The general public easily recognises the faces of people with Down’s syndrome, but there are over 700 genetic conditions where there are characteristic facial features: the eyes may be set further apart than usual, the nose shorter and the ears set lower down on the head along with many other possible permutations.
Clinical geneticists use these face shape differences as important clues in the early stages of diagnosis prior to detailed clinical examination and genetic testing. These facial differences are often hard to detect, especially for less experienced doctors, but now non-invasive 3D photography and novel analysis techniques are set to make the facial recognition easier.
Professor Peter Hammond from the UCL Institute of Child Health has developed new computer software that compares the faces of undiagnosed children with those with a diagnosed condition that also affects the development of their face, with a 90 per cent success rate.
The technique is an important addition to the diagnostic toolbag as some conditions are so rare that a clinician might only see a handful of cases over a career and so may not recognise the characteristic facial features, especially if the child being examined is much younger than previous cases or from a different ethnic background.
Professor Hammond says: ‘Delay in diagnosis causes anxiety to parents who need advice on risks to future children. Moreover, delay may defer important medical treatment or behavioural training that could improve the prognosis for affected children.’
The specially written software is based on dense surface modelling techniques developed at UCL and compares the child’s face to groups of individuals with known conditions and selects which syndromes look most similar. In order to do this, extensive collections of 3D face images of children and adults with the same genetic condition had to be gathered, as well as controls or individuals with no known genetic condition. Each image contains 25,000 or so points on a face surface capturing even the most subtle contours in 3D. The images are then converted to a compact form that requires only a 100 or so numeric values to represent each face in the subsequent analysis.
Once the software has narrowed down conditions with similar facial features, molecular testing can then be used to confirm the diagnosis. Testing for fewer conditions will save money, time and reduce the amount of stress the child and the parents are put under.
So far the technique has proved fruitful, Professor Hammond says: ‘The technique is currently being applied to over 30 conditions with an underlying genetic abnormality. The discriminatory capability of the approach has proven highly accurate in identifying the characteristic facial features of a variety of genetic conditions, including Cornelia de Lange, Fragile X, Noonan, Smith-Magenis and Velocardiofacial syndromes. It has identified unusual facial asymmetry in children with autism spectrum disorder reflecting known brain asymmetry and has helped to identify genes affecting facial development in Williams syndrome.’
Professor Peter Hammond will give his talk, ‘Your face, your image, your genes’ as part of the session entitled ‘Facing up to genetics’ on 10 September at Physics PX/001, University of York as part of the BA Festival of Science.
Materials provided by British Association for the Advancement of Science. Note: Content may be edited for style and length.
Cite This Page: