Lampiran 1. Citra Mammogram Data Training. Citra Mammogram Hasil Pemotongan Asli dan Menghilangkan Background. Klasifikasi Asli.

Transkripsi

1 LAMPIRAN 129

2 Lampiran 1 Citra Mammogram Data Training No Data Klasifikasi Asli Citra Mammogram Hasil Pemotongan Asli dan Menghilangkan Background 1 mdb003 Normal 2 mdb004 Normal 3 mdb006 Normal 4 mdb008 Normal 5 mdb009 Normal 130

3 6 mdb011 Normal 7 mdb014 Normal 8 mdb016 Normal 9 mdb020 Normal 10 mdb027 Normal 11 mdb029 Normal 131

7 30 mdb068 Normal 31 mdb070 Normal 32 mdb078 Normal 33 mdb001 Tumor 34 mdb002 Tumor 35 mdb005 Tumor 135

8 36 mdb010 Tumor 37 mdb013 Tumor 38 mdb019 Tumor 39 mdb021 Tumor 40 mdb030 Tumor 41 mdb032 Tumor 136

12 60 mdb193 Tumor 61 mdb195 Tumor 62 mdb198 Tumor 63 mdb240 Tumor 64 mdb312 Tumor 65 mdb023 Kanker 140

13 66 mdb028 Kanker 67 mdb058 Kanker 68 mdb075 Kanker 69 mdb090 Kanker 70 mdb105 Kanker 71 mdb111 Kanker 141

18 96 mdb271 Kanker 146

19 Lampiran 2 Citra Mammogram Data Testing No Data Klasifikasi Asli Citra Mammogram Hasil Pemotongan Asli dan Menghilangkan Background 1 mdb024 Normal 2 mdb026 Normal 3 mdb037 Normal 4 mdb061 Normal 5 mdb076 Normal 147

20 6 mdb100 Normal 7 mdb109 Normal 8 mdb112 Normal 9 mdb015 Tumor 10 mdb091 Tumor 11 mdb097 Tumor 148

21 12 mdb204 Tumor 13 mdb219 Tumor 14 mdb222 Tumor 15 mdb236 Tumor 16 mdb248 Tumor 17 mdb072 Kanker 149

23 24 mdb265 Kanker 151

24 Lampiran 3 Script M-file GLCM Ekstraksi 14 Parameter Statistik function [out] = GLCM_Features4(glcmin,pairs) % If 'pairs' not entered: set pairs to 0 if ((nargin > 2) (nargin == 0)) error('too many or too few input arguments. Enter GLCM and pairs.'); elseif ( (nargin == 2) ) if ((size(glcmin,1) <= 1) (size(glcmin,2) <= 1)) error('the GLCM should be a 2-D or 3-D matrix.'); elseif ( size(glcmin,1) ~= size(glcmin,2) ) error('each GLCM should be square with NumLevels rows and NumLevels cols'); end elseif (nargin == 1) % only GLCM is entered pairs = 0; % default is numbers and input 1 for percentage if ((size(glcmin,1) <= 1) (size(glcmin,2) <= 1)) error('the GLCM should be a 2-D or 3-D matrix.'); elseif ( size(glcmin,1) ~= size(glcmin,2) ) error('each GLCM should be square with NumLevels rows and NumLevels cols'); end end format longe if (pairs == 1) newn = 1; for nglcm = 1:2:size(glcmin,3) glcm(:,:,newn) = glcmin(:,:,nglcm) + glcmin(:,:,nglcm+1); newn = newn + 1; end elseif (pairs == 0) glcm = glcmin; end size_glcm_1 = size(glcm,1); size_glcm_2 = size(glcm,2); size_glcm_3 = size(glcm,3); % checked out.autoc = zeros(1,size_glcm_3); % Autocorrelation: [2] out.contr = zeros(1,size_glcm_3); % Contrast: matlab/[1,2] out.corrm = zeros(1,size_glcm_3); % Correlation: matlab out.corrp = zeros(1,size_glcm_3); % Correlation: [1,2] out.cprom = zeros(1,size_glcm_3); % Cluster Prominence: [2] out.cshad = zeros(1,size_glcm_3); % Cluster Shade: [2] out.dissi = zeros(1,size_glcm_3); % Dissimilarity: [2] out.energ = zeros(1,size_glcm_3); % Energy: matlab / [1,2] out.entro = zeros(1,size_glcm_3); % Entropy: [2] out.homom = zeros(1,size_glcm_3); % Homogeneity: matlab out.homop = zeros(1,size_glcm_3); % Homogeneity: [2] out.maxpr = zeros(1,size_glcm_3); % Maximum probability: [2] out.sosvh = zeros(1,size_glcm_3); % Sum of sqaures: Variance [1] out.savgh = zeros(1,size_glcm_3); % Sum average [1] out.svarh = zeros(1,size_glcm_3); % Sum variance [1] 152

