MRI may predict intelligence level in children, study reveals

The MRI technique helps to obtain images of human internal organs and tissues

In a new study, researchers have claimed that Magnetic Resonance Imaging (MRI) may predict intelligence level in children. The MRI technique helps to obtain images of human internal organs and tissues.

To answer the global Magnetic Resonance Imaging (MRI) prevision challenge for children, the researchers used ensemble methods based on deep learning 3D analysis networks and predicted for both the fluid intelligence level as well as the target variable independent from age, gender, brain size or MRI scanner used.

Ekaterina Kondratyev from Skolkovo Institute of Science and Technology (Skoltech) in Russia, said: "In this study, 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."

Adolescent Brain Cognitive Development

In 2013, the US National Institutes of Health (NIH) had launched the first grand-scale study of its kind in adolescent brain research, Adolescent Brain Cognitive Development. The study was aimed to understand how teenagers' hobbies and habits affect their further brain development. According to reports, NIH database contains a total of over 11,000 structural and functional MRI images of children aged 9-10.

Recently, the NIH had launched an international competition to build a predictive model based on brain images and gave access to the enormous NIH database to all the participants. The Skoltech team applied neural networks for MRI image processing as a part of the competition.

Mathematical models

The researchers built a network architecture enabling several mathematical models to be applied to the same data in order to increase the prediction accuracy, and used a novel ensemble method to analyse the MRI data.

According to the Skoltech researchers, they focused on predicting the intelligence level, or the so called "fluid intelligence", which characterises the biological abilities of the nervous system and has little to do with acquired knowledge or skills.

The study findings found the correlation between the child's "fluid intelligence" and brain anatomy. The researchers said that though the prediction is not completely perfect, the models that were produced during the competition will shed light on various aspects of cognitive, social, emotional and physical development of adolescents.