The value of fetal magnetic resonance imaging in diagnosis of congenital anomalies of the fetal body: a systematic review and meta-analysis.

OBJECTIVES: To undertake a systematic review to assess the accuracy of fetal MRI in diagnosis of non-CNS congenital anomalies of the fetal body in comparison with antenatal ultrasound when correlated to postnatal diagnosis. METHODS: Searches were conducted from electronic databases, key journals and reference lists for eligible papers. Inclusion criteria was original research studies comparing the diagnostic results of antenatal ultrasound, fetal MRI and final postnatal diagnosis via imaging, surgery or post-mortem testing. Studies of CNS anomalies were excluded. Studies were assessed for risk of bias by two reviewers working independently and data was then extracted by a single reviewer. RESULTS: 12 studies were included with a total of 361 eligible patients who underwent USS and MRI and had a postnatal diagnosis. USS alone had a diagnostic accuracy of 60.6% whereas MRI had an improved diagnostic accuracy of 86.4%. The overall odds ratio was 0.86 (CI 0.202-1.519 and p-value < 0.01). CONCLUSION: Fetal MRI makes a significant contribution to accurate diagnosis of congenital abnormalities of the fetal body; especially in genito-urinary anomalies. More research is needed to improve the evidence base for the role of fetal MRI in diagnosis of congenital anomalies in other body systems.

Prenatal diagnosis of fetuses with absent/hypoplastic nasal bone in second-trimester using chromosomal microarray analysis.

BACKGROUND: Pathogenic copy number variants (pCNVs) are associated with fetal ultrasound anomalies, which can be efficiently identified through chromosomal microarray analysis (CMA). The primary objective of the present study was to enhance understanding of the genotype-phenotype correlation in fetuses exhibiting absent or hypoplastic nasal bones using CMA. METHODS: Enrolled in the present study were 94 cases of fetuses with absent/hypoplastic nasal bone, which were divided into an isolated absent/hypoplastic nasal bone group (n = 49) and a non-isolated group (n = 45). All pregnant women enrolled in the study underwent karyotype analysis and CMA to assess chromosomal abnormalities in the fetuses. RESULTS: Karyotype analysis and CMA detection were successfully performed in all cases. The results of karyotype and CMA indicate the presence of 11 cases of chromosome aneuploidy, with trisomy 21 being the most prevalent among them. A small supernumerary marker chromosome (sSMC) detected by karyotype analysis was further interpreted as a pCNV by CMA. Additionally, CMA detection elicited three cases of pCNVs, despite normal findings in their karyotype analysis results. Among them, one case of Roche translocation was identified to be a UPD in chromosome 15 with a low proportion of trisomy 15. Further, a significant difference in the detection rate of pCNVs was observed between non-isolated and isolated absent/hypoplastic nasal bone (24.44% vs. 8.16%, p < .05). CONCLUSION: The present study enhances the utility of CMA in diagnosing the etiology of absent or hypoplastic nasal bone in fetuses. Further, isolated cases of absent or hypoplastic nasal bone strongly suggest the presence of chromosomal abnormalities, necessitating genetic evaluation through CMA.

Automatic segmentation of 15 critical anatomical labels and measurements of cardiac axis and cardiothoracic ratio in fetal four chambers using nnU-NetV2.

BACKGROUND: Accurate segmentation of critical anatomical structures in fetal four-chamber view images is essential for the early detection of congenital heart defects. Current prenatal screening methods rely on manual measurements, which are time-consuming and prone to inter-observer variability. This study develops an AI-based model using the state-of-the-art nnU-NetV2 architecture for automatic segmentation and measurement of key anatomical structures in fetal four-chamber view images. METHODS: A dataset, consisting of 1,083 high-quality fetal four-chamber view images, was annotated with 15 critical anatomical labels and divided into training/validation (867 images) and test (216 images) sets. An AI-based model using the nnU-NetV2 architecture was trained on the annotated images and evaluated using the mean Dice coefficient (mDice) and mean intersection over union (mIoU) metrics. The model's performance in automatically computing the cardiac axis (CAx) and cardiothoracic ratio (CTR) was compared with measurements from sonographers with varying levels of experience. RESULTS: The AI-based model achieved a mDice coefficient of 87.11% and an mIoU of 77.68% for the segmentation of critical anatomical structures. The model's automated CAx and CTR measurements showed strong agreement with those of experienced sonographers, with respective intraclass correlation coefficients (ICCs) of 0.83 and 0.81. Bland-Altman analysis further confirmed the high agreement between the model and experienced sonographers. CONCLUSION: We developed an AI-based model using the nnU-NetV2 architecture for accurate segmentation and automated measurement of critical anatomical structures in fetal four-chamber view images. Our model demonstrated high segmentation accuracy and strong agreement with experienced sonographers in computing clinically relevant parameters. This approach has the potential to improve the efficiency and reliability of prenatal cardiac screening, ultimately contributing to the early detection of congenital heart defects.

