PURFECT
Research type
Research Study
Full title
Perception Ultrasound for Reassuring Fetal Echo Clinical Trainees
IRAS ID
282262
Contact name
Aris T. Papageorghiou
Contact email
Sponsor organisation
University of Oxford / Research Governance, Ethics and Assurance
Duration of Study in the UK
0 years, 6 months, 31 days
Research summary
Ultrasound is a mandatory tool for safely monitoring the growth and development of foetuses during pregnancy. Although pregnancy ultrasound is routinely used in developed countries, it has a major disadvantage, namely a high level of operator dependence: non-experts (or infrequent) users of the technology are often not able to acquire and interpret diagnostic ultrasound images consistently and reliably. Consequently, there is a significant requirement for training, and lack of adequately trained staff is the most commonly reported barrier to the use of ultrasound in developing countries.
Given the biggest challenges of ultrasound use is because it requires a high level of skill to operate, we recognise that to overcome this, we need to simplify the interactions with the ultrasound machine to make it more accessible to healthcare professionals. In clinical obstetrics, imaging planes for obtaining fetal biometry measurements are defined by standard guidelines, however, these provide definitions of what is considered a good diagnostic plane, and not detailed guidelines on how to navigate to the correct view. Our findings in our previous study PULSE (18/WS/0051), has found that the majority of time scanning is spent on searching for an image plane and very little time on analysing/interpreting it.
Within PURFECT we propose to develop ultrasound assistive software that can demonstrate real-time automated image plane guidance based on algorithms developed in PURE. This requires both making the algorithms run in real time, but also understanding how to design an effective communication interface between the AI-based prediction algorithm and human actions. The aim of this project is to build this ultrasound assistive software and to evaluate it in a series of pilot usability studies to understand how AI-assisted image plane navigation can assist a trainee in diagnostic scanning and give them reassurance as a tutor or expert might do in practice.
REC name
North of Scotland Research Ethics Committee 2
REC reference
22/NS/0105
Date of REC Opinion
16 Aug 2022
REC opinion
Favourable Opinion