Sorry for the inconvenience.

Chinese users are only allowed to visit websites which complies with the PIPL (Personal Information Protection Law of the People's Republic of China) effective November 1st.

▲ Scan or click the QR code to visit 三星医疗




The personal information of existing Samsunghealthcare.com chinese users will be kept until October 29th and will be safely deleted thereafter.

Upgrade browser for full Samsung Healthcare experience

It looks like you may be using a web browser that we don’t support.
Make sure you’re using one of these recommended browsers,
or upgrade your browser by clicking the icons, to get the full Samsung Healthcare experience.

To check which browser you use

https://whatsmybrowser.org/
본문 바로가기

Document

Experience the advances and contributions we have made

White Paper

The intelligent way to evaluate fetal CNS: ViewAssist™ and BiometryAssist™

  • #Ultrasound System>Womens Health
  • writerJa-Young Kwon MD, PhD
  • date2022.08.02
Ultrasound (US) is an indispensable tool in the field of obstetric care. However, fetal US scanning is a time-consuming and labor-intensive process of which performance outcome is greatly affected by the operator’s skill level and knowledge. As overcoming such workload or operator-dependency associated with fetal scanning is a paramount issue, the role of artificial intelligence (AI) technology in fetal ultrasound has been actively explored. Recently, machine-learning techniques have brought significant advancements in US image classification, localization and automated measurement in the field of obstetric US.1-6 Application of AI-assisted systems is very promising in reducing redundant manual steps and improving accuracy of structure localization, caliper placement and measurement.7-9 ViewAssist™ and BiometryAssist™ are built-in, commercially available automated ultrasound imaging software installed on the high-resolution ultrasound system HERA W10, W9, and I10 (SAMSUNG MEDISON Co., Ltd, Seoul, Korea). Recently, ViewAssistTM and BiometryAssistTM have been upgraded to include standard measurements on axial fetal head planes based on machine learning.