Journal of Healthcare Engineering / 2018 / Article / Tab 6

Research Article

Local Binary Patterns Descriptor Based on Sparse Curvelet Coefficients for False-Positive Reduction in Mammograms

Table 6

Performance evaluation of curvelet-based LBP descriptor algorithm.

DatasetClassificationNormal-malignantNormal-abnormalBenign-malignant
ClassifierSensitivitySpecificityAUCSensitivitySpecificityAUCSensitivitySpecificityAUC

MIASANN0.940.930.940.940.940.941.000.970.99
SVM0.850.850.850.830.860.850.880.840.86
KNN0.670.630.650.580.570.580.620.680.63

DDSMANN0.980.950.950.830.910.850.990.970.98
SVM0.970.880.920.710.910.830.940.890.92
KNN0.960.640.870.670.900.800.870.730.79

TMCH: Scanner1ANN0.970.910.94
SVM0.960.910.94
KNN0.980.820.89

TMCH: Scanner2ANN0.980.920.96
SVM0.970.900.94
KNN0.920.830.88

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.