Computational and Mathematical Methods in Medicine / 2015 / Article / Tab 2

Research Article

A Computer-Aided Diagnosis System for Dynamic Contrast-Enhanced MR Images Based on Level Set Segmentation and ReliefF Feature Selection

Table 2

Classification results of the different segmentation methods (leave-half-case-out).

Segmentation methodClassification modelAccuracy (%)Sensitivity (%)Specificity (%)

FCMFisher79.587.757.1
SVM74.482.552.4

FCM-GVF-snakeFisher80.886.066.7
SVM82.186.071.4

CV-level setFisher91.096.576.2
SVM92.398.276.2