Fetal Cardiac Imaging Research Articles

Birth in the Operating Room for Immediate Cardiac Surgery: A Rare but Effective Strategy.

Background: With significant advancements in fetal cardiac imaging, patients with complex congenital heart disease (CHD) carrying a high risk for postnatal demise are now being diagnosed earlier. We sought to assess an interdisciplinary strategy for delivering these children in an operating room (OR) adjacent to a cardiac OR for immediate surgery or stabilization. Methods: All children prenatally diagnosed with CHD at risk for immediate postnatal hemodynamic instability and cardiogenic shock who were delivered in the operating room (OR) between 2012 and 2023 in which the senior author was consulted were included. Results: Eight patients were identified. Six (75%) patients were operated on day-of-life zero, all requiring obstructed total anomalous pulmonary venous return (TAPVR) repair. Of these six patients, 2 (33%) required a simultaneous Norwood procedure, 2 (33%) required pulmonary artery unifocalization and modified Blalock-Taussig-Thomas shunt, and 2 (33%) patients had repair of obstructed mixed TAPVR. The remaining 2 patients potentially planned for immediate surgery had nonimmune hydrops fetalis and went into cardiogenic shock at 12 and 72 hours postnatally, requiring a novel Norwood procedure with left-ventricular exclusion for severe aortic/mitral valve insufficiency. The median ventilation and inpatient durations were 19 [IQR: 11-26] days and 41 [IQR: 32-128] days, respectively. Three(38%) patients required one or more in-hospital reoperations. Subsequent staged procedures included Glenn (n = 5), Fontan (n = 3), biventricular repair (n = 2), ventricular assist device placement (n = 1), and heart transplant (n = 1). Median follow-up was 5.7 [IQR:1.3-7.8] years. The five-year postoperative survival was 88% (n = 7/8). Conclusion: While children with these diagnoses have historically had poor survival, the strategy of birth in the OR adjacent to a cardiac OR where emergent surgery is planned is a potentially promising strategy with excellent clinical outcomes. However, this is a high-resource strategy whose feasibility in any program requires thoughtful assessment.

Structural and functional fetal cardiac imaging using low field (0.55 T) MRI.

This study aims to investigate the feasibility of using a commercially available clinical 0.55 T MRI scanner for comprehensive structural and functional fetal cardiac imaging. Balanced steady-state free precession (bSSFP) and phase contrast (PC) sequences were optimized by in utero studies consisting of 14 subjects for bSSFP optimization and 9 subjects for PC optimization. The signal-to-noise ratio (SNR) of the optimized sequences were investigated. Flow measurements were performed in three vessels, umbilical vein (UV), descending aorta (DAo), and superior vena cava (SVC) using the PC sequences and retrospective gating. The optimized bSSFP, PC and half-Fourier single shot turbo spin-echo (HASTE) sequences were acquired in a cohort of 21 late gestation-age fetuses (>36 weeks) to demonstrate the feasibility of a fetal cardiac exam at 0.55 T. The HASTE stacks were reconstructed to create an isotropic reconstruction of the fetal thorax, followed by automatic great vessel segmentations. The intra-abdominal UV blood flow measurements acquired with MRI were compared to ultrasound UV free-loop flow measurements. Using the parameters from 1.5 T as a starting point, the bSSFP sequences were optimized at 0.55 T, resulting in a 1.6-fold SNR increase and improved image contrast compared to starting parameters, as well as good visibility of most cardiac structures as rated by two experienced fetal cardiologists. The PC sequence resulted in increased SNR and reduced scan time, subsequent retrospective gating enabled successful blood flow measurements. The reconstructions and automatic great vessel segmentations showed good quality, with 18/21 segmentations requiring no or minor refinements. Blood flow measurements were within the expected range. A comparison of the UV measurements performed with ultrasound and MRI showed agreement between the two sets of measurements, with better correlation observed at lower flows. We demonstrated the feasibility of low-field (0.55 T) MRI for fetal cardiac imaging. The reduced SNR at low field strength can be effectively compensated for by strategically optimizing sequence parameters. Major fetal cardiac structures and vessels were consistently visualized, and flow measurements were successfully obtained. The late gestation study demonstrated the robustness and reproducibility at low field strength. MRI performed at 0.55 T is a viable option for fetal cardiac examination.

