sir, I have tried the below code for the lung cancer detection but at the last part it showing the error "Index exceeds matrix dimensions'' why this error coming and how to fix it

clc;
clear all;
close all;
% read the input CT image
I=imread('image5c.png');
figure
imshow(I);
title('INPUT CT IMAGE');
Igra1=rgb2gray(I);
figure
imshow(Igra1);
title('GRAY IMAGE');
Ifil2=medfilt2(Igra1,[3,3]);
 figure
imshow(Ifil2);
 title('FILTERED GRAY IMAGE');

text(732,501,'Image courtesy of Corel(R)',...
     'FontSize',7,'HorizontalAlignment','right')
hy = fspecial('sobel');
hx = hy';
Iy = imfilter(double(Ifil2), hy, 'replicate');
Ix = imfilter(double(Ifil2), hx, 'replicate');
gradmag = sqrt(Ix.^2 + Iy.^2);
figure
imshow(gradmag,[]), title('Gradient magnitude (gradmag)')
L = watershed(gradmag);
Lrgb = label2rgb(L);
figure, imshow(Lrgb), title('Watershed transform of gradient magnitude (Lrgb)')
se = strel('disk', 20);
Io = imopen(Ifil2, se);
figure
imshow(Io), title('Opening (Io)')
Ie = imerode(Ifil2, se);
Iobr = imreconstruct(Ie, Ifil2);
figure
imshow(Iobr), title('Opening-by-reconstruction (Iobr)')
Ioc = imclose(Io, se);
figure
imshow(Ioc), title('Opening-closing (Ioc)')
Iobrd = imdilate(Iobr, se);
Iobrcbr = imreconstruct(imcomplement(Iobrd), imcomplement(Iobr));
Iobrcbr = imcomplement(Iobrcbr);
figure
imshow(Iobrcbr), title('Opening-closing by reconstruction (Iobrcbr)')
fgm = imregionalmax(Iobrcbr);
figure
imshow(fgm), title('Regional maxima of opening-closing by reconstruction (fgm)')
I21 = Ifil2;
Ifil2(fgm) = 255;
figure
imshow(I21), title('Regional maxima superimposed on original image (I21)')
se2 = strel(ones(5,5));
fgm2 = imclose(fgm, se2);
fgm3 = imerode(fgm2, se2);
fgm4 = bwareaopen(fgm3, 20);
I3 = Ifil2;
I3(fgm4) = 255;
figure
imshow(I3)
title('Modified regional maxima superimposed on original image (fgm4)')
bw = imbinarize(Iobrcbr);
figure
imshow(bw), title('Thresholded opening-closing by reconstruction (bw)')
D = bwdist(bw);
DL = watershed(D);
bgm = DL == 0;
figure
imshow(bgm), title('Watershed ridge lines (bgm)')
gradmag2 = imimposemin(gradmag, bgm | fgm4);
L = watershed(gradmag2);
I4 = Ifil2;
I4(imdilate(L == 0, ones(3, 3)) | bgm | fgm4) = 255;
figure
imshow(I4)
title('Markers and object boundaries superimposed on original image (I4)')
Lrgb = label2rgb(L, 'jet', 'w', 'shuffle');
figure
imshow(Lrgb)
title('Colored watershed label matrix (Lrgb)')
figure
imshow(Ifil2)
hold on
himage = imshow(Lrgb);
himage.AlphaData = 0.3;
title('Lrgb superimposed transparently on original image')
x = double(fgm);
m = size(fgm,1);
n = size(fgm,2);
signal1 = fgm(:,:);
%Feat = getmswpfeat(signal,winsize,wininc,J,'matlab');
%Features = getmswpfeat(signal,winsize,wininc,J,'matlab');

[cA1,cH1,cV1,cD1] = dwt2(signal1,'db4');
[cA2,cH2,cV2,cD2] = dwt2(cA1,'db4');
[cA3,cH3,cV3,cD3] = dwt2(cA2,'db4');

