A team of researchers say they may be able to diagnose autism in children from an early age using 3D facial imaging software that can detect minute details in a person’s face.
The team from the University of Missouri-Columbia combined 3D imaging technology with statistical analysis techniques they developed that appear to show a particular pattern among children who have already been diagnosed with autism.
Ye Duan, associate professor of computer science at the university and one of the leads on the project, worked with Judith Miles, professor emerita of child health-genetics, also at the university, to expand upon the existing 2D imaging among children of between eight and 12 years of age.
The addition of 3D imaging gave them access to the curvature of the children’s faces for the first time, which can give a more accurate representation of the child’s face and, according to the university’s page on the research, their analysis revealed there are three distinct facial groupings that could be related to autism.
These sub-groups could then be broken down into the severity of the autism, which could then be applied to early diagnosis of children by scientific means.
According to Miles, it is now up to other research teams elsewhere to run their own analysis using this technique to confirm the findings and create even more accurate diagnoses for autism.
Speaking of why she and Duan undertook the research, Miles said, “Over years of treating children, I noticed that a portion of those diagnosed with autism tend to look alike with similar facial characteristics. I thought perhaps there was something more than coincidence at play. The differences were not abnormal, rather they appeared analogous to similarities observed among siblings.”