Voxelwise multivariate statistics and brain-wide machine learning using the full diffusion tensor

  • Authors:

  • Anne-Laure Fouque;Pierre Fillard;Anne Bargiacchi;Arnaud Cachia;Monica Zilbovicius;Benjamin Thyreau;Edith Le Floch;Philippe Ciuciu;Edouard Duchesnay

  • Affiliations:

  • CEA, Neurospin, LNAO, Saclay, France and INSERM-CEA U.1000 Imaging and Psychiatry, Orsay, France;CEA, Neurospin, LNAO, Saclay, France and INRIA Saclay-Île-de-France, Parietal, Saclay, France;INSERM-CEA U.1000 Imaging and Psychiatry, Orsay, France;UMR 894 INSERM - Paris Descartes University, Laboratory of Pathophysiology of Psychiatric Diseases, Sainte-Anne Hospital, Paris, France;INSERM-CEA U.1000 Imaging and Psychiatry, Orsay, France;CEA, Neurospin, LNAO, Saclay, France;CEA, Neurospin, LNAO, Saclay, France and INSERM-CEA U.1000 Imaging and Psychiatry, Orsay, France;CEA, Neurospin, LNAO, Saclay, France;CEA, Neurospin, LNAO, Saclay, France and INSERM-CEA U.1000 Imaging and Psychiatry, Orsay, France

  • Venue:
  • MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part II
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose to use the full diffusion tensor to perform brain-wide score prediction on diffusion tensor imaging (DTI) using the log-Euclidean framework., rather than the commonly used fractional anisotropy (FA). Indeed, scalar values such as the FA do not capture all the information contained in the diffusion tensor. Additionally, full tensor information is included in every step of the pre-processing pipeline: registration, smoothing and feature selection using voxelwise multivariate regression analysis. This approach was tested on data obtained from 30 children and adolescents with autism spectrum disorder and showed some improvement over the FA-only analysis.