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.

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.

Glucose control during pregnancy in patients with type 1 diabetes correlates with fetal hemodynamics: a prospective longitudinal study.

BACKGROUND: Maternal diabetes adversely affects fetal cardiovascular system development. Previous studies have reported that the fetuses of mothers with diabetes exhibit both structural and functional changes; nevertheless, prior studies have not examined the association between glucose control and fetal cardiac morphology and performance. Thus, the objective was to determine the association between fetal cardiac morphology and function and maternal glucose control in type 1 diabetes and to compare the differences in measured cardiac parameters between the fetuses of mothers with diabetes and healthy controls. METHODS: In this prospective, longitudinal case-control study - including 62 pregnant women with type 1 diabetes mellitus and 30 healthy pregnant women - fetal cardiac assessment using B-mode, M-mode, and spectral pulsed-wave Doppler was performed in the second and third trimesters. In women with T1DM, glycated hemoglobin and data obtained from glucose sensors - including the percentage of time in, below, and above the range (TIR, TBR, and TAR, respectively), and coefficient of variation (CV) - were analyzed across three time periods: the last menstrual period to 13 (V1), 14-22 (V2), and 23-32 weeks (V3) of gestation. Fetal cardiac indices were compared between groups, and the correlation between glucose control and fetal cardiac indices was assessed. RESULTS: At 28-32 weeks, the fetuses of women with T1DM exhibited increased left ventricular end-diastolic length, relative interventricular septum thickness, right ventricular cardiac output, and pulmonary valve peak systolic velocity compared with healthy controls. At 18-22 weeks, pulmonary and aortic valve diameters, left and right ventricular stroke volumes, and left cardiac output inversely correlated with the CV and glycated hemoglobin levels at V1 and V2. Furthermore, at 28-32 weeks, pulmonary and aortic valve diameters, left ventricular stroke volume, cardiac output, and right/left atrioventricular valve ratio inversely correlated with the TBR at V1, V2, and V3. Moreover, diastolic functional parameters correlated with the TAR and glycated hemoglobin levels, particularly after the first trimester. CONCLUSION: In women with T1DM, maternal hyperglycemia during pregnancy correlates with fetal diastolic function, whereas glucose variability and hypoglycemia inversely correlate with fetal left ventricular systolic function in the second and third trimesters.

Fetal Cardiac MRI Using Doppler US Gating: Emerging Technology and Clinical Implications.

Fetal cardiac MRI using Doppler US gating is an emerging technique to support prenatal diagnosis of congenital heart disease and other cardiovascular abnormalities. Analogous to postnatal electrocardiographically gated cardiac MRI, this technique enables directly gated MRI of the fetal heart throughout the cardiac cycle, allowing for immediate data reconstruction and review of image quality. This review outlines the technical principles and challenges of cardiac MRI with Doppler US gating, such as loss of gating signal due to fetal movement. A practical workflow of patient preparation for the use of Doppler US-gated fetal cardiac MRI in clinical routine is provided. Currently applied MRI sequences (ie, cine or four-dimensional flow imaging), with special consideration of technical adaptations to the fetal heart, are summarized. The authors provide a literature review on the clinical benefits of Doppler US-gated fetal cardiac MRI for gaining additional diagnostic information on cardiovascular malformations and fetal hemodynamics. Finally, future perspectives of Doppler US-gated fetal cardiac MRI and further technical developments to reduce acquisition times and eliminate sources of artifacts are discussed. Keywords: MR Fetal, Ultrasound Doppler, Cardiac, Heart, Congenital, Obstetrics, Fetus Supplemental material is available for this article. © RSNA, 2024.

Fetal cardiac functional changes in pregnancies with Behcet's disease: A case-control study.

