Magnetic Resonance Imaging (MRI) -- a common technique used to obtain images of human internal organs and tissues -- may help predict intelligence levels in children, a study suggests.
Scientists from Skolkovo Institute of Science and Technology in Russia used ensemble methods based on deep learning 3D networks to analyse whether the intelligence level can be predicted from an MRI brain image.
They used the US National Institutes of Health (NIH) database containing a total of over 11,000 structural and functional MRI images of children aged 9-10.
The study, published in the journal Adolescent Brain Cognitive Development Neurocognitive Prediction, focused on predicting the intelligence level, or the so called "fluid intelligence."
Fluid intelligence is the capacity to think logically and solve problems in novel situations, independent of acquired knowledge.
The researchers made predictions for both the fluid intelligence level and the target variable independent from age, gender, brain size or MRI scanner used.
"We applied ensembles of classifiers to 3D of super precision neural networks: with this approach, one can classify an image as it is, without first reducing its dimension and, therefore, without losing valuable information," said PhD student, Ekaterina Kondratyeva.
The study helped find the correlation between the child's "fluid intelligence" and brain anatomy.
Although the prediction accuracy is less than perfect, the models produced will help shed light on various aspects of cognitive, social, emotional and physical development of adolescents, the researchers said.
Disclaimer: No Business Standard Journalist was involved in creation of this content
