Automating quality assessment of B-mode ultrasound scans (AQABUS)

Diagnostic quality of ultrasound (US) scans of the same patient can vary significantly, depending on the level of skill and
expertise of the sonographer and the equipment used. This well documented operator dependence of quality can lead to
misdiagnosis; unnecessary referrals to other imaging modalities; rescans; and results in inefficiencies in clinical workflow
with associated added healthcare costs.
In order to avoid the resultant delayed or incorrect stratification, sonographers are encouraged to follow standardised
acquisition protocol guidelines. Clinical studies show the benefit of this. However, no systematic image reviews are
undertaken. This lack of standardization and monitoring of conformance has implications for the quality of diagnosis and
clinical decisions made in a health service, and is also a key barrier to wider adoption of US as a cost-effective technology
for stratified medicine.
In a collaboration between Intelligent Ultrasound Ltd and Oxford University, the AQABUS project proposes to develop and
evaluate a technology platform for automated quality assessment of US scans. The solution will be delivered as a Quality
Assurance Service (QAS) to imaging departments, to assess whether scans are fit for purpose. Innovations include
creation of the IT infrastructure for delivering such a service; clinical design of QA reporting; and machine learning to
automate image QA which is key to the business proposition.

Beyond academic engineering and clinical medicine researchers, beneficiaries of the research are:
1. Clinicians - feedback on scan quality will help imaging leads to identify sonographers who may need remedial training,
and ensure scanning is of a consistently high standard. Monitoring should reduce the number of recalls, lead to fewer
missed diagnoses, and hence reduce costs and increase department efficiency. Obstetrics is the first clinical area that will
benefit (the area chosen for this project) but if successful, other areas of medicine may adopt similar practices.
2. NHS/hospital managers - feedback on imaging department performance will ensure hospital imaging services are of the
highest level, identify areas of improvement, and reduce the likely of litigation due to "wrongful birth" (estimated to cost the
NHS around £60 million annually).
3. Patients - monitoring of scanning quality may reduce the number of recalls and lead to fewer missed diagnoses, thus
improving patient management and reducing pregnancy risk.
4. Industry - Intelligent Ultrasound will be the immediate commercial beneficiary of the outputs of this research and use it to
inform new products. Product sales will allow the company to grow and creates jobs. Ensuring ultrasound imaging is of
consistently high quality has been a barrier to introduction of ultrasound imaging in some areas of medicine. Ultrasound
equipment manufacturers (eg. Philips, GE, Siemens, Toshiba etc), may benefit by increased sales of equipment if quality
issues can be overcome by using such a QA service.
5. Beneficiaries are not restricted to the UK health service, and the outputs of this project has the potential to impact
ultrasound-based healthcare delivery worldwide, including in the developing world where ultrasound is one of a few lowcost
imaging solutions.
The timescale of demonstrated impact are likely to be on the short to medium scale, post project end. Short term impact
will be demonstrated in obstetrics. Medium term impacts are likely to be demonstration in other areas of medicine, and
eventually through adoption of the QA approach as a NICE guideline or equivalent.