Fetal cardiac axis in tetralogy of Fallot: associations with prenatal findings, genetic anomalies and postnatal outcome

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.

Increased Pulmonary-Aortic Interspace in Fetal Right Aortic Arch: A Matched Case-Control Study

INTRODUCTION

The prenatal detection rate of a right aortic arch (RAA) has increased with the implementation of the three-vessel view (3VV) to the second-trimester anomaly scan formed by the pulmonary artery (PA), aorta (Ao), and superior vena cava (SVC). We examined the value of measuring the distance between PA and Ao in the 3VV in cases with an RAA.

METHODS

We conducted a case-control study in which fetuses with an isolated RAA were matched to 3 healthy controls. Using 3VV images, the distances between PA, Ao, and SVC were measured and the ratio between PA to Ao (PAAo) distance and Ao to SVC (AoSVC) distance was calculated.

RESULTS

Fifty-four RAA cases and 162 matched controls were included. The mean absolute distance PAAo was 3.1 mm in cases and 1.8 mm in controls (p < 0.001), and the mean PAAo/AoSVC ratio was 2.9 and 1.4, respectively (p < 0.001). The ROC curve of PAAo/AoSVC ratio showed a cut-off point of 1.9 with sensitivity and specificity over 87% for the diagnosis of RAA.

CONCLUSIONS

The pulmonary-aortic interspace and the PAAo/AoSVC ratio were significantly larger for RAA cases as compared to controls. If an increased pulmonary-aortic interspace is observed, a PAAo/AoSVC of ≥1.9 can be helpful in the diagnosis of an RAA.

Cardiac Axis in Early Gestation and Congenital Heart Disease

Congenital heart defects represent the most common structural anomalies observed in the fetal population, and they are often associated with significant morbidity and mortality. The fetal cardiac axis, which indicates the orientation of the heart in relation to the chest wall, is formed by the angle between the anteroposterior axis of the chest and the interventricular septum of the heart. Studies conducted during the first trimester have demonstrated promising outcomes with respect to the applicability of cardiac axis measurement in fetuses with congenital heart defects as well as fetuses with extracardiac and chromosomal anomalies, which may result in improved health outcomes and reduced healthcare costs. The main aim of this review article was to highlight the cardiac axis as a reliable and powerful marker for the detection of congenital heart defects during early gestation, including defects that would otherwise remain undetectable through the conventional four-chamber view.

Semi-Automatic Measurement of Fetal Cardiac Axis in Fetuses with Congenital Heart Disease (CHD) with Fetal Intelligent Navigation Echocardiography (FINE)

Congenital heart disease (CHD) is one of the most common organ-specific birth defects and a major cause of infant morbidity and mortality. Despite ultrasound screening guidelines, the detection rate of CHD is limited. Fetal intelligent navigation echocardiography (FINE) has been introduced to extract reference planes and cardiac axis from cardiac spatiotemporal image correlation (STIC) volume datasets. This study analyses the cardiac axis in fetuses affected by CHD/thoracic masses (n = 545) compared to healthy fetuses (n = 1543) generated by FINE. After marking seven anatomical structures, the FINE software generated semi-automatically nine echocardiography standard planes and calculated the cardiac axis. Our study reveals that depending on the type of CHD, the cardiac axis varies. In approximately 86% (471 of 542 volumes) of our pathological cases, an abnormal cardiac axis (normal median = 40-45°) was detectable. Significant differences between the fetal axis of the normal heart versus CHD were detected in HLHS, pulmonary atresia, TOF (p-value < 0.0001), RAA, situs ambiguus (p-value = 0.0001-0.001) and absent pulmonary valve syndrome, DORV, thoracic masses (p-value = 0.001-0.01). This analysis confirms that in fetuses with CHD, the cardiac axis can significantly deviate from the normal range. FINE appears to be a valuable tool to identify cardiac defects.

Diagnostic Value of Chromosomal Microarray Analysis for Fetal Congenital Heart Defects with Different Cardiac Phenotypes and Extracardiac Abnormalities

