Artificial Intelligence-Based Automated Assessment of the Four-Chamber View in Fetal Cardiac Ultrasound Videos

The clinical application of artificial intelligence (AI) can provide technical support for examiners and improve obstetric workflow efficiency. In this study, we developed AI models that automatically extract the four-chamber view (4CV) from fetal cardiac ultrasound videos and compute the cardiothoracic area ratio, cardiac axis, and cardiac position for prenatal screening of congenital heart disease. Fetal cardiac ultrasound videos from 301 patients in the second trimester were analyzed. The 4CV was automatically extracted using YOLOv7, followed by image segmentation with UNet 3+ and SegFormer, after which automated parameter calculation and estimation were performed. A clinical comparison study involving 22 obstetricians was conducted to evaluate the screening performance of the AI models. The models demonstrated stable performance in both normal and abnormal cases, including examinations acquired using different ultrasound systems. Furthermore, the AI models achieved screening performance comparable to that of expert obstetricians. These findings indicate that the proposed AI framework enables reliable 4CV extraction and accurate biometric parameter computation. This fully automated approach has the potential to reduce missed abnormalities and improve the consistency of fetal cardiac ultrasound screening.