DWT_feat = [cA3,cH3,cV3,cD3];
G = pca(DWT_feat);

g = graycomatrix(G);
stats = graycoprops(g,'Contrast Correlation Energy Homogeneity');
Contrast = stats.Contrast;
Correlation = stats.Correlation;
Energy = stats.Energy;
Homogeneity = stats.Homogeneity;
Mean = mean2(G);
Standard_Deviation = std2(G);
Entropy = entropy(G);
RMS = mean2(rms(G));
%Skewness = skewness(img)
Variance = mean2(var(double(G)));
a = sum(double(G(:)));
Smoothness = 1-(1/(1+a));
Kurtosis = kurtosis(double(G(:)));
Skewness = skewness(double(G(:)));
% Inverse Difference Movement
m = size(G,1);
n = size(G,2);
in_diff = 0;
for i = 1:m
    for j = 1:n
        temp = G(i,j)./(1+(i-j).^2);
        in_diff = in_diff+temp;
    end
end
IDM = double(in_diff);
 feat = [Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Variance, Smoothness, Kurtosis, Skewness, IDM];

%%SVM TRAINING AND CLASSIFICATION
 database = xlsread('datacan.xls');   
% Read Database in excel file
disp('data base of patients ');
disp(database);
Contrast = database(1:10,1);
Correlation = database(1:10,2);
Energy = database(1:10,3);
Homogeneity = database(1:10,4);
Mean = database(1:10,5);
Standard_Deviation = database(1:10,6);
Entropy = database(1:10,7);
RMS = database(1:10,8);
Variance = database(1:10,9);
Smoothness = database(1:10,10);
Kurtosis = database(1:10,11);
Skewness = database(1:10,12);
IDM = database(1:10,13);
xdata = ([Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Variance, Smoothness, Kurtosis, Skewness, IDM]);
group = database(1:10,14);
svmStruct= svmtrain(xdata,group,'kernel_function','rbf','rbf_sigma',3,'ShowPlot',true);
% Classifying New input data
disease = svmclassify(svmStruct,[feat],'ShowPlot',true);
if (disease==1)
disp('Patient is having cancer');
h=msgbox('Patient is having cancer','RESULT','custom',I);
else
disp('Patient is not having cancer');
 h=msgbox('Patient is not having cancer','RESULT','custom',I);

end

[KSSV]

YOu have to specify the line number, where you got error..Also attach the input image, so that we can try your code.

[SUCHITHRA K S]

this is my input image and i got error in %% SVM TRAINING AND CLASSIFICATION( line number after 131)

[Walter Roberson]

So your code failed to find a datacan.xls to load.

[SUCHITHRA K S]

i uploaded it then also it showing error

[KSSV]

The code demands an excel file too.....datacan.xls

[SUCHITHRA K S]

this is my database

[Sagar V]

how to create datacan.xls

please attach the code to extract features and store to a single file of many images

[sparsh gola]

plzz upload the link for image dataset of lung

[Walter Roberson]

https://www.kaggle.com/kmader/finding-lungs-in-ct-data

Answer 1

[KSSV]

Your excel file has data of size 9*14.....you are trying to access data data(1:10,i). So this is the error. Either you replace 1:10 with : or 1:end, from lines 132 to 142.

The data of the patient has cancer..poor him.

Answer 2

[Sagar V]

how train the datacan.xls file or .mat file please help me to perform for my dataset images

[Walter Roberson]

The code line

svmStruct= svmtrain(xdata,group,'kernel_function','rbf','rbf_sigma',3,'ShowPlot',true);

does the training.

Note that svmtrain() has been replaced in newer MATLAB releases.

[Sagar V]

how to create datacan.xls file or .mat file of an 50 images at a time and storing to

a file

Answer 3

[LAKSHIPRIYA GOGOI]

Getting problem in this syntax

svmStruct= svmtrain(xdata,group,'kernel_function','rbf','rbf_sigma',3,'ShowPlot',true);

I am using Matlab2014a.. I will be pleased if I got the answer..

[Walter Roberson]

What is the exact error message?

svmtrain existed in the Statistics toolbox in the time period you mentioned, using the pattern of parameters that you show. There is also a third party svm package that had a different svmtrain that used a different set of parameters, and it is possible that you are trying to use that.