(1) Background: The objective of this study was to investigate the diagnostic value of chromosomal microarray analysis (CMA) for congenital heart defects (CHDs) with different cardiac phenotypes and extracardiac abnormalities (ECAs) and to explore the pathogenic genetic factors of CHDs. (2) Methods: We collected fetuses diagnosed with CHDs by echocardiography at our hospital from January 2012 to December 2021. We analyzed the CMA results of 427 fetuses with CHDs. We then categorized the CHD into different groups according to two dimensions: different cardiac phenotypes and whether it was combined with ECAs. The correlation between the numerical chromosomal abnormalities (NCAs) and copy number variations (CNVs) with CHDs was analyzed. Statistical analyses, including Chi-square tests and t-tests, were performed on the data using IBM SPSS and GraphPad Prism. (3) Results: In general, CHDs with ECAs increased the detection rate for CA, especially the conotruncal defects. CHD combined with the thoracic and abdominal walls and skeletal, thymic and multiple ECAs, were more likely to exhibit CA. Among the CHD phenotypes, VSD and AVSD were associated with NCA, while DORV may be associated with NCA. The cardiac phenotypes associated with pCNVs were IAA (type A and B), RAA, TAPVC, CoA and TOF. In addition, IAA, B, RAA, PS, CoA and TOF were also associated with 22q11.2DS. The length distribution of the CNV was not significantly different between each CHD phenotype. We detected twelve CNV syndromes, of which six syndromes may be related to CHDs. The pregnancy outcome in this study suggests that termination of pregnancy with fetal VSD and vascular abnormality is more dependent on genetic diagnosis, whereas the outcome in other phenotypes of CHDs may be associated with other additional factors. (4) Conclusions: CMA examination for CHDs is still necessary. We should identify the existence of fetal ECAs and specific cardiac phenotypes, which are helpful for genetic counseling and prenatal diagnosis.

New and advanced features of fetal intelligent navigation echocardiography (FINE) or 5D heart

Congenital heart disease (CHD) is the leading organ-specific birth defect, as well as the leading cause of infant morbidity and mortality from congenital malformations. Therefore, a comprehensive screening examination of the fetal heart should be performed in all women to maximize the detection of CHD. Four-dimensional sonography with spatiotemporal image correlation (STIC) technology displays a cine loop of a complete single cardiac cycle in motion. A novel method known as Fetal Intelligent Navigation Echocardiography (or FINE) was previously developed to interrogate STIC volume datasets using "intelligent navigation" technology. Such method allows the automatic display of nine standard fetal echocardiography views required to diagnose most cardiac defects. FINE considerably simplifies fetal cardiac examinations and reduces operator dependency. It has both high sensitivity and specificity for the detection of CHD. Indeed, FINE has been integrated into several commercially available ultrasound platforms.Recently, eight novel and advanced features have been developed for the FINE method and they will be described herein. Such features can be categorized based upon their broad goals. The first goal is to simplify FINE further, and consists of the following features: (1) Auto fetal positioning (or FINE align); (2) Skip points; (3) Predictive cursor; (4) Static mode volume; and (5) Breech sweep. The second goal is to allow quantitative measurements to be performed on the cardiac views generated by FINE: (6) Automatic cardiac axis; and (7) Cardiac biometry. Finally, the last goal is to improve the success of obtaining fetal echocardiography view(s); and consists of (8) Maestro planar navigation.

Evaluation of Fetal Cardiac Size and Shape: A New Screening Tool to Identify Fetuses at Risk for Tetralogy of Fallot

OBJECTIVE

Prenatal detection rates for tetralogy of Fallot (TOF) vary between 23 and 85.7%, in part because of the absence of significant structural abnormalities of the 4-chamber view (4CV), as well as the relative difficulty in detection of abnormalities during the screening examination of the outflow tracts. The purpose of this study was to evaluate whether the 4CV and ventricles in fetuses with TOF may be characterized by abnormalities of size and shape of these structures.

METHODS

This study retrospectively evaluated 44 fetuses with the postnatal diagnosis of TOF. Measurements were made from the 4CV (end-diastolic length, width, area, global sphericity index, and cardiac axis) and the right (RV) and left (LV) ventricles (area, length, 24-segment transverse widths, sphericity index, and RV/LV ratios). Logistic regression analysis was performed to identify variables that might separate fetuses with TOF from normal controls.

RESULTS

The mean gestational age at the time of the last examination prior to delivery was 28 weeks 5 days (SD 4 weeks, 4 days). The mean z-scores were significantly lower in fetuses with TOF for the 4CV and RV and LV measurements of size and shape. Logistic regression analysis identified simple linear measurements of the 4CV, RV, and LV that had a sensitivity of 90.9 and specificity of 98.5% that outperformed the 4CV cardiac axis (sensitivity of 22.7%) as a screening tool for TOF.

CONCLUSIONS

Measurements of the 4CV, RV, and LV can be used as an adjunct to the outflow tract screening examination to identify fetuses with TOF.