RTSeg-net: A lightweight network for real-time segmentation of fetal head and pubic symphysis from intrapartum ultrasound images.

The segmentation of the fetal head (FH) and pubic symphysis (PS) from intrapartum ultrasound images plays a pivotal role in monitoring labor progression and informing crucial clinical decisions. Achieving real-time segmentation with high accuracy on systems with limited hardware capabilities presents significant challenges. To address these challenges, we propose the real-time segmentation network (RTSeg-Net), a groundbreaking lightweight deep learning model that incorporates innovative distribution shifting convolutional blocks, tokenized multilayer perceptron blocks, and efficient feature fusion blocks. Designed for optimal computational efficiency, RTSeg-Net minimizes resource demand while significantly enhancing segmentation performance. Our comprehensive evaluation on two distinct intrapartum ultrasound image datasets reveals that RTSeg-Net achieves segmentation accuracy on par with more complex state-of-the-art networks, utilizing merely 1.86 M parameters-just 6 % of their hyperparameters-and operating seven times faster, achieving a remarkable rate of 31.13 frames per second on a Jetson Nano, a device known for its limited computing capacity. These achievements underscore RTSeg-Net's potential to provide accurate, real-time segmentation on low-power devices, broadening the scope for its application across various stages of labor. By facilitating real-time, accurate ultrasound image analysis on portable, low-cost devices, RTSeg-Net promises to revolutionize intrapartum monitoring, making sophisticated diagnostic tools accessible to a wider range of healthcare settings.

Absent or hypoplastic nasal bone: What to tell the prospective parents?

BACKGROUND: Absent or hypoplastic nasal bone (AHNB) on first or second-trimester ultrasonography (USG) is an important soft marker of Down syndrome. However, due to its varied incidence in euploid and aneuploid fetuses, there is always a dilemma of whether to go for invasive fetal testing for isolated AHNB. This study aims to assess outcomes specifically within the context of Indian ethnicity women. MATERIALS AND METHODS: This was a prospective observational study. All patients who reported with AHNB in the first- or second-trimester USG were included. Genetic counseling was done, and noninvasive and invasive testing was offered. Chromosomal anomalies were meticulously recorded, and pregnancy was monitored. RESULTS: The incidence of AHNB in our study was 1.16% (47/4051). Out of 47 women with AHNB, the isolated condition was seen in 32 (0.78%) cases, while AHNB with structural anomalies was seen in nine cases (0.22%). Thirty-nine women opted for invasive testing. Six out of 47 had aneuploidy (12.7%), while two euploid cases (4.25%) developed nonimmune hydrops. The prevalence of Down syndrome in fetuses with AHNB was 8.5% (4/47) and 0.42% (17/4004) in fetuses with nasal bone present. This difference was statistically significant (p = .001). CONCLUSION: The results indicate that isolated AHNB cases should be followed by a comprehensive anomaly scan rather than immediately recommending invasive testing. However, invasive testing is required when AHNB is associated with other soft markers or abnormalities. As chromosomal microarray is more sensitive than standard karyotype in detecting chromosomal aberrations, it should be chosen over karyotype.

Prenatal diagnosis of interrupted aortic arch using high-definition flow render mode and spatiotemporal image correlation.

