In diffusion MRI, numerical biomarkers are us uallycalculated for research and clinical purposes as GeneralizedFractional Anisotropy (GFA). Recently, more eloquentindices allowing a more accurate description of tissuemicrostructure were derived from the SHORE model. Undercertain experimental conditions, such indices express themorphological properties of the compartments where spinsdiffuse. Evidence of the suitability of such indices asbiomarkers for stroke was provided in a previous studybased on diffusion spectrum imaging (DSI) and focusing onthe cortical motor loop. The goal of this work was toinvestigate the suitability of such indices for stratification,namely for distinguishing pathological from healthysubjects. To this end, two complementary paths werefollowed. First, the same approach used in the previouswork for longitudinal analysis (statistics-based) was appliedto detect inter-group variations. Then, a new approach basedon the LASSO regressor was proposed. Results providedevidence of the suitability of the proposed indices forstratification purposes.

SHORE-based biomarkers allow patients versus control classification in stroke

OBERTINO, SILVIA;Brusini, Lorenza;Boscolo Galazzo, Ilaria;Zucchelli, Mauro;CRISTANI, Marco;MENEGAZ, Gloria
2016-01-01

Abstract

In diffusion MRI, numerical biomarkers are us uallycalculated for research and clinical purposes as GeneralizedFractional Anisotropy (GFA). Recently, more eloquentindices allowing a more accurate description of tissuemicrostructure were derived from the SHORE model. Undercertain experimental conditions, such indices express themorphological properties of the compartments where spinsdiffuse. Evidence of the suitability of such indices asbiomarkers for stroke was provided in a previous studybased on diffusion spectrum imaging (DSI) and focusing onthe cortical motor loop. The goal of this work was toinvestigate the suitability of such indices for stratification,namely for distinguishing pathological from healthysubjects. To this end, two complementary paths werefollowed. First, the same approach used in the previouswork for longitudinal analysis (statistics-based) was appliedto detect inter-group variations. Then, a new approach basedon the LASSO regressor was proposed. Results providedevidence of the suitability of the proposed indices forstratification purposes.
2016
Diffusion MRI, Classificat ion, Stroke, Tractography, 3D-SHORE
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/933456
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact