Predicting cognitive scores with graph neural networks through sample selection learning

Martin Hanik, Mehmet Arif Demirtaş, Mohammed Amine Gharsallaoui, Islem Rekik (Lead / Corresponding author)

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
49 Downloads (Pure)

Abstract

Analyzing the relation between intelligence and neural activity is of the utmost importance in understanding the working principles of the human brain in health and disease. In existing literature, functional brain connectomes have been used successfully to predict cognitive measures such as intelligence quotient (IQ) scores in both healthy and disordered cohorts using machine learning models. However, existing methods resort to flattening the brain connectome (i.e., graph) through vectorization which overlooks its topological properties. To address this limitation and inspired from the emerging graph neural networks (GNNs), we design a novel regression GNN model (namely RegGNN) for predicting IQ scores from brain connectivity. On top of that, we introduce a novel, fully modular sample selection method to select the best samples to learn from for our target prediction task. However, since such deep learning architectures are computationally expensive to train, we further propose a learning-based sample selection method that learns how to choose the training samples with the highest expected predictive power on unseen samples. For this, we capitalize on the fact that connectomes (i.e., their adjacency matrices) lie in the symmetric positive definite (SPD) matrix cone. Our results on full-scale and verbal IQ prediction outperforms comparison methods in autism spectrum disorder cohorts and achieves a competitive performance for neurotypical subjects using 3-fold cross-validation. Furthermore, we show that our sample selection approach generalizes to other learning-based methods, which shows its usefulness beyond our GNN architecture.

Original languageEnglish
Pages (from-to)1123-1138
Number of pages16
JournalBrain Imaging and Behavior
Volume16
Early online date10 Nov 2021
DOIs
Publication statusPublished - Jun 2022

Keywords

  • Regression
  • Graph neural network
  • Sample selection
  • Functional brain connectome
  • Cognitive score prediction

Fingerprint

Dive into the research topics of 'Predicting cognitive scores with graph neural networks through sample selection learning'. Together they form a unique fingerprint.

Cite this