Comprehensive quantitative analyses of fetal magnetic resonance imaging in isolated cerebral ventriculomegaly

Graph-based prototype inverse-projection for identifying cortical sulcal pattern abnormalities in congenital heart disease

Examining the altered arrangement and patterning of sulcal folds offers insights into the mechanisms of neurodevelopmental differences in psychiatric and neurological disorders. Previous sulcal pattern analysis used spectral graph matching of sulcal pit-based graph structures to assess deviations from normative sulcal patterns. However, challenges exist, including the absence of a standard criterion for defining a typical reference set, time-consuming cost of graph matching, user-defined feature weight sets, and assumptions about uniform node distribution. We developed a deep learning-based sulcal pattern analysis to address these challenges by adapting prototype-based graph neural networks to sulcal pattern graphs. Additionally, we proposed a prototype inverse-projection for better interpretability. Unlike other prototype-based models, our approach inversely projects prototypes onto individual node representations to calculate the inverse-projection weights, enabling efficient visualization of prototypes and focusing the model on selective regions. We evaluated our method through a classification task between healthy controls (n = 174, age = 15.4 ±1.9 [mean ± standard deviation, years]) and patients with congenital heart disease (n = 345, age = 15.8 ±4.7) from four cohort studies and a public dataset. Our approach demonstrated superior classification performance compared to other state-of-the-art models, supported by extensive ablative studies. Furthermore, we visualized and examined the learned prototypes to enhance understanding. We believe our method has the potential to be a sensitive and understandable tool for sulcal pattern analysis.

Diencephalic-mesencephalic junction dysplasia: case report and literature review

Diencephalic-mesencephalic junction (DMJ) dysplasia is a rare congenital brain malformation characterized by a poorly defined junction between the diencephalon and mesencephalon, often associated with a butterfly-like contour of the midbrain on magnetic resonance imaging (MR). We report the case of a newborn female diagnosed prenatally with DMJ dysplasia who presented with severe ventriculomegaly, hydrocephalus, and oligohydramnios. Prenatal MRI at 32 weeks revealed a thickened interthalamic adhesion, an elongated midbrain with ventral cleft, aqueductal stenosis, and corpus callosum dysgenesis. Postnatal MRI confirmed these findings, along with the characteristic "butterfly" midbrain morphology. Genetic analysis revealed a pathogenic 11.9 Mb terminal deletion in the 6q25.3q27 region, encompassing candidate neurodevelopmental genes, such as DLL1, and a 3.8 Mb partial duplication in 22q13.31q13.33, of unknown significance. Parental genetic testing revealed a maternal balanced reciprocal translocation between chromosomes 6 and 22 (asymptomatic carrier), which was inherited in an unbalanced form by the proband. A ventriculoperitoneal shunt was placed within the first 48 h of life to manage hydrocephalus, with subsequent adjustments and revisions as needed. This case highlights the importance of advanced prenatal imaging and genetic testing in the diagnosis of complex brain malformations as well as the need for multidisciplinary management of rare congenital anomalies. Further research is essential to elucidate the underlying genetic mechanisms and improve the outcomes in patients with DMJ dysplasia.

Impact of high maternal body mass index on fetal cerebral cortical and cerebellar volumes

OBJECTIVES

Maternal obesity increases a child's risk of neurodevelopmental impairment. However, little is known about the impact of maternal obesity on fetal brain development.

METHODS

We prospectively recruited 20 healthy pregnant women across the range of pre-pregnancy or first-trimester body mass index (BMI) and performed fetal brain magnetic resonance imaging (MRI) of their healthy singleton fetuses. We examined correlations between early pregnancy maternal BMI and regional brain volume of living fetuses using volumetric MRI analysis.

RESULTS

Of 20 fetuses, there were 8 males and 12 females (median gestational age at MRI acquisition was 24.3 weeks, range: 19.7-33.3 weeks, median maternal age was 33.3 years, range: 22.0-37.4 years). There were no significant differences in clinical demographics between overweight (OW, 25≤BMI<30)/obese (OB, BMI≥30 kg/m2) (n=12) and normal BMI (18.5≤BMI<25) (n=8) groups. Fetuses in the OW/OB group had significantly larger left cortical plate (p=0.0003), right cortical plate (p=0.0002), and whole cerebellum (p=0.049) compared to the normal BMI group. In the OW/OB BMI group, cortical plate volume was larger relative to other brain regions after 28 weeks.