A Coarse-Fine Collaborative Learning Model for Three Vessel Segmentation in Fetal Cardiac Ultrasound Images.

Congenital heart disease (CHD) is the most frequent birth defect and a leading cause of infant mortality, emphasizing the crucial need for its early diagnosis. Ultrasound is the primary imaging modality for prenatal CHD screening. As a complement to the four-chamber view, the three-vessel view (3VV) plays a vital role in detecting anomalies in the great vessels. However, the interpretation of fetal cardiac ultrasound images is subjective and relies heavily on operator experience, leading to variability in CHD detection rates, particularly in resource-constrained regions. In this study, we propose an automated method for segmenting the pulmonary artery, ascending aorta, and superior vena cava in the 3VV using a novel deep learning network named CoFi-Net. Our network incorporates a coarse-fine collaborative strategy with two parallel branches dedicated to simultaneous global localization and fine segmentation of the vessels. The coarse branch employs a partial decoder to leverage high-level semantic features, enabling global localization of objects and suppression of irrelevant structures. The fine branch utilizes attention-parameterized skip connections to improve feature representations and improve boundary information. The outputs of the two branches are fused to generate accurate vessel segmentations. Extensive experiments conducted on a collected dataset demonstrate the superiority of CoFi-Net compared to state-of-the-art segmentation models for 3VV segmentation, indicating its great potential for enhancing CHD diagnostic efficiency in clinical practice. Furthermore, CoFi-Net outperforms other deep learning models in breast lesion segmentation on a public breast ultrasound dataset, despite not being specifically designed for this task, demonstrating its potential and robustness for various segmentation tasks.

Automatic segmentation based on optimization U-Net neural network (OU-NetNN) for fetal cardiac ultrasound images

Automatic segmentation based on optimization U-Net neural network (OU-NetNN) for fetal cardiac ultrasound images

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

BackgroundCongenital 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.MethodIn 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.ResultsWe 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.ConclusionsOur 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.

Fetal cardiac ultrasound standard section detection model based on multitask learning and mixed attention mechanism

Fetal cardiac ultrasound is a valuable tool for screening fetal cardiac health during pregnancy. Ultrasound standard section testing is an essential part of fetal heart ultrasound diagnosis. Due to the many scattered and partially similar anatomical structures in standard ultrasound views of the fetal heart, the results strongly depend on the clinical experience and knowledge of the sonographer. To improve detection efficiency and reduce misdiagnosis and omission, we propose a single-stage fetal cardiac ultrasound standard plane detection model (FCUM) based on multitask learning and a hybrid attention mechanism to assist sonographers in diagnosis. The feature fusion pyramids of the backbone and detection networks of this model are each embedded with a hybrid attention mechanism module of our design, which enables the multitasking network to extract shared features more accurately and efficiently and improves the accuracy of the detection and classification networks. We designed a classification module for multilayer residual network feature fusion that leads to better classification and faster convergence time. We conducted comprehensive experiments on a dataset of fetal cardiac ultrasound images acquired with several types of devices and in different geographic regions. The experimental results show that our model outperforms baseline models such as YOLOv8 and ResNet-50 in terms of detection precision and classification accuracy.

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI.

