【摘要】 超声由于其无辐射、操作方便等优点已经成为产前筛查的最主要的成像模态之一，广泛应用于整个孕期。随着人工智能的快速发展，基于深度学习的超声图像识别在产前筛查的应用中得到了广泛研究，在胎儿颅脑、心脏等结构的识别及胎儿异常识别等方面，表现出较大优势。该技术可以提高产前超声检查效率、提高胎儿异常检出率、优化医疗服务质量，提高专业水平和患者满意度；且有助于改善农村地区或低收入国家医疗保健，支持现有临床操作，改善工作流程。该文对基于深度学习的超声图像识别在产前筛查中的应用进行综述。更多还原

【Abstract】 Ultrasound has become one of the most important imaging modalities for prenatal screening because of its advantages of not requiring irradiation and easy operation, and it is widely used throughout pregnancy.With the rapid development of artificial intelligence, ultrasound image recognition based on deep learning has been researched extensively in the application of prenatal screening and has shown significant advantages in the detection of fetal cranial and cardiac structures and fetal anomalies.This technology can improve the efficiency of prenatal ultrasound screening, increase the detection rate of fetal anomalies, optimize the quality of healthcare services, and improve patient professionalism and patient satisfaction.Moreover, it plays a crucial role in improving healthcare access in rural and low-income areas, supporting existing clinical practices, and streamlining workflow processes.更多还原