[suji murali]

can u give training code for svm for the above mentioned code

[Agent]

suji murali bro can u give me code for svm

[Walter Roberson]

Agent: we need to know which MATLAB version you are using, and whether you have the Statistics toolbox, and if not whether you have installed the third party SVM toolbox

[Kunala Sahith]

can u give training code for svm for the above mentioned code R2021B VRSION

Answer 4

[Vinithra P]

May I know, which part is the detection in this?

[Walter Roberson]

All of it.

In particular, the part from

 [cA1,cH1,cV1,cD1] = dwt2(signal1,'db4'); 

is creating features, through to

feat = [Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Variance, Smoothness, Kurtosis, Skewness, IDM];

puts the completed feature vector together.

Then the part from

%%SVM TRAINING AND CLASSIFICATION

to

svmStruct= svmtrain(xdata,group,'kernel_function','rbf','rbf_sigma',3,'ShowPlot',true);

extracts features from a database and does svm training on it.

Then

disease = svmclassify(svmStruct,[feat],'ShowPlot',true);

processes the features extracted from the patient image through the trained SVM system, making a prediction about which group it belongs to.

Answer 5

[khushboo singh]

THIS SYNTAX IS NOT WORKING IN R2021b

svmStruct= svmtrain(xdata,group,'kernel_function','rbf','rbf_sigma',3,'ShowPlot',true);

[Walter Roberson]

In particular you get the message

'svmtrain' has been removed. With appropriate code changes, use 'fitcsvm' instead.

The message is correct. svmtrain() was removed as of R2019a. Replace it with https://www.mathworks.com/help/stats/fitcsvm.html and replace calls to svmclassify() with class to predict()

[Kunala Sahith]

Error using classreg.learning.FitTemplate/fillIfNeeded (line 714)

kernel_function is not a valid parameter name.

Error in classreg.learning.FitTemplate.make (line 140)

temp = fillIfNeeded(temp,type);

Error in ClassificationSVM.template (line 235)

temp = classreg.learning.FitTemplate.make('SVM','type','classification',varargin{:});

Error in ClassificationSVM.fit (line 239)

temp = ClassificationSVM.template(varargin{:});

Error in fitcsvm (line 342)

obj = ClassificationSVM.fit(X,Y,RemainingArgs{:});

Error in dipmain (line 141)

svmStruct= fitcsvm(xdata,group,'kernel_function','rbf','rbf_sigma',3,'ShowPlot',true);

why am i getting these errors.ive installed smv toolbox too.

[Walter Roberson]

@Kunala Sahith

fitcsvm does not have a 'kernel_function' option. It has a 'KernelFunction' option that can be set to 'rbf' -- though 'rbf' is the same as 'gaussian' which is the default.

The rbf_sigma parameter has been replaced by the KernelScale option

https://www.mathworks.com/matlabcentral/answers/346055-for-svm-what-is-the-difference-between-gamma-and-sigma-in-the-kernel-scale-for-rbf

[Kunala Sahith]

Im still getting error even after making changes told by you

Can you pls help. Me by editing the code for classification. Thanks in advance

xdata = ([Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Variance, Smoothness, Kurtosis, Skewness, IDM]);
group = database(:,14);
svmStruct= fitcsvm(xdata,group,'KernelFunction','rbf',' KernelScale',3,'ShowPlot',true);
% Classifying New input data
disease = ClassificationSVM(svmStruct,[feat],'ShowPlot',true);
if (disease==1)
    disp('Patient is having cancer');
    h=msgbox('Patient is having cancer','RESULT','custom',I);
else
    disp('Patient is not having cancer');
    h=msgbox('Patient is not having cancer','RESULT','custom',I);
end

c

[Walter Roberson]

What is the error message you are getting ?

[Kunala Sahith]

Error using internal.stats.parseArgs (line 42)

Wrong number of arguments.

Error in classreg.learning.paramoptim.parseOptimizationArgs (line 10)

[OptimizeHyperparameters,HyperparameterOptimizationOptions,~,RemainingArgs] = internal.stats.parseArgs(...