This study aims to evaluate deep learning (DL) denoising reconstructions for image quality improvement of Doppler ultrasound (DUS)-gated fetal cardiac MRI in congenital heart disease (CHD). Twenty-five fetuses with CHD (mean gestational age: 35 ± 1 weeks) underwent fetal cardiac MRI at 3T. Cine imaging was acquired using a balanced steady-state free precession (bSSFP) sequence with Doppler ultrasound gating. Images were reconstructed using both compressed sensing (bSSFP CS) and a pre-trained convolutional neural network trained for DL denoising (bSSFP DL). Images were compared qualitatively based on a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent) and quantitatively by calculating the apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (aCNR). Diagnostic confidence was assessed for the atria, ventricles, foramen ovale, valves, great vessels, aortic arch, and pulmonary veins. Fetal cardiac cine MRI was successful in 23 fetuses (92%), with two studies excluded due to extensive fetal motion. The image quality of bSSFP DL cine reconstructions was rated superior to standard bSSFP CS cine images in terms of contrast [3 (interquartile range: 2-4) vs. 5 (4-5), P < 0.001] and endocardial edge definition [3 (2-4) vs. 4 (4-5), P < 0.001], while the extent of artifacts was found to be comparable [4 (3-4.75) vs. 4 (3-4), P = 0.40]. bSSFP DL images had higher aSNR and aCNR compared with the bSSFP CS images (aSNR: 13.4 ± 6.9 vs. 8.3 ± 3.6, P < 0.001; aCNR: 26.6 ± 15.8 vs. 14.4 ± 6.8, P < 0.001). Diagnostic confidence of the bSSFP DL images was superior for the evaluation of cardiovascular structures (e.g., atria and ventricles: P = 0.003). DL image denoising provides superior quality for DUS-gated fetal cardiac cine imaging of CHD compared to standard CS image reconstruction.

Utility of Fetal Cardiac Resonance Imaging in Prenatal Clinical Practice: Current State of the Art

The field of prenatal cardiac imaging has revolutionized the way we understand and manage congenital heart diseases (CHD) in the developing fetus. In the prenatal period, cardiac imaging plays a pivotal role in the diagnostic pathway, from screening to classification and follow-up of CHD. The ability to visualize the fetal heart in utero allows healthcare professionals to detect abnormalities early, thus enabling timely interventions and informed decision-making processes for both the mother and the medical team. Early CHD detection improves preparation for delivery, postnatal care, and postnatal outcomes. Advancements in medical technology and imaging techniques have provided clinicians with insights into the fascinating workings of the fetal heart. Several imaging modalities have proven to be helpful in this field, with echocardiography undoubtedly representing the primary modality for evaluating the fetus. By providing detailed anatomical and functional information, fetal cardiac magnetic resonance (CMR) imaging contributes to better prenatal counseling and enhances the coordination of care between obstetricians, maternal–fetal medicine specialists, and pediatric cardiologists. Shortcomings of fetal CMR are due to technical concerns related to the intrauterine position of the fetus and subsequent challenges to following a standard scan protocol. The aim of this paper was to revise the current state-of-the-art in the field of fetal CMR and its clinical applications and to delve into methods, challenges, and future directions of fetal CMR in prenatal imaging.

Prenatal Diagnosis Rate of Critical Congenital Heart Disease Remains Inadequate with Significant Racial/Ethnic and Socioeconomic Disparities and Technical Barriers

Prenatal diagnosis (preDx) of critical congenital heart disease (CCHD) decreases neonatal morbidity and mortality. Obstetrical fetal cardiac imaging guidelines in 2013 aimed to increase preDx. The objectives of this study were to determine the contemporary preDx rate of CCHD and identify maternal–fetal factors and variations in prenatal care that may be potential barriers. This retrospective single center study evaluated maternal demographics and characteristics of infants with CCHD (requiring cardiac catheterization or surgical intervention before 6 months-old) between 2016 and 2019. 58% of the 339 infants with CCHD had preDx. Infants with preDx were more likely to have mothers ≥ 35 years-old (p = 0.028), family history of CHD (p = 0.017), health insurance (p = 0.002), or anatomic scan with perinatology (p < 0.001). Hispanic infants were less likely to have preDx (45.6%, p = 0.005). PreDx rates were higher in infants with extracardiac/genetic anomalies (p < 0.001) and significantly different between CCHD subtypes (76% for single ventricle, 51% for biventricular/four-chamber view, 59% for proximal outflow tract anomalies, and 48% for distal great artery anomalies; p = 0.024). In infants without preDx, 25% of their mothers had indication for, but did not undergo, fetal echocardiography. PreDx rates of CCHD remains inadequate across subtypes detectable by standard fetal cardiac screening views, particularly in uninsured and Hispanic communities.

