================================================================= hyp_rnf_train.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[1667 9 46 33 0 58 171 21 102] [ 0 0 0 0 0 0 0 0 0] [ 933 17 558 213 0 579 453 142 238] [ 8 0 0 393 0 2 13 3 0] [ 0 0 0 0 0 0 0 0 0] [ 28 0 3 22 0 408 36 4 8] [ 70 1 16 33 0 100 511 8 7] [ 0 0 0 0 0 0 0 0 0] [ 35 29 3 7 0 5 25 32 2290]] Scoring Summary: (0) norm = 20.8828% (2) nneo = 82.1896% (3) infl = 6.2053% (5) dcis = 19.8428% (6) indc = 31.5013% (8) bckg = 5.6059% avg lbls = 32.1244% avg bckg = 5.6059% score = 29.4725% <** ================================================================= hyp_rnf_dev.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[ 973 4 40 27 0 22 153 14 108] [ 0 0 0 0 0 0 0 0 0] [ 682 13 212 131 2 275 225 52 224] [ 16 0 4 240 0 18 32 9 1] [ 0 0 0 0 0 0 0 0 0] [ 27 2 38 28 0 160 19 14 8] [ 40 1 11 31 0 40 147 25 7] [ 0 0 0 0 0 0 0 0 0] [ 47 15 4 5 0 4 29 31 1200]] Scoring Summary: (0) norm = 27.4422% (2) nneo = 88.3260% (3) infl = 25.0000% (5) dcis = 45.9459% (6) indc = 51.3245% (8) bckg = 10.1124% avg lbls = 47.6077% avg bckg = 10.1124% score = 43.8582% <** ================================================================= hyp_rnf_eval.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[ 875 5 45 29 0 38 230 23 104] [ 0 0 0 0 0 0 0 0 0] [ 800 25 234 137 2 401 354 99 161] [ 8 0 1 203 0 4 12 3 0] [ 0 0 0 0 0 0 0 0 0] [ 34 0 28 9 0 94 29 5 44] [ 41 1 14 39 0 121 135 111 2] [ 0 0 0 0 0 0 0 0 0] [ 34 19 6 0 0 1 21 26 1075]] Scoring Summary: (0) norm = 35.1371% (2) nneo = 89.4261% (3) infl = 12.1212% (5) dcis = 61.3169% (6) indc = 70.9052% (8) bckg = 9.0525% avg lbls = 53.7813% avg bckg = 9.0525% score = 49.3084% <** ======================================================================== ================================================================= hyp_cnn_train.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[ 0 29 2 143 0 23 2 1908 0] [ 0 0 0 0 0 0 0 0 0] [ 0 94 0 167 0 17 1 2854 0] [ 0 0 0 203 0 3 0 213 0] [ 0 0 0 0 0 0 0 0 0] [ 0 2 0 20 0 3 0 484 0] [ 0 1 0 82 0 7 0 656 0] [ 0 0 0 0 0 0 0 0 0] [ 3 554 3 11 0 11 2 1837 5]] Scoring Summary: (0) norm = 100.0000% (2) nneo = 100.0000% (3) infl = 51.5513% (5) dcis = 99.4106% (6) indc = 100.0000% (8) bckg = 99.7939% avg lbls = 90.1924% avg bckg = 99.7939% score = 91.1525% <** ================================================================= hyp_cnn_dev.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[ 0 25 0 101 0 10 2 1202 1] [ 0 0 0 0 0 0 0 0 0] [ 1 80 1 106 0 13 3 1612 0] [ 0 0 0 114 0 1 0 205 0] [ 0 0 0 0 0 0 0 0 0] [ 0 4 0 4 0 0 0 288 0] [ 0 3 0 43 0 2 0 254 0] [ 0 0 0 0 0 0 0 0 0] [ 2 144 2 11 0 9 0 1165 2]] Scoring Summary: (0) norm = 100.0000% (2) nneo = 99.9449% (3) infl = 64.3750% (5) dcis = 100.0000% (6) indc = 100.0000% (8) bckg = 99.8502% avg lbls = 92.8640% avg bckg = 99.8502% score = 93.5626% <** ================================================================= hyp_cnn_eval.csv : Legend: 0 = norm <** 1 = artf 2 = nneo <** 3 = infl <** 4 = susp 5 = dcis <** 6 = indc <** 7 = null 8 = bckg <** Confusion Matrix: [[ 0 15 0 100 0 10 0 1224 0] [ 0 0 0 0 0 0 0 0 0] [ 0 74 0 149 0 15 0 1975 0] [ 0 0 0 96 0 0 0 135 0] [ 0 0 0 0 0 0 0 0 0] [ 0 7 0 5 0 0 0 231 0] [ 0 0 0 36 0 0 0 428 0] [ 0 0 0 0 0 0 0 0 0] [ 2 216 3 2 0 9 5 941 4]] Scoring Summary: (0) norm = 100.0000% (2) nneo = 100.0000% (3) infl = 58.4416% (5) dcis = 100.0000% (6) indc = 100.0000% (8) bckg = 99.6616% avg lbls = 91.6883% avg bckg = 99.6616% score = 92.4856% <** ========================================================================