Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

Professor Sally Collins has been awarded the prestigious and highly competitive Sir Jules Thorn Translational Biomedical Research Award 2021 for further translational development of the OxNNet Toolkit.

Woman having an ultrasound scan performed by Professor Sally Collins © Professor Sally Collins

It is with great pleasure we announce that Professor Sally Collins (Nuffield Department of Women’s & Reproductive Health) with the support of our Translational Research Office (Dr Deepak Kumar) and Oxford University Innovation (Dr Benedicte Menn) has been awarded the prestigious and highly competitive Sir Jules Thorn Translational Biomedical Research Award 2021. The last time this award was made to the University of Oxford was 10 years ago in 2011. Professor Collins receives just under £1 million by the charitable trust to further the translational development of the OxNNet Toolkit.

Professor Collins’ project aims to test the clinical performance of a robust, non-invasive, early screening test to identify babies at risk of adverse pregnancy outcomes through early detection of fetal growth restriction (FGR). FGR is the single greatest risk factor for stillbirth, a pregnancy outcome which is not only devastating for families but also costs the NHS >£12 million annually.  This test aims to identify pregnancies at greatest risk of FGR, thereby appropriately targeting NHS resources to monitoring those pregnancies where timely delivery of the baby would prevent stillbirth and result in the greatest clinical benefit.

The test for FGR that Professor Collins’s group has built uses placental metrics automatically generated from 3D-ultrasound images using state-of-the-art artificial intelligence (AI) technology. The patented software, the OxNNet Toolkit, is based on a multi-class fully convolutional neural network, developed using 2,400 first trimester 3D-ultrasound scans, which has been combined with other novel imaging solutions including automated measures of vascularity and artefact removal techniques. Pilot data has shown that the performance of the placental metrics automatically generated by the OxNNet Toolkit is equivalent to those produced by manual segmentation for the prediction of FGR, and outperforms the only available, semi-automated tool, VOCAL™.

Professor Collins has made rapid progress in the translational development of this project due to the support of the multi-disciplinary team she has established with relevant world-leading expertise and solid stakeholder engagement (Perspectum Ltd). The project is supported by the University’s Technology Transfer Office (Oxford University Innovations) and Medical Sciences Division Translational Research Office, which has resulted in patent protection of the OxNNet Toolkit and its swift progression towards commercialisation. Funding by Sir Jules Thorn will allow the study to recruit 3500 women in Oxford to assess the clinical efficacy and healthcare economics of using the OxNNet toolkit to predict fetal growth restriction over the next three years.

Similar stories

Long COVID: vaccination could reduce symptoms, new research suggests

While evidence suggests that people who are vaccinated before they get COVID are less likely to develop long COVID than unvaccinated people, the effectiveness of vaccination on existing long COVID has been less clear.

Com-COV vaccine study to research third dose booster options for 12-to-15-year-olds

Researchers running the University of Oxford-led Com-COV programme have launched a further study of COVID-19 vaccination schedules in young people aged 12 to 15 – with a focus on assessing different options for a third dose booster vaccination.

Population-scale study highlights ongoing risk of COVID-19 in some cancer patients despite vaccination

COVID-19 vaccination is effective in most cancer patients, but the level of protection against COVID-19 infection, hospitalisation and death offered by the vaccine is less than in the general population and vaccine effectiveness wanes more quickly.

New reporting guidelines developed to improve AI in healthcare settings

New reporting guidelines, jointly published in Nature Medicine and the BMJ by Oxford researchers, will ensure that early studies on using Artificial Intelligence (AI) to treat real patients will give researchers the information needed to develop AI systems safely and effectively.

Major boost for Oxford’s mission to counter future pandemic threats

The Moh Family Foundation has given a substantial gift to support the work of Oxford University’s Pandemic Sciences Institute, greatly strengthening its ability to identify and counter future pandemic threats and ensure equitable access to treatments and vaccines around the world.