GIC-experimental-databases/OASIS deformation feature vectors

Datasets of features extracted from the subset of 98 females from OASIS

These features are based on deformation measures (displacement vector magnitudes and Jacobian determinant of gradient matrices) of a custom template made with all the 98 subjects registered to each subject. Some feature sets doesn't exist because the correlation values were lower than the percentile limit.

Reference paper with results on these datasets

Alexandre Savio Supervised classification using deformation-based features for Alzheimer’s disease detection on the OASIS cross-sectional database Advances in Knowledge-Based and Intelligent Information and Engineering Systems. Frontiers in Artificial Intelligence and Applications (FAIA) series, Vol. 243, pages 2191 - 2200, 2012. Eds: Manuel Graña, Carlos Toro, Jorge Posada, Robert J. Howlett and Lakhmi C. Jain.

Pipelines trying to explain how these features were extracted:

• Obtaining the measures of the displacement vectors.
• Obtaining the correlation values from the displacement measures.

Feature sets extracted from transformation displacement magnitudes (DM)

• Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.990 percentile
• Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.995 percentile
• Feature sets of Spearman and Kendall correlation measures over a 0.999 percentile

Feature sets extracted from transformation gradient Jacobian matrices determinant (JD)

• Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.990 percentile
• Feature sets of Spearman and Kendall correlation measures over a 0.995 percentile
• Feature sets of Spearman and Kendall correlation measures over a 0.999 percentile

Contact: Alexandre Savio.