Meta-RegGNN: Predicting Verbal and Full-Scale Intelligence Scores Using Graph Neural Networks and Meta-learning

Creative Commons License

Jegham I., Rekik I.

5th International Workshop on Predictive Intelligence in Medicine (PRIME MICCAI), Singapore, Singapore, 22 September 2022, vol.13564, pp.203-211 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 13564
  • Doi Number: 10.1007/978-3-031-16919-9_19
  • City: Singapore
  • Country: Singapore
  • Page Numbers: pp.203-211
  • Keywords: Meta-learning, Graph neural networks, Behavioral score prediction, Brain connectivity regression, Functional brain connectomes
  • Istanbul Technical University Affiliated: Yes

Abstract

Decrypting intelligence from the human brain construct is vital in the detection of particular neurological disorders. Recently, functional brain connectomes have been used successfully to predict behavioral scores. However, state-of-the-art methods, on one hand, neglect the topological properties of the connectomes and, on the other hand, fail to solve the high inter-subject brain heterogeneity. To address these limitations, we propose a novel regression graph neural network through metalearning namely Meta-RegGNN for predicting behavioral scores from brain connectomes. The parameters of our proposed regression GNN are explicitly trained so that a small number of gradient steps combined with a small training data amount produces a good generalization to unseen brain connectomes. Our results on verbal and full-scale intelligence quotient (IQ) prediction outperform existing methods in both neurotypical and autism spectrum disorder cohorts. Furthermore, we show that our proposed approach ensures generalizability, particularly for autistic subjects.