Identifying Non-Math Students from Brain MRIs with an Ensemble Classifier Based on Subspace-Enhanced Contrastive Learning.

In current research processes, mathematical learning has significantly impacted the brain's plasticity and cognitive functions. While biochemical changes in brain have been investigated by magnetic resonance spectroscopy, our study attempts to identify non-math students by using magnetic resonance imaging scans (MRIs). The proposed method crops the left middle front gyrus (MFG) region from the MRI, resulting in a multi-instance classification problem. Then, subspace enhanced contrastive learning is employed on all instances to learn robust deep features, followed by an ensemble classifier based on multiple-layer-perceptron models for student identification. The experiments were conducted on 123 MRIs taken from 72 math students and 51 non-math students. The proposed method arrived at an accuracy of 73.7% for image classification and 91.8% for student classification. Results show the proposed workflow successfully identifies the students who lack mathematical education by using MRI data. This study provides insights into the impact of mathematical education on brain development from structural imaging.