Fetal Imaging Research Articles

Effects of 1.5-T versus 3-T magnetic resonance imaging in fetuses: is there a difference in postnatal neurodevelopmental outcome? Evaluation in a fetal population with left-sided congenital diaphragmatic hernia.

The utilization of 3-T magnetic field strength in obstetric imaging is increasingly common. It is important to ensure that magnetic resonance (MR) imaging with higher magnetic field strength is safe for the fetus. Comparison of neurodevelopmental outcome in neonates undergoing prenatal MR imaging with 1.5-T versus 3-T is of interest but has not yet been examined. We hypothesized no clinically meaningful difference in neurodevelopmental outcome between fetuses undergoing 1.5-T versus 3-T fetal MR imaging. As imaging a normal fetus for research purposes is illegal in Pennsylvania, this study was conducted in a population of fetuses with left congenital diaphragmatic hernia (left-CDH). A retrospective review of neurodevelopmental outcome of fetuses with left-CDH scanned at 1.5-T (n=75) versus 3-T (n=25) magnetic field strength between July of 2012 and December of 2019 was performed. Neurodevelopmental outcomes were assessed using the Bayley Scales of Infant Development, 3rd Edition (BSID-III). There were no statistical differences in median age of assessment (1.5-T: 18 [12, 25] versus 3-T: 21 [11, 26], P=0.79), in mean BSID-III cognitive (1.5-T: 91 ± 14 versus 3-T: 90 ± 16, P=0.82), language (1.5-T: 92 ± 20 versus 3-T: 91 ± 20, P=0.91), and motor composite (1.5-T: 89 ± 15 versus 3-T: 87 ± 18, P=0.59) scores, subscales scores (for all, P>0.50), or in risk of abnormal neuromuscular exam (P=0.29) between neonates with left-CDH undergoing a 1.5-T versus 3-T MR imaging during fetal life. Additionally, the distribution of patients with average, mildly delayed, and severely delayed BSID-III scores was similar between the two groups (for all, P>0.50). The overall distribution of the composite scores in this CDH population was similar to the general population independent of exposure to 1.5-T or 3-T fetal MR imaging. Two 3-T patients (8%) and five 1.5-T patients (7%) scored within the significant delayed range for all BSID-III domains. Subjects with lower observed-to-expected fetal lung volume (O/E FLV) and postnatal need for ECMO had lower cognitive, language, motor, and subscales scores (for all, P<0.03) regardless of being imaged at 1.5-T versus 3-T. This preliminary study suggests that, compared to 1.5-T MR imaging, fetal exposure to 3-T MR imaging does not increase the risk of neurodevelopmental impairment in fetuses with left-CDH. Additional MR imaging studies in larger CDH cohorts and other fetal populations are needed to replicate and extend the present findings.

Identification of micrognathia by prenatal ultrasound may improve timely diagnosis and management of infants with Robin sequence.

Robin sequence (RS) is a craniofacial anomaly characterized by small jaw (micrognathia) with associated tongue base airway obstruction. With advances in fetal imaging, micrognathia may be detected prenatally. This study aims to determine if prenatal recognition of micrognathia offers any advantage over being unaware of the condition until after delivery and to assess if prenatal consultation for micrognathia adds benefits beyond merely noting the presence of the condition. Retrospective chart review examining cases from 01/01/2010 to 12/31/2020 at an urban tertiary medical center. Forty seven infants with RS were included. 40.4% (n=19) had micrognathia/retrognathia noted on prenatal ultrasound. 47.4% (n=9) of those 19 pregnancies saw a maternal fetal medicine (MFM) program with craniofacial consultation. Compared to 28 infants not diagnosed with micrognathia until after birth, the 19 infants identified prenatally required fewer transfers from birth hospital (p=0.02). Additionally, those referred to MFM with craniofacial consultation had shorter lengths of stay when airway intervention was required (p=0.05). Prenatal recognition of micrognathia may lead to early detection and management of RS. When RS is suspected, prenatal consultation with MFM and craniofacial team may further optimize care of the infant following delivery.