BACKGROUND: Behcet's disease usually progresses with remission during pregnancy, but early subtle changes might be detected in the heart of these fetuses due to inflammation. AIMS: We aimed to evaluate the cardiac functions in fetuses of pregnant women with Behcet's disease (BD). STUDY DESIGN: Prospective case-control study. SUBJECTS: This prospective study enrolled pregnant women diagnosed with Behcet's disease before pregnancy. Twenty-four pregnancies with Behcet's disease and 48 healthy pregnancies were included at 32-34 gestational weeks. OUTCOME MEASURES: Pulsed-wave Doppler and tissue Doppler imaging (TDI) were used to assess cardiac functions. RESULTS: Right ventricle (RV) E (early) wave and left ventricle (LV) E were significantly increased in pregnancies with BD (p = .008, p = .041, respectively). Decreased right ventricle E' (peak systolic velocity) was detected with TDI in the case group (6.2 ± 0.5, p < .001). E/E' ratios for RV and LV were significantly increased in the case group (p < .001, p = .001, respectively). The correlation between the duration of the disease and fetal cardiac functions was also evaluated. For RV, E (r = 0.735, p < .001), E' (r = -0.735, p < .001), E/E' (r = 0.894, p < .001), were strongly correlated with the disease duration. The study also showed the correlation between disease duration and LV E' (r = -0.735, p = .005), LV E (r = 0.750, p < .001), and LV E/E' (r = 0.820, p < .001). CONCLUSION: This is the first study to evaluate the fetal cardiac functions in fetuses of pregnancies with BD. Although BD usually progresses with remission during pregnancy, early subclinical diastolic changes might occur in the heart of these fetuses due to inflammation.

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.

Predicting High-Risk Fetal Cardiac Disease Anticipated to Need Immediate Postnatal Stabilization and Intervention with Planned Pediatric Cardiac Operating Room Delivery.

BACKGROUND: Distances between delivery and cardiac services can make the care of fetuses with cardiac disease at risk of acute cardiorespiratory instability at birth a challenge. In 2013 we implemented a fetal echocardiography-based algorithm targeting fetuses considered high risk for acute cardiorespiratory instability at ≤2 hours of birth for delivery in our pediatric cardiac operating room of our children's hospital, and, herein, examine our experience. METHODS AND RESULTS: We reviewed maternal and postnatal medical records of all fetuses with cardiac disease encountered January 2013 to March 2022 considered high risk for acute cardiorespiratory instability. Secondary analysis was performed including all fetuses with diagnoses of d-transposition of the great arteries/intact ventricular septum (d-TGA/IVS) and hypoplastic left heart syndrome (HLHS) encountered over the study period. Forty fetuses were considered high risk for acute cardiorespiratory instability: 15 with d-TGA/IVS and 7 with HLHS with restrictive atrial septum, 4 with absent pulmonary valve syndrome, 3 with obstructed anomalous pulmonary veins, 2 with severe Ebstein anomaly, 2 with thoracic/intracardiac tumors, and 7 others. Pediatric cardiac operating room delivery occurred for 33 but not for 7 (5 with d-TGA/IVS, 2 with HLHS with restrictive atrial septum). For high-risk cases, fetal echocardiography had a positive predictive value of 50% for intervention/extracorporeal membrane oxygenation/death at ≤2 hours and 70% at ≤24 hours. Of "low-risk" cases, 6/46 with d-TGA/IVS and 0/45 with HLHS required intervention at ≤2 hours. Fetal echocardiography for predicting intervention/extracorporeal membrane oxygenation/death at ≤2 hours had a sensitivity of 67%, specificity 93%, and positive and negative predictive values of 80% and 87%, respectively, for d-TGA/IVS, and 100%, 95%, 71%, and 100% for HLHS, respectively. CONCLUSIONS: Fetal echocardiography can predict the need for urgent intervention in a majority with d-TGA/IVS and HLHS and in half of the entire spectrum of high-risk cardiac disease.

Variation in prenatal surveillance and management of anti-SSA/Ro autoantibody positive pregnancies.