Role of Fetal Cardiac MRI in Assessment of Congenital Heart Diseases in Comparison to Fetal Echocardiography

Introduction •Abnormalities of the cardiovascular system are the most common congenital diseases in the fetus and the first cause of infant mortality (Johnson et al. 2014). •Without a doubt, Echocardiography is the method of choice to visualize the fetal cardiac cardiovascular abnormalities. Unlike fetal echocardiography imaging, cardiovascular magnetic resonance (CMR) is relatively unaected by maternal and fetal conditions such as maternal obesity, uterine myoma, twins, oligohydramnios, fetal position and rib calcification, which particularly impair sonographic visualization of the fetal heart (Donofrio et al. 2014; Wielandner et al. 2013). •Fetal cardiac MR imaging is a novel MRI technique which can provide valuable information that could add to the prenatal diagnosis and evaluation of cardiac and most of extra-cardiac anomalies. The evaluation of pre-natal congenital cardiac anomalies is important for postnatal management. Aim of the work To highlight the advantage of MRI over fetal echocardiography in assessment of fetal congenital cardiac anomalies. Methods and material Twenty-six feti with suspected or diagnosed congenital cardiac anomalies. All cases underwent detailed history taking, fetal echocardiography and fetal cardiac MR. Study is approved by the ethics review board of Ain Shams University Hospital. Fetal echocardiography was done according to standard protocol and performed by suitable curvilinear probe. Then MRI of the fetal heart was done with uterine SURVEY_BFFE (balanced fast field echo), Black blood single shot -BH, white blood Cine, sBFFE_RLT DYN 3D(real time 3Ddynamic). Images were acquired in the transverse, four-chamber, shortaxis, coronal and oblique sagittal views. Findings of fetal echocardiography were compared with that of cardiac MRI. Results •Regarding the diagnostic performance of prenatal Echo and fetal cardiac MRI showed significant moderate agreement between the two modalities in the detection of different congenital cardiac anomalies, Kappa test: 0.500; p-value 0.021*. •Qualitative analysis: All cardiac structures were delineable by echocardiography and cardiac MRI. There was full agreement(κ = 1) between fetal echocardiography and cardiac MRI in evaluating the cardiac situs(24normal,1 levocardia, 1 ectopia cordis), aorta (20normal, 3 hypoplastic aorta,1 aortic stenosis,1 rt. Sided aortic arch and 1 small sized aorta), transverse cardiac diameter (22 normal, 4 cardiomegaly), foramen ovale (25 normal, 1 large single atrium), Good agreement was found between echocardiography and cardiac MRI for detection of position of the cardiac apex (23 normal, 2 dextrocardia and 1 mesocardia) •Fetal MRI had a significant role in detection of additional extracardiac anomalies in 13 cases. Conclusion fetal cardiac MR imaging as an adjunct to fetal echocardiography may provide valuable information that could add to the prenatal diagnosis and evaluation of cardiac and most of extra cardiac anomalies.

Evaluating How Physician Attitudes May Affect Practice in Fetal Cardiac Counseling.

Advances in fetal cardiac imaging over the last few decades have allowed for increased prenatal detection and detailed counseling of congenital heart disease (CHD). When CHD is detected, fetal cardiologists are faced with the challenge of providing nuanced prenatal counseling. Studies in other specialties have shown that differences in physician attitudes exist around termination of pregnancy and correlate with variations in the counseling provided to parents. We conducted an anonymous cross-sectional survey of fetal cardiologists in New England (n = 36) regarding attitudes toward termination of pregnancy and the counseling provided to parents with a fetal diagnosis of hypoplastic left heart syndrome. Using a screening questionnaire, there was no significant difference in the counseling provided to parents regardless of the physician's personal or professional views on termination of pregnancy, age, gender, location, type of practice, or years of experience. There were, however, differences among physicians on reasons to consider termination and their perceived professional responsibility to the fetus or mother. Further investigation on a larger geographic scale may reveal additional insights on variations in physician beliefs and whether such beliefs affect variability in counseling practices.

