Computer-aided diagnosis of rare genetic disorders from family snaps

June 24, 2014
This image shows an average face taking on the average facial features of eight rare genetic disorders that have been built from a growing bank of photographs of people diagnosed with different syndromes. Oxford University scientists have developed a computer program to help doctors diagnose rare genetic disorders by recognizing facial structure in photographs. Credit: Christoffer Nellåker/Oxford University

Computer analysis of photographs could help doctors diagnose which condition a child with a rare genetic disorder has, say Oxford University researchers.

The researchers, funded in part by the Medical Research Council (MRC), have come up with a computer programme that recognises in photographs; looks for similarities with facial structures for various conditions, such as Down's syndrome, Angelman syndrome, or Progeria; and returns possible matches ranked by likelihood.

Using the latest in computer vision and , the algorithm increasingly learns what facial features to pay attention to and what to ignore from a growing bank of photographs of people diagnosed with different syndromes.

The researchers report their findings in the journal eLife. The study was funded by the MRC, the Wellcome Trust, the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre (BRC) and the European Research Council (ERC VisRec).

While genetic disorders are each individually rare, collectively these conditions are thought to affect one person in 17. Of these, a third may have symptoms that greatly reduce quality of life. However, most people fail to receive a genetic diagnosis.

'A diagnosis of a can be a very important step. It can provide parents with some certainty and help with genetic counselling on risks for other children or how likely a condition is to be passed on,' says lead researcher Dr Christoffer Nellåker of the MRC Functional Genomics Unit at the University of Oxford. 'A diagnosis can also improve estimates of how the disease might progress, or show which symptoms are caused by the genetic disorder and which are caused by other clinical issues that can be treated.'

The team of researchers at the University of Oxford included first author Quentin Ferry, a DPhil research student, and Professor Andrew Zisserman of the Department of Engineering Science, who brought expertise in computer vision and machine learning.

Professor Zisserman says: 'It is great to see such an inventive and beneficial use of modern face representation methods.'

Identifying a suspected developmental disorder tends to require clinical geneticists to come to a conclusion based on facial features, follow up tests and their own expertise. It's thought that 30–40% of rare genetic disorders involve some form of change in the face and skull, possibly because so many genes are involved in development of the face and cranium as a baby grows in the womb.

The researchers set out to teach a computer to carry out some of the same assessments objectively.

They developed a programme that – like Google, Picasa and other photo software – recognises faces in ordinary, everyday photographs. The programme accounts for variations in lighting, image quality, background, pose, facial expression and identity. It builds a description of the face structure by identifying corners of eyes, nose, mouth and other features, and compares this against what it has learnt from other photographs fed into the system.

The algorithm the researchers have developed sees patients sharing the same condition automatically cluster together.

The computer algorithm does better at suggesting a diagnosis for a photo where it has previously seen lots of other photos of people with that syndrome, as it learns more with more data.

Patients also cluster where no documented diagnosis exists, potentially helping in identifying ultra-rare genetic disorders.

'A doctor should in future, anywhere in the world, be able to take a smartphone picture of a patient and run the computer analysis to quickly find out which the person might have,' says Dr Nellåker.

'This objective approach could help narrow the possible diagnoses, make comparisons easier and allow doctors to come to a conclusion with more certainty.'

Explore further: Researchers advance autism diagnosis

More information: The paper 'Diagnostically-relevant facial gestalt information from ordinary photos' by Quentin Ferry and colleagues is to be published in the journal eLife on Tuesday 24 January 2014.

Related Stories

Researchers advance autism diagnosis

June 5, 2014
(Medical Xpress)—University of Queensland researchers have led a study that will help unravel the genetic mystery of autism and, for the first time, help diagnose children under two years of age with the disorder.

Researchers pinpoint genetic pathway of rare facial malformation in children

May 3, 2012
Researchers at Seattle Children's Research Institute and their collaborators have discovered a pair of defective genes that cause a rare congenital malformation syndrome that can make it impossible for the child to breathe ...

Scientists develop refined diagnostic tool for inherited dementias

September 16, 2013
Researchers at the Medical Research Council (MRC) have developed and tested a more efficient and cost effective way to diagnose early onset, genetic forms of dementia.

Recommended for you

Scientists identify new way cells turn off genes

July 19, 2017
Cells have more than one trick up their sleeve for controlling certain genes that regulate fetal growth and development.

South Asian genomes could be boon for disease research, scientists say

July 18, 2017
The Indian subcontinent's massive population is nearing 1.5 billion according to recent accounts. But that population is far from monolithic; it's made up of nearly 5,000 well-defined sub-groups, making the region one of ...

Mutant yeast reveals details of the aberrant genomic machinery of children's high-grade gliomas

July 18, 2017
St. Jude Children's Research Hospital biologists have used engineered yeast cells to discover how a mutation that is frequently found in pediatric brain tumor high-grade glioma triggers a cascade of genomic malfunctions.

Late-breaking mutations may play an important role in autism

July 17, 2017
A study of nearly 6,000 families, combining three genetic sequencing technologies, finds that mutations that occur after conception play an important role in autism. A team led by investigators at Boston Children's Hospital ...

Newly discovered gene variants link innate immunity and Alzheimer's disease

July 17, 2017
Three new gene variants, found in a genome wide association study of Alzheimer's disease (AD), point to the brain's immune cells in the onset of the disorder. These genes encode three proteins that are found in microglia, ...

Newly identified genetic marker may help detect high-risk flu patients

July 17, 2017
Researchers have discovered an inherited genetic variation that may help identify patients at elevated risk for severe, potentially fatal influenza infections. The scientists have also linked the gene variant to a mechanism ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.