Application Progress of Artificial Intelligence in Ultrasound Diagnosis of Fetal Central Nervous System

Fetal central nervous system (CNS) developmental abnormalities are common congenital malformations, and ultrasound imaging is the gold standard for prenatal assessment of fetal health. Three-dimensional (3D) ultrasound can improve the comprehensiveness of diagnostic information, but its diagnostic accuracy is highly dependent on the operator's professional experience, with a risk of missed diagnosis. Artificial intelligence (AI), especially deep learning (DL) methods, provides an important means to solve the above problems. In fetal craniocerebral ultrasound, AI mainly achieves three core applications: first, completing standard section recognition and key structure measurement, standardizing processes through algorithms, eliminating subjective deviations of operators, and promoting the transformation of fetal craniocerebral ultrasound from experience-dependent to standard-quantitative; second, assisting in malformation screening, detection, and classification diagnosis, reducing the dependence of diagnosis on doctors' experience, and narrowing the diagnostic gap between medical institutions at different levels; third, integrating multi-dimensional information to conduct risk assessment and prognosis prediction, providing quantitative basis for clinical consultation and personalized management. At present, the clinical application of AI still faces problems such as the scarcity of high-quality, large-sample, multi-center standardized ultrasound image databases, insufficient algorithm interpretability, poor compatibility with clinical systems, and unclear responsibility definition. In summary, AI has significantly improved the scientificity and reliability of fetal CNS ultrasound diagnosis. In the future, it is necessary to expand multi-center data sets and optimize algorithm performance to promote its clinical popularization and assist the precise development of prenatal medicine. This article reviews the application progress of artificial intelligence technology in ultrasound diagnosis of fetal central nervous system in recent years.