CONCLUSIONS

This pilot study supports the concept that maternal obesity impacts fetal brain volume, detectable via MRI in living fetuses using quantitative analysis.

Deep Learning-based Brain Age Prediction Using MRI to Identify Fetuses with Cerebral Ventriculomegaly

Fetal ventriculomegaly (VM) and its severity and associated central nervous system (CNS) abnormalities are important indicators of high risk for impaired neurodevelopmental outcomes. Recently, a novel fetal brain age prediction method using a two-dimensional (2D) single-channel convolutional neural network (CNN) with multiplanar MRI sections showed the potential to detect fetuses with VM. This study examines the diagnostic performance of a deep learning-based fetal brain age prediction model to distinguish fetuses with VM (n = 317) from typically developing fetuses (n = 183), the severity of VM, and the presence of associated CNS abnormalities. The predicted age difference (PAD) was measured by subtracting the predicted brain age from the gestational age in fetuses with VM and typical development. PAD and absolute value of PAD (AAD) were compared between VM and typically developing fetuses. In addition, PAD and AAD were compared between subgroups by VM severity and the presence of associated CNS abnormalities in VM. Fetuses with VM showed significantly larger AAD than typically developing fetuses (P < .001), and fetuses with severe VM showed larger AAD than those with moderate VM (P = .004). Fetuses with VM and associated CNS abnormalities had significantly lower PAD than fetuses with isolated VM (P = .005). These findings suggest that fetal brain age prediction using the 2D single-channel CNN method has the clinical ability to assist in identifying not only the enlargement of the ventricles but also the presence of associated CNS abnormalities. Keywords: MR-Fetal (Fetal MRI), Brain/Brain Stem, Fetus, Supervised Learning, Machine Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms Supplemental material is available for this article. ©RSNA, 2025.

Fetal gestational age prediction via shape descriptors of cortical development

Introduction

Gyrification is the intricate process through which the mammalian cerebral cortex develops its characteristic pattern of sulci and gyri. Monitoring gyrification provides valuable insights into brain development and identifies potential abnormalities at an early stage. This study analyzes the cortical structure in neurotypical and pathological (spina bifida) fetuses using various shape descriptors to shed light on the gyrification process during pregnancy.

Methods

We compare morphometric properties encoded by commonly used scalar point-wise curvature-based signatures-such as mean curvature (H), Gaussian curvature (K), shape index (SI), and curvedness (C)-with multidimensional point-wise shape signatures, including spectral geometry processing methods like the Heat Kernel Signature (HKS) and Wave Kernel Signature (WKS), as well as the Signature of Histograms of Orientations (SHOT), which combines histogram and signature techniques. These latter signatures originate from computer graphics techniques and are rarely applied in the medical field. We propose a novel technique to derive a global descriptor from a given point-wise signature, obtaining GHKS, GWKS, and GSHOT. The extracted signatures are then evaluated using Support Vector Regression (SVR)-based algorithms to predict fetal gestational age (GA).

Results

GSHOT better encodes the GA to other global multidimensional point-wise shape signatures (GHKS, GWKS) and commonly used scalar point-wise curvature-based signatures (C, H, K, SI, FI), achieving a prediction R 2 of 0.89 and a mean absolute error of 6 days in neurotypical fetuses, and a R 2 of 0.64 and a mean absolute error of 10 days in pathological fetuses.

Conclusion

GSHOT provides researchers with an advanced tool to capture more nuanced aspects of fetal brain development and, specifically, of the gyrification process.

Machine learning in prenatal MRI predicts postnatal ventricular abnormalities in fetuses with isolated ventriculomegaly

OBJECTIVES

To evaluate the intracranial structures and brain parenchyma radiomics surrounding the occipital horn of the lateral ventricle in normal fetuses (NFs) and fetuses with ventriculomegaly (FVs), as well as to predict postnatally enlarged lateral ventricle alterations in FVs.