25 out.senth = zeros(1,size_glcm_3); % Sum entropy [1] out.dvarh = zeros(1,size_glcm_3); % Difference variance [4] %out.dvarh2 = zeros(1,size_glcm_3); % Difference variance [1] out.denth = zeros(1,size_glcm_3); % Difference entropy [1] out.inf1h = zeros(1,size_glcm_3); % Information measure of correlation1 [1] out.inf2h = zeros(1,size_glcm_3); % Informaiton measure of correlation2 [1] %out.mxcch = zeros(1,size_glcm_3);% maximal correlation coefficient [1] %out.invdc = zeros(1,size_glcm_3);% Inverse difference (INV) is homom [3] out.indnc = zeros(1,size_glcm_3); % Inverse difference normalized (INN) [3] out.idmnc = zeros(1,size_glcm_3); % Inverse difference moment normalized [3] glcm_sum = zeros(size_glcm_3,1); glcm_mean = zeros(size_glcm_3,1); glcm_var = zeros(size_glcm_3,1); % confuses the range of % i and j used in calculating the means and standard deviations. % As of now I am not sure if the range of i and j should be [1:Ng] or % [0:Ng-1]. I am working on obtaining the values of mean and std that get % the values of correlation that are provided by matlab. u_x = zeros(size_glcm_3,1); u_y = zeros(size_glcm_3,1); s_x = zeros(size_glcm_3,1); s_y = zeros(size_glcm_3,1); % checked p_x p_y p_xplusy p_xminusy p_x = zeros(size_glcm_1,size_glcm_3); % Ng x #glcms[1] p_y = zeros(size_glcm_2,size_glcm_3); % Ng x #glcms[1] p_xplusy = zeros((size_glcm_1*2-1),size_glcm_3); %[1] p_xminusy = zeros((size_glcm_1),size_glcm_3); %[1] % checked hxy hxy1 hxy2 hx hy hxy = zeros(size_glcm_3,1); hxy1 = zeros(size_glcm_3,1); hx = zeros(size_glcm_3,1); hy = zeros(size_glcm_3,1); hxy2 = zeros(size_glcm_3,1); corm = zeros(size_glcm_3,1); corp = zeros(size_glcm_3,1); for k = 1:size_glcm_3 glcm_sum(k) = sum(sum(glcm(:,:,k))); glcm(:,:,k) = glcm(:,:,k)./glcm_sum(k); % Normalize each glcm glcm_mean(k) = mean2(glcm(:,:,k)); % compute mean after norm glcm_var(k) = (std2(glcm(:,:,k)))^2; for i = 1:size_glcm_1 for j = 1:size_glcm_2 p_x(i,k) = p_x(i,k) + glcm(i,j,k); p_y(i,k) = p_y(i,k) + glcm(j,i,k); 153

26 % taking i for j and j for i %if (ismember((i + j),[2:2*size_glcm_1])) p_xplusy((i+j)-1,k) = p_xplusy((i+j)-1,k) + glcm(i,j,k); %end %if (ismember(abs(i-j),[0:(size_glcm_1-1)])) p_xminusy((abs(i-j))+1,k) = p_xminusy((abs(i-j))+1,k) +... glcm(i,j,k); %end end end end % marginal probabilities are now available [1] % p_xminusy has +1 in index % for matlab (no 0 index) % computing sum average, sum variance and sum entropy: %Q = zeros(size(glcm)); i_matrix = repmat([1:size_glcm_1]',1,size_glcm_2); j_matrix = repmat([1:size_glcm_2],size_glcm_1,1); % i_index = [ ] i_index = j_matrix(:); % j_index = [ ] j_index = i_matrix(:); xplusy_index = [1:(2*(size_glcm_1)-1)]'; xminusy_index = [0:(size_glcm_1-1)]'; mul_contr = abs(i_matrix - j_matrix).^2; mul_dissi = abs(i_matrix - j_matrix); %div_homop = ( 1 + mul_contr); % used from the above two formulae %div_homom = ( 1 + mul_dissi); for k = 1:size_glcm_3 % number glcms out.contr(k) = sum(sum(mul_contr.*glcm(:,:,k))); out.dissi(k) = sum(sum(mul_dissi.*glcm(:,:,k))); out.energ(k) = sum(sum(glcm(:,:,k).^2)); out.entro(k) = - sum(sum((glcm(:,:,k).*log(glcm(:,:,k) + eps)))); out.homom(k) = sum(sum((glcm(:,:,k)./( 1 + mul_dissi)))); out.homop(k) = sum(sum((glcm(:,:,k)./( 1 + mul_contr)))); % [1] explains sum of squares variance with a mean value; % the exact definition for mean has not been provided in % the reference: I use the mean of the entire normalized glcm out.sosvh(k) = sum(sum(glcm(:,:,k).*((i_matrix - glcm_mean(k)).^2))); out.indnc(k) = sum(sum(glcm(:,:,k)./( 1 + (mul_dissi./size_glcm_1) ))); out.idmnc(k) = sum(sum(glcm(:,:,k)./( 1 + (mul_contr./(size_glcm_1^2))))); out.maxpr(k) = max(max(glcm(:,:,k))); u_x(k) = sum(sum(i_matrix.*glcm(:,:,k))); u_y(k) = sum(sum(j_matrix.*glcm(:,:,k))); % using for s_x % s_y : This solves the difference in value of correlation and might be 154

27 % the right value of standard deviations required % According to this website there is a typo in [2] which provides % values of variance instead of the standard deviation hence a square % root is required as done below: s_x(k) = (sum(sum( ((i_matrix - u_x(k)).^2).*glcm(:,:,k) )))^0.5; s_y(k) = (sum(sum( ((j_matrix - u_y(k)).^2).*glcm(:,:,k) )))^0.5; corp(k) = sum(sum((i_matrix.*j_matrix.*glcm(:,:,k)))); corm(k) = sum(sum(((i_matrix - u_x(k)).*(j_matrix - u_y(k)).*glcm(:,:,k)))); out.autoc(k) = corp(k); out.corrp(k) = (corp(k) - u_x(k)*u_y(k))/(s_x(k)*s_y(k)); out.corrm(k) = corm(k) / (s_x(k)*s_y(k)); out.cprom(k) = sum(sum(((i_matrix + j_matrix - u_x(k) - u_y(k)).^4).*... glcm(:,:,k))); out.cshad(k) = sum(sum(((i_matrix + j_matrix - u_x(k) - u_y(k)).^3).*... glcm(:,:,k))); out.savgh(k) = sum((xplusy_index + 1).*p_xplusy(:,k)); % the summation for savgh is for i from 2 to 2*Ng hence (i+1) out.senth(k) = - sum(p_xplusy(:,k).*... log(p_xplusy(:,k) + eps)); % compute sum variance with the help of sum entropy out.svarh(k) = sum((((xplusy_index + 1) - out.senth(k)).^2).*... p_xplusy(:,k)); % the summation for savgh is for i from 2 to 2*Ng hence (i+1) % compute difference variance, difference entropy, % out.dvarh2(k) = var(p_xminusy(:,k)); % but using the formula in l % we have for dvarh out.denth(k) = - sum((p_xminusy(:,k)).*... log(p_xminusy(:,k) + eps)); out.dvarh(k) = sum((xminusy_index.^2).*p_xminusy(:,k)); % compute information measure of correlation(1,2) [1] hxy(k) = out.entro(k); glcmk = glcm(:,:,k)'; glcmkv = glcmk(:); hxy1(k) = - sum(glcmkv.*log(p_x(i_index,k).*p_y(j_index,k) + eps)); hxy2(k) = - sum(p_x(i_index,k).*p_y(j_index,k).*... log(p_x(i_index,k).*p_y(j_index,k) + eps)); hx(k) = - sum(p_x(:,k).*log(p_x(:,k) + eps)); hy(k) = - sum(p_y(:,k).*log(p_y(:,k) + eps)); out.inf1h(k) = ( hxy(k) - hxy1(k) ) / ( max([hx(k),hy(k)]) ); out.inf2h(k) = ( 1 - exp( -2*( hxy2(k) - hxy(k) ) ) )^0.5; % eig_q(k,:) = eig(q(:,:,k)); % sort_eig(k,:)= sort(eig_q(k,:),'descend'); % out.mxcch(k) = sort_eig(k,2)^0.5; 155