OBJECTIVES: To evaluate the clinical utility of two dimensional (2D) ultrasound combined with spatiotemporal image correlation (STIC) in diagnosing interrupted aortic arch (IAA) in fetal life. METHODS: A total of 53 cases of fetal IAA were diagnosed using 2D ultrasound combined with STIC, and 53 normal fetuses of the same gestational week were selected. These cases were retrospectively analyzed to assess the utility of employing 2D ultrasound combined with STIC in the diagnosis of IAA. RESULTS: 2D ultrasound combined with STIC detected 22 cases of type A IAA, 24 cases of type B IAA, and seven cases of type C IAA. Furthermore, combining 2D ultrasound with STIC enabled dynamic visualization of the IAA, aiding in prenatal diagnosis. The diagnostic coincidence rate of IAA was found to be higher in the HD-flow combined with STIC than that in the 2D combined with HD-flow. CONCLUSION: HD-flow combined with STIC can assist in diagnosing fetal IAA, and this technique has important clinical value.

Investigation on ultrasound images for detection of fetal congenital heart defects.

Congenital heart defects (CHD) are one of the serious problems that arise during pregnancy. Early CHD detection reduces death rates and morbidity but is hampered by the relatively low detection rates (i.e., 60%) of current screening technology. The detection rate could be increased by supplementing ultrasound imaging with fetal ultrasound image evaluation (FUSI) using deep learning techniques. As a result, the non-invasive foetal ultrasound image has clear potential in the diagnosis of CHD and should be considered in addition to foetal echocardiography. This review paper highlights cutting-edge technologies for detecting CHD using ultrasound images, which involve pre-processing, localization, segmentation, and classification. Existing technique of preprocessing includes spatial domain filter, non-linear mean filter, transform domain filter, and denoising methods based on Convolutional Neural Network (CNN); segmentation includes thresholding-based techniques, region growing-based techniques, edge detection techniques, Artificial Neural Network (ANN) based segmentation methods, non-deep learning approaches and deep learning approaches. The paper also suggests future research directions for improving current methodologies.

Accuracy and repeatability of fetal facial measurements in 3D ultrasound: A longitudinal study.

OBJECTIVE: Fetal face measurements in prenatal ultrasound can aid in identifying craniofacial abnormalities in the developing fetus. However, the accuracy and reliability of ultrasound measurements can be affected by factors such as fetal position, image quality, and the sonographer's expertise. This study assesses the accuracy and reliability of fetal facial measurements in prenatal ultrasound. Additionally, the temporal evolution of measurements is studied, comparing prenatal and postnatal measurements. METHODS: Three different experts located up to 23 facial landmarks in 49 prenatal 3D ultrasound scans from normal Caucasian fetuses at weeks 20, 26, and 35 of gestation. Intra- and inter-observer variability was obtained. Postnatal facial measurements were also obtained at 15 days and 1 month postpartum. RESULTS: Most facial landmarks exhibited low errors, with overall intra- and inter-observer errors of 1.01 mm and 1.60 mm, respectively. Landmarks on the nose were found to be the most reliable, while the most challenging ones were those located on the ears and eyes. Overall, scans obtained at 26 weeks of gestation presented the best trade-off between observer variability and landmark visibility. The temporal evolution of the measurements revealed that the lower face area had the highest rate of growth throughout the latest stages of pregnancy. CONCLUSIONS: Craniofacial landmarks can be evaluated using 3D fetal ultrasound, especially those located on the nose, mouth, and chin. Despite its limitations, this study provides valuable insights into prenatal and postnatal biometric changes over time, which could aid in developing predictive models for postnatal measurements based on prenatal data.

Ultrasonographic placental parameters at 11-13+6 weeks' gestation in the prediction of complications in pregnancy after assisted reproductive technology.