METHODS

Between January 2014 and August 2023, 141 NFs and 101 FVs underwent 1.5 T balanced steady-state free precession (BSSFP), including 68 FVs with resolved lateral ventricles (FVM-resolved) and 33 FVs with stable lateral ventricles (FVM-stable). Demographic data and intracranial structures were analyzed. To predict the enlarged ventricle alterations of FVs postnatally, logistic regression models with 5-fold cross-validation were developed based on lateral ventricle morphology, blended-cortical or/and subcortical radiomics characteristics. Validation of the models' performance was conducted using the receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA).

RESULTS

Significant alterations in cerebral structures were observed between NFs and FVs (p < 0.05), excluding the maximum frontal horn diameter (FD). However, there was no notable distinction between the FVM-resolved and FVM-stable groups (all p > 0.05). Based on subcortical-radiomics on the aberrant sides of FVs, this approach exhibited high efficacy in distinguishing NFs from FVs in the training/validation set, yielding an impressive AUC of 1/0.992. With an AUC value of 0.822/0.743 in the training/validation set, the Subcortical-radiomics model demonstrated its ability to predict lateral ventricle alterations in FVs, which had the greatest predictive advantages indicated by DCA.

CONCLUSIONS

Microstructural alterations in subcortical parenchyma associated with ventriculomegaly can serve as predictive indicators for postnatal lateral ventricle variations in FVs.

CLINICAL RELEVANCE STATEMENT

It is critical to gain pertinent information from a solitary fetal MRI to anticipate postnatal lateral ventricle alterations in fetuses with ventriculomegaly. This approach holds the potential to diminish the necessity for recurrent prenatal ultrasound or MRI examinations.

KEY POINTS

Fetal ventriculomegaly is a dynamic condition that affects postnatal neurodevelopment. Machine learning and subcortical-radiomics can predict postnatal alterations in the lateral ventricle. Machine learning, applied to single-fetal MRI, might reduce required antenatal testing.

[Research Progress in Magnetic Resonance Imaging of Fetal Ventriculomegaly]

Fetal ventriculomegaly is a central nervous system disorder commonly seen in prenatal imaging, and the prognosis ranges from normal health to severe dysfunction. Currently, fetal predictive markers associated with postpartum individual neurodevelopmental function are still not available, which increases the difficulty of prenatal diagnosis and clinical management. Constant advancements in magnetic resonance imaging (MRI) technology have brought better accuracy and reliability of MRI applied in the diagnosis, prognosis assessment, and etiology investigation of ventriculomegaly. MRI plays a critical role in prognostic management and prenatal consultation. Nevertheless, due to the potential safety hazards and economic and technical constraints of MRI, it is not the first choice for prenatal imaging diagnosis. Moreover, there are different opinions regarding the measurement results and grading criteria of ultrasound and MRI. At present, it is accepted that three-dimensional volume may provide reliable information for prognosis. However, accurate segmentation and measurement of brain structure remain serious challenges, and no consensus on the MRI measurement of lateral ventricle volume has been reached. In this paper, based on the latest research reports from China and around the world, we reviewed the progress in applying MRI in the prenatal diagnosis and treatment of ventriculomegaly. This review offers a theoretical foundation for further exploration of the role of lateral ventricle volume measurement in disease diagnosis and management. We suggest that researchers combine two-dimensional width with three-dimensional volume in the future to identify the optimal cutoff value for prognostic prediction of fetal ventriculomegaly.

Volume development changes in the occipital lobe gyrus assessed by MRI in fetuses with isolated ventriculomegaly correlate with neurological development in infancy and early childhood

OBJECTIVE

This study was to systematically assess the occipital lobe gray and white matter volume of isolated ventriculomegaly (IVM) fetuses with MRI and to follow up the neurodevelopment of participants.

METHOD

MRI was used to evaluate 37 IVM fetuses and 37 control fetuses. The volume of gray and white matter in each fetal occipital gyrus was manually segmented and compared, and neurodevelopment was followed up and assessed in infancy and early childhood.

RESULT

Compared with the control group, the volume of gray matter in occipital lobe increased in the IVM group, and the incidence of neurodevelopmental delay increased.

CONCLUSION

We tested the hypothesis that prenatal diagnosis IVM represents a biological marker for development in fetal occipital lobe. Compared with the control group, the IVM group showed differences in occipital gray matter development and had a higher risk of neurodevelopmental delay.