28 % The maximal correlation coefficient was not calculated due to % computational instability % l end % GLCM Features (Soh, 1999; Haralick, 1973; Clausi 2002) % f1. Uniformity / Energy / Angular Second Moment (done) % f2. Entropy (done) % f3. Dissimilarity (done) % f4. Contrast / Inertia (done) % f5. Inverse difference % f6. correlation % f7. Homogeneity / Inverse difference moment % f8. Autocorrelation % f9. Cluster Shade % f10. Cluster Prominence % f11. Maximum probability % f12. Sum of Squares % f13. Sum Average % f14. Sum Variance % f15. Sum Entropy % f16. Difference variance % f17. Difference entropy % f18. Information measures of correlation (1) % f19. Information measures of correlation (2) % f20. Maximal correlation coefficient % f21. Inverse difference normalized (INN) % f22. Inverse difference moment normalized (IDN) 156

29 Lampiran 4 Script Matlab untuk operasi titik dan ekstraksi A=imread('mdb003.png'); pic=imadjust(a,[ ],[0 1]); Iec=imresize(pic,[ ]); % perintah di atas digunakan untuk proses operasi titik GLCM2 = graycomatrix(iec); S=GLCM_Features4(GLCM2,0); p1=s.contr; p2=s.corrm; p3=s.energ; p4=s.homop; p5=s.entro; p6=s.sosvh; p7=s.idmnc; p8=s.savgh; p9=s.senth; p10=s.svarh; p11=s.dvarh; p12=s.denth; p13=s.maxpr; p14=s.dissi; B=[p1 p2 p3 p4 p5 p6 p7 p8 p9 p10 p11 p12 p13 p14]; 157

30 Lampiran 5 Tabel Hasil Ekstraksi Citra Mammogram Data Training (dengan Operasi Titik) No Kontras Korelasi Energi Homogenitas Entropi SS IDM SA SE SV DV DE Prob Maks Dissimilarity

31

32

33

34 Lampiran 6 Tabel Hasil Ekstraksi Citra Mammogram Data Testing (dengan Operasi Titik) No Kontras Korelasi Energi Homogenitas Entropi SS IDM SA SE SV DV DE Prob Maks Dissimilarity

35

36 Lampiran 7 Tabel Hasil Ekstraksi Citra Mammogram Data Training (tanpa Operasi Titik) No Kontras Korelasi Energi Homogenitas Entropi SS IDM SA SE SV DV DE Prob Maks Dissimilarity

37

38

39

40 Lampiran 8 Tabel Hasil Ekstraksi Citra Mammogram Data Testing (tanpa Operasi Titik) No Kontras Korelasi Energi Homogenitas Entropi SS IDM SA SE SV DV DE Prob Maks Dissimilarity