Advances in Maternal–Fetal Imaging

Advances in Maternal–Fetal Imaging

Fetal Cardiac Cine MRI with Doppler US Gating in Complex Congenital Heart Disease.

To apply Doppler US (DUS)-gated fetal cardiac cine MRI in clinical routine and investigate diagnostic performance in complex congenital heart disease (CHD) compared with that of fetal echocardiography. In this prospective study (May 2021 to March 2022), women with fetuses with CHD underwent fetal echocardiography and DUS-gated fetal cardiac MRI on the same day. For MRI, balanced steady-state free precession cine images were acquired in the axial and optional sagittal and/or coronal orientations. Overall image quality was assessed on a four-point Likert scale (from 1 = nondiagnostic to 4 = good image quality). The presence of abnormalities in 20 fetal cardiovascular features was independently assessed by using both modalities. The reference standard was postnatal examination results. Differences in sensitivities and specificities were determined by using a random-effects model. The study included 23 participants (mean age, 32 years ± 5 [SD]; mean gestational age, 36 weeks ± 1). Fetal cardiac MRI was completed in all participants. The median overall image quality of DUS-gated cine images was 3 (IQR, 2.5-4). In 21 of 23 participants (91%), underlying CHD was correctly assessed by using fetal cardiac MRI. In one case, the correct diagnosis was made by using MRI only (situs inversus and congenitally corrected transposition of the great arteries). Sensitivities (91.8% [95% CI: 85.7, 95.1] vs 93.6% [95% CI: 88.8, 96.2]; P = .53) and specificities (99.9% [95% CI: 99.2, 100] vs 99.9% [95% CI: 99.5, 100]; P > .99) for the detection of abnormal cardiovascular features were comparable between MRI and echocardiography, respectively. Using DUS-gated fetal cine cardiac MRI resulted in performance comparable with that of using fetal echocardiography for diagnosing complex fetal CHD.Keywords: Pediatrics, MR-Fetal (Fetal MRI), Cardiac, Heart, Congenital, Fetal Imaging, Cardiac MRI, Prenatal, Congenital Heart DiseaseClinical trial registration no. NCT05066399 Supplemental material is available for this article. © RSNA, 2023See also the commentary by Biko and Fogel in this issue.

Automated placental abruption identification using semantic segmentation, quantitative features, SVM, ensemble and multi-path CNN

The placenta is a fundamental organ throughout the pregnancy and the fetus’ health is closely related to its proper function. Because of the importance of the placenta, any suspicious placental conditions require ultrasound image investigation. We propose an automated method for processing fetal ultrasonography images to identify placental abruption using machine learning methods in this paper. The placental imaging characteristics are used as the semantic identifiers of the region of the placenta compared with the amniotic fluid and hard organs. The quantitative feature extraction is applied to the automatically identified placental regions to assign a vector of optical features to each ultrasonographic image. In the first classification step, two methods of kernel-based Support Vector Machine (SVM) and decision tree Ensemble classifier are elaborated and compared for identification of the abruption cases and controls. The Recursive Feature Elimination (RFE) is applied for optimizing the feature vector elements for the best performance of each classifier. In the second step, the deep learning classifiers of multi-path ResNet-50 and Inception-V3 are used in combination with RFE. The resulting performances of the algorithms are compared together to reveal the best classification method for the identification of the abruption status. The best results were achieved for optimized ResNet-50 with an accuracy of 82.88% ± SD 1.42% in the identification of placental abruption on the testing dataset. These results show it is possible to construct an automated analysis method with affordable performance for the detection of placental abruption based on ultrasound images.