The role of cortical structural variance in deep learning-based prediction of fetal brain age

Background

Deep-learning-based brain age estimation using magnetic resonance imaging data has been proposed to identify abnormalities in brain development and the risk of adverse developmental outcomes in the fetal brain. Although saliency and attention activation maps have been used to understand the contribution of different brain regions in determining brain age, there has been no attempt to explain the influence of shape-related cortical structural features on the variance of predicted fetal brain age.

Methods

We examined the association between the predicted brain age difference (PAD: predicted brain age-chronological age) from our convolution neural networks-based model and global and regional cortical structural measures, such as cortical volume, surface area, curvature, gyrification index, and folding depth, using regression analysis.

Results

Our results showed that global brain volume and surface area were positively correlated with PAD. Additionally, higher cortical surface curvature and folding depth led to a significant increase in PAD in specific regions, including the perisylvian areas, where dramatic agerelated changes in folding structures were observed in the late second trimester. Furthermore, PAD decreased with disorganized sulcal area patterns, suggesting that the interrelated arrangement and areal patterning of the sulcal folds also significantly affected the prediction of fetal brain age.

Conclusion

These results allow us to better understand the variance in deep learning-based fetal brain age and provide insight into the mechanism of the fetal brain age prediction model.

Fetal neuroimaging applications for diagnosis and counseling of brain anomalies: Current practice and future diagnostic strategies

Advances in fetal brain neuroimaging, especially fetal neurosonography and brain magnetic resonance imaging (MRI), allow safe and accurate anatomical assessments of fetal brain structures that serve as a foundation for prenatal diagnosis and counseling regarding fetal brain anomalies. Fetal neurosonography strategically assesses fetal brain anomalies suspected by screening ultrasound. Fetal brain MRI has unique technological features that overcome the anatomical limits of smaller fetal brain size and the unpredictable variable of intrauterine motion artifact. Recent studies of fetal brain MRI provide evidence of improved diagnostic and prognostic accuracy, beginning with prenatal diagnosis. Despite technological advances over the last several decades, the combined use of different qualitative structural biomarkers has limitations in providing an accurate prognosis. Quantitative analyses of fetal brain MRIs offer measurable imaging biomarkers that will more accurately associate with clinical outcomes. First-trimester ultrasound opens new opportunities for risk assessment and fetal brain anomaly diagnosis at the earliest time in pregnancy. This review includes a case vignette to illustrate how fetal brain MRI results interpreted by the fetal neurologist can improve diagnostic perspectives. The strength and limitations of conventional ultrasound and fetal brain MRI will be compared with recent research advances in quantitative methods to better correlate fetal neuroimaging biomarkers of neuropathology to predict functional childhood deficits. Discussion of these fetal sonogram and brain MRI advances will highlight the need for further interdisciplinary collaboration using complementary skills to continue improving clinical decision-making following precision medicine principles.

White matter changes in fetal brains with ventriculomegaly

Introduction

Ventriculomegaly (VM) is a fetal brain malformation which may present independently (isolated form) or in association with different cerebral malformations, genetic syndromes or other pathologies (non-isolated form).

Methods

This paper aims to study the effect of ventriculomegaly on the internal tridimensional architecture of fetal brains by way of Klingler's dissection. Ventriculomegaly was diagnosed using fetal ultrasonography during pregnancy and subsequently confirmed by necropsy. Taking into consideration the diameter of the lateral ventricle (measured at the level of the atrium), the brains were divided into two groups: moderate ventriculomegaly (with atrial diameter between 13 and 15 mm) and severe ventriculomegaly (with atrial diameter above 15 mm).

Results and discussion

The results of each dissection were described and illustrated, then compared with age-matched reference brains. In the pathological brains, fascicles in direct contact with the enlarged ventricles were found to be thinner and displaced inferiorly, the opening of the uncinate fasciculus was wider, the fornix was no longer in contact with the corpus callosum and the convexity of the corpus callosum was inverted. We have studied the prevalence of neurodevelopmental delay in children born with ventriculomegaly in the literature and discovered that a normal developmental outcome was found in over 90% of the mild VM cases, approximately 75% of the moderate and 60% in severe VM, with the correlated neurological impairments ranging from attention deficits to psychiatric disorders.