Computer Vision recognizes signs of autism in infants

Photo courtesy of MIT Technology Review

The M.I.T. Technology Review reports on the use of a computer vision system that is helping doctors diagnose autism in infants by age 2 and 3 instead of age 5.

Earlier diagnosis makes it possible to teach social and communication skills before other, maladaptive patterns become ingrained in a child’s behavior.

Diagnosing autism in children at younger ages requires a psychologist with expertise in autism to monitor the child closely for long periods of time.

Even when a child or infant’s behavior can be recorded on video, it takes hours of expert analysis, frame by frame, to arrive at a diagnosis.

Now, Jordan Hashemi and a team at the University of Minnesota is using computer vision to discover those at a higher risk for autism, earlier.

For example, child psychologists have developed several tests that screen for delayed tracking by infants with autism like a rattle shaken from one side of the head and then from the other.

To support this and other tests, the custom-developed computer vision system makes very fine assessments such as monitoring head movement along with the position of the left ear, left eye, and nose. Other behaviors analyzed include changes in limb position and gait in response to stimuli.

This blog is sponsored by ImageGraphicsVideo, a company offering ComputerVision Software Development Services.


Kinect cameras may help detect autism

There are stories of new innovative games or programs being developed daily, thanks to the release of Microsoft’s Kinect. However, at the Institute of Child Development in Minneapolis, Minnesota, this technology is being used to help detect autism.

Researchers have installed Kinect cameras in a nursery, which, when combined with specific algorithms, are trained to observe children. The cameras are able to identify children based on their clothing and size, and then compare information about how active the children are as compared to their “classmates,” highlighting those who are more or less active than the average, which could be markers for autism.

Children who show signs of interacting less socially or not possessing fully developed motor skills – indicators of autism – will then be referred to doctors who can better analyze individual cases. While the purpose is not to detect autism 100 percent, the hopes are that this program will pinpoint students who may be cause for concern and catch them early.

Additionally, the creators are working to make the program more advanced, in that it will be able to detect if a child is capable of following an object, as autistic children often have trouble making eye contact, among other things.

Already, some centers are using Kinect not to detect autism, but to help children with it learn to interact socially with others as well as better their own skills.

How else might Kintect assis in detecting or treating autism? What other medical fields might be able to use Kinect to an advantage?