41

42 Lampiran 9 Script M-file Fuzzy Neural Network untuk Klasifikasi Kanker Payudara %mencari banyak neuron pada lapisan tersembunyi %yang memberikan MSE kecil syms y t; jawab ='y'; while jawab=='y'; n11= input ('Berapa neuron pada lapisan tersembunyi= '); %jumlah neuron lapisan tersembunyi diubah-ubah hingga diperoleh %neuron yang MSE-nya kecil X1=xlsread('training operasi titik.xlsx');% X1 adalah matriks input-target training, 13 Fitur X2=xlsread('testing operasi titik.xlsx');% X2 adalah matriks input-target testing, 13 Fitur P= X1(:,1:13)'; %input training1 Pc= X2(:,1:13)'; %input testing [m, n]=size(p); [mc, nc]=size(pc); T=X1(:,14)';%target training Tc=X2(:,14)';%target testing %normalisasi input dan target training dan testing [Pn,meanp,stdp,Tn,meant,stdt]=prestd(P,T); %inisialisasi FNN net=newff(minmax(pn),[n11 1],{'logsig' 'purelin'}, 'traingdx'); %Melihat bobot awal input, lapisan, dan bias BobotAwal_Input=net.IW{1,1}; BobotAwal_Bias_Input=net.b{1,1}; BobotAwal_Lapisan=net.LW{2,1}; BobotAwal_Bias_Lapisan=net.b{2,1}; %set parameter net.trainparam.epochs=5000; net.trainparam.goal=1e-5; net.trainparam.max_perf_inc=1.06; net.trainparam.lr=0.1; net.trainparam.lr_inc=1.2; net.trainparam.lr_dec=0.6; net.trainparam.mc=0.8; net.trainparam.show=500; %melakukan pembelajaran net=train(net,pn,tn); %melihat bobot akhir input, lapisan, dan bias BobotAkhir_Input=net.IW{1,1}; BobotAkhir_Bias_Input=net.b{1,1}; BobotAkhir_Lapisan=net.LW{2,1}; BobotAkhir_Bias_Lapisan=net.b{2,1}; %menampilkan target, output jaringan dan error data training ab = sim(net,pn); a=poststd(ab,meant,stdt); e1 = T-a; MSE1 = mse(e1); H1=[(1:size(P,2))' T' a' (T'-a')]; d1=['mse training adalah ',num2str(mse1)]; %dibulantakn 2 angka di belakang koma sprintf('%2d %9.2f %7.2f %5.2f\n',H1'); %Normalisasi input dan target output data testing 170

43 Qn=trastd(Pc,meanp,stdp); %menampilkan target, output jaringan dan error data testing bn=sim(net,qn); b=poststd(bn,meant,stdt); E2=Tc-b; MSE2=mse(E2); H2=[(1:size(Pc,2))' Tc' b' (Tc'-b')]; d2=['mse testing adalah ',num2str(mse2)]; %dibulantakn 2 angka di belakang koma sprintf('%2d %9.2f %7.2f %5.2f\n',H2'); %Evaluasi output NN [m1,b1,r1] = postreg(a(1,:),t(1,:));%data training dengan target %display MSE disp(d1); disp(d2); %Hasil Akurasi Training sizet=size(t); r=round(a); hitung = (find(t==r)); sizehit = size(hitung); Akurasi = (sizehit(1,2)/sizet(1,2))*100; disp('akurasi Data Training'); disp(akurasi); %Hasil Akurasi Testing sizetc=size(tc); s=round(b); hitung2=(find(tc==s)); sizeh2=size(hitung2); Akurasi2=(sizeh2(1,2)/sizetc(1,2))*100; disp('akurasi Data Testing'); disp(akurasi2) jawab=input('ingin mengulang lagi?(y/t)'); end 171

44 Lampiran 10 Hasil Klasifikasi Stadium Kanker Payudara dengan Operasi Titik pada Data Training No Data Klasifikasi Klasifikasi Hasil Asli dengan model Keterangan 1 mdb003 Normal Normal Benar (TN) 2 mdb004 Normal Normal Benar (TN) 3 mdb006 Normal Normal Benar (TN) 4 mdb008 Normal Normal Benar (TN) 5 mdb009 Normal Normal Benar (TN) 6 mdb011 Normal Normal Benar (TN) 7 mdb014 Normal Normal Benar (TN) 8 mdb016 Normal Normal Benar (TN) 9 mdb020 Normal Normal Benar (TN) 10 mdb027 Normal Normal Benar (TN) 11 mdb029 Normal Normal Benar (TN) 12 mdb031 Normal Normal Benar (TN) 13 mdb033 Normal Normal Benar (TN) 14 mdb034 Normal Normal Benar (TN) 15 mdb035 Normal Normal Benar (TN) 16 mdb038 Normal Normal Benar (TN) 17 mdb039 Normal Normal Benar (TN) 18 mdb045 Normal Normal Benar (TN) 19 mdb047 Normal Normal Benar (TN) 20 mdb048 Normal Normal Benar (TN) 21 mdb049 Normal Normal Benar (TN) 22 mdb050 Normal Normal Benar (TN) 23 mdb052 Normal Normal Benar (TN) 24 mdb053 Normal Normal Benar (TN) 25 mdb054 Normal Normal Benar (TN) 26 mdb055 Normal Normal Benar (TN) 27 mdb060 Normal Normal Benar (TN) 28 mdb062 Normal Normal Benar (TN) 29 mdb067 Normal Normal Benar (TN) 30 mdb068 Normal Normal Benar (TN) 31 mdb070 Normal Normal Benar (TN) 32 mdb078 Normal Normal Benar (TN) 33 mdb001 Tumor Tumor Benar (TP) 172