OBJECTIVE: To evaluate the performance of maternal factors, biophysical and biochemical markers at 11-13 + 6 weeks' gestation in the prediction of gestational diabetes mellitus with or without large for gestational age (GDM ± LGA) fetus and great obstetrical syndromes (GOS) among singleton pregnancy following in-vitro fertilisation (IVF)/embryo transfer (ET). MATERIALS AND METHODS: A prospective cohort study was conducted between December 2017 and January 2020 including patients who underwent IVF/ET. Maternal mean arterial pressure (MAP), ultrasound markers including placental volume, vascularisation index (VI), flow index (FI) and vascularisation flow index (VFI), mean uterine artery pulsatility index (mUtPI) and biochemical markers including placental growth factor (PlGF) and soluble fms-like tyrosine kinase-1 (sFlt-1) were measured at 11-13 + 6 weeks' gestation. Logistic regression analysis was performed to determine the significant predictors of complications. RESULTS: Among 123 included pregnancies, 38 (30.9%) had GDM ± LGA fetus and 28 (22.8%) had GOS. The median maternal height and body mass index were significantly higher in women with GDM ± LGA fetus. Multivariate logistic regression analysis demonstrated that in the prediction of GDM ± LGA fetus and GOS, there were significant independent contributions from FI MoM (area under curve (AUROC) of 0.610, 95% CI 0.492-0.727; p = 0.062) and MAP MoM (AUROC of 0.645, 95% CI 0.510-0.779; p = 0.026), respectively. CONCLUSION: FI and MAP are independent predictors for GDM ± LGA fetus and GOS, respectively. However, they have low predictive value. There is a need to identify more specific novel biomarkers in differentiating IVF/ET pregnancies that are at a higher risk of developing complications.

Statistical Characterisation of Fetal Anatomy in Simple Obstetric Ultrasound Video Sweeps.

OBJECTIVE: We present a statistical characterisation of fetal anatomies in obstetric ultrasound video sweeps where the transducer follows a fixed trajectory on the maternal abdomen. METHODS: Large-scale, frame-level manual annotations of fetal anatomies (head, spine, abdomen, pelvis, femur) were used to compute common frame-level anatomy detection patterns expected for breech, cephalic, and transverse fetal presentations, with respect to video sweep paths. The patterns, termed statistical heatmaps, quantify the expected anatomies seen in a simple obstetric ultrasound video sweep protocol. In this study, a total of 760 unique manual annotations from 365 unique pregnancies were used. RESULTS: We provide a qualitative interpretation of the heatmaps assessing the transducer sweep paths with respect to different fetal presentations and suggest ways in which the heatmaps can be applied in computational research (e.g., as a machine learning prior). CONCLUSION: The heatmap parameters are freely available to other researchers (https://github.com/agleed/calopus_statistical_heatmaps).

Malformations of cortical development: Fetal imaging and genetics.

BACKGROUND: Malformations of cortical development (MCD) are a group of congenital disorders characterized by structural abnormalities in the brain cortex. The clinical manifestations include refractory epilepsy, mental retardation, and cognitive impairment. Genetic factors play a key role in the etiology of MCD. Currently, there is no curative treatment for MCD. Phenotypes such as epilepsy and cerebral palsy cannot be observed in the fetus. Therefore, the diagnosis of MCD is typically based on fetal brain magnetic resonance imaging (MRI), ultrasound, or genetic testing. The recent advances in neuroimaging have enabled the in-utero diagnosis of MCD using fetal ultrasound or MRI. METHODS: The present study retrospectively reviewed 32 cases of fetal MCD diagnosed by ultrasound or MRI. Then, the chromosome karyotype analysis, single nucleotide polymorphism array or copy number variation sequencing, and whole-exome sequencing (WES) findings were presented. RESULTS: Pathogenic copy number variants (CNVs) or single-nucleotide variants (SNVs) were detected in 22 fetuses (three pathogenic CNVs [9.4%, 3/32] and 19 SNVs [59.4%, 19/32]), corresponding to a total detection rate of 68.8% (22/32). CONCLUSION: The results suggest that genetic testing, especially WES, should be performed for fetal MCD, in order to evaluate the outcomes and prognosis, and predict the risk of recurrence in future pregnancies.

A deep learning framework for identifying and segmenting three vessels in fetal heart ultrasound images.

