Ultrasound is the most commonly used diagnostic imaging technique during pregnancy. It is cheap, does not require ionizing radiation and can be performed at the bedside. Despite these advantages, it does have some drawbacks such as relatively low imaging quality, low contrast, and high variability. With these constraints, automating the interpretation of ultrasound images is challenging. With the development of hardware and open-source software packages, deep learning has emerged, achieving state-of-the-art performance in various research fields, notably medical image analysis involving classification, segmentation, and object detection. Due to its increased performance with large dataset, it has gained great interest in clinical practice. I will first talk about the deep learning applications to ultrasound in pregnancy, and then introduce our fully automated screening tool developed based on deep learning and image processing techniques and its application to the human placenta using the 3D ultrasound scans from the first trimester.