45 34 mdb002 Tumor Tumor Benar (TP) 35 mdb005 Tumor Tumor Benar (TP) 36 mdb010 Tumor Tumor Benar (TP) 37 mdb013 Tumor Tumor Benar (TP) 38 mdb019 Tumor Tumor Benar (TP) 39 mdb021 Tumor Tumor Benar (TP) 40 mdb030 Tumor Tumor Benar (TP) 41 mdb032 Tumor Tumor Benar (TP) 42 mdb063 Tumor Tumor Benar (TP) 43 mdb080 Tumor Tumor Benar (TP) 44 mdb081 Tumor Tumor Benar (TP) 45 mdb083 Tumor Tumor Benar (TP) 46 mdb099 Tumor Tumor Benar (TP) 47 mdb104 Tumor Tumor Benar (TP) 48 mdb107 Tumor Tumor Benar (TP) 49 mdb121 Tumor Tumor Benar (TP) 50 mdb132 Tumor Tumor Benar (TP) 51 mdb142 Tumor Tumor Benar (TP) 52 mdb145 Tumor Tumor Benar (TP) 53 mdb150 Tumor Tumor Benar (TP) 54 mdb152 Tumor Tumor Benar (TP) 55 mdb165 Tumor Tumor Benar (TP) 56 mdb167 Tumor Tumor Benar (TP) 57 mdb175 Tumor Tumor Benar (TP) 58 mdb190 Tumor Tumor Benar (TP) 59 mdb191 Tumor Tumor Benar (TP) 60 mdb193 Tumor Tumor Benar (TP) 61 mdb195 Tumor Tumor Benar (TP) 62 mdb198 Tumor Tumor Benar (TP) 63 mdb240 Tumor Tumor Benar (TP) 64 mdb312 Tumor Tumor Benar (TP) 65 mdb023 Kanker Kanker Benar (TP) 66 mdb028 Kanker Kanker Benar (TP) 67 mdb058 Kanker Kanker Benar (TP) 68 mdb075 Kanker Kanker Benar (TP) 69 mdb090 Kanker Kanker Benar (TP) 70 mdb105 Kanker Kanker Benar (TP) 71 mdb111 Kanker Kanker Benar (TP) 72 mdb115 Kanker Kanker Benar (TP) 173

46 73 mdb117 Kanker Kanker Benar (TP) 74 mdb120 Kanker Kanker Benar (TP) 75 mdb124 Kanker Kanker Benar (TP) 76 mdb125 Kanker Kanker Benar (TP) 77 mdb130 Kanker Kanker Benar (TP) 78 mdb134 Kanker Kanker Benar (TP) 79 mdb141 Kanker Kanker Benar (TP) 80 mdb148 Kanker Kanker Benar (TP) 81 mdb179 Kanker Kanker Benar (TP) 82 mdb181 Kanker Kanker Benar (TP) 83 mdb184 Kanker Kanker Benar (TP) 84 mdb206 Kanker Kanker Benar (TP) 85 mdb209 Kanker Kanker Benar (TP) 86 mdb216 Kanker Kanker Benar (TP) 87 mdb231 Kanker Kanker Benar (TP) 88 mdb233 Kanker Kanker Benar (TP) 89 mdb239 Kanker Kanker Benar (TP) 90 mdb241 Kanker Kanker Benar (TP) 91 mdb245 Kanker Kanker Benar (TP) 92 mdb256 Kanker Kanker Benar (TP) 93 mdb264 Kanker Kanker Benar (TP) 94 mdb267 Kanker Kanker Benar (TP) 95 mdb270 Kanker Kanker Benar (TP) 96 mdb271 Kanker Kanker Benar (TP) 174

Menunjukkan lagi