Skip to main content
. Author manuscript; available in PMC: 2013 Oct 1.
Published in final edited form as: Med Eng Phys. 2012 Mar 7;34(8):1058–1065. doi: 10.1016/j.medengphy.2011.11.010

Figure 6.

Figure 6

Illustration of the AUC (a), Sensitivity (b), and Specificity (c) after a leave-one-out crossvalidation for the multi-linear classifier, AdaBoost, and Extra-Trees. The multi-linear utilizes the optimal subset of 13 morphological features, while AdaBoost and Extra-Trees use the 24 metrics. Extra-trees performance ranks best and is followed by the AdaBoost and Multi-linear classifier.