The inclusion of circularity in the analysis of neuroimaging data can lead to some bias in the results, often leading to optimistic conclusions. In this study, we show the differences in results obtained performing an experiment with no circularity and the same one with circularity effect (double dipping). We obtain discriminant features from structural magnetic resonance images (MRI) to train and test classifiers able to discriminate cocaine dependent patients from healthy subjects. Feature selection is done computing Pearson’s correlation between voxel values across subjects with the subject class as control variable. Feature selection processes with double dipping obtain higher accuracy and specificity values.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com