Magnetomechanical fetal cardiac imaging: Feasibility of a new multimodal technique

Postnatally, a comprehensive assessment of heart rhythm and function is obtained by recording ECG and echocardiography simultaneously. Every clinical-grade cardiac ultrasound scanner has an ECG input for this purpose. Prenatally, however, such assessments are not routinely possible. Fetal ECG suffers from modest signal quality, and fMCG is generally difficult to combine with other techniques because the sensors are highly susceptible to contamination from electronic interference.

Four-dimensional fetal cardiac imaging in a cohort of fetuses with suspected congenital heart disease.

Fetal cardiac magnetic resonance imaging (MRI) requires high spatial and temporal resolution and robustness to random fetal motion to capture the dynamics of the beating fetal heart. Slice-to-volume reconstruction techniques can produce high-resolution isotropic images while compensating for random fetal motion. The objective of this study was to evaluate image quality for slice-to-volume reconstruction of four-dimensional balanced steady-state free precession (bSSFP) imaging of the fetal heart. A cohort of 13 women carrying fetuses with congenital heart disease were imaged with real-time bSSFP sequences. Real-time bSSFP sequences were post-processed using a slice-to-volume reconstruction algorithm to produce retrospectively gated 4-D sequences with isotropic spatial resolution. Two radiologists evaluated slice-to-volume reconstruction image quality on a scale from 0 to 4 using 11 categories based on a segmental approach to defining cardiac anatomy and pathology. A score of 0 corresponded to cardiac structures not visualized at all and four corresponded to high quality and distinct appearance of structures. In 11 out of 13 cases, the average radiologist score of image quality across all categories was 3.0 or greater. In the remaining two cases, slice-to-volume reconstruction was not possible due to insufficient image quality in the acquisition. Slice-to-volume reconstruction has the potential to produce isotropic images with high spatial and temporal resolution that can display the anatomy of the fetal heart in arbitrary imaging planes retrospectively. More rapid, motion-robust acquisitions may be necessary to successfully reconstruct the fetal heart in all patients.

Guidance for fetal cardiac imaging in patients with degraded acoustic windows.

Guidance for fetal cardiac imaging in patients with degraded acoustic windows.

Feasibility study in assessment of congenital cardiovascular malformation by recent technique of fetal cardiac MR imaging

BackgroundAbnormalities of the cardiovascular system are the most common congenital diseases in the fetus and the first cause of infant mortality. Echocardiography is still the method of choice to visualize the fetal cardiac cardiovascular abnormalities, yet cardiovascular magnetic resonance (CMR) is relatively unaffected by maternal and fetal conditions such as maternal obesity, uterine myoma, twins, oligohydramnios, fetal position and rib calcification, which particularly impair sonographic visualization of the fetal heart. Fetal cardiac MR imaging is a novel MRI technique which can provide valuable information that could add to the prenatal diagnosis and evaluation of cardiac and most of extra-cardiac anomalies. In this work, we aimed to highlight the advantage of FCMRI over fetal echocardiography in assessment of fetal congenital cardiac anomalies.ResultsFifty-Two fetuses with suspected or diagnosed congenital cardiac anomalies. All cases underwent detailed history taking, underwent fetal echocardiography using suitable curvilinear probe and performed according to standard protocol, then fetal cardiac MR was done with Balanced fast field echo, Black blood single shot, white blood Cine, Real-time 3D dynamic sequences, images were acquired in the transverse, four-chamber, short-axis, coronal and oblique sagittal views. Findings of fetal echocardiography were compared with that of cardiac MRI and with standard post-natal echocardiography. Prenatal Echo and fetal cardiac MRI showed significant moderate agreement between the two modalities in the detection of different congenital cardiac anomalies, Kappa test: 0.500; p value 0.021. Fetal MRI had a significant role in detection of extra cardiac anomalies in most cases. Comparing to gold standard post-natal echo. Accuracy of fetal CMRI is 95.5% and of fetal Echo is 86.4% regarding overall cardiac anomalies:ConclusionFetal cardiac MR imaging as an adjunct to fetal echocardiography may provide valuable information that could add to the prenatal diagnosis and evaluation of cardiac and most of extra cardiac anomalies.