Applicability of the Magnetic Resonance Technique during the Gestational Period: a narrative review

Over the last few decades, fetal imaging has led to significant improvements in prenatal counseling and postnatal therapy options, as obstetric MRI examination mainly plays a complementary role to the morphological ultrasound study when there is any diagnostic doubt or even to confirm If there is any abnormal finding in the conventional ultrasound exam. It is worth noting that there is no evidence that MRI causes biological effects in the fetus, the exams should be reserved for patients in the second and third trimester of pregnancy. Here, we performed a literature review to point out the importance of the applicability of gestational Magnetic Resonance for the identification of changes in embryonic development, gestational pathologies, maternal diseases, sequelae of infections, fetal malformations, diagnosis of placental deficiency and creation of three-dimensional prototypes for surgical planning and fetal visualization. From this narrative review it was possible to identify that the applicability of gestational MRI is related to the identification of alterations in embryonic development, gestational pathologies in general, maternal diseases, sequelae of infections, fetal malformations, diagnosis of placental deficiency and creation of prototypes three-dimensional (3D) models for surgical planning and fetal visualization.

Predicting Outcome of Congenital Cytomegalovirus Infection by Differentiating and Revisiting Severe versus Mild Prenatal Imaging Features

Introduction: Our objective was to evaluate the outcome of fetuses with first- and second-trimester fetal cytomegalovirus infection (CMVi) according to prenatal imaging patterns, especially fetuses presenting with mild imaging features (MF), being currently of uncertain prognosis. Material and Methods: In a retrospective study of 415 suspected CMVi cases, 59 cases were confirmed. Among prenatal imaging features, microcephaly, cortical disorder, and cerebellar hypoplasia as well as severe IUGR and fetal hydrops were considered as severe imaging features (SF). Other imaging features were considered as MF. Postnatal outcome was classified as “normal outcome,” “mild sequelae” characterized mainly by sensorineural disorder (SND) and “severe sequelae” characterized by cognitive impairment. Results: Only first-trimester (T1) and second-trimester (T2) CMVi cases were included in our study (n = 49) since all third-trimester cases (n = 10) had normal imaging and outcome. Sixteen fetuses had normal prenatal imaging and normal outcome, except one showing SND. Abnormal ultrasound findings were present in 33 fetuses, including SF noted in 16 fetuses, related exclusively to first-trimester CMVi. Termination of pregnancy was performed in 18 cases. Twelve first-trimester infected fetuses presented SF, whereas 6 fetuses (T1: n = 5, T2: n = 1) presented isolated MF. Four fetal deaths were encountered. Live-born babies with abnormal imaging included 10 fetuses with MF and one with SF. Among the 10 live babies with isolated MF, SND was encountered in 5 cases, whereas 5 children demonstrated normal outcome. Overall, 50% of our babies showing MF suffered from SND. No case of cognitive disorders was reported in babies showing only MF. Conclusion: SF were encountered only in first-trimester CMVi and should be distinguished from MF. Among our 10 live babies with prenatal MF following first- or second-trimester infection, 50% showed SND, whereas none presented severe sequelae. In 16 fetuses displaying normal fetal imaging, SND was encountered in one first-trimester case (6%).

Overcoming roadblocks in clinical innovation via high fidelity simulation: use of a phantom simulator to achieve FDA and IRB approval of a clinical trial of fetal embolization of vein of Galen malformations

BackgroundVein of Galen malformation (VOGM) is a rare, life-threatening vascular malformation in neonates and is treated with embolization. However, even at the most experienced centers, patients face high mortality and...

Institutional Evaluation of Fetal Neurology Consults and Postnatal Outcomes: A 10-Year Retrospective Cohort Review.

