By AuntMinnieEurope.com staff writers

November 28, 2018 -- U.K. ultrasound training and quality assurance firm MedaPhor announced its database used for artificial intelligence (AI) training now exceeds 1 million obstetric ultrasound images.

Large image libraries are a prerequisite to creating AI software, and they have helped MedaPhor develop its ScanNav AI-based clinical software for ultrasound professionals. The 1 million mark is a significant milestone for the company as it will enable MedaPhor to build on its ScanNav software for the global obstetric ultrasound market, the firm said.

MedaPhor's ScanNav is currently being piloted in U.K. hospitals to support sonographers carrying out the 20-week anatomy scan. ScanNav assists sonographers to ensure the images conform to the U.K. Fetal Anomaly Screening Programme protocol. In the future, the software will also be capable of automatically recording required images during the ultrasound scan, MedaPhor said.

To develop ScanNav, MedaPhor worked with anonymized ultrasound scans taken throughout pregnancy in eight countries. The latest addition to the ScanNav image library comes from a collaboration with University College London Hospitals National Health Service (NHS) Foundation Trust (UCLH) in the U.K., which is using the ScanNav software to audit its routine obstetric ultrasound practice.

By continuing to increase the image library, MedaPhor is able to improve the discrimination of existing software; develop ScanNav for a range of other global obstetric protocols at different stages of fetal development; and push forward automatic recognition and recording of images during routine scans.


Copyright © 2018 AuntMinnieEurope.com
 

To read this and get access to all of the exclusive content on AuntMinnieEurope.com create a free account or sign-in now.

Member Sign In:
MemberID or Email Address:  
Do you have a AuntMinnieEurope.com password?
No, I want a free membership.
Yes, I have a password:  
Forgot your password?
Sign in using your social networking account:
Sign in using your social networking
account: