AI Predicts Autism From Infant Brain Scans – IEEE Spectrum

Twenty-two years ago, researchers first reported that adolescents with autism spectrum disorder had increased brain volume. During the intervening years, studies of younger and younger children showed that this brain overgrowth occurs inchildhood.

Now, a team at the University of North Carolina, Chapel Hill, has detected brain growth changes linked to autism in children as young as 6 months old. And it piqued our interest because a deep-learning algorithm was able to use that data to predict whether a child at high-risk of autism would be diagnosed with the disorder at 24 months.

The algorithm correctly predicted the eventualdiagnosis in high-risk children with 81 percentaccuracy and 88 percentsensitivity. Thats pretty damn good compared withbehavioral questionnaires, which yield informationthat leads to early autism diagnoses(at around 12 months old) that are just 50 percent accurate.

This is outperforming those kinds of measures, and doing it at a younger age, says senior author Heather Hazlett, a psychologist and brain development researcher at UNC.

As part of the Infant Brain Imaging Study, a U.S. National Institues of Healthfunded study of early brain development in autism, the research team enrolled 106 infants withan older sibling who had been givenan autism diagnosis, and 42 infants with no family history of autism. They scanned each childs brainno easy feat with an infantat 6-, 12-, and 24 months.

The researchers saw no change in any of the babies overall brain growth between 6- and12-month mark.But there was a significant increase in the brain surface area of the high-risk children who were later diagnosed with autism. That increase in surface area was linked to brain volume growth that occurred between ages 12 and 24 months. In other words, in autism, the developing brain first appears to expand in surface area by 12 months, then in overall volume by 24 months.

The team also performed behavioral evaluations on the children at 24 months, when they were old enough to begin to exhibit the hallmark behaviors of autism, such as lack of social interest, delayed language, and repetitive body movements. The researchers note that the greater thebrain overgrowth, the more severe a childs autistic symptoms tended to be.

Though thenew findings confirmed that brain changes associated with autism occur very early in life,the researchers did not stop there. In collaboration with computer scientists at UNC and the College of Charleston, the team built an algorithm, trained it with the brain scans, and tested whether it could use these early brain changes to predict which children would later be diagnosed with autism.

It worked well. Using just three variablesbrain surface area, brain volume, and gender (boys are more likely to have autism than girls)the algorithm identified up eight out of 10 kids with autism. Thats pretty good, and a lot better than some behavioral tools, says Hazlett.

To train the algorithm, the team initially used halfthe data for training and the other half for testingthe cleanest possible analysis, according to team memberMartin Styner, co-director of the Neuro Image Analysis and Research Lab at UNC. But at the request of reviewers, they subsequently performed a more standard 10-fold analysis, in which data is subdivided into 10 equal parts. Machine learning is then done 10 times, each time with 9 folds used for training and the 10th saved for testing. In the end, the final program gathers together the testing only results from all 10 rounds to use in its predictions.

Happily, the two types of analysesthe initial 50/50 and the final 10-foldshowed virtually the same results, says Styner. And the team was pleased with the prediction accuracy. We do expect roughly the same prediction accuracy when more subjects are added, said co-author Brent Munsell, an assistant professor at College of Charleston, in an email to IEEE. In general, over the last several years, deep learning approached that have been applied to image data have proved to be very accurate, says Munsell.

But, like our other recent stories on AI out-performing medical professionals, the results need to be replicated before well see a computer-detected biomarker for autism. That will take some time, because it is difficult and expensive to get brain scans of young children for replication tests, emphasizes Hazlett.

And such an expensive diagnostic test will not necessarily be appropriate for all kids, she adds. Its not something I can imagine being clinically useful for every baby being born. But if a child were found to have some risk for autism through a genetic test or other marker, imaging could help identify brain changes that put them at greater risk, she notes.

IEEE Spectrums biomedical blog, featuring the wearable sensors, big data analytics, and implanted devices that enable new ventures in personalized medicine.

Sign up for The Human OS newsletter and get biweekly news about how technology is making healthcare smarter.

Doctors outperform online apps at diagnosing symptoms 10Oct2016

Artificial intelligence performs just as well as eye docs in diagnosing congenital cataracts 1Feb

Deep learning algorithm identifies skin cancers as accurately as dermatologists 25Jan

Language barriers and human interfaces slow adoption of diagnostic-aid tech 11Nov2016

Medtronic's 252-electrode vest helps doctors pinpoint electrical malfunctions of the heart 9Feb

System captures Mach cone from laser pulse 20Jan

Class-action lawsuits target the biometric privacy policies of several Internet giants 29Dec2016

3D visualization of flu particles helps a vaccine manufacturer predict how to protect against the virus 15Dec2016

With wireless optogenetic tools, neuroscientists steer mice around their cages 28Nov2016

The new device can wrap around objects to image items with 3D curves 14Nov2016

Each fellow gets $825,000 to further their inventions 2Nov2016

Now used to brighten displays, quantum dots could one day guide a surgeons hand 21Sep2016

Researchers use fMRI feedback to "brain train" volunteers so that they had more positive or negative feelings about a person's face 16Sep2016

Raising $2.7 million was the easy part. Making devices for 13,000 backers has proven harder 14Sep2016

Low production costs make technique available to developing countries for detecting a wide variety of diseases 21Jul2016

Iris scanners provide excellent biometric identification, but they can be spoofed 20Jul2016

The U.S. governments Human Connectome Project moves into its second phaseand its brain scans are being used to predict individuals behavior and intelligence 21Jun2016

Brain scans provide a glimpse of a patients prognosis 15Jun2016

The virtual biopsy could lead to more accurate diagnoses of brain injury and PTSD, and better treatments 10Jun2016

New method exploits the luminescence of carbon nanotubes to detect tumors deep inside tissue 24May2016

Read the rest here:

AI Predicts Autism From Infant Brain Scans - IEEE Spectrum