An increasing number of centers are offering fetal neurology consultation services; however, there is limited information available in overall institutional experiences. Data are lacking on the fetal characteristics, pregnancy course, and the influence of fetal consultation on perinatal outcomes. The aim of this study is to provide insight on the institutional fetal neurology consult process and areas of strengths and weaknesses. We performed a retrospective electronic chart review of fetal consults from April 2, 2009, to August 8, 2019, at Nationwide Children's Hospital. The objectives were to summarize clinical characteristics, agreement of prenatal and postnatal diagnoses based on best available imaging, and postnatal outcomes. Of the 174 maternal-fetal neurology consults placed, 130 qualified for inclusion based on data available for review. Of the 131 anticipated fetuses, 5 experienced fetal demise, 7 underwent elective termination, and 10 died in the postnatal period. The majority were admitted to the neonatal intensive care unit; 34 (31%) required supportive intervention for feeding, breathing, or hydrocephalus, and 10 (8%) experienced seizures during their neonatal intensive care unit (NICU) stay. Imaging results from 113 babies who had prenatal and postnatal imaging of the brain were analyzed based on the primary diagnosis. The most common malformations were as follows (prenatal % vs postnatal %): midline anomalies (37% vs 29%), posterior fossa abnormalities (26% vs 18%), and ventriculomegaly (14% vs 8%). Additional disorders of neuronal migration were not seen on fetal imaging but were present in 9% of the postnatal studies. Analysis of agreement between prenatal and postnatal diagnostic imaging for the 95 babies who had MRIs at both time points found moderate concordance (Cohen kappa: 0.62, 95% CI 0.5-0.73; percent agreement: 69%, 95% CI 60%-78%). Consult recommendations for neonatal blood tests affected postnatal care in 64 of 73 cases in which the infant survived and data were available. Establishing a multidisciplinary fetal clinic can provide timely counseling and create rapport with families to have continuity of care for birth planning and postnatal management. Prognosis based on radiographic prenatal diagnosis requires caution as some neonatal outcomes may vary considerably.

The segmentation effect of style transfer on fetal head ultrasound image: a study of multi-source data.

The generalization ability of the fetal head segmentation method is reduced due to the data obtained by different machines, settings, and operations. To keep the generalization ability, we proposed a Fourier domain adaptation (FDA) method based on amplitude and phase to achieve better multi-source ultrasound data segmentation performance. Given the source/target image, the Fourier domain information was first obtained using fast Fourier transform. Secondly, the target information was mapped to the source Fourier domain through the phase adjustment parameter α and the amplitude adjustment parameter β. Thirdly, the target image and the preprocessed source image obtained through the inverse discrete Fourier transform were used as the input of the segmentation network. Finally, the dice loss was computed to adjust α and β. In the existing transform methods, the proposed method achieved the best performance. The adaptive-FDA method provides a solution for the automatic preprocessing of multi-source data. Experimental results show that it quantitatively improves the segmentation results and model generalization performance.

The effect of colorization on the fetal lung heterogeneity index.

No previous studies have quantitatively assessed the effect of color tones on ultrasound texture analysis techniques. Our objective was to compare heterogeneity index (HI) between fetal lung images captured in grayscale and those same images after conversion to Ice and Sepia. Fetal lung images were obtained during medically indicated ultrasound examinations. We observed that HI is affected by the application of color tones to ultrasound images of the fetal lung. Therefore, for each type of biological tissue and color tone, determination of distinct HI nomograms and cut off points is recommended.

Tunicate swarm-based grey wolf algorithm for fetal heart chamber segmentation and classification: a heuristic-based optimal feature selection concept

Ultrasound image quality management and assessment are an important stage in clinical diagnosis. This operation is often carried out manually, which has several issues, including reliance on the operator’s experience, lengthy labor, and considerable intra-observer variance. As a result, automatic quality evaluation of Ultrasound images is particularly desirable in medical applications. This research work plans to perform the fetal heart chamber segmentation and classification using the novel intelligent technology named as hybrid optimization algorithm Tunicate Swarm-based Grey Wolf Algorithm (TS-GWA). Initially, the US fetal images data is collected and data undergoes the preprocessing using the total variation technique. From the preprocessed images, the optimal features are extracted using the TF-IDF approach. Then, Segmentation is processed on optimally selected features using Spatially Regularized Discriminative Correlation Filters (SRDCF) method. In the final step, the classification of fetal images is done using the Modified Long Short-Term Memory (MLSTM) Network. The fitness function behind the optimal feature selection as well as the hidden neuron optimization of MLSTM is the maximization of PSNR and minimization of MSE. The PSNR value is improved from 3.1 to 9.8 in the proposed method and accuracy of the proposed classification algorithm is improved from 1.9 to 12.13 compared to other existing techniques. The generalization ability and the adaptability of proposed TS-GWA method are described by conducting the various performance analysis. Extensive performance result shows that proposed intelligent techniques performs better than the existing segmentation methods.

