within a 1-3-mm range. In the prospective evaluation, more than 98% of landmark placements were graded as acceptable for interpretation and measurements. The processing time of the pipeline was less than 5 min per case, with measurements and centiles available at the time of reporting. Inspection of the automated landmark placement and computed biometrics took 1-3 min per case. The generated normative growth charts demonstrate strong correlation with the trends in the previously reported works. Conclusion: Our approach is the first to develop a fully automated biometry reporting pipeline for 3-D T2-weighted fetal MRI which integrates deep learning-based measurements, centile and z -score calculation vs. normative growth charts and report generation. Graphical

Objectives: Despite sonography studies being integral to routine high quality antenatal care, clinical research in this field is less commonly initiated or led by sonography professionals. It is also unclear what the research priorities are for service users within the UK’s sonography screening and diagnostic pathway. Methods: Here, we present a national priority setting partnership project, which included 2 surveys, coproduced with the oversight of a stakeholder priority setting partnerships (PSP) group, comprising service users and healthcare professionals, n = 12. Results: From the surveys, there were 348 individual responses and 616 validated research questions/uncertainties submitted. The top-ranked 26 indicative questions were discussed at a final joint stakeholder meeting (n = 17) and the top 10 research priorities for pregnancy scanning research were voted for and agreed by consensus. These fell into 6 main themes: (1) maternal and parental experience; (2) emerging technology; (3) screening, prediction, and diagnosis, (4) role of pregnancy MRI, (5) continued professional development, training and education, and (6) service delivery and workforce. Conclusions: We envisage this PSP will support teams of researchers and clinicians with important and achievable targets to move the field of pregnancy scanning forward. Advances in knowledge: This is the first coproduced antenatal scanning priority setting partnership highlighting real world issues and lines of enquiry as proposed by service users and health care professionals.

Fetal diffusion MRI (dMRI) provides fascinating and clinically crucial insights into the microstructure of the human brain during development, but is highly sensitive to motion artifacts of fetal movement and maternal breathing, which impact data quality and limit diagnostic accuracy. This study introduces HERON, a robust, real-time, automatic pipeline designed to enhance fetal brain dMRI by performing motion assessment and re-acquisition. HERON leverages AI-driven brain localization, segmentation, and motion assessment on a clinical 0.55T scanner to automatically plan, quality check, and reacquire motion-affected dMRI volumes. Remaining inter-volume motion is corrected during post-processing. Tested in 20 cases, the pipeline effectively improved image quality, reduced intra- and inter-volume motion, and enabled more reliable quantitative analysis even in challenging cases. Excellent agreement with human observers (specificity 97%, sensitivity 92%) was shown and the mean Apparent Diffusion Coefficient and Intravoxel Incoherent Motion dropped in the majority of cases after correction. Improving fetal dMRI through an automatic AI-driven pipeline enables higher diagnostic quality and thus potentially wider use in both research and clinical applications.

Background: Motion correction methods based on slice-to-volume registration (SVR) for fetal magnetic resonance imaging (MRI) allow reconstruction of three-dimensional (3-D) isotropic images of the fetal brain and body. However, all existing SVR methods are confined to research settings, which limits clinical integration. Furthermore, there have been no reported SVR solutions for low-field 0.55-T MRI. Objective: Integration of automated SVR motion correction methods directly into fetal MRI scanning process via the Gadgetron framework to enable automated T2-weighted (T2W) 3-D fetal brain and body reconstruction in the low-field 0.55-T MRI scanner within the duration of the scan. Materials and methods: A deep learning fully automated pipeline was developed for T2W 3-D rigid and deformable (D/SVR) reconstruction of the fetal brain and body of 0.55-T T2W datasets. Next, it was integrated into 0.55-T low-field MRI scanner environment via a Gadgetron workflow that enables launching of the reconstruction process directly during scanning in real-time. Results: During prospective testing on 12 cases (22–40 weeks gestational age), the fetal brain and body reconstructions were available on average 6:42 ± 3:13 min after the acquisition of the final stack and could be assessed and archived on the scanner console during the ongoing fetal MRI scan. The output image data quality was rated as good to acceptable for interpretation. The retrospective testing of the pipeline on 83 0.55-T datasets demonstrated stable reconstruction quality for low-field MRI. Conclusion: The proposed pipeline allows scanner-based prospective T2W 3-D motion correction for low-field 0.55-T fetal MRI via direct online integration into the scanner environment. Graphical

Cortical gyrification takes place predominantly during the second to third trimester, alongside other fundamental developmental processes, such as the development of white matter connections, lamination of the cortex and formation of neural circuits. The mechanistic biology that drives the formation cortical folding patterns remains an open question in neuroscience. In our previous work, we modelled the in utero diffusion signal to quantify the maturation of microstructure in transient fetal compartments, identifying patterns of change in diffusion metrics that reflect critical neurobiological transitions occurring in the second to third trimester. In this work, we apply the same modelling approach to explore whether microstructural maturation of these compartments is correlated with the process of gyrification. We quantify the relationship between sulcal depth and tissue anisotropy within the cortical plate (CP) and underlying subplate (SP), key transient fetal compartments often implicated in mechanistic hypotheses about the onset of gyrification. Using in utero high angular resolution multi-shell diffusion-weighted imaging (HARDI) from the Developing Human Connectome Project (dHCP), our analysis reveals that the anisotropic, tissue component of the diffusion signal in the SP and CP decreases immediately prior to the formation of sulcal pits in the fetal brain. By back-projecting a map of folded brain regions onto the unfolded brain, we find evidence for cytoarchitectural differences between gyral and sulcal areas in the late second trimester, suggesting that regional variation in the microstructure of transient fetal compartments precedes, and thus may have a mechanistic function, in the onset of cortical folding in the developing human brain.