Sex differences in predicting fluid intelligence of adolescent brain from T1-weighted MRIs

TL;DR

This study investigates sex differences in predicting adolescent fluid intelligence from T1-weighted MRI data using CNN and random forest models, revealing better performance for females and highlighting the need for additional data for accurate predictions.

Contribution

The paper introduces sex-specific models for predicting adolescent fluid intelligence from T1-weighted MRI, demonstrating improved performance when trained separately by sex.

Findings

Random forest models outperformed CNNs in prediction accuracy.

External validation showed better results for females than males.

More data is needed for accurate Gf prediction from MRI features.

Abstract

Fluid intelligence (Gf) has been defined as the ability to reason and solve previously unseen problems. Links to Gf have been found in magnetic resonance imaging (MRI) sequences such as functional MRI and diffusion tensor imaging. As part of the Adolescent Brain Cognitive Development Neurocognitive Prediction Challenge 2019, we sought to predict Gf in children aged 9-10 from T1-weighted (T1W) MRIs. The data included atlas-aligned volumetric T1W images, atlas-defined segmented regions, age, and sex for 3739 subjects used for training and internal validation and 415 subjects used for external validation. We trained sex-specific convolutional neural net (CNN) and random forest models to predict Gf. For the convolutional model, skull-stripped volumetric T1W images aligned to the SRI24 brain atlas were used for training. Volumes of segmented atlas regions along with each subject's age were used to train the random forest regressor models. Performance was measured using the mean squared error (MSE) of the predictions. Random forest models achieved lower MSEs than CNNs. Further, the external validation data had a better MSE for females than males (60.68 vs. 80.74), with a combined MSE of 70.83. Our results suggest that predictive models of Gf from volumetric T1W MRI features alone may perform better when trained separately on male and female data. However, the performance of our models indicates that more information is necessary beyond the available data to make accurate predictions of Gf.