Individual classification of MCI subtypes by support vector machine analysis of white matter diffusion tensor imaging (DTI)
| Autor: | Haller S Missonnier P Herrmann FR Rodriguez C Deiber MP Nguyen D Gold G Lovblad KO, Giannakopoulos P |
|---|---|
| Rok vydání: | 2013 |
| Zdroj: | Americal Journal of Neuroradiology |
| DOI: | 10.3174/ajnr.A3223 |
| Popis: | Mild cognitive impairment (MCI) was recently subdivided into single domain amnestic (sd aMCI) single dysexecutive deficit frontal lobe related (sd fMCI) and multiple domain (md aMCI). This study aimed to discriminate between MCI subtypes using diffusion tensor imaging (DTI). 66 prospective participants were included: 18 sd aMCI 13 sd fMCI and 35 md aMCI. Statistics included group comparison using Tract Based Spatial Statistics (TBSS) and individual classification using support vector machines (SVM). The group level analysis revealed a decrease in fractional anisotropy (FA) in md aMCI versus sd aMCI in an extensive bilateral right dominant network and a more pronounced reduction of FA in md aMCI compared to sd dMCI in right inferior fronto occipital fasciculus and inferior longitudinal fasciculus. The comparison between sd dMCI and sd aMCI as well as the analysis of the other diffusion parameters yielded no significant group differences. The individual level SVM analysis provided discrimination between the MCI subtypes with accuracies around 97. The major limitation is the relatively small number of MCI cases. These data show that at the group level the md aMCI subgroup has the most pronounced damage in white matter integrity. Individually SVM analysis of white matter FA provided highly accurate classification of MCI subtypes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|