A method for the optimisation of feature selection with imaging data

Year
2015
Type(s)
Author(s)
Jollans, Lee and Watts, Richard and Duffy, Daniel and Spechler, Philip and Garavan, Hugh and Whelan, Robert and IMAGEN Consortium and others
Source
In Poster presented at the Organisation of Human Brain Mapping Annual Meeting, Honolulu, HI, 2015
Url
https://www.researchgate.net/profile/Lee_Jollans/publication/281281126_A_Method_for_the_Optimisation_of_Feature_Selection_with_Imaging_Data/links/560515f708aea25fce3212d5/A-Method-for-the-Optimisation-of-Feature-Selection-with-Imaging-Data.pdf

Imaging datasets typically include a large number of features (e.g. voxels or Regions of Interest, ROIs), and have relatively small sample sizes.
Including all possible features in a regression model can easily lead to overfitting and a consequent lack of generalizability. A large number of
features also make it difficult to perform feature selection, and thereby identify the relevant voxels or ROIs. We report a novel Machine
Learning method for automated data-driven feature selection with large neuroimaging dataset