Error in fitcsvm (line 338)

[IsOptimizing, RemainingArgs] = classreg.learning.paramoptim.parseOptimizationArgs(varargin);

Error in dipmain (line 141)

svmStruct= fitcsvm(xdata,group,'KernelFunction',' KernelScale',3,'ShowPlot',true);

[Walter Roberson]

svmStruct= fitcsvm(xdata,group,'KernelFunction',' KernelScale',3,'ShowPlot',true);

That line does not match your posted code. Your posted code says

svmStruct= fitcsvm(xdata,group,'KernelFunction','rbf',' KernelScale',3,'ShowPlot',true);

Notice that in the error message, there is no 'rbf' . Also, you introduced a space at the beginning of the KernelScale option.

[Kunala Sahith]

Im still getting error bro:/

Answer 6

[Kunala Sahith]

I=imread('000114.png');
figure
imshow(I);
title('INPUT CT IMAGE');
Igra1=rgb2gray(I);
figure
imshow(Igra1);
title('GRAY IMAGE');
Ifil2=medfilt2(Igra1,[3,3]);
figure
imshow(Ifil2);
title('FILTERED GRAY IMAGE');
text(732,501,'Image courtesy of Corel(R)',...
    'FontSize',7,'HorizontalAlignment','right')
hy = fspecial('sobel');
hx = hy';
Iy = imfilter(double(Ifil2), hy, 'replicate');
Ix = imfilter(double(Ifil2), hx, 'replicate');
gradmag = sqrt(Ix.^2 + Iy.^2);
figure
imshow(gradmag,[]), title('Gradient magnitude (gradmag)')
L = watershed(gradmag);
Lrgb = label2rgb(L);
figure, imshow(Lrgb), title('Watershed transform of gradient magnitude (Lrgb)')
se = strel('disk', 20);
Io = imopen(Ifil2, se);
figure
imshow(Io), title('Opening (Io)')
Ie = imerode(Ifil2, se);
Iobr = imreconstruct(Ie, Ifil2);
figure
imshow(Iobr), title('Opening-by-reconstruction (Iobr)')
Ioc = imclose(Io, se);
figure
imshow(Ioc), title('Opening-closing (Ioc)')
Iobrd = imdilate(Iobr, se);
Iobrcbr = imreconstruct(imcomplement(Iobrd), imcomplement(Iobr));
Iobrcbr = imcomplement(Iobrcbr);
figure
imshow(Iobrcbr), title('Opening-closing by reconstruction (Iobrcbr)')
fgm = imregionalmax(Iobrcbr);
figure
imshow(fgm), title('Regional maxima of opening-closing by reconstruction (fgm)')
I21 = Ifil2;
Ifil2(fgm) = 255;
figure
imshow(I21), title('Regional maxima superimposed on original image (I21)')
se2 = strel(ones(5,5));
fgm2 = imclose(fgm, se2);
fgm3 = imerode(fgm2, se2);
fgm4 = bwareaopen(fgm3, 20);
I3 = Ifil2;
I3(fgm4) = 255;
figure
imshow(I3)
title('Modified regional maxima superimposed on original image (fgm4)')
bw = imbinarize(Iobrcbr);
figure
imshow(bw), title('Thresholded opening-closing by reconstruction (bw)')
D = bwdist(bw);
DL = watershed(D);
bgm = DL == 0;
figure
imshow(bgm), title('Watershed ridge lines (bgm)')
gradmag2 = imimposemin(gradmag, bgm | fgm4);
L = watershed(gradmag2);
I4 = Ifil2;
I4(imdilate(L == 0, ones(3, 3)) | bgm | fgm4) = 255;
figure
imshow(I4)
title('Markers and object boundaries superimposed on original image (I4)')
Lrgb = label2rgb(L, 'jet', 'w', 'shuffle');
figure
imshow(Lrgb)
title('Colored watershed label matrix (Lrgb)')
figure
imshow(Ifil2)
hold on
himage = imshow(Lrgb);
himage.AlphaData = 0.3;
title('Lrgb superimposed transparently on original image')
x = double(fgm);
m = size(fgm,1);
n = size(fgm,2);
signal1 = fgm(:,:);
%Feat = getmswpfeat(signal,winsize,wininc,J,'matlab');
%Features = getmswpfeat(signal,winsize,wininc,J,'matlab');
[cA1,cH1,cV1,cD1] = dwt2(signal1,'db4');
[cA2,cH2,cV2,cD2] = dwt2(cA1,'db4');
[cA3,cH3,cV3,cD3] = dwt2(cA2,'db4');
DWT_feat = [cA3,cH3,cV3,cD3];
G = pca(DWT_feat);
g = graycomatrix(G);
stats = graycoprops(g,'Contrast Correlation Energy Homogeneity');
Contrast = stats.Contrast;
Correlation = stats.Correlation;
Energy = stats.Energy;
Homogeneity = stats.Homogeneity;
Mean = mean2(G);
Standard_Deviation = std2(G);
Entropy = entropy(G);
RMS = mean2(rms(G));
%Skewness = skewness(img)
Variance = mean2(var(double(G)));
a = sum(double(G(:)));
Smoothness = 1-(1/(1+a));
Kurtosis = kurtosis(double(G(:)));
Skewness = skewness(double(G(:)));
% Inverse Difference Movement
m = size(G,1);
n = size(G,2);
in_diff = 0;
for i = 1:m
    for j = 1:n
        temp = G(i,j)./(1+(i-j).^2);
        in_diff = in_diff+temp;
    end
end
IDM = double(in_diff);
feat = [Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Variance, Smoothness, Kurtosis, Skewness, IDM];
%%SVM TRAINING AND CLASSIFICATION
database = readmatrix('datacan.xls','UseExcel', false);   
% Read Database in excel file
disp('data base of patients ');
disp(database);
Contrast = database(:,1);
Correlation = database(:,2);
Energy = database(:,3);
Homogeneity = database(:,4);
Mean = database(:,5);
Standard_Deviation = database(:,6);
Entropy = database(:,7);
RMS = database(:,8);
Variance = database(:,9);
Smoothness = database(:,10);
Kurtosis = database(:,11);
Skewness = database(:,12);
IDM = database(:,13);
xdata = ([Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Variance, Smoothness, Kurtosis, Skewness, IDM]);
group = database(:,14);
svmStruct= fitcsvm(xdata,group,'KernelFunction','rbf','KernelScale',3,'ShowPlot',true);
% Classifying New input data
disease = ClassificationSVM(svmStruct,(feat),'ShowPlot',true);
if (disease==1)
    disp('Patient is having cancer');
    h=msgbox('Patient is having cancer','RESULT','custom',I);
else
    disp('Patient is not having cancer');
    h=msgbox('Patient is not having cancer','RESULT','custom',I);
end

