Please note, this page may contain outdated information or subject matter.

You are here:

Brain damage in babies: could sophisticated computing allow earlier diagnosis and better care?

Published on


This research was completed on

Around 50,000 babies are born prematurely each year in the UK, putting them at risk of developing brain damage.1,2,a,b This can cause serious, lifelong disabilities such as cerebral palsy, blindness and learning difficulties. However, brain damage often goes undiagnosed, sometimes for months or even years, until a child’s disability becomes apparent. Researchers are developing sophisticated new computer software, which analyses MRI scans of babies’ brains and helps diagnose abnormalities, so babies can get an earlier diagnosis and better care.

This award is part of a Healthcare Partnerships grant jointly funded by the Engineering and Physical Sciences Research Council (EPSRC) and Action Medical Research. The EPSRC has awarded £1,023,477 to the research team.

What's the problem and who does it affect?

Brain damage in babies can cause lifelong disability

Around 7% of births in the UK are premature.2,b Sadly, an early birth puts babies at risk of death and disability, often because of brain damage.

Damage to a tiny baby’s vulnerable brain can lead to lifelong difficulties such as cerebral palsy, blindness, hearing loss, speech problems, behavioural problems and learning disabilities.

The statistics make worrying reading: one in five babies born before 26 weeks of pregnancy – that’s about six months – develops severe disabilities and four in ten have learning difficulties at the age of six.3

It’s not easy to tell whether or not a baby has suffered brain damage, as their problems may not become apparent until months or even years later. MRI scans can sometimes help, particularly if brain damage is severe, but they are not normally available routinely – interpreting the scans is extremely time-consuming and complicated, and is dependent on the subjective assessment of trained experts.

Without accurate information from scans, parents can face an anxious wait to find out whether their baby is going to develop a disability, and babies can miss out on getting the right sort of help as early as possible.

What is the project trying to achieve?

Automated diagnosis and prediction

The researchers are developing computer software, which will automate the analysis of MRI information, helping interpret scans of babies’ brains, diagnose any brain damage and predict whether the babies are likely to develop disabilities as they grow and develop. MRI scanning is a well-established and safe technique that can provide detailed, three-dimensional pictures of inside the body.

The researchers’ ambitious plan of action involves several steps:

  1. developing computerised ‘growth charts’, which show how babies’ brains develop both during pregnancy and after a premature birth, using MRI images from 100 unborn babies in the womb and over 1000 premature babies
  2. identifying salient differences between normal, and abnormal, patterns of brain development as evident in MRI images; these differences, known as biomarkers, will be used to diagnose brain damage and predict whether babies will develop disabilities
  3. developing computer software, for use by doctors, which analyses MRI scans, helping diagnose brain damage and predict how babies will be affected
  4. assessing the software’s performance – in two clinical trials of possible new treatments for babies with brain damage, for example
  5. informing doctors, radiographers, nurses and parents about the research, and providing training in how to use the new technique.

What are the researchers' credentials?


Several world-leading researchers with complementary expertise – in computer science, taking MRI scans of babies’ brains and caring for newborns – are working together on this ambitious project.

The project leader, Professor Daniel Rueckert is a computer scientist with an established track record in developing computer programs that analyse and interpret MRI scans of the brain automatically. Dr Paul Aljabar also specialises in this area of research.

Professor Jo Hajnal is a physicist with extensive experience of researching new and better ways of acquiring MRI scans. He is particularly interested in obtaining high-quality images of newborn babies, and babies within the womb, who cannot be told to stay still during the scanning procedure.

Professor Mary Rutherford is a renowned expert, with over 20 years’ experience of using MRI scans to assess babies’ developing brains, both after birth and during pregnancy. Professor David Edwards is a neonatologist – a doctor who specialises in caring for newborn babies. He has led ground-breaking research into the causes of brain damage in babies and has a track record of innovation in developing new therapies.

The team has access to state-of-the-art facilities, including a dedicated MRI scanner within a neonatal intensive care unit.

Who stands to benefit from this research and how?

Helping babies combat brain damage

The researchers hope to improve the lives of premature babies and their families. They are developing a new, computer-aided way of interpreting MRI scans of babies’ brains. This could help doctors to tell whether or not a baby has suffered brain damage, what sort of damage it is, and whether the baby is likely to develop a disability as he, or she, grows and develops.

This information can be invaluable for parents, who generally want to know what sort of outlook their baby has for the future. It could also mean babies stand a better chance of getting earlier and more appropriate care, which could improve their quality of life. The new technique could also help researchers assess the pros and cons of possible new therapies.

Babies born at full term could benefit too, as the new technique could help all babies who are suspected of having a brain injury, whatever the cause. That includes babies with a serious condition called birth asphyxia, who can develop brain damage after being starved of oxygen at birth, and babies who suffer a brain injury during pregnancy, who account for a significant proportion of all children with cerebral palsy.4


  1.  Office for National Statistics. Health Statistics Quarterly 43 (Autumn 2009), Table 2.1 
  2. The Information Centre, Community Health Statistics. NHS Maternity Statistics, England: 2006-07, 2007-08, 2008-09 http://www.ic.nhs.uk/statistics-and-data-collections/hospital-care/mater...
  3. Marlow N, Wolke D, Bracewell MA, Samara M. Neurologic and developmental disability at six years of age after extremely preterm birth. N Engl J Med 2005; 352:9-19.
  4. Surman G., Newdick H. and Johnson A. Cerebral palsy rates among low-birthweight infants fell in the 1990s. Developmental Medicine & Child Neurology 2003; 45: 456-462.
    a. Calculation made by Action Medical Research based on figures in references 1 and 2 for the number of births a year in the UK and the number of preterm deliveries in England, respectively.
    b. Estimate assumes incidence of premature birth is the same for the UK overall as it is for England.


Project Leader Professor D Rueckert PhD MSc
Project Team Professor A David Edwards FMED SCiProfessor Joseph Hajnal PhDProfessor Mary A Rutherford MD FRCPCH FRCR Dr Paul Aljabar PhD MSc
Project Location Department of Computing and Division of Clinical Sciences, Imperial College and Hammersmith Hospital, London
Project Location Other Division of Clinical Sciences, Imperial College London and Hammersmith HospitalDivision of Imaging Sciences & Biomedical Engineering, King's College London
Project duration 4 years
Date awarded 22-Jun-10
Project start date 01-Oct-10
Project end date 30-Sep-14
Grant amount £50,000
Grant code SP4578, GN1772


We do not provide medical advice. If you would like more information about a condition or would like to talk to someone about your health, contact NHS Choices or speak to your GP.