How to Extract skin/region outside the bone (white part in image 1)?

Considering the two images, I want to extract the part of image in 1 outside the bone shown in image 2. Being a novice, I could not get to any solution to extract that region. Any help would be appreciated.

[ash fairy]

how did you extract the bone image from the ct image??

[Image Analyst]

ash fairy, I gave full code, if you expand my hidden comment below. I'm also attaching it here.

[ash fairy]

suppose we have an image with both skull and mandible, then how do we extract each of them individually?

[Image Analyst]

I don't think anusha reddy knows how to solve it or even cares about your problem. So why don't you start your own question so we don't keep bugging anusha? By the way, I don't even know how to answer your question or even know what you want or what the arrows are pointing to.

[anusha gorrila]

Hello ash fairy, apologize for the delay. Usually in scans, the bone pixels are at a higher intensity compared to the soft tissue. We could extract the bone pixels by using a minimum threshold intensity of the bone pixel intensities, capturing all the pixels above the threshold leaving you with the bone.

Answer 1

[Image Analyst]

Take the bone-only image and fill it, then use it as a mask against the original image

mask = imfill(boneOnlyImage, 'holes'); % Fill holes.
outsideSkin = grayImage; % Initialize
outsideSkin(mask) = 0; % Zero out inside the mask.

[Image Analyst]

Alright, perhaps you're having trouble so I'm giving you the full 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 = 20;

% Get the base filename.
baseFileName = 'image 1.jpg'; % Assign the one on the button that they clicked on.
% Get the full filename, with path prepended.
folder = pwd; % Current folder
fullFileName = fullfile(folder, baseFileName);

% Check if file exists.
if ~exist(fullFileName, 'file')
  % File doesn't exist -- didn't find it there.  Check the search path for it.
  fullFileNameOnSearchPath = baseFileName; % No path this time.
  if ~exist(fullFileNameOnSearchPath, 'file')
    % Still didn't find it.  Alert user.
    errorMessage = sprintf('Error: %s does not exist in the search path folders.', fullFileName);
    uiwait(warndlg(errorMessage));
    return;
  end
end
% Read in image.
grayImage = imread(fullFileName);
% Get the dimensions of the image.
% numberOfColorBands should be = 1.
[rows, columns, numberOfColorBands] = size(grayImage);
if numberOfColorBands > 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 = min(grayImage, [], 3); % Take green channel.
end
% Display the original gray scale image.
subplot(2, 2, 1);
imshow(grayImage, []);
axis on;
title('Original Grayscale Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;

% 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')

% Let's compute and display the histogram.
subplot(2, 2, 2);
histogram(grayImage);
grid on;
title('Histogram of original image', 'FontSize', fontSize, 'Interpreter', 'None');
xlabel('Gray Level', 'FontSize', fontSize);
ylabel('Pixel Count', 'FontSize', fontSize);

% Threshold to find dark.
binaryImage = grayImage > 180;
% Get rid of white surround.
binaryImage = imclearborder(binaryImage);
% Fill it.
binaryImage = imfill(binaryImage, 'holes');
% Take just the largest blob.
mask = bwareafilt(binaryImage, 1); % Fill holes.
% Display the binary image.
subplot(2, 2, 3);
imshow(mask, []);
axis on;
hold on; % So we can draw boxes.
title('Mask', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;

outsideSkin = grayImage; % Initialize
outsideSkin(mask) = 0; % Zero out inside the mask.
subplot(2, 2, 4);
imshow(outsideSkin);
axis on;
title('Final Image', 'FontSize', fontSize);

[anusha reddy]

I tried the imfill method for the bone and the resulting image is as follows, I tried using the imfill again but it did not work. Any suggestion on this ?

[Image Analyst]

For that image, you changed my code and raised the threshold from what I picked (I'm not sure why). Lower it back down to what I picked, 180 and it will work.

[anusha reddy]

i'm getting a blank image if I give it a threshold. so i had to take out the threshold and then fill in the holes. And also in the code you gave latter, you used image 1, during threshold and creating mask but we need to use the bone image to create the mask, if I'm not wrong.

[Image Analyst]

"image 1" was the original image with 3 gray levels (actually more because you unfortunately jpegged it). So I had to use that to threshold and get the bone-only image. Like I said, you did not use the same threshold. You said you took it out so I'm not even sure how you got the bone-only binary image. But however you're doing it, it's picking a threshold that's wrong because there is a little break on the left side which prevents the blob from getting filled. My code does not have a little gap in the skull like yours does. Again, follow my guidance and you'll be alright.

Answer 2

[anusha gorrila]

Worked the problem a year ago. Apologize for the delay. I filled in both regions separately with same pixel intensities and negated the filled whole face region (image 1) with the filled skull region in image 2, leaving me the soft tissue depth, which was what I was looking for.

[ash fairy]

Ohhh ...Do you still have that program ?

[anusha gorrila]

No, I do not. I solved it a year ago.

[Image Analyst]

ash, did you not expand my comments to see my full code? Click on this.