Predicting intelligence based on cortical WM/GM contrast, cortical thickness and volumetry

TL;DR

This paper introduces a neural network model that predicts fluid intelligence scores from MRI-derived features, including cortical contrast and thickness, achieving moderate correlation on a large dataset.

Contribution

The study presents a novel application of a four-layer neural network utilizing cortical contrast and thickness features for intelligence prediction from MRI data.

Findings

Achieved a correlation of 0.151 on validation data.

MSE of 71.596 on validation set, 94.027 on test set.

Utilized 283 features including cortical and demographic data.

Abstract

We propose a four-layer fully-connected neural network (FNN) for predicting fluid intelligence scores from T1-weighted MR images for the ABCD-challenge. In addition to the volumes of brain structures, the FNN uses cortical WM/GM contrast and cortical thickness at 78 cortical regions. These last two measurements were derived from the T1-weighted MR images using cortical surfaces produced by the CIVET pipeline. The age and gender of the subjects and the scanner manufacturer are also used as features for the learning algorithm. This yielded 283 features provided to the FNN with two hidden layers of 20 and 15 nodes. The method was applied to the data from the ABCD study. Trained with a training set of 3736 subjects, the proposed method achieved a MSE of 71.596 and a correlation of 0.151 in the validation set of 415 subjects. For the final submission, the model was trained with 3568 subjects and it achieved a MSE of 94.0270 in the test set comprised of 4383 subjects.