OBJECTIVE: To describe international surveillance and treatment strategies for managing anti-SSA/Ro autoantibody positive pregnancies. STUDY DESIGN: An electronic REDCap questionnaire was distributed to Fetal Heart Society and North American Fetal Therapy Network members which queried institution-based risk stratification, surveillance methods/frequency, conduction abnormality treatments, and postnatal anti-SSA/Ro pregnancy assessment. RESULTS: 101 responses from 59 centers (59% US, 17% international) were collected. Most (79%) do not risk stratify pregnancies by anti-SSA/Ro titer; those that do use varied cutoff values. Many pregnant rheumatology patients are monitored for cardiac abnormalities regardless of maternal anti-SSA/Ro status. Surveillance strategies were based on maternal factors (anti-SSA/Ro status 85%, titer 25%, prior affected child 79%) and monitoring durations varied. Most respondents treat 2° and 3° fetal atrioventricular block, commonly with dexamethasone and/or IVIG. CONCLUSIONS: Wide variation exists in current fetal cardiac surveillance and treatment for anti-SSA/Ro autoantibody positive pregnancies, highlighting the need for evidence-based protocols to optimize care.

Subclinical cardiac impairments in fetuses conceived through assisted reproductive technology by speckle tracking echocardiography.

OBJECTIVES: To evaluate the changes of cardiac morphology and function in fetuses conceived through assisted reproductive technologies (ART) by speckle tracking echocardiography. METHODS: A retrospective study was conducted in 101 spontaneously conceived (SC) fetuses and 99 ART-conceived ones. Fetal echocardiography was performed, fetal cardiac morphology and function were analyzed using two-dimensional speckle tracking software, including global sphericity index (GSI), global longitudinal strain (GLS), fractional area change (FAC) of the left and right ventricles, as well as segmental sphericity index (SI), end-diastolic diameter (ED), and fractional shortening (FS) in 24 segments. RESULTS: Compared to the SC fetuses, the ART-conceived fetuses exhibited decreased GSI (median [interquartile range], 1.22 [1.16-1.27] vs. 1.18 [1.11-1.24], p=0.007), decreased right ventricular GLS (24.9 [21.5-27.6] vs. 23.2 [20.4-26.8], p=0.026), and decreased right ventricular FAC (mean ± standard deviation, 39.7 ± 6.4 vs. 37.2 ± 7.1, p=0.003). Analysis of the 24 segments showed that ART-conceived fetuses had reduced SI in the apical segments of right ventricle and increased ED in several segments of the right ventricle. CONCLUSIONS: Fetuses conceived through ART had a more spherical shape of the global heart and predominantly right-sided cardiac remodeling and systolic function impairment.

Fetal hemodynamic changes and mitochondrial dysfunction in myocardium and brain tissues in response to anemia: a lesson from hemoglobin Bart's disease.

OBJECTIVE: Whether or not the effects of anemia in the early phase, while the fetuses attempts to increase cardiac output to meet oxygen requirement in peripheral organs, is detrimental to the fetal developing vital organs is little-known. The objective of this is to compare prenatal cardiovascular changes and post-abortal cellular damages in the myocardium as a pumping organ and the brain as a perfused organ between anemic fetuses (using fetal Hb Bart's disease as a study model) in pre-hydropic phase and non-anemic fetuses. METHODS: Fetuses affected by Hb Bart's disease and non-anemic fetuses at 16-22 weeks were recruited to undergo comprehensive fetal echocardiography. Cord blood analysis was used to confirm the definite diagnosis of fetal Hb Bart's disease and normal fetuses. Fetal cardiac and brain tissues were collected shortly after pregnancy termination for the determination of oxidative stress and mitochondrial function, including mitochondrial ROS production and mitochondrial membrane changes. RESULTS: A total of 18 fetuses affected by Hb Bart's disease and 13 non-anemic fetuses were recruited. The clinical characteristics of both groups were comparable. The affected fetuses showed a significant increase in cardiac dimensions, cardiac function, cardiac output and brain circulation without deteriorating cardiac contractility and preload. However, in the affected fetuses, mitochondrial dysfunction was clearly demonstrated in brain tissues and in the myocardium, as indicated by a significant increase in the membrane potential change (p-value < 0.001), and a significant increase in ROS production in brain tissues, with a trend to increase in myocardium. The findings indicated cellular damage in spite of good clinical compensation. CONCLUSION: The new insight is that, in response to fetal anemia, fetal heart increases in size (dilatation) and function to increase cardiac output and blood flow velocity to provide adequate tissue perfusion, especially brain circulation. However, the myocardium and brain showed a significant increase in mitochondrial dysfunction, suggesting cellular damage secondary to anemic hypoxia. The compensatory increase in circulation could not completely prevent subtle brain and heart damage.

