A comparative study of machine learning methods for predicting the evolution of brain connectivity from a baseline timepoint.

Journal: Journal of neuroscience methods
Published Date:

Abstract

BACKGROUND: Predicting the evolution of the brain network, also called connectome, by foreseeing changes in the connectivity weights linking pairs of anatomical regions makes it possible to spot connectivity-related neurological disorders in earlier stages and detect the development of potential connectomic anomalies. Remarkably, such a challenging prediction problem remains least explored in the predictive connectomics literature. It is a known fact that machine learning (ML) methods have proven their predictive abilities in a wide variety of computer vision problems. However, ML techniques specifically tailored for the prediction of brain connectivity evolution trajectory from a single timepoint are almost absent.

Authors

  • Şeymanur Aktı
    Faculty of Computer and Informatics, Istanbul Technical University, Turkey. Electronic address: akti15@itu.edu.tr.
  • Doğay Kamar
    Faculty of Computer and Informatics, Istanbul Technical University, Turkey. Electronic address: kamard@itu.edu.tr.
  • Özgür Anıl Özlü
    Faculty of Computer and Informatics, Istanbul Technical University, Turkey.
  • Ihsan Soydemir
    Faculty of Computer and Informatics, Istanbul Technical University, Turkey.
  • Muhammet Akcan
    Faculty of Computer and Informatics, Istanbul Technical University, Turkey.
  • Abdullah Kul
    Faculty of Computer and Informatics, Istanbul Technical University, Turkey.
  • Islem Rekik
    Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, USA.