A 'holistic' sonographic view on congenital heart disease - How automatic reconstruction using fetal intelligent navigation echocardiography (FINE) eases the unveiling of abnormal cardiac anatomy part I: Right heart anomalies

Attempting a comprehensive examination of the fetal heart remains challenging for unexperienced operators as it emphasizes the acquisition and documentation of sequential cross-sectional and sagittal views and inevitably results in diminished detection rates of fetuses affected by congenital heart disease. The introduction of four-dimensional spatio-temporal image correlation (4D STIC) technology facilitated a volumetric approach for thorough cardiac anatomic evaluation by the acquisition of cardiac 4D datasets. By analyzing and re-arranging of numerous frames according to their temporal event within the heart cycle, STIC allows visualization of cardiac structures as an endless cine loop sequence of a complete single cardiac cycle in motion. However, post-analysis with manipulation and repeated slicing of the volume usually requires experience and in-depth anatomic knowledge, which limits the widespread application of this advanced technique in clinical care and unfortunately leads to the underestimation of its diagnostic value to date. Fetal intelligent navigation echocardiography (FINE), a novel method that automatically generates and displays nine standard fetal echocardiographic views in normal hearts, has shown to be able to overcome these limitations. Very recent data on the detection of congenital heart defects (CHDs) using the FINE method revealed a high sensitivity and specificity of 98% and 93%, respectively. In this two-part manuscript, we focused on the performance of FINE in delineating abnormal anatomy of typical right and left heart lesions and thereby emphasized the educational potential of this technology for more than just teaching purposes. We further discussed recent findings in a pathophysiological and/or functional context.

An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease

Congenital heart disease (CHD) is the most common birth defect. Fetal screening ultrasound provides five views of the heart that together can detect 90% of complex CHD, but in practice, sensitivity is as low as 30%. Here, using 107,823 images from 1,326 retrospective echocardiograms and screening ultrasounds from 18- to 24-week fetuses, we trained an ensemble of neural networks to identify recommended cardiac views and distinguish between normal hearts and complex CHD. We also used segmentation models to calculate standard fetal cardiothoracic measurements. In an internal test set of 4,108 fetal surveys (0.9% CHD, >4.4 million images), the model achieved an area under the curve (AUC) of 0.99, 95% sensitivity (95% confidence interval (CI), 84-99%), 96% specificity (95% CI, 95-97%) and 100% negative predictive value in distinguishing normal from abnormal hearts. Model sensitivity was comparable to that of clinicians and remained robust on outside-hospital and lower-quality images. The model's decisions were based on clinically relevant features. Cardiac measurements correlated with reported measures for normal and abnormal hearts. Applied to guideline-recommended imaging, ensemble learning models could significantly improve detection of fetal CHD, a critical and global diagnostic challenge.

Human fetal hearts with tetralogy of Fallot have altered fluid dynamics and forces

Studies have suggested the effect of blood flow forces in pathogenesis and progression of some congenital heart malformations. It is therefore of interest to study the fluid mechanic environment of the malformed prenatal heart, such as the tetralogy of Fallot (TOF), especially when little is known about fetal TOF. In this study, we performed patient-specific ultrasound-based flow simulations of three TOF and seven normal human fetal hearts. TOF right ventricles (RVs) had smaller end-diastolic volumes (EDVs) but similar stroke volumes (SVs), whereas TOF left ventricles (LVs) had similar EDVs but slightly increased SVs compared with normal ventricles. Simulations showed that TOF ventricles had elevated systolic intraventricular pressure gradient (IVPG) and required additional energy for ejection but IVPG elevations were considered to be mild relative to arterial pressure. TOF RVs and LVs had similar pressures because of equalization via ventricular septal defect (VSD). Furthermore, relative to normal, TOF RVs had increased diastolic wall shear stresses (WSS) but TOF LVs were not. This was caused by high tricuspid inflow that exceeded RV SV, leading to right-to-left shunting and chaotic flow with enhanced vorticity interaction with the wall to elevate WSS. Two of the three TOF RVs but none of the LVs had increased thickness. As pressure elevations were mild, we hypothesized that pressure and WSS elevation could play a role in the RV thickening, among other causative factors. Finally, the endocardium surrounding the VSD consistently experienced high WSS because of RV-to-LV flow shunt and high flow rate through the over-riding aorta. NEW & NOTEWORTHY Blood flow forces are thought to cause congenital heart malformations and influence disease progression. We performed novel investigations of intracardiac fluid mechanics of tetralogy of Fallot (TOF) human fetal hearts and found essential differences from normal hearts. The TOF right ventricle (RV) and left ventricle had similar and elevated pressure but only the TOF RV had elevated wall shear stress because of elevated tricuspid inflow, and this may contribute to the observed RV thickening. TOF hearts also expended more energy for ejection.