Journal of Healthcare Engineering / 2018 / Article / Tab 3

Research Article

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

Table 3

Reduction in curvelet coefficients for sample mammograms from TMCH Scanner1 and Scanner2 dataset.

Sr. no.TMCH: Scanner 1: “GE Medical Senograph System”TMCH: Scanner 2: “Hologic Selenia System”
ROI sizeTotal number of curvelet coefficients from subbandsTotal number of selected curvelet coefficients from subbands% reduction in curvelet coefficientsROI sizeTotal number of curvelet coefficients from subbandsTotal number of selected curvelet coefficients from subbands% reduction in curvelet coefficients

1459 × 41211,40,6177,94,88530.31291 × 2784,89,2433,17,01435.20
2548 × 51316,93,40311,17,87333.99545 × 2468,09,6275,31,60434.34
3415 × 3037,58,3234,45,58541.24560 × 48316,30,58310,68,43934.47
4645 × 49519,51,44311,45,58041.29782 × 51024,00,13712,75,07346.87
5437 × 69118,16,6519,85,12045.7787 × 14175,77367,87110.43
6812 × 50024,39,93712,87,06547.25311 × 1853,48,5652,40,54630.99
7468 × 37910,66,3337,10,24233.40262 × 3485,50,3032,82,82148.61
8673 × 58223,55,58917,30,91526.52610 × 44016,14,5158,42,87647.79
9250 × 2013,04,5132,35,67022.61949 × 39122,27,20913,59,33838.97
10525 × 48815,44,69111,61,94224.78365 × 3858,46,5236,04,47328.59
11488 × 77922,87,54716,11,38529.56393 × 2475,85,0634,90,47416.17
121434 × 96683,26,58137,42,27755.06341 × 3016,18,1114,10,54233.58
13348 × 4218,81,7016,16,50130.08523 × 70222,06,0978,00,05763.73
14460 × 53014,67,2277,99,88545.48370 × 2846,32,5394,23,72733.01
15398 × 45010,78,4418,28,06423.22344 × 2024,18,9553,02,42727.81
16247 × 2724,04,4013,44,82214.73264 × 1882,99,9972,31,92622.69
17411 × 3057,57,6574,05,91946.42233 × 2473,46,9832,67,68622.85
18286 × 3445,93,1554,48,56624.38370 × 2916,50,7014,86,12525.29
19417 × 2075,23,4774,29,75517.90680 × 48319,79,54310,52,79346.82
20463 × 45812,75,0218,57,60832.74202 × 2663,24,2952,15,04233.69
Average16,33,3359,84,98333Average9,52,7385,63,54334

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.