Skip to main content
. 2019 Oct 4;13:1053. doi: 10.3389/fnins.2019.01053

Table 2.

High-level comparison between the two feature sets from different imaging pipelines used to test the robustness of the new method.

Freesurfer version Number of samples used for ML pipeline (AD/CN) Number of features
Feature set 1 5.1 93 (60/39) 340
Feature set 2 6.0 93 (60/39) 117