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

Lead Research Organisation: University of Oxford
Department Name: Engineering Science

Abstract

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.

Planned Impact

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 n 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.

Publications

10 25 50
 
Description Automated methods were developed and validated to detect and grade obstetric ultrasound images using machine learning methods. Methods were validated on a large hospital database of images and agreement with experts assessed. Methods have been licensed to the business partner to be taken forward towards commercialization.
This is a "world first" in this area addressing an important issue in medical imaging of how to ensure images are "fit for purpose".

A side project looked at, through an Impact Acceleration Award, how related ideas might be adapted to improve manual quality assessment of UK Biobank carotid ultrasound data. This led to an academic publication.
Exploitation Route The business partner is taking this work forward for commercialization. We have also learned a lot about real world sonography in hsospitals and how to assess sonographer performance which will inform future academic research.
We have discussed our findings with international clinical experts in the field.
We are now looking into other related problems to advance uses of ultrasound in clinical practice and have secured NIHR Biomedical Research Centre funding for a further applied project in this area.
Sectors Healthcare

 
Description Methods have been licensed to the business partner to be taken forward towards commercialization. The business partner has gone on to significantly improve on the methods and original research ideas which have been developed into a CE marked device which is undergoing evaluation in a UK hospital as of February 2018. The business partner secured a follow-on InnovateUK award to look at ultrasound image guidance (2017/18).
First Year Of Impact 2016
Sector Healthcare
Impact Types Societal,Economic

 
Description ERC Advanced Grant
Amount € 2,500,000 (EUR)
Organisation European Research Council (ERC) 
Sector Public
Country European Union (EU)
Start 11/2016 
End 10/2021
 
Description GCRF: Growing Research Capability Call
Amount £8,000,000 (GBP)
Funding ID MR/P027938/1 
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 10/2017 
End 09/2021
 
Description Grand Challenge Exploration Phase 1 Round 14
Amount $100,000 (USD)
Funding ID OPP1128941 
Organisation Bill and Melinda Gates Foundation 
Sector Charity/Non Profit
Country United States
Start 11/2015 
End 04/2017
 
Description Oxford EPSRC Impact Acceleration Award (Technology award: AQABUS extension to UK Biobank QA assessment)
Amount £70,000 (GBP)
Funding ID EP/K503769/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 08/2015 
End 07/2016
 
Description Oxford EPSRC Impact Acceleration Award (Technology award: Six-steps)
Amount £70,000 (GBP)
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 01/2015 
End 03/2016
 
Description Oxford NIHR Biomedical Research Centre
Amount £250,000 (GBP)
Organisation National Institute for Health Research 
Department NIHR Biomedical Research Centre
Sector Academic/University
Country United Kingdom
Start 04/2017 
End 03/2022
 
Description CCRF University of Oxford 
Organisation University of Oxford
Department Oxford Cardiovascular Clinical Research Facility (CCRF)
Country United Kingdom 
Sector Academic/University 
PI Contribution A collaboration funded by the Oxford Impact Acceleration Award fund has explored the feasibility of using the software auditing system developed for this project on echocardiography and carotid ultrasound data. Specifically the IAA project funded a clinical research fellow to manually audit data and the viability of automating analysis in the future.
Collaborator Contribution The partner performed manual analysis and contributed to discussions on how analysis might be automated. Data came from CCRF clinical research trials and pilot data from the UK Biobank carotid ultrasound study.
Impact The output was the report on findings which suggest directions in which the work might be taken forward. Options are being explored that might fund future work.
Start Year 2015
 
Description Intelligent Ultrasound Ltd 
Organisation Intelligent Ultrasound Ltd
PI Contribution Partner on EPSRC/Innovate UK SMI Project.
Collaborator Contribution Licence agreement to use IDF software for research purposes. Licence to use AQABUS software for research purposes. IU is an medical image analysis SME and is also part of the MedIAN Network.
Impact See separate entry
Start Year 2013
 
Title Aqabus software 
Description Automated image analysis for describing ultrasound scans. 
IP Reference  
Protection Copyrighted (e.g. software)
Year Protection Granted 2016
Licensed Commercial In Confidence
Impact Licensing the impact.
 