About the Contributors

About the Contributors

Role of fetal magnetic resonance imaging in fetuses with congenital cytomegalovirus infection

Role of fetal magnetic resonance imaging in fetuses with congenital cytomegalovirus infection

An automated pipeline for quantitative T2* fetal body MRI and segmentation at low field.

Fetal Magnetic Resonance Imaging at low field strengths is emerging as an exciting direction in perinatal health. Clinical low field (0.55T) scanners are beneficial for fetal imaging due to their reduced susceptibility-induced artefacts, increased T2* values, and wider bore (widening access for the increasingly obese pregnant population). However, the lack of standard automated image processing tools such as segmentation and reconstruction hampers wider clinical use. In this study, we introduce a semi-automatic pipeline using quantitative MRI for the fetal body at low field strength resulting in fast and detailed quantitative T2* relaxometry analysis of all major fetal body organs. Multi-echo dynamic sequences of the fetal body were acquired and reconstructed into a single high-resolution volume using deformable slice-to-volume reconstruction, generating both structural and quantitative T2* 3D volumes. A neural network trained using a semi-supervised approach was created to automatically segment these fetal body 3D volumes into ten different organs (resulting in dice values > 0.74 for 8 out of 10 organs). The T2* values revealed a strong relationship with GA in the lungs, liver, and kidney parenchyma (R2 >0.5). This pipeline was used successfully for a wide range of GAs (17-40 weeks), and is robust to motion artefacts. Low field fetal MRI can be used to perform advanced MRI analysis, and is a viable option for clinical scanning.

Whole Exome Sequencing in an Enriched Population of Fetuses with Structural Anomalies

Exome Sequencing (ES) has emerged as a newer diagnostic modality with a reported detection rate of up to 20% in the prenatal setting among fetuses with multiple congenital anomalies. The objective of this study was to review the clinically-relevant detection rate among fetuses with congenital anomalies, given the number of anomalies and whether perinatal autopsy was performed. A single-center retrospective chart review was conducted for all pregnancies that underwent ES over a 10 year period from May 2012 – June 2022. Imaging modalities included high-resolution ultrasound, fetal echocardiography and in some cases fetal MR. Medical record review included maternal demographics, fetal imaging, and genetic diagnoses. 231 anomalous fetuses that underwent ES were identified. Initiation of ES occurred prenatally in 32%, at termination of pregnancy in 60%, neonatally in 11%, or following fetal demise in 6%. Of the exomes performed prenatally, 32.8% ended in termination while awaiting the ES results, 65.7% continued the pregnancy to delivery, and 1% resulted in fetal demise. The overall positive rate was 37.2%. The rate was higher in cases with multiple malformations (40%) versus single anomaly (31%). The rate was higher amongst those who underwent perinatal autopsy (51.8%) compared to those who did not (33.3%), which was found to be statistically significant (p = 0.01). Of note, both groups had a similar distribution of fetuses with multiple malformations (72% in the autopsy vs 64% in the no-autopsy group) that was not statistically different. Families who had a previously affected child had a higher diagnostic rate (53%) compared to those with a single occurrence (36%). A genetic diagnosis was made in 37.2% of anomalous fetuses undergoing ES in an enriched population. The utility of ES in prenatal diagnosis will certainly continue to increase as more individuals undergo testing and the positive diagnostic rate increases. Additionally, families in this setting are often experiencing grief and may learn meaningful information from ES that may assist in their coping.

A review on deep-learning algorithms for fetal ultrasound-image analysis.

