Feature Selection Based on Machine Learning in MRIs for Hippocampal Segmentation

Table 8

Classification result on 23 features selected through backward elimination method using Näive Bayes Classifier in -fold cross validation based on confusion matrix.

23 features; Backward elimination	Completeness of a class	Purity of a class	Contamination of a class
Hippocampus	83%	70%	30%
Not-hippocampus	73%	85%	15%
Efficiency	77%