iFIND- 1. US Data
Research type
Research Study
Full title
Intelligent Fetal Imaging and Diagnosis-1. Ultrasound Scan Data Collection
IRAS ID
164026
Contact name
Reza Razavi
Sponsor organisation
King's College London
Duration of Study in the UK
6 years, 1 months, 24 days
Research summary
Ultrasound, which passes sound waves into the body to create pictures from their reflections, is commonly used to check that babies in the womb (or fetuses) are healthy. Although every pregnant mother in the country has a scan at around 20 weeks, not all of the babies who have problems are picked up on these ultrasound scans. Despite substantial improvement in detection rates over the last few years there is still regional and hospital-specific variation in prenatal detection rates of major anomalies, as well as limitations in current ultrasound technology including restricted views and poor image quality.
We are proposing new technologies that allow scanning to be carried out with not just one probe (the device which takes the ultrasound picture), but up to four of these that can be used at the same time and which move automatically to the right place to get the best pictures. This will mean we get a detailed picture of the whole baby which can then be analysed in an automatic way using advanced computer technologies to ensure we do not miss babies with potential problems. This should mean a high quality scanning service across the country which is not dependent on local expertise, and fewer babies who have major problems will be missed.
In this phase we hope to improve fetal ultrasound imaging through automated image processing. We will capture the data from routine 20 week anomaly scans and use the information to help create machine learning algorithms to determine normal from abnormal structures in future ultrasound scans.
REC name
London - London Bridge Research Ethics Committee
REC reference
14/LO/1805
Date of REC Opinion
10 Dec 2014
REC opinion
Further Information Favourable Opinion