Journal of Healthcare Engineering / 2018 / Article / Tab 4

Research Article

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

Table 4

Number of ROIs resulted in FP reduction using curvelet-based LBP (without sparse) & ANN classification at training and validation stage.

ClassDataset usedBenign/malignant massNonmass/benign massTotal (#) imagesTPR (true-positive rate) = TP/#lesionsFPPI (false-positive per image) = FP/# images
Previous stageSelected (TP)Lost (FN)Previous stageSelected (TN)Lost (FP)

Normal vs abnormalMIAS108 ∗ 2 = 2162031327325716315(203/216) = 0.94(16/315) = 0.05
DDSM140 ∗ 4 = 5604659512031095108240(465/560) = 0.83(108/240) = 0.45

Benign vs malignantMIAS4949059572108(49/49) = 1.00(2/108) = 0.02
DDSM46 ∗ 2 = 9291194913140(91/92) = 0.99(3/140) = 0.02

Normal vs malignantMIAS49 ∗ 4 = 1961841227325419256(184/196) = 0.94(19/256) = 0.07
DDSM46 ∗ 4 = 18418041203114360146(180/184) = 0.98(60/146) = 0.41
TMCH: Scanner1107 ∗ 4 = 4284161260555154217(416/428) = 0.97(54/217) = 0.25
TMCH: Scanner265 ∗ 4 = 260255523221418135(255/260) = 0.98(18/135) = 0.13

Augmentation of image.

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.