Scientific article
Open access

Multilevel diffusion tensor imaging classification technique for characterizing neurobehavioral disorders

Published inBrain Imaging and Behavior, vol. 14, no. 3, p. 641-652
Publication date2020

This proposed novel method consists of three levels of analyses of diffusion tensor imaging data: 1) voxel level analysis of fractional anisotropy of white matter tracks, 2) connection level analysis, based on fiber tracks between specific brain regions, and 3) network level analysis, based connections among multiple brain regions. Machine-learning techniques of (Fisher score) feature selection, (Support Vector Machine) pattern classification, and (Leave-one-out) cross-validation are performed, for recognition of the neural connectivity patterns for diagnostic purposes. For validation proposes, this multilevel approach achieved an average classification accuracy of 90% between Alzheimer's disease and healthy controls, 83% between Alzheimer's disease and mild cognitive impairment, and 83% between mild cognitive impairment and healthy controls. The results indicate that the multilevel diffusion tensor imaging approach used in this analysis is a potential diagnostic tool for clinical evaluations of brain disorders. The presented pipeline is now available as a tool for scientifically applications in a broad range of studies from both clinical and behavioral spectrum, which includes studies about autism, dyslexia, schizophrenia, dementia, motor body performance, among others.

Citation (ISO format)
DALBONI DA ROCHA, Josue Luiz et al. Multilevel diffusion tensor imaging classification technique for characterizing neurobehavioral disorders. In: Brain Imaging and Behavior, 2020, vol. 14, n° 3, p. 641–652. doi: 10.1007/s11682-018-0002-2
Main files (1)
Article (Published version)
ISSN of the journal1931-7557

Technical informations

Creation09/28/2020 12:11:00 PM
First validation09/28/2020 12:11:00 PM
Update time03/15/2023 10:43:17 PM
Status update03/15/2023 10:43:17 PM
Last indexation08/30/2023 11:37:02 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack