Research Article

Classification of Region of Interest in Mammograms Using Dual Contourlet Transform and Improved KNN

Table 6

Classification accuracy (%) of different methods tested between benign and malignant.

AccuracyImproved KNNKNN
Dual-CTContourletWaveletDual-CTContourletWavelet

Mean91.5391.5387.2976.2778.8181.36
SD93.2288.1485.5976.2771.1975.42
Smoothness95.7688.9883.0570.3477.1277.97
Skewness90.6886.4487.2972.0377.9775.42
Uniformity94.9288.9883.9075.4274.5877.12
Entropy90.6888.9886.4467.8077.9776.27
Contrast95.7687.2986.4475.4275.4272.03
Correlation91.5386.4486.4476.2778.8180.51
Homogeneity94.9288.1481.3676.2772.8872.88

SD represents standard deviation; bold font number indicates the best performance in each class.