US lab uses Kinect sensors to spot signs of autism

Microsoft’s Kinect motion-sensing device now has yet another new application in medicine: helping keep track of children for signs of autism so they can be treated early.

 

“Diagnosing an autism spectrum disorder (ASD) in young children is tricky, but the earlier a child can begin speech therapy and get help learning social and communication skills, the better. Many different symptoms may suggest a child has an ASD, but they are subtle. It usually takes an experienced doctor to spot the signs by analyzing video footage of the child playing - a costly and time-consuming process,” NewScientist.com said.  

“Early diagnosis is critical in helping people with autism get the support they need,” added Caroline Hattersley of The National Autistic Society in London. A setup using five Kinect motion sensors has been set up at the Shirley G. Moore Laboratory School in Minneapolis, where children’s every move is watched, NewScientist.com reported.

 

The setup combines Kinect hardware with computer-vision algorithms programmed to detect behavioral abnormalities to automate the early diagnosis of autism.

 

Researchers Guillermo Sapiro, Nikolaos Papanikolopoulos and colleagues set up the devices in the nursery to monitor groups of around 10 children aged between 3 and 5 as they play.

 

“The cameras identify and track children based on their shape and the color of the clothes they are wearing. The information is fed to three PCs, which run software that logs each child’s activity level - including how they move each of their limbs - and plots it against the room’s average. The system can flag up children who are hyperactive or unusually still - both possible markers for autism,” NewScientist.com said.

 

With the data, medical staff can decide if a child requires closer attention from a specialist for a one-on-one diagnosis.

 

NewScientist.com said the system will be presented at the IEEE International Conference on Robotics and Automation in St Paul, Minnesota, this month.

 

“The idea is not that we are going to replace the diagnosis, but we are going to bring diagnosis to everybody. The same way a good teacher flags a problem child, the system will do automatic flagging and say, ‘Hey, this kid needs to see an expert,’” Sapiro said.

 

Next level

 

NewScientist.com said the team aims to merge its work with another project - by studying video footage of children interacting with a psychiatrist, computer-vision algorithms can learn to identify behavioral markers as defined in the Autism Observation Scale for Infants.

 

The system measures traits like a child’s ability to follow an object as it passes in front of the eyes, as well as noting certain mannerisms or postures that are classified as being early signs of a possible ASD. Early tests have been in agreement with professional diagnosis, says Sapiro.

 

But Hattersley said specialists are still needed even if this technology could potentially identify some signs of autism, since there are factors it may miss such as language delay and limited eye contact.

 

Sapiro said they are trying to do very difficult and expert analysis that a psychiatrist would do, but automatically.

 

He is eyeing a specially developed video game for Kinect that would test a child as they played with a parent and flag up any concerns. — ELR, GMA News