Prenatal diagnosis of fetal left ventricular diverticulum: 3D virtual and physical reconstruction models.

Congenital diverticulum is a very rare congenital heart disease. 3D virtual and physical models from ultrasound scan data provide a spatial visualization and better understanding of congenital heart disease to the parents and support possible surgical procedures.

HFSCCD: A Hybrid Neural Network for Fetal Standard Cardiac Cycle Detection in Ultrasound Videos.

In the fetal cardiac ultrasound examination, standard cardiac cycle (SCC) recognition is the essential foundation for diagnosing congenital heart disease. Previous studies have mostly focused on the detection of adult CCs, which may not be applicable to the fetus. In clinical practice, localization of SCCs needs to recognize end-systole (ES) and end-diastole (ED) frames accurately, ensuring that every frame in the cycle is a standard view. Most existing methods are not based on the detection of key anatomical structures, which may not recognize irrelevant views and background frames, results containing non-standard frames, or even it does not work in clinical practice. We propose an end-to-end hybrid neural network based on an object detector to detect SCCs from fetal ultrasound videos efficiently, which consists of 3 modules, namely Anatomical Structure Detection (ASD), Cardiac Cycle Localization (CCL), and Standard Plane Recognition (SPR). Specifically, ASD uses an object detector to identify 9 key anatomical structures, 3 cardiac motion phases, and the corresponding confidence scores from fetal ultrasound videos. On this basis, we propose a joint probability method in the CCL to learn the cardiac motion cycle based on the 3 cardiac motion phases. In SPR, to reduce the impact of structure detection errors on the accuracy of the standard plane recognition, we use XGBoost algorithm to learn the relation knowledge of the detected anatomical structures. We evaluate our method on the test fetal ultrasound video datasets and clinical examination cases and achieve remarkable results. This study may pave the way for clinical practices.

Pre-intervention myocardial stress is a good predictor of aortic valvoluplasty outcome for fetal critical aortic stenosis and evolving HLHS.

Fetal critical aortic stenosis with evolving hypoplastic left heart syndrome (CAS-eHLHS) causes biomechanical and functional aberrations, leading to a high risk of progression to hypoplastic left heart syndrome (HLHS) at birth. Fetal aortic valvuloplasty (FAV) can resolve outflow obstruction and may reduce progression risk. However, it is currently difficult to accurately predict which patients will respond to the intervention and become functionally biventricular (BV) at birth, as opposed to becoming functionally univentricular (UV). This prediction is important for patient selection, parental counselling, and surgical planning. Therefore, we investigated whether biomechanics parameters from pre-FAV image-based computations could robustly distinguish between CAS-eHLHS cases with BV or UV outcomes in a retrospective cohort. To do so we performed image-based finite element biomechanics modelling of nine CAS-eHLHS cases undergoing intervention and six healthy fetal control hearts, and found that a biomechanical parameter, peak systolic myofibre stress, showed a uniquely large difference between BV and UV cases, which had a larger magnitude effect than echocardiography parameters. A simplified equation was derived for quick and easy estimation of myofibre stress from echo measurements via principal component analysis. When tested on a retrospective cohort of 37 CAS-eHLHS cases, the parameter outperformed other parameters in predicting UV versus BV outcomes, and thus has a high potential of improving outcome predictions, if incorporated into patient selection procedures. Physiologically, high myocardial stresses likely indicate a healthier myocardium that can withstand high stresses and resist pathological remodelling, which can explain why it is a good predictor of BV outcomes. KEY POINTS: Predicting the morphological birth outcomes (univentricular versus biventricular) of fetal aortic valvuloplasty for fetal aortic stenosis with evolving HLHS is important for accurate patient selection, parental counselling and management decisions. Computational simulations show that a biomechanics parameter, pre-intervention peak systolic myofibre stress, is uniquely robust in distinguishing between such outcomes, outperforming all echo parameters. An empirical equation was developed to quickly compute peak systolic myofibre stress from routine echo measurements and was the best predictor of outcomes among a wide range of parameters tested.