[Kunala Sahith]

Could you please check where am i getting it wrong pls

[Walter Roberson]

As discussed at https://www.mathworks.com/help/stats/fitcsvm.html#d123e342206

'ShowPlot' is not an option. Instead you need

'HyperparameterOptimizationOptions', struct('ShowPlots', true)

[Kunala Sahith]

Finally IT WORKED SIR BY USING OLD VERSION OF MATLAB

but

showplot still doesnt work

Warning: The display option can only plot 2D training data.

> In svmtrain (line 399)

In dipmain1 (line 141)

Warning: No figure was created during SVMTRAIN so the showplot argument will be set false.

> In svmclassify (line 122)

In dipmain1 (line 143)

im using smvtrain as it is matlab2016b version.

can you pls correct me

code:-

xdata = ([Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Variance, Smoothness, Kurtosis, Skewness, IDM]);

group = database(:,14);

svmStruct= svmtrain(xdata,group,'ShowPlot',true);

% Classifying New input data

disease = svmclassify(svmStruct,[feat],'ShowPlot',true);

[Walter Roberson]

Shrug. ShowPlot is restricted to plotting data that has two columns. You cannot use it for your data.

ShowPlot is intended to show the line of division between the two classes. That only works if you only have two input dimensions, not 13.

Answer 7

[Ahmed Alsheikhy]

Could you send the Execl file to test it.

[Arham Tabish]

Do have it now?