Ensemble learning with 3D convolutional neural networks for functional connectome-based prediction. Academic Article uri icon

Overview

abstract

  • The specificity and sensitivity of resting state functional MRI (rs-fMRI) measurements depend on preprocessing choices, such as the parcellation scheme used to define regions of interest (ROIs). In this study, we critically evaluate the effect of brain parcellations on machine learning models applied to rs-fMRI data. Our experiments reveal an intriguing trend: On average, models with stochastic parcellations consistently perform as well as models with widely used atlases at the same spatial scale. We thus propose an ensemble learning strategy to combine the predictions from models trained on connectivity data extracted using different (e.g., stochastic) parcellations. We further present an implementation of our ensemble learning strategy with a novel 3D Convolutional Neural Network (CNN) approach. The proposed CNN approach takes advantage of the full-resolution 3D spatial structure of rs-fMRI data and fits non-linear predictive models. Our ensemble CNN framework overcomes the limitations of traditional machine learning models for connectomes that often rely on region-based summary statistics and/or linear models. We showcase our approach on a classification (autism patients versus healthy controls) and a regression problem (prediction of subject's age), and report promising results.

publication date

  • June 18, 2019

Research

keywords

  • Autism Spectrum Disorder
  • Brain
  • Connectome
  • Image Interpretation, Computer-Assisted
  • Machine Learning
  • Magnetic Resonance Imaging
  • Neural Networks, Computer

Identity

PubMed Central ID

  • PMC6777738

Scopus Document Identifier

  • 85067562158

Digital Object Identifier (DOI)

  • 10.1016/j.neuroimage.2019.06.012

PubMed ID

  • 31220576

Additional Document Info

volume

  • 199