What is the mistake which I did in this Breast cancer detection codes especially on segmentation part ?

https://github.com/st186/Detection-of-Breast-Cancer-using-Neural-Networks

There is a link above breast cancer detection system .

I tried to use code , I couldn't manage to apply exactly especially image segmentation part.

I follow codes in the link guidemo.m part and wrote this codes . What are my mistakes ?

Or how can I use codes in the link exactly ?

I inserted image mdb005.png

clear;
close all;

a=imread('C:\Users\Ali\Desktop\all-mias\mdb005.png');
b=im2gray(a);

%adaptive median filter part
NoisyImage=b;
NoisyImage=double(b);
        [R C P]=size(NoisyImage);
        OutImage=zeros(R,C);
        Zmin=[];
        Zmax=[];
        Zmed=[];
        

        for i=1:R
        
            for j=1:C
                       if (i==1 & j==1)


                  % for right top corner[8,7,6]
                        elseif (i==1 & j==C)


                    % for bottom left corner[2,3,4]
                        elseif (i==R & j==1)


                             % for bottom right corner[8,1,2]

                        elseif (i==R & j==C)


                            %for top edge[8,7,6,5,4]

                        elseif (i==1)


                                                    % for right edge[2,1,8,7,6]

                        elseif (i==R)

                                % // for bottom edge[8,1,2,3,4]

                        elseif (j==C)


                                 %// for left edge[2,3,4,5,6]

                        elseif (j==1)





                       else



                                     SR1 = NoisyImage((i-1),(j-1));
                                     SR2 = NoisyImage((i-1),(j));
                                     SR3 = NoisyImage((i-1),(j+1));
                                     SR4 = NoisyImage((i),(j-1));
                                     SR5 = NoisyImage(i,j);
                                     SR6 = NoisyImage((i),(j+1));
                                     SR7 = NoisyImage((i+1),(j-1));
                                     SR8 = NoisyImage((i+1),(j));
                                     SR9 = NoisyImage((i+1)),((j+1));
                                     TempPixel=[SR1,SR2,SR3,SR4,SR5,SR6,SR7,SR8,SR9];
                                     Zxy=NoisyImage(i,j);
                                     Zmin=min(TempPixel);
                                     Zmax=max(TempPixel);
                                     Zmed=median(TempPixel);
                                     A1 = Zmed - Zmin;
                                     A2 = Zmed - Zmax;

                                     if A1 > 0 && A2 < 0

                                          %   go to level B
                                          B1 = Zxy - Zmin;
                                          B2 = Zxy - Zmax;
                                          if B1 > 0 && B2 < 0
                                              PreProcessedImage(i,j)= Zxy;
                                          else
                                              PreProcessedImage(i,j)= Zmed;

                                          end
                                     else

                                         if ((R > 4 && R < R-5) && (C > 4 && C < C-5))

                                         S1 = NoisyImage((i-1),(j-1));
                                         S2 = NoisyImage((i-2),(j-2));
                                         S3 = NoisyImage((i-1),(j));
                                         S4 = NoisyImage((i-2),(j));
                                         S5 = NoisyImage((i-1),(j+1));
                                         S6 = NoisyImage((i-2),(j+2));
                                         S7 = NoisyImage((i),(j-1));
                                         S8 = NoisyImage((i),(j-2));

                                         S9 = NoisyImage(i,j);
                                         S10 = NoisyImage((i),(j+1));
                                         S11 = NoisyImage((i),(j+2));
                                         S12 = NoisyImage((i+1),(j-1));
                                         S13 = NoisyImage((i+2),(j-2));
                                         S14 = NoisyImage((i+1),(j));
                                         S15 = NoisyImage((i+2),(j));
                                         S16 = NoisyImage((i+1)),((j+1));
                                         S17 = NoisyImage((i+2)),((j+2));
                                         TempPixel2=[S1,S2,S3,S4,S5,S6,S7,S8,S9,S10,S11,S12,S13,S14,S15,S16,S17];
                                         Zmed2=median(TempPixel2);
                                         PreProcessedImage(i,j)= Zmed2;
                                         else

                                         PreProcessedImage(i,j)= Zmed;

                                         end

                                     end         

                  end    

            end
        end
        
        imshow(PreProcessedImage,[])
        
        %Segmentation part
        
        Y=double(PreProcessedImage);

        k=2; % k: number of regions

        g=2; % g: number of GMM components

        beta=1; % beta: unitary vs. pairwise

        EM_iter=10; % max num of iterations

        MAP_iter=10; % max num of iterations

       % fprintf('Performing k-means segmentation\n');

        [X,GMM,ShapeTexture]=image_kmeans(Y,k,g);
        [X,Y,GMM]=HMRF_EM(X,Y,GMM,k,g,EM_iter,MAP_iter,beta);

        Y=Y*80;

        Y=uint8(Y);
        figure, imshow(Y);

[Ali Zulfikaroglu]

@Image Analyst I am still trying to apply segmentation part from 1,5 years .But I couldn't manage . Could you please look at codes . I have thesis , If I don't manage I have to quit. I just need this mdb005 image exact segmentation codes.

[Image Analyst]

@Ali Zulfikaroglu it's not my code. I suggest you contact the author. He says he's a mentor so he should be willing to help you with his own code.

Answer 1

[Walter Roberson]

In a couple of places, you end the indexing too early -- A((i)),((j)) where you should have had A((i),(j))

Cleaned up version of the code is attached.

