Journal of Healthcare Engineering / 2018 / Article / Tab 8

Research Article

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

Table 8

Comparison of classification accuracy, AUC, and FP/image values from different approaches in breast cancer diagnosis.


Eltoukhy et al. [33]MIASBiggest curvelet coefficients as a feature vectorEuclidean classifier94.07%
Eltoukhy et al. [42]98.59
Eltoukhy et al. [8]SVM97.3
Dhahbi et al. [34]Mini-MIASCurvelet momentsKNN91.27
Bruno et al. [4]DDSMCurvelet + LBPSVM850.85
da Rocha et al. [40]DDSMLBPSVM88.310.88
Kanadam and Chereddy [3]MIASSparse ROISVM97.42
Pereira et al. [18]DDSMWavelet and Wiener filterMultiple thresholding, wavelet, and GA1.37
Liu and Zeng [29]DDSM, FFDMGLCM, CLBP, and geometric featuresSVM1.48
De Sampaio et al. [39]DDSMLBPDBSCAN98.260.19
Zyout et al. [30]DDSMSecond order statistics of wavelet coefficients (SOSWC)SVM96.80.970.018
Casti et al. [31]DDSMDifferential featuresFisher linear discriminant analysis (FLDA)1.68
Proposed methodMIASLBP based on sparse curvelet subband coefficientsANN98.570.980.01
TMCH: Scanner198.300.980.05
TMCH: Scanner210010

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 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.