Artificial intelligence and obstetric ultrasound

Abstract

Artificial intelligence (AI) technology is currently in its third era. Current AI technology is driven by machine learning (ML), particularly deep learning (DL). Deep learning is a computer technology that allows a computational model with multiple processing layers to learn the features of data. Convolutional neural networks have led to breakthroughs in the processing of images, videos, and audio. In medical imaging, computer-aided diagnosis algorithms for diabetic retinopathy, diabetic macular edema, tuberculosis, skin lesions, and colonoscopy classifiers are highly accurate and comparable to clinician performance. Although the application of AI technology in the field of ultrasound (US) has lagged behind other modalities such as radiography, computed tomography (CT), and magnetic resonance imaging (MRI), it has been rapidly applied in the field of obstetrics and gynecology in recent years. The results of AI processing of US images to determine the malignancy of ovarian tumors are comparable to the International Ovarian Tumor Analysis results, and it is now possible to identify each part of the body and calculate the estimated weight from fetal US movies. However, the application of AI to the central nervous system and especially to the fetal heart, which is the main part of fetal US morphological examination, is just beginning to progress.