Please re-examine your code. You have

                if ((R > 4 && R < R-5) && (C > 4 && C < C-5))

What value of R exists such that R < R-5 could be true ? Subtract R from both sides and you see you are asking 0 < -5 which is always false.

Answer 2

[yanqi liu]

clc; clear all; close all;
warning off all
a=imread('https://ww2.mathworks.cn/matlabcentral/answers/uploaded_files/808504/mdb005.png');
a=imcrop(a,[270 147 377 533]);
b=im2gray(a);

%adaptive median filter part
NoisyImage=b;
NoisyImage=double(b);
[R, C, P]=size(NoisyImage);
OutImage=zeros(R,C);
Zmin=[];
Zmax=[];
Zmed=[];


for i=1:R
    
    for j=1:C
        if (i==1 && j==1)
            
            
            % for right top corner[8,7,6]
        elseif (i==1 && j==C)
            
            
            % for bottom left corner[2,3,4]
        elseif (i==R && j==1)
            
            
            % for bottom right corner[8,1,2]
            
        elseif (i==R && j==C)
            
            
            %for top edge[8,7,6,5,4]
            
        elseif (i==1)
            
            
            % for right edge[2,1,8,7,6]
            
        elseif (i==R)
            
            % // for bottom edge[8,1,2,3,4]
            
        elseif (j==C)
            
            
            %// for left edge[2,3,4,5,6]
            
        elseif (j==1)
            
            
            
            
            
        else
            
            
            
            SR1 = NoisyImage((i-1),(j-1));
            SR2 = NoisyImage((i-1),(j));
            SR3 = NoisyImage((i-1),(j+1));
            SR4 = NoisyImage((i),(j-1));
            SR5 = NoisyImage(i,j);
            SR6 = NoisyImage((i),(j+1));
            SR7 = NoisyImage((i+1),(j-1));
            SR8 = NoisyImage((i+1),(j));
            SR9 = NoisyImage((i+1),(j+1));
            TempPixel=[SR1,SR2,SR3,SR4,SR5,SR6,SR7,SR8,SR9];
            Zxy=NoisyImage(i,j);
            Zmin=min(TempPixel);
            Zmax=max(TempPixel);
            Zmed=median(TempPixel);
            A1 = Zmed - Zmin;
            A2 = Zmed - Zmax;
            
            if A1 > 0 && A2 < 0
                
                %   go to level B
                B1 = Zxy - Zmin;
                B2 = Zxy - Zmax;
                if B1 > 0 && B2 < 0
                    PreProcessedImage(i,j)= Zxy;
                else
                    PreProcessedImage(i,j)= Zmed;
                    
                end
            else
                
                if ((R > 4 && R < R-5) && (C > 4 && C < C-5))
                    
                    S1 = NoisyImage((i-1),(j-1));
                    S2 = NoisyImage((i-2),(j-2));
                    S3 = NoisyImage((i-1),(j));
                    S4 = NoisyImage((i-2),(j));
                    S5 = NoisyImage((i-1),(j+1));
                    S6 = NoisyImage((i-2),(j+2));
                    S7 = NoisyImage((i),(j-1));
                    S8 = NoisyImage((i),(j-2));
                    
                    S9 = NoisyImage(i,j);
                    S10 = NoisyImage((i),(j+1));
                    S11 = NoisyImage((i),(j+2));
                    S12 = NoisyImage((i+1),(j-1));
                    S13 = NoisyImage((i+2),(j-2));
                    S14 = NoisyImage((i+1),(j));
                    S15 = NoisyImage((i+2),(j));
                    S16 = NoisyImage((i+1),(j+1));
                    S17 = NoisyImage((i+2),(j+2));
                    TempPixel2=[S1,S2,S3,S4,S5,S6,S7,S8,S9,S10,S11,S12,S13,S14,S15,S16,S17];
                    Zmed2=median(TempPixel2);
                    PreProcessedImage(i,j)= Zmed2;
                else
                    
                    PreProcessedImage(i,j)= Zmed;
                    
                end
                
            end
            
        end
        
    end
end

imshow(PreProcessedImage,[])

%Segmentation part

Y=double(PreProcessedImage);

k=2; % k: number of regions

g=2; % g: number of GMM components

beta=1; % beta: unitary vs. pairwise

EM_iter=10; % max num of iterations

MAP_iter=10; % max num of iterations

% fprintf('Performing k-means segmentation\n');

[X,GMM,ShapeTexture]=image_kmeans(Y,k,g);
if ndims(Y) == 2
    Y = cat(3,Y,Y,Y);
end
[X,Y,GMM]=HMRF_EM(X,Y,GMM,k,g,EM_iter,MAP_iter,beta);

Y=Y*80;

Y=uint8(Y);
figure, imshow(Y);

[Ali Zulfikaroglu]

yeah I got this too but in real segmentation process , label and pectoral musscle should be removed and only tumor left. So this segmentation is not useful for me

[yanqi liu]

yes，sir，i think the gmm segment not used in this code

[Image Analyst]

@Ali Zulfikaroglu, so what did the authors (not yanqi, but the people who wrote the functions you found) say when you contacted them? Did they ignore you or tell you to get lost? Or did you not even try to contact them? It's possible that their algorithm was not meant for images such as yours, so ask them if they think it should work.

[Ali Zulfikaroglu]

@Image Analyst I asked him but there is no answer yet.

https://www.mathworks.com/matlabcentral/answers/1593074-how-i-can-develop-this-segmentation-codes-i-am-so-close-to-exact-shape?s_tid=mlc_ans_email_ques I developed a code in here so close the result . maybe you can see that missing part