Abstract 13314: Development of a Computational Fluid Dynamics Model for Assessing Hemodynamics in Aortic Arches in Human Fetuses

Background and Objective: The hemodynamics of fetal circulation and its alterations, as in cases of congenital heart defects (CHD), have been investigated in instrumented animal models or in human fetuses by noninvasive fetal echocardiography and Doppler (FED). There is little data in computational modeling of fetal circulation due to challenges in fetal cardiac imaging and the availability of validation methodologies. This study aims to develop and validate a computational model for assessing hemodynamics in aortic and ductal arches in human fetuses. Methods: Figure 1 shows our computational workflow. The process started by preparing a reconstructed 3D aortic and ductal arch anatomy derived from 3D FED. Then, the computational model was built and validated using clinical data from five human fetuses. The primary output was the velocity waveform at the aortic isthmus (AoI), validated using tracings from spectral Doppler. Results: Upon superimposing the reconstructed fetal aortic arch anatomies onto the original 3D FED stack, our results demonstrated a precise rendering of each subject’s unique vessel structure. Simulations were run for ten cardiac cycles, with each velocity waveform at the AoI showing a discrepancy of less than 15% when compared with the Doppler echocardiography tracings. These findings indicate a good agreement between our computational model and the FED data. Conclusion: This study presents the development and validation of a computational model for assessing patient-specific hemodynamics in the aortic arches of human fetuses. Continued investigation is warranted to further validate and apply this approach to improve the diagnosis, prognosis, and treatment of CHD in human fetuses.

Super-Resolution Cine Image Enhancement for Fetal Cardiac Magnetic Resonance Imaging.

Fetal cardiac magnetic resonance imaging (MRI) improves the diagnosis of congenital heart defects, but is sensitive to fetal motion due to long image acquisition time. This may be overcome with faster image acquisition with low resolution, followed by image enhancement to provide clinically useful images. To combine phase-encoding undersampling with super-resolution neural networks to achieve high-resolution fetal cine cardiac MR images with short acquisition time. Prospective. Twenty-eight fetuses (gestational week 36 [interquartile range 33-38 weeks]). 1.5 T, balanced steady-state free precession (bSSFP) cine sequence. Images were acquired using fully sampled Doppler ultrasound-gated clinical bSSFP cine as reference, with equivalent cine sequences with decreased phase-encoding resolution (25%, 33%, and 50% of clinical standard). Two super-resolution methods based on convolutional neural networks were proposed and evaluated (phasrGAN and phasrresnet). Data were partitioned into training (36 cine slices), validation (3 cine slices), and test sets (67 cine slices) without overlap. Conventional reconstruction methods using bicubic interpolation and k-space zeropadding were used for comparison. Three blinded observers scored image quality between 1 and 10. Image scores are reported as median [interquartile range] and were compared using Mann-Whitney's nonparametric test with P < 0.05 showing statistically significant differences. Both proposed methods showed no significant difference in image quality compared to clinical images (8 [7-8.5]) down to 33% (phasrGAN 8 [6.5-8]; phasrresnet 8 [7-8], all P ≥ 0.19) phase-encoding resolution, i.e., up to three times faster image acquisition, whereas bicubic interpolation and k-space zeropadding showed significantly lower quality for 33% phase-encoding resolution (both 7 [6-8]). Super-resolution enhancement can be used for fetal cine cardiac MRI to reduce image acquisition time while maintaining image quality. This may lead to an improved success rate for fetal cine MR imaging, as the impact of fetal motion is lessened by shortened acquisitions. 1 TECHNICAL EFFICACY: Stage 2.

