Not Logged In

Learning Macroscopic Brain Connectomes via Group-Sparse Factorization

Mapping structural brain connectomes for living human brains typically requires expert analysis and rule-based models on diffusion-weighted magnetic resonance imaging. A data-driven approach, however, could overcome limitations in such rule-based approaches and improve precision mappings for individuals. In this work, we explore a framework that facilitates applying learning algorithms to automatically extract brain connectomes. Using a tensor encoding, we design an objective with a group-regularizer that prefers biologically plausible fascicle structure. We show that the objective is convex and has unique solutions, ensuring identifiable connectomes for an individual. We develop an efficient optimization strategy for this extremely high-dimensional sparse problem, by reducing the number of parameters using a greedy algorithm designed specifically for the problem. We show that this greedy algorithm significantly improves on a standard greedy algorithm, called Orthogonal Matching Pursuit. We conclude with an analysis of the solutions found by our method, showing we can accurately reconstruct the diffusion information while maintaining contiguous fascicles with smooth direction changes.

Citation

F. Aminmansour, A. Patterson, L. Le, Y. Pen, D. Mitchell, F. Pestilli, C. Caiafa, R. Greiner, M. White. "Learning Macroscopic Brain Connectomes via Group-Sparse Factorization". Neural Information Processing Systems (NIPS), (ed: H. Wallach, H. Larochelle, A. Beygelzimer, F. de-Buc, E. Fox, R. Garnett), pp 8847-8857, December 2019.

Keywords: Brain, fascicle, group-sparse, connectome
Category: In Conference
Web Links: NeurIPS

BibTeX

@incollection{Aminmansour+al:NIPS19,
  author = {Farzane Aminmansour and Andrew Patterson and Lei Le and Yisu Pen
    and Daniel Mitchell and Franco Pestilli and Cesar Caiafa and Russ Greiner
    and Martha White},
  title = {Learning Macroscopic Brain Connectomes via Group-Sparse
    Factorization},
  Editor = {H. Wallach, H. Larochelle, A. Beygelzimer, F. de-Buc, E. Fox, R.
    Garnett},
  Pages = {8847-8857},
  booktitle = {Neural Information Processing Systems (NIPS)},
  year = 2019,
}

Last Updated: July 14, 2020
Submitted by Sabina P

University of Alberta Logo AICML Logo