uFlowAM: an unsupervised framework for detection and visualization of abnormal intracardiac microflow on early-pregnancy fetal cardiac microflow imaging

Beyond the Standard Fetal Echocardiogram: Emerging Tools in Fetal Cardiology

ROI-Guided Echocardiographic Image Analysis and Case Aggregation for Differentiating Atrial and Ventricular Septal Defects

This study implemented strict subject-disjoint partitioning to eliminate data leakage, and simultaneously introduced cross-frame case aggregation to emulate the multi-frame visual synthesis process of expert echocardiographers, suggesting that the proposed workflow has the potential to serve as an adjunctive tool for septal defect screening.

Value of the Newly Designed Major and Minor Checklists in Diagnosis of Congenital Cardiovascular Disease and Associated Malformation: New Era of Fetal Cardiac MRI.

RATIONALE AND OBJECTIVES Fetal echocardiography is the standard, rapid, affordable, and noninvasive modality for prenatal assessment of suspected congenital heart disease. Fetal cardiac magnetic resonance imaging (FCMRI) has emerged as a valuable adjunct, particularly when ultrasound is limited by maternal obesity, uterine fibroids, oligohydramnios, fetal malposition, or late-gestational acoustic shadowing. Consequently, this study aimed to evaluate the diagnostic utility of a newly proposed structured major/minor checklist system for FCMRI interpretation. By correlating structured FCMRI interpretations with postnatal echocardiographic outcomes, we assess the framework's reliability in characterizing structural cardiovascular anomalies, particularly when initial ultrasound evaluation is suboptimal. MATERIALS AND METHODS Between May 2024 and November 2025, an initial cohort of 60 pregnant women was screened, yielding 52 singleton pregnancies with suspected fetal cardiac anomalies. These cases were prospectively evaluated with fetal echocardiography and FCMRI. Image interpretation was performed by two radiologists experienced in prenatal imaging and one pediatric cardiologist. Postnatal confirmation was available for 40 live-born infants; 12 intrauterine fetal death cases were excluded from postnatal diagnostic-performance analysis. RESULTS Based on postnatal echocardiography, both modalities demonstrated high diagnostic performance. Fetal echocardiography yielded slightly higher sensitivity than FCMRI (96.5% vs. 93.1%), whereas FCMRI exhibited higher specificity (100% vs. 81.8%) and overall diagnostic accuracy (95.0% vs. 92.5%). Notably, FCMRI demonstrated a significantly higher overall concordance with postnatal echocardiography compared to fetal echocardiography for ductus-dependent critical lesions (90.0% vs. 77.5% total agreement). This superior concordance for FCMRI was particularly pronounced in identifying emergency ductus-dependent lesions (72.7% vs. 36.4% agreement in positive cases), alongside higher exact concordance in normal, conotruncal, and hypoplastic heart-spectrum categories, whereas fetal echocardiography showed higher concordance in tetralogy of Fallot and Ebstein anomaly. Both modalities showed similar concordance for atrioventricular septal defects. CONCLUSION FCMRI is a useful complementary adjunct to fetal echocardiography, improving diagnostic confidence in complex cases and supporting prenatal counseling, delivery planning, and postnatal management.

4D flow cardiac magnetic resonance postprocessing in congenital heart disease: SCMR FLIICR workgroup recommendations.

This document addresses the needs for an "ideal" post-processing software for 4D flow in patients with CHD and provides information on general requirements, velocity encoding, offset and aliasing correction, visualization, segmentation and reconstruction as well as output data.

Automatic Detection of Key Fetal Head Anatomical Structures in the First Trimester Using Ultrasound Images

— Ultrasound imaging is essential for early pregnancy assessment; however, manual interpretation remains limited by operator dependency and speckle noise. Unlike previous studies that employed You Only Look Once (YOLO)v5, YOLOv6, or YOLOv7, this study introduces an automated approach for detecting key fetal head anatomical structures during the first trimester based on the YOLOv8 architecture. The study systematically compares raw ultrasound images with Hybrid Speckle Noise Reduction (HSNR) preprocessing to evaluate the trade-off between visual enhancement and fine-structure preservation, as quantified by a Structural Similarity Index Measure (SSIM) of 0.912 and a Peak Signal-to-Noise Ratio (PSNR) of 29.8 decibels. Semi-automated annotation with expert validation, yielding a Cohen’s kappa value of 0.84, ensured high labeling reliability. YOLOv8 was trained under multiple configurations, including different optimizers such as stochastic gradient descent, Adam, and AdamW, combined with early stopping and stratified five-fold cross-validation at a resolution of 320 by 320 pixels to balance anatomical detail and real-time efficiency. The optimal configuration using AdamW with early stopping achieved strong detection performance, with a mean average precision at an Intersection-over-Union (IoU) threshold of 0.50 of 0.907 and a recall of 0.857, outperforming models trained on images processed with speckle noise reduction. While speckle noise reduction improved overall image clarity, it slightly reduced the detectability of subtle anatomical features such as nuchal translucency and nasal skin due to excessive smoothing. The proposed model achieved an inference speed of 45 frames per second on a graphics processing unit, demonstrating its feasibility for real-time clinical deployment. Overall, these results highlight the potential of an optimized YOLOv8 model trained on raw ultrasound images as an efficient, reliable, and clinically applicable approach for artificial intelligence – assisted prenatal screening

Fetal Ultrasound Monitoring Using MedSegDiff-V2–DUCKNet Ensemble Segmentation and Explainable Head Circumference Estimation

Fetal health monitoring is a vital component of prenatal care. Ultrasonography is the primary imaging technique for assessing fetal development and detecting abnormalities. In this work, an AI-enhanced ultrasound monitoring system has been developed that automates the segmentation and analysis of fetal anatomical structures. We used the Radboudumc HC18 dataset comprising 1,335 fetal head ultrasound images with segmentation masks, pixel-size metadata, and ground-truth HC/AC measurements. We collected a novel dataset (Aalok dataset) comprising 400 2D ultrasound scans from a local hospital in Dhaka, Bangladesh. The scans were obtained using a Samsung WS80A Elite system, which covers gestational ages of 18–38 weeks and includes precise manual annotations by radiologists. It consists of imaging, biometric measurements, and clinical annotations for complete fetal estimation. We applied multiple segmentation architectures, including U-NeXt, Attention U-Net, TransUNet, DUCK-Net, and MedSegDiff-V2. Among them, MedSegDiff-V2 and DUCK-Net achieved the highest segmentation performance with Dice scores of 0.9852 and recall of 0.9864 with ~70 minutes training time, outperforming DUCK-Net, TransUNet and UNeXt. The proposed ensemble framework combines MedSegDiff-V2 and DUCK-Net through learnable and attention-based fusion mechanisms. The learnable ensemble achieved a Dice score of 0.9892 and a Recall of 0.9871. The proposed MedSegDiff-V2-Duck-Net ensemble technique demonstrated a strong correlation between predicted and actual HC values with a correlation of 0.9988. Grad-CAM++ explainable AI technique, has been applied to the ensemble model, visualizing the key ROI for clearer human understanding. The proposed system significantly reduces examination time and interobserver variability and increases diagnostic precision. The collected Aalok fetal head segmentation dataset is publicly available at the Aalok Dataset GitHub Repository