How to do Skull striping to a .dcm image in MATLAB

I have tried this link to do skull striping. For .jpeg images, the answer is giving good solution. But when I tried that to .dcm image, I'm getting black image only.How can I do the skull striping to .dcm images without affecting it's internal parts. Please help me to do this

Answer 1

[Image Analyst]

That link looks like it finds a tumor. Why don't you try searching for the tag skull stripping. I know I've given code for precisely that in prior posts. http://www.mathworks.com/matlabcentral/answers/?term=tag%3A%22skull+stripping%22

[Suba Suba]

@Image Analyst Actually I also need to find tumor, in some .dcm images,I need to do skull striping to find the tumor, so I tried some of the links that you gave answers previously, but I couldn't apply those codes for my .dcm images.Can you show me a way to achieve it

[Suba Suba]

I have attached my .dcm images below, one image is after image segmentation and other is the original image.

[Image Analyst]

Why couldn't my skull stripping code work? Is your code in the attached zip file? Maybe I can fix it.

I don't know whether dumb thresholding will work that great for tumors. Maybe it will, but I'm sure you'll find more sophisticated and robust algorithms here: http://www.visionbib.com/bibliography/contentsmedical.html#Medical%20Applications,%20CAT,%20MRI,%20Ultrasound,%20Heart%20Models,%20Brain%20Models Check some of them out for the latest and greatest algorithms.

[Suba Suba]

No in the zip file,I attached my .dcm images. I tried this coding,but it didn't give any error. At last I'm getting black image.

img = dicomread('C:\Users\Desktop\y.dcm');
bw = (img > 0.5*255);   %thresholded to remove background and white/gray matter
lbl = bwlabel(bw);      %labelled regions
props = regionprops(lbl, 'Solidity', 'Area');
% solidity is the percentage "filled" of an area. For the skull, 
%the solidity will be really low.
solidity = [props.Solidity];
area = [ props.Area];  
hiSolid= solidity > 0.2;  %get only high solidity objects
maxArea = max( area(hiSolid));  
tumorLabel = find( area==maxArea);  %label of tumor
tumor = ismember(lbl, tumorLabel);  %b/w image of tumor
imshow(tumor);  %this isolates tumor

[Image Analyst]

The image you attached is already binarized, though badly. It does get the tumor, though it's certainly not a very robust algorithm that would work for many images.

[Suba Suba]

Can you please tell me how can I do skull striping for my original image which I have attached above?

[Image Analyst]

The only image you attached was in your.zip file and it was already binarized. The skull was broken into tiny bits. Your code already removed it, though, like I said, it's not too robust. If you were talking about a different image, then let me know exactly (what exact comment, question, or answer) where you attached it to, because it's not in the .zip file you attached - that has only the binary image.

[Suba Suba]

@Image Analyst Sorry for the late reply,here with this comment I'm again attaching my .dcm image. I just download the image from this link. Please help me to do this.

Answer 2

[Walter Roberson]

The code there assumes that the data is uint8 ,in the range 0 to 255. Data from dicom files is usually quite different ranges than that, with the range depending on the modality and instrument.

[Suba Suba]

So,can you please tell me how can I modify that code to use DICOM images

[Suba Suba]

Is there any other method to do skull striping in .dcm images? Please help me to sort out this problem.

[Image Analyst]

Attach your .dcm image with the paper clip icon.

Answer 3

[Image Analyst]

Actually you're not attaching it again. This is the first time you've attached the gray scale image. Here is my code:

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 15;

%===============================================================================
% Get the name of the image the user wants to use.
baseFileName = 'IM-0001-0009.dcm';
% Get the full filename, with path prepended.
folder = pwd
fullFileName = fullfile(folder, baseFileName);

%===============================================================================
% Read in a demo image.
grayImage = dicomread(fullFileName);
% Get the dimensions of the image.  
% numberOfColorBands should be = 1.
[rows, columns, numberOfColorChannels] = size(grayImage);
if numberOfColorChannels > 1
  % It's not really gray scale like we expected - it's color.
  % Convert it to gray scale by taking only the green channel.
  grayImage = grayImage(:, :, 2); % Take green channel.
end
% Display the image.
subplot(2, 3, 1);
imshow(grayImage, []);
axis on;
caption = sprintf('Original Grayscale Image, %s', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo();

% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);
% Get rid of tool bar and pulldown menus that are along top of figure.
set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off') 

% Display the histogram so we can see what gray level we need to threshold it at.
subplot(2, 3, 2:3);
histogram(grayImage);
grid on;
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

% Threshold the image to make a binary image.
binaryImage = grayImage > 250;
% Display the image.
subplot(2, 3, 4);
imshow(binaryImage, []);
axis on;
caption = sprintf('Initial Binary Image');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

% Extract the outer blob, which is the skull
labeledImage = bwlabel(binaryImage);
binaryImage = ismember(labeledImage, 1);
% Thicken it a little
binaryImage = imdilate(binaryImage, true(5));

% Display the final binary image.
subplot(2, 3, 5);
imshow(binaryImage, []);
axis on;
caption = sprintf('Final Binary Image of Skull Alone');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

% Mask out the skull from the original gray scale image.
outputImage = grayImage; % Initialize
outputImage(binaryImage) = 0; % Mask out.
% Display the image.
subplot(2, 3, 6);
imshow(outputImage, []);
axis on;
caption = sprintf('Skull-Stripped Gray Scale Image');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

[Suba Suba]

Thank you so much.You made my day

[Image Analyst]

You're welcome. Thanks for accepting. I'm attaching a fancier demo where I find the tumor and then indicate it in the overlay in two ways, by a red outline and by a red solid patch in the overlay.