I am a beginner of using matlab. I have a extracted ROI of lung CT scan. I want to remove the rod (stick) like structures from that binary image in order to left only the round objects ( nodules). Please, kindly advise me.

    %%Checking Round 

[B,L]=bwboundaries(bw,'noholes');
imshow(L);
% imshow(label2rgb(L, @jet, [.5 .5 .5]));
hold on
% for k = 1:length(B)
%   boundary = B{k};
%   plot(boundary(:,2), boundary(:,1), 'w', 'LineWidth', 2);
% end

stats= regionprops(L,'Area','Centroid');
% threshold= 0.94;
% loop over the boundaries
for k=1:length(B)
    % obtain (X,Y) boundary coordinates corresponding to label 'k'
    boundary=B{k};

     % compute a simple estimate of the object's perimeterd
     delta_sq= diff(boundary).^2;
     perimeter= sum(sqrt(sum(delta_sq,2)));

     %obtain the area calculation corresponding to label 'k'
     area = stats (k).Area;

     %compute the roundness metric
     metric = 4*pi*area/perimeter^2;

     %display the results
     metric_string = sprintf('%2.2f',metric);

     % mark objects above the threshold with a black circle 
      if metric > 0.5

%       text(boundary(1,2)-35,boundary(1,1)+13,metric_string,'Color','y',...
%           'FontSize',13,'FontWeight','bold');
%         centroid = stats(k).Centroid;        

%     plot(centroid(1),centroid(2),'ko');
    end

% text(boundary(1,2)-35,boundary(1,1)+13,metric_string,'Color','y',...
%      'FontSize',13,'FontWeight','bold');

end

Answer 1

[Takuji Fukumoto]

I recommend you to use regionprops function. You can measure properties of binary image with this.

https://www.mathworks.com/help/images/ref/regionprops.html?s_tid=srchtitle#input_argument_properties

stats = regionprops(BW,'Eccentricity')

The eccentricity is the ratio of the distance between the foci of the ellipse and its major axis length. The value is between 0 and 1. (0 and 1 are degenerate cases. An ellipse whose eccentricity is 0 is actually a circle, while an ellipse whose eccentricity is 1 is a line segment.)

You can identify the round objects if you choose the BWs whose eccentricity value is small.

[May]

Thanks you for your kind recommendation. It is helpful for me. I can find the eccentricity but I don't know how to remove the objects that are grater than the specified eccentricity (for example 0.5).

[Takuji Fukumoto]

Here is command.

I = imread('2.jpg');
BW = imbinarize(rgb2gray(I));

BW_out = bwpropfilt(BW, 'Eccentricity', [0.5, 1]);

figure ,imshow(BW_out);

I think eccentricity of all region is greater than 0.7.

Please set appropriate value.

And type this command on MATLAB.

imageRegionAnalyzer

This application make it easy to analyze and filter regions by properties.

https://www.mathworks.com/help/images/filter-images-on-region-properties-using-image-region-analyzer-app.html