Deep-learning (DL) algorithms are becoming the standard for processing ultrasound (US) fetal images. A number of survey papers in the field is today available, but most of them are focusing on a broader area of medical-image analysis or not covering all fetal US DL applications. This paper surveys the most recent work in the field, with a total of 153 research papers published after 2017. Papers are analyzed and commented from both the methodology and the application perspective. We categorized the papers into (i) fetal standard-plane detection, (ii) anatomical structure analysis and (iii) biometry parameter estimation. For each category, main limitations and open issues are presented. Summary tables are included to facilitate the comparison among the different approaches. In addition, emerging applications are also outlined. Publicly-available datasets and performance metrics commonly used to assess algorithm performance are summarized, too. This paper ends with a critical summary of the current state of the art on DL algorithms for fetal US image analysis and a discussion on current challenges that have to be tackled by researchers working in the field to translate the research methodology into actual clinical practice.

Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound.

Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations that are inconsistent in appearance and semantics. In this paper, we propose to improve visual representations of medical images via anatomy-aware contrastive learning (AWCL), which incorporates anatomy information to augment the positive/negative pair sampling in a contrastive learning manner. The proposed approach is demonstrated for automated fetal ultrasound imaging tasks, enabling the positive pairs from the same or different ultrasound scans that are anatomically similar to be pulled together and thus improving the representation learning. We empirically investigate the effect of inclusion of anatomy information with coarse- and fine-grained granularity, for contrastive learning and find that learning with fine-grained anatomy information which preserves intra-class difference is more effective than its counterpart. We also analyze the impact of anatomy ratio on our AWCL framework and find that using more distinct but anatomically similar samples to compose positive pairs results in better quality representations. Extensive experiments on a large-scale fetal ultrasound dataset demonstrate that our approach is effective for learning representations that transfer well to three clinical downstream tasks, and achieves superior performance compared to ImageNet supervised and the current state-of-the-art contrastive learning methods. In particular, AWCL outperforms ImageNet supervised method by 13.8% and state-of-the-art contrastive-based method by 7.1% on a cross-domain segmentation task. The code is available at https://github.com/JianboJiao/AWCL.

Does Peer Pressure Have The Same Effect On Intelligent Decision Support System As It Does On Human Decision Systems? Case Study: Fetal Ultrasound Movies

The aim of this paper is to explore whether the peer pressure environment makes Artificial Intelligence machines behave just like humans do. We propose a two-step multi-participant intelligent decision support system that uses a committee of deep learning algorithms and soft voting classifier to classify fetal ultrasound morphology images. The formed intelligent decision support system is subjected to peer pressure when used to classify fetal ultrasound movies. The results show that in 82% cases the peer pressure environment makes the intelligent decision system take the correct decision.

The growth and shape of the eyeball and crystalline lens in utero documented by fetal MR imaging

PurposeTo study the growth model, shape, and developmental relationship of lens and eyeball, we used two-dimensional Magnetic Resonance (MR) imaging to investigate gestationally age-related changes in the selected ocular parameters in vivo. Materials and methodsWe retrospectively reviewed the MR images from 126 fetuses ranging from 21 to 39 weeks' gestation. Ocular parameters on MR imaging of transverse plane were measured including lens diameter (LD), anteroposterior lens diameter (APLD), lens surface area (LS), globe diameter (GD), anteroposterior globe diameter (APGD), globe surface area (GS). The growth model of each biometric against gestational age (GA), aspect ratio of lens and globe (LD/APLD and GD/APGD), and growing relationship between the ratio of lens and globe surface area (LS/GS) were studied by statistical analysis. ResultsThe growth model of most biometry for gestational age is logarithmic, except for the diameter of the ocular globe (GD and APGD) showing a quadratic growth pattern. Our study showed that the lens was consistently larger in the transverse than the anteroposterior diameters during 21–39 weeks(P < 0.001). Besides, the ratio of surface area (LS/GS) was not significantly changing with GA(P = 0.4908), while the increase of LS was significantly accorded with that of GS(P < 0.001). ConclusionThe lens shape throughout fetal life may take part in the process, shape changing from vertical ellipsoid, spherical to transversal ellipsoid, based on the logarithmically increased ratio of lens transverse and anteroposterior diameters. In the meanwhile, the aspect ratio of eyeball in late fetal life may imply a gradually spherical shape during gestation. Nomogram data from this study may provide appropriate information about morphological changes in the fetal lens and the synchronous relationship between lens and eyeball.