BACKGROUND: Congenital heart disease (CHD) is one of the most common birth defects in the world. It is the leading cause of infant mortality, necessitating an early diagnosis for timely intervention. Prenatal screening using ultrasound is the primary method for CHD detection. However, its effectiveness is heavily reliant on the expertise of physicians, leading to subjective interpretations and potential underdiagnosis. Therefore, a method for automatic analysis of fetal cardiac ultrasound images is highly desired to assist an objective and effective CHD diagnosis. METHOD: In this study, we propose a deep learning-based framework for the identification and segmentation of the three vessels-the pulmonary artery, aorta, and superior vena cava-in the ultrasound three vessel view (3VV) of the fetal heart. In the first stage of the framework, the object detection model Yolov5 is employed to identify the three vessels and localize the Region of Interest (ROI) within the original full-sized ultrasound images. Subsequently, a modified Deeplabv3 equipped with our novel AMFF (Attentional Multi-scale Feature Fusion) module is applied in the second stage to segment the three vessels within the cropped ROI images. RESULTS: We evaluated our method with a dataset consisting of 511 fetal heart 3VV images. Compared to existing models, our framework exhibits superior performance in the segmentation of all the three vessels, demonstrating the Dice coefficients of 85.55%, 89.12%, and 77.54% for PA, Ao and SVC respectively. CONCLUSIONS: Our experimental results show that our proposed framework can automatically and accurately detect and segment the three vessels in fetal heart 3VV images. This method has the potential to assist sonographers in enhancing the precision of vessel assessment during fetal heart examinations.

Comparing three cardiothoracic ratio measurement techniques and creating multivariable scoring system to predict Bart's hydrops fetalis at 17-22 weeks' gestation.

To assess the diagnostic performance of three cardiothoracic (CT) ratio techniques, including diameter, circumference, and area, for predicting hemoglobin (Hb) Bart's disease between 17 and 22 weeks' gestation, and to create a multivariable scoring system using multiple ultrasound markers. Before invasive testing, three CT ratio techniques and other ultrasound markers were obtained in 151 singleton pregnancies at risk of Hb Bart's disease. CT diameter ratio demonstrated the highest sensitivity among the other techniques. Significant predictors included CT diameter ratio > 0.5, middle cerebral artery-peak systolic velocity (MCA-PSV) > 1.5 multiples of the median, and placental thickness > 3 cm. MCA-PSV exhibited the highest sensitivity (97.8%) in predicting affected fetuses. A multivariable scoring achieved excellent sensitivity (100%) and specificity (84.9%) for disease prediction. CT diameter ratio exhibited slightly outperforming the other techniques. Increased MCA-PSV was the most valuable ultrasound marker. Multivariable scoring surpassed single-parameter analysis in predictive capabilities.

IMU-Assisted Manual 3D-Ultrasound Imaging Using Motion-Constrained Swept-Fan Scans.

Three-dimensional (3D) ultrasonic imaging can enable post-facto plane of interest selection. It can be performed with devices such as wobbler probes, matrix probes, and sensor-based probes. Ultrasound systems that support 3D-imaging are expensive with added hardware complexity compared to 2D-imaging systems. An inertial measurement unit (IMU) can potentially be used for 3D-imaging by using it to track the motion of a one-dimensional array probe and constraining its motion in one degree of freedom (1-DoF) rotation (swept-fan). This work demonstrates the feasibility of an affordable IMU-assisted manual 3D-ultrasound scanner (IAM3US). A consumer-grade IMU-assisted 3D scanner prototype is designed with two support structures for swept-fan. After proper IMU calibration, an appropriate KF-based algorithm estimates the probe orientation during the swept-fan. An improved scanline-based reconstruction method is used for volume reconstruction. The evaluation of the IAM3US system is done by imaging a tennis ball filled with water and the head region of a fetal phantom. From fetal phantom reconstructed volumes, suitable 2D planes are extracted for biparietal diameter (BPD) manual measurements. Later, in-vivo data is collected. The novel contributions of this paper are (1) the application of a recently proposed algorithm for orientation estimation of swept-fan for 3D imaging, chosen based on the noise characteristics of selected consumer grade IMU (2) assessment of the quality of the 1-DoF swept-fan scan with a deflection detector along with monitoring of maximum angular rate during the scan and (3) two probe holder designs to aid the operator in performing the 1-DoF rotational motion and (4) end-to-end 3D-imaging system-integration. Phantom studies and preliminary in-vivo obstetric scans performed on two patients illustrate the usability of the system for diagnosis purposes.

On the use of contrastive learning for standard-plane classification in fetal ultrasound imaging.

