Medical products: Facial recognition technology to diagnose rare genetic diseases
1 Dec 2015
Dr Christoffer Nellaker at the MRC Functional Genomics Unit, University of Oxford has developed facial recognition technology that could help diagnose rare genetic diseases.
Around 30-40 per cent of genetic disorders, including Down’s syndrome and Marfan syndrome, involve changes to the face or skull. This is because many genes are involved when the face and head develop and so if there is a DNA change in one of these genes it is very likely that it will cause a change to the head or facial structure.
The new software is based on research involving thousands of pictures of previously diagnosed patients. It is able to ‘learn’ the facial features characterising each disorder and recognise which to look for and which to ignore when suggesting a diagnosis. It will also be able to group together patients with unknown disorders who have similar skull structures and facial features. This will potentially enable doctors to identify new disorders and the DNA variations that cause them.
The software is based on an algorithm that uses basic equipment and so could fairly easily be adapted for use in countries where genetic disease diagnosis is not readily accessible. It could help narrow down the tests needed to diagnose an individual, critical in healthcare systems where money is a factor in determining how many tests are carried out.
Dr Nellaker developed the software in collaboration with Professor Andrew Zisserman at the university’s department of engineering science who was funded by the Engineering and Physical Sciences Research Council (EPSRC).
The researchers are now taking this forward with an MRC Methodology Research Fellowship and a MRC Methodology Research Grant. Collaborations are being formed with clinicians around the world with the aim to bring this to patients as soon as possible.
Image: An artistic representation of the facial recognition software. Credit: Emma Nellaker.