Quantitative Analysis of Morphology and Function in the Fetal Heart with Severe Tricuspid Regurgitation by Speckle Tracking Imaging.

Morphology and function in a fetal heart with severe tricuspid regurgitation remains challenging. The aim of this study was to assess cardiac morphology and function in fetuses with severe tricuspid regurgitation by fetal heart quantification (HQ) and to assess the practical value of fetal HQ. Clinical information was analyzed for 63 pregnant women who underwent fetal cardiac ultrasonography. The women were divided into those who had a fetus with severe tricuspid regurgitation (n = 20) and those with a normal fetus (n = 40). The global sphericity index (GSI), fractional area change (FAC), and global longitudinal strain (GLS) of both ventricles and the sphericity index (SI) and fractional shortening (FS) of 24 segments were quantified by fetal HQ using speckle tracking imaging. Fetuses with severe tricuspid regurgitation had a significantly lower GSI (1.14 ± 0.10 vs. 1.26 ± 0.08, p < 0.001) and a higher GSI Z-score (-0.98 ± 1.01 vs. 0.25 ± 0.87, p < 0.001) as well as a significantly lower right ventricular FAC (36.50 ± 7.34% vs. 45.19 ± 3.39%, p < 0.001), FAC Z-score (-1.02 ± 1.41 vs. 0.49 ± 0.74, p < 0.001), and GLS (-21.01 ± 5.66% vs. 45.19 ± 3.49%, p < 0.001). The SI and SI Z-score were significantly lower in segments 1-18 of the right ventricle in fetuses with severe tricuspid regurgitation (p < 0.05); furthermore, FS of segments 1-12 and 19-24 and the FS Z-score of segments 18-24 were significantly lower in fetuses with severe tricuspid regurgitation (p < 0.05). Fetal HQ is useful for evaluation of cardiac morphology and function in fetuses with severe tricuspid regurgitation and can provide important reference information for both clinical diagnosis and treatment.

Do Maternal Heart Diseases Affect Fetal Cardiac Functions?

OBJECTIVES: To investigate whether fetal cardiac function is affected by underlying heart disease in pregnant women. METHODS: A total of 100 pregnant women who were ≥34 gestational weeks were included in the study, 40 in the maternal heart disease (MHD) group diagnosed with heart disease and 60 in the control group. All cardiac diseases in pregnant women were diagnosed preconceptionally and categorized according to the New York Heart Association (NYHA) classification system. Fetal cardiac functions of study groups were evaluated by M-mode, color tissue Doppler imaging (c-TDI), and pulsed wave Doppler. RESULTS: Tricuspid annular plane systolic excursion and myocardial performance index (MPI) values were significantly higher and isovolumetric relaxation time was prolonged in the MHD group. The MPI value was found higher in MHD group with NYHA Class II compared to those with NYHA Class I. No significant change in any of the fetal tricuspid annular peak velocity values measured by c-TDI in the MHD group. There were no differences in fetal cardiac functions and perinatal outcomes between pregnant women with acquired and congenital heart diseases. Patients in NYHA Class II had lower birth weight, 1st and 5th minute APGAR scores, and higher neonatal intensive care unit admission rates. CONCLUSIONS: Underlying heart diseases in pregnant women can cause alterations in the systolic and diastolic function of the fetal heart. High fetal MPI values detected in cardiac patients may indicate that cardiac pathologies during pregnancy affect fetal cardiac globular myocardial function. Cardiac pathologies that progress with restricted physical activity may cause changes in fetal cardiac function and may be associated with adverse perinatal outcomes.

Left Ventricular Vortex Characteristics in Fetuses With Coarctation of the Aorta by Blood Speckle-Tracking Echocardiography.

OBJECTIVES: The aims of this study were to assess the vortex characteristics of left ventricle (LV) in fetuses with coarctation of the aorta (CoA) using high-frame rate ultrasound with blood speckle-tracking (BST) and explore its relationships with cardiac function and morphology parameters. METHODS: Thirty fetuses with CoA and 30 gestational-age matched normal fetuses were included in this cross-sectional study. The area, length, width, and position of the vortex in the LV were recorded and quantitatively analyzed by BST echocardiography. The associations of vortex properties with ventricular function and morphology were also determined. RESULTS: Based on BST imaging, the LV vortex can be observed in 93% of the fetuses. The fetuses with CoA exhibited significantly larger and wider vortex than the controls (P < .05). Linear regression analysis indicated that vortex area was positively related to sphericity index of LV as well as isovolumic relaxation time (r = .52, P = .003 and r = .42, P = .021). There was a negative correlation between vortex area and mitral valve size (r = -.443, P = .014). No significant association was found between vortex area and myocardial performance index and aortic isthmus size. CONCLUSIONS: It is feasible to quantitatively evaluate the left ventricular vortex in fetuses by BST. The fetuses with CoA exhibited greater vortex area and width, and the altered vortex property is associated with geometry of LV. This will facilitate our comprehension of the unique flow patterns and early cardiac remodeling in fetuses with CoA.

An intelligent quantification system for fetal heart rhythm assessment: A multicenter prospective study.

BACKGROUND: The motion relationship and time intervals of the pulsed-wave Doppler (PWD) spectrum are essential for diagnosing fetal arrhythmia. However, few technologies currently are available to automatically calculate fetal cardiac time intervals (CTIs). OBJECTIVE: The purpose of this study was to develop a fetal heart rhythm intelligent quantification system (HR-IQS) for the automatic extraction of CTIs and establish the normal reference range for fetal CTIs. METHODS: A total of 6498 PWD spectrums of 2630 fetuses over the junction between the left ventricular inflow and outflow tracts were recorded across 14 centers. E, A, and V waves were manually labeled by 3 experienced fetal cardiologists, with 17 CTIs extracted. Five-fold cross-validation was performed for training and testing of the deep learning model. Agreement between the manual and HR-IQS-based values was evaluated using the intraclass correlation coefficient and Spearman's rank correlation coefficient. The Jarque-Bera test was applied to evaluate the normality of CTIs' distributions, and the normal reference range of 17 CTIs was established with quantile regression. Arrhythmia subset was compared with the non-arrhythmia subset using the Mann-Whitney U test. RESULTS: Significant positive correlation (P <.001) and moderate-to-excellent consistency (P <.001) between the manual and HR-IQS automated measurements of CTIs was found. The distribution of CTIs was non-normal (P <.001). The normal range (2.5th to 97.5th percentiles) was successfully established for the 17 CTIs. CONCLUSIONS: Using our HR-IQS is feasible for the automated calculation of CTIs in practice and thus could provide a promising tool for the assessment of fetal rhythm and function.

Advances in the Application of Artificial Intelligence in Fetal Echocardiography.

Congenital heart disease is a severe health risk for newborns. Early detection of abnormalities in fetal cardiac structure and function during pregnancy can help patients seek timely diagnostic and therapeutic advice, and early intervention planning can significantly improve fetal survival rates. Echocardiography is one of the most accessible and widely used diagnostic tools in the diagnosis of fetal congenital heart disease. However, traditional fetal echocardiography has limitations due to fetal, maternal, and ultrasound equipment factors and is highly dependent on the skill level of the operator. Artificial intelligence (AI) technology, with its rapid development utilizing advanced computer algorithms, has great potential to empower sonographers in time-saving and accurate diagnosis and to bridge the skill gap in different regions. In recent years, AI-assisted fetal echocardiography has been successfully applied to a wide range of ultrasound diagnoses. This review systematically reviews the applications of AI in the field of fetal echocardiography over the years in terms of image processing, biometrics, and disease diagnosis and provides an outlook for future research.