This paper begins with the medical digital ultrasonic imaging workstations' development history and stages of PACS (Picture Archiving and Communication Systems). We analyze the actual application scenarios and pain points in medical digital ultrasonic imaging and introduce the support of medical digital ultrasonic imaging workstations for the entire business process. At the same time, we explain the role of AI functions in promoting business improvements throughout the process, using Shenzhen Maternal and Child Health Hospital as an application case study. This paper also discusses the difficulties faced by the development of AI in medical digital ultrasonic imaging and provides some solutions and suggestions. We offer a perspective on the future development of artificial intelligence in medical digital ultrasonic imaging. We explore potential application scenarios in areas such as empowering the ultrasound process with intelligent management, ultrasound consultation, cloud-based electronic films, and the Internet of Things (IoT) services.

This review article introduces the main concepts and architectures of deep learning networks for medical imaging tasks, such as classification, detection, segmentation, and generation. It then surveys how deep learning has been applied to ultrasound imaging for various purposes, such as image processing, diagnosis, and workflow enhancement. It covers different organs and body parts that can be imaged by ultrasound, such as liver, breast, thyroid, heart, kidney, prostate, nerve, muscle, and fetus. It also discusses how deep learning can help with view recognition, registration, and quantification, measurement, image registration for interventional guidance, and real-time assistance while scanning. Moreover, it explores how generative AI can be used in the future medical field by leveraging deep learning for ultrasound imaging, such as generating realistic and diverse images, virtual organs/patients with diseases, synthesizing missing or corrupted data and augmenting existing data for training and testing.

In 2009, Hitachi commercialized “Mappie^*1, the world’s first Capacitive Micro-machined Ultrasound Transducer (CMUT) using semiconductor based technology. It generated high quality diagnostic images of mammary glands, thanks to its broad-band characteristics^[1]. This year, the 4^th generation CMUT (4G CMUT) “SML44” has been brought to the market, achieved using advanced design and precise control of the fabrication process. When combined with new imaging technologies avail-able with the ARIETTA^*2 850, the SML44, in addition to excellent image quality, offers commonly used modalities and func- tions such as Tissue Harmonic Imaging (THI), Color Flow Mapping (CFM), Real-time Tissue Elastography^*3 (RTE), and Real-time Virtual Sonography^*4 (RVS). This report introduces the latest technology adopted in the 4G CMUT design.

There are two ultrasound elastography methods currently available for evaluating liver fibrosis: Strain Imaging and Shear Wave Elastography. Strain imaging can estimate the degree of liver fibrosis without the influence of inflammation whilst the Shear Wave Elastography measurement of fibrosis will be influenced by inflammation, congestion, and jaundice. The two elastography methods use different physical properties, so we examined whether a more accurate diagnosis of liver fibrosis and degree of inflammation is possible by using Real-time Tissue Elastography (RTE, a strain imaging method) and Shear Wave Measurement (SWM, a point Shear Wave Elastography method) simultaneously, and combining the results.