Company Name Intelligent Ultrasound Ltd 
Description Intelligent Ultrasound (IU) develops and sells products and services that make medical ultrasound imaging a more effective diagnostic tool and help hospitals provide a better quality, more consistent ultrasound imaging service for their patients. IUs products are based on sophisticated, proprietary computer algorithms and well-researched insights into patient, clinician and healthcare provider needs. 
Year Established 2012 
Impact Founded by Professor Alison Noble, Dr Aris Papageorghiou and Mr Andy Hill in 2012. Founding investment included funds from the NHS. First product launched 2014. Winner OBN Best Emerging Medtech Company Award 2014. Intelligent Ultrasound Ltd was bought by MedaPhor Group PLC in 2017. IU's AI-based ScanNav product was CE marked in 2017 and the company announced the first evaluation of ScaNav in a UK hospital (St George's London) in February 2018. IU held a InnovateUK project in partnership with Oxford University from 2014-16 (AQABUS).
Website http://www.intelligentultrasound.com/
 
Description Invited talk at CVPR 2017 workshop 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Gave an invited talk as part of a workshop at CVPR 2017 (Hawaii) which aimed to give an overview to computer vision researchers or problems and state-of-the-art research in medical image analysis. A little follow-up but discussion was quite passive (we might have been competing with the weather on the last day of the meeting!)
Year(s) Of Engagement Activity 2017
 
Description Invited talk at International Ultrasonics Symposium 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Invited key note talk in the inaugural session on machine learning in ultrasonics. The session was packed reflecting the interest in not only my group's work but the interest in machine learning as well.
Year(s) Of Engagement Activity 2017
 
Description MISS Summer School 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Invited lecturer at international summer school.
Year(s) Of Engagement Activity 2016
 
Description Microsoft Postgraduate Summer School 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Invited talk at Microsoft Summer school
Year(s) Of Engagement Activity 2016
 
Description OxFest (Oxford) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Postgraduate students
Results and Impact Careers talk as part of OxFest which included presentation of outputs of this research.
Year(s) Of Engagement Activity 2016
 
Description Placenta workshop (New Delhi, India) 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Study participants or study members
Results and Impact The international workshop explored the state-of-art understanding in placental biology through to clinical management of conditions related to abnormal placental function with a focus on understanding implications to the Indian population. International leaders in the field were invited to attend. There was interest in better understanding the state-of-art in placental and fetal imaging and image analysis and I gave a talk on this topic. A number of directions of follow-on were discussed as follow-on.
Year(s) Of Engagement Activity 2015
 
Description Samsung Satellitte Symposium, European Congress in Radiology 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Talk was part of a lunch symposium presenting latest research in AI applied to radiology
Year(s) Of Engagement Activity 2017
 
Description School Visit (Oxford) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Talk to year 9-12 Biomedical Sciences Society on biomedical engineering which including presenting work from this grant.
Year(s) Of Engagement Activity 2016
 
Description School talk 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Talk at Headington School as the Key Note speaker for their Year of Science.
Year(s) Of Engagement Activity 2017
 
Description Schools Careers Evening (Oxford) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Speaker as careers evening for Girls School. Discussions with the school girls including discussion of my research.
Year(s) Of Engagement Activity 2015,2016
 
Description Speaker - International Women in Engineering Day 2017 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Secondary school girls from a number of local schools visited the department to see different areas of engineering and do some simple activities related to engineering. I gave the short talk at tea on some of emerging areas of engineering (wacky engineering) and talked a little about my own research and my field. Feedback from schools was positive for the whole event.
Year(s) Of Engagement Activity 2017
 
Description University of Bath Annual Athena Swan Lecture 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Other audiences
Results and Impact Careers talk which included presentation of work from the research grant.
Year(s) Of Engagement Activity 2015