================================================================= 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: [[1799 0 92 38 0 33 13 0 132] [ 0 0 0 0 0 0 0 0 0] [ 324 0 2181 88 0 170 20 0 350] [ 1 0 3 389 0 7 18 0 1] [ 0 0 0 0 0 0 0 0 0] [ 39 0 21 30 0 338 67 0 14] [ 68 0 84 56 0 202 315 0 21] [ 0 0 0 0 0 0 0 0 0] [ 67 0 73 10 0 5 13 0 2258]] Scoring Summary: (0) norm = 14.6179% (2) nneo = 30.3862% (3) infl = 7.1599% (5) dcis = 33.5953% (6) indc = 57.7748% (8) bckg = 6.9250% avg lbls = 28.7068% avg bckg = 6.9250% score = 26.5286% <** ================================================================= 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: [[ 816 0 231 44 0 52 81 0 117] [ 0 0 0 0 0 0 0 0 0] [ 561 0 509 179 0 195 72 0 300] [ 6 0 9 276 0 14 15 0 0] [ 0 0 0 0 0 0 0 0 0] [ 51 0 107 18 0 89 8 0 23] [ 45 0 73 59 0 67 45 0 13] [ 0 0 0 0 0 0 0 0 0] [ 118 0 85 2 0 4 23 0 1103]] Scoring Summary: (0) norm = 39.1499% (2) nneo = 71.9714% (3) infl = 13.7500% (5) dcis = 69.9324% (6) indc = 85.0993% (8) bckg = 17.3783% avg lbls = 55.9806% avg bckg = 17.3783% score = 52.1204% <** ================================================================= 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: [[ 755 0 308 56 0 63 71 0 96] [ 0 0 0 0 0 0 0 0 0] [ 609 0 770 183 0 295 124 0 232] [ 3 0 7 211 0 4 6 0 0] [ 0 0 0 0 0 0 0 0 0] [ 65 0 91 9 0 21 8 0 49] [ 32 0 106 72 0 215 35 0 4] [ 0 0 0 0 0 0 0 0 0] [ 98 0 42 3 0 1 13 0 1025]] Scoring Summary: (0) norm = 44.0326% (2) nneo = 65.2056% (3) infl = 8.6580% (5) dcis = 91.3580% (6) indc = 92.4569% (8) bckg = 13.2826% avg lbls = 60.3422% avg bckg = 13.2826% score = 55.6363% <** ======================================================================== ================================================================= 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: [[ 991 21 21 19 19 705 118 88 125] [ 0 0 0 0 0 0 0 0 0] [ 595 31 47 166 28 1339 325 240 362] [ 1 0 1 376 4 19 13 5 0] [ 0 0 0 0 0 0 0 0 0] [ 11 0 1 6 0 415 54 7 15] [ 8 0 0 44 7 233 424 5 25] [ 0 0 0 0 0 0 0 0 0] [ 49 41 5 2 10 33 51 23 2212]] Scoring Summary: (0) norm = 52.9663% (2) nneo = 98.4998% (3) infl = 10.2625% (5) dcis = 18.4676% (6) indc = 43.1635% (8) bckg = 8.8211% avg lbls = 44.6720% avg bckg = 8.8211% score = 41.0869% <** ================================================================= 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: [[ 561 8 22 16 19 440 104 55 116] [ 0 0 0 0 0 0 0 0 0] [ 329 15 30 84 16 723 188 132 299] [ 0 0 1 270 4 27 5 13 0] [ 0 0 0 0 0 0 0 0 0] [ 17 1 5 8 0 184 39 18 24] [ 10 0 2 24 10 128 103 14 11] [ 0 0 0 0 0 0 0 0 0] [ 36 36 5 4 11 25 28 13 1177]] Scoring Summary: (0) norm = 58.1655% (2) nneo = 98.3480% (3) infl = 15.6250% (5) dcis = 37.8378% (6) indc = 65.8940% (8) bckg = 11.8352% avg lbls = 55.1741% avg bckg = 11.8352% score = 50.8402% <** ================================================================= 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: [[ 412 7 24 21 23 529 135 76 122] [ 0 0 0 0 0 0 0 0 0] [ 348 12 22 105 20 1045 268 141 252] [ 1 0 0 205 0 12 9 4 0] [ 0 0 0 0 0 0 0 0 0] [ 36 0 3 4 2 108 23 6 61] [ 12 0 2 45 9 220 143 30 3] [ 0 0 0 0 0 0 0 0 0] [ 14 41 1 0 10 20 30 11 1055]] Scoring Summary: (0) norm = 69.4589% (2) nneo = 99.0059% (3) infl = 11.2554% (5) dcis = 55.5556% (6) indc = 69.1810% (8) bckg = 10.7445% avg lbls = 60.8913% avg bckg = 10.7445% score = 55.8767% <** ========================================================================