BACKGROUND: To investigate the effectiveness of contrastive learning, in particular SimClr, in reducing the need for large annotated ultrasound (US) image datasets for fetal standard plane identification. METHODS: We explore SimClr advantage in the cases of both low and high inter-class variability, considering at the same time how classification performance varies according to different amounts of labels used. This evaluation is performed by exploiting contrastive learning through different training strategies. We apply both quantitative and qualitative analyses, using standard metrics (F1-score, sensitivity, and precision), Class Activation Mapping (CAM), and t-Distributed Stochastic Neighbor Embedding (t-SNE). RESULTS: When dealing with high inter-class variability classification tasks, contrastive learning does not bring a significant advantage; whereas it results to be relevant for low inter-class variability classification, specifically when initialized with ImageNet weights. CONCLUSIONS: Contrastive learning approaches are typically used when a large number of unlabeled data is available, which is not representative of US datasets. We proved that SimClr either as pre-training with backbone initialized via ImageNet weights or used in an end-to-end dual-task may impact positively the performance over standard transfer learning approaches, under a scenario in which the dataset is small and characterized by low inter-class variability.

Importance of Prenatal Diagnosis of Ileal Atresia in Gestational Diabetes Cases.

BACKGROUND Maldevelopment of the fetal bowel can result in the rare condition of intestinal atresia, which results in congenital bowel obstruction. This report describes a case of prenatal diagnosis of fetal ileal atresia at 22 weeks' gestation. CASE REPORT Here, we present a 24-year old woman who was 22 weeks into her first pregnancy when she underwent routine fetal ultrasound. She was diagnosed with gestational diabetes mellitus. Her body mass index was normal and she had normal weight gain. The ultrasonographic examination performed revealed a hyperechoic bowel and a small dilatation of the bowel. The couple was counselled for possible intestinal atresia and its postnatal implications. At 33 weeks of gestation, polyhydramnios appeared, and the intestinal distension was much more pronounced, with hyperechoic debris in the intestinal lumen (succus-entericus). After birth, surgery was performed and we concluded the patient had type II atresia, which was surgically treated. CONCLUSIONS This report has highlighted the importance of antenatal ultrasound in detecting fetal abnormalities, and has shown that rare conditions such as intestinal atresia can be accurately diagnosed and successfully managed. Surgical correction, if implemented promptly after stabilizing the general condition, can have a relatively good prognosis. Coexisting fetal ileal atresia and gestational diabetes mellitus are rare occurrences, which can make each condition even more difficult to treat.

Deep-learning computer vision can identify increased nuchal translucency in the first trimester of pregnancy.

OBJECTIVE: Many fetal anomalies can already be diagnosed by ultrasound in the first trimester of pregnancy. Unfortunately, in clinical practice, detection rates for anomalies in early pregnancy remain low. Our aim was to use an automated image segmentation algorithm to detect one of the most common fetal anomalies: a thickened nuchal translucency (NT), which is a marker for genetic and structural anomalies. METHODS: Standardized mid-sagittal ultrasound images of the fetal head and chest were collected for 560 fetuses between 11 and 13 weeks and 6 days of gestation, 88 (15.7%) of whom had an NT thicker than 3.5 mm. Image quality was graded as high or low by two fetal medicine experts. Images were divided into a training-set (n = 451, 55 thick NT) and a test-set (n = 109, 33 thick NT). We then trained a U-Net convolutional neural network to segment the fetus and the NT region and computed the NT:fetus ratio of these regions. The ability of this ratio to separate thick (anomalous) NT regions from healthy, typical NT regions was first evaluated in ground-truth segmentation to validate the metric and then with predicted segmentation to validate our algorithm, both using the area under the receiver operator curve (AUROC). RESULTS: The ground-truth NT:fetus ratio detected thick NTs with 0.97 AUROC in both the training and test sets. The fetus and NT regions were detected with a Dice score of 0.94 in the test set. The NT:fetus ratio based on model segmentation detected thick NTs with an AUROC of 0.96 relative to clinician labels. At a 91% specificity, 94% of thick NT cases were detected (sensitivity) in the test set. The detection rate was statistically higher (p = 0.003) in high versus low-quality images (AUROC 0.98 vs. 0.90, respectively). CONCLUSION: Our model provides an explainable deep-learning method for detecting increased NT. This technique can be used to screen for other fetal anomalies in the first trimester of pregnancy.