Convolutional neural network for semantic segmentation of fetal echocardiography based on four-chamber view

The acute shortage of trained and experienced sonographers causes the detection of congenital heart defects (CHDs) extremely difficult. In order to minimize this difficulty, an accurate fetal heart segmentation to the early location of such structural heart abnormalities prior to delivery is essential. However, the segmentation process is not an easy task due to the small size of the fetal heart structure. Moreover, the manual task for identifying the standard cardiac planes, primarily based on a four-chamber view, requires a well-trained clinician and experience. In this paper, a CNN method using U-Net architecture was proposed to automate fetal cardiac standard planes segmentation from ultrasound images. A total of 519 fetal cardiac images was obtained from three videos. All data is divided into training and testing data. The testing data consist of 106 slices of the four-chamber segmentation tasks, i.e. atrial septal defect (ASD), ventricular septal defect (VSD), and normal. The segmentation of the post-processing method is needed to enhanced the segmentation result. In this paper, a combination technique with U-Net and Otsu thresholding gives the best performances with 99.48%-pixel accuracy, 96.73% mean accuracy, 94.92% mean intersection over union, and 0.21% segmentation error. In the future, the implementation of Deep Learning in the study of CHDs holds significant potential for identifying novel CHDs in heterogeneous fetal hearts.

Counseling for fetal heart disease-current standards and best practice.

Congenital heart disease (CHD) is the most common cause of major congenital anomalies affecting newborns. Prenatal detection of CHD has been improving continuously during the last two decades due to technical advances and thus optimized fetal cardiac imaging. Besides the in-utero diagnosis of CHD effective parental counseling is an integral part of any Fetal Cardiology Program. However, studies on the most effective techniques are scarce, as well as data on empirical assessment of counseling and its effectiveness. In this review article, we summarize current guidelines from different international associations and societies. We provide an updated literature overview evaluating current standards of counseling with regard to parental needs. This includes ethical aspects, counseling for univentricular disease and in-utero cardiac interventions. We discuss our method to assess counseling success for fetal heart defects by exploring different analytical dimensions that may be considered helpful in order to improve efficacy. Finally, we present a proposal of how to optimize a setting for counseling based on the current literature and our own data. In summary, parental counseling for fetal heart disease is complex and multidimensional. Significant expertise in fetal cardiology and physiology, potential progression of CHD, postnatal treatment strategies and knowledge of long-term sequelae is necessary. A structured approach, together with continuous improvement of communicative skills, may lead to more effective counseling for parents following a diagnosis of CHD in the fetus.

Convolutional neural network for semantic segmentation of fetal echocardiography based on four-chamber view

The acute shortage of trained and experienced sonographers causes the detection of congenital heart defects (CHDs) extremely difficult. In order to minimize this difficulty, an accurate fetal heart segmentation to the early location of such structural heart abnormalities prior to delivery is essential. However, the segmentation process is not an easy task due to the small size of the fetal heart structure. Moreover, the manual task for identifying the standard cardiac planes, primarily based on a four-chamber view, requires a well-trained clinician and experience. In this paper, a CNN method using U-Net architecture was proposed to automate fetal cardiac standard planes segmentation from ultrasound images. A total of 519 fetal cardiac images was obtained from three videos. All data is divided into training and testing data. The testing data consist of 106 slices of the four-chamber segmentation tasks, i.e. atrial septal defect (ASD), ventricular septal defect (VSD), and Normal. The segmentation of the post-processing method is needed to enhanced the segmentation result. In this paper, a combination technique with U-Net and Otsu thresholding gives the best performances with 99.48%-pixel accuracy, 96.73% mean accuracy, 94.92% mean intersection over union, and 0.21% segmentation error. In the future, the implementation of Deep Learning in the study of CHDs holds significant potential for identifying novel CHDs in heterogeneous fetal hearts.