How can i get rid of some part of image ?

I'd like to ged rid of some part of image that light pixels of out of breast organ (I drew the region with red line that i don't want). Could you please help me for this problem.

Original Image(p287):

Original Image (p179)

%  it's for second image. p179
se = strel('disk',4);

clc;    % Clear the command window.
fprintf('Beginning to run %s.m ...\n', mfilename);
close all;  % Close all figures (except those of imtool.)
clearvars;
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;
grayImage = rgb2gray(imread('p287.jpg'));
en = imsharpen(grayImage,'Radius',2,'Amount',1);
B = double(imgaussfilt(en,1.4));
ed=edge(B ,'canny',0.3,0.5);
subplot(2, 2, 1);
imshow(ed);
title('Initial Canny Edge', 'FontSize', fontSize);
bw1=bwareaopen(ed,10);
se = strel('disk',5);
bw=imdilate(bw1,se);
subplot(2, 2, 2);
imshow(bw);
title('Next Mask', 'FontSize', fontSize);
% Take largest 2 blobs.
 bw = bwareafilt(bw, 2);
%  Erase top half
 [rows, columns] = size(bw);
 bw(1:round(rows/2), :) = false;
%  Skeletonize
 bw = bwskel(bw);
%  Find branchpoints.
 [bpRows, bpColumns] = find(bwmorph(bw, 'branchpoints'))
%  Erase branchpoints.
 hold on;
 for k = 1 : length(bpRows)
 	bw(bpRows(k), bpColumns(k)) = false;
 	plot(bpColumns(k), bpRows(k), 'r.', 'MarkerSize', 50);
 end
% %Erase any blobs with a centroid below 400.
 props = regionprops(bw, 'Centroid');
 xy = vertcat(props.Centroid)
%  Don't keep the two with the highest centroid.
 indexesToKeep = find(xy(:, 2) < 405);
%  Extract all but the lowest two.
labeledImage = bwlabel(bw);
 bw = ismember(labeledImage, indexesToKeep);
 subplot(2, 2, 3);
 imshow(bw);
  axis('on', 'image');
 title('Final Mask', 'FontSize', fontSize);
%  Put the branchpoints back in to make each breast just one curve.
 for k = 1 : length(bpRows)
 	bw(bpRows(k), bpColumns(k)) = true;
 end
 labeledImage = bwlabel(bw);
 % Find the left breast curve
 [yr, xr] = find(labeledImage == 1);
 % Find the right breast curve
 [yl, xl] = find(labeledImage == 2);
 % Find the left breast circle
%   x=xr;y=yr; hullflag=1;
%  [centerr,radiusr] = minboundcircle(x, y, hullflag);
%  x1=xl;y1=yl; hullflag1=1;
%  [centerl,radiusl] = minboundcircle(x1,y1,hullflag1);
 
 % Find the leftmost point and don't include any points with y values above it.
[xMin, index] = min(xl);
keeperIndexes = yl > yl(index)
xll = xl(keeperIndexes);
yll = yl(keeperIndexes);
% Fit a circle to the left coordinates
[xCenter1, yCenter1, radius1, a1] = circlefit(xll, yll);
% Find the rightmost point and don't include any points with y values above it.
[xMax, index] = max(xr);
keeperIndexes = yr > yr(index)
xrr = xr(keeperIndexes);
yrr = yr(keeperIndexes);
% Fit a circle to the right coordinates
[xCenter2, yCenter2, radius2, a2] = circlefit(xrr, yrr);
% View the circles
%  center1= [xCenter1, yCenter1]; 
%  center2=[xCenter2, yCenter2];
%  radii = [radius1; radius2];
 
%  centerl = [xCenter1, yCenter1];
% centerr=[xCenter2, yCenter2];
 
 theta = 0 : 0.01 : 2*pi;
%  Equation of left
x = radius1 * cos(theta) + xCenter1;
y = radius1 * sin(theta) + yCenter1;
%  Equation of right
x2 = radius2 * cos(theta) + xCenter2;
y2 = radius2 * sin(theta) + yCenter2;
subplot(2, 2, 4);
imshow(grayImage, 'border', 'tight' );
 
hold all
 roi = drawpolygon(gca,'Position',[x;y]');
 plot(xr, yr, 'r.', 'MarkerSize', 4);
 plot(xl, yl, 'y.', 'MarkerSize', 4);
 plot(x, y, 'b.', 'MarkerSize', 4);
 plot(x2, y2, 'b.', 'MarkerSize', 4);
 
 xMiddle = mean([max(xl), min(xr)]);
 xline(xMiddle, 'Color', 'm', 'LineWidth', 4);
 title('Breast Outlines Overlaid on Original Image', 'FontSize', fontSize);
hold off
 grayImage1=grayImage
  [nx,ny,d] = size(grayImage1) ;
 [X,Y] = meshgrid(1:ny,1:nx) ;
   idx = inpolygon(X(:),Y(:),x,y) ;
 for i = 1:d
     I1 = grayImage1(:,:,i) ;
    I1(~idx) = 255 ;
     grayImage1(:,:,i) = I1 ;
 end
 figure();
imshow(grayImage1);
grayImage5=grayImage;
idx3=inpolygon(xr',yr,x2',y2);
 for i = 1:d
    I1 = grayImage5(:,:,i) ;
    I1(~idx) = 255 ;
    grayImage5(:,:,i) = I1 ;
end
figure();
imshow(grayImage5);
grayImage6 = min(grayImage5, [], 3);
binaryImage = grayImage6 < 200;
binaryImage = bwareafilt(binaryImage, 1);
[rows, columns] = find(binaryImage);
row1r = min(rows);
row2r = max(rows);
col1r = min(columns);
col2r = max(columns);
% Crop
croppedImage1 = grayImage5(row1r:row2r, col1r:col2r, :);
figure();imshow(croppedImage1);
croppedImage1(croppedImage1  == 255) = 233;
subplot(2, 3, 1);
figure();imshow(croppedImage1);

grayImage2=grayImage;
[nx1,ny1,d1] = size(grayImage2) ;
[X1,Y1] = meshgrid(1:ny1,1:nx1) ;
 idx1 = inpolygon(X1(:),Y1(:),x2,y2) ;
 for i = 1:d1
    I1 = grayImage2(:,:,i) ;
    I1(~idx1) = 255 ;
    grayImage2(:,:,i) = I1 ;
end
figure();
imshow(grayImage2);
grayImage3=grayImage;
idx2=inpolygon(xl',yl,x',y);
 for i = 1:d1
    I1 = grayImage3(:,:,i) ;
    I1(~idx1) = 255 ;
    grayImage3(:,:,i) = I1 ;
end
figure();
imshow(grayImage3);
grayImage4 = min(grayImage3, [], 3);
binaryImage = grayImage4 < 200;
binaryImage = bwareafilt(binaryImage, 1);
[rows, columns] = find(binaryImage);
row1 = min(rows);
row2 = max(rows);
col1 = min(columns);
col2 = max(columns);
% Crop
croppedImage = grayImage3(row1:row2, col1:col2, :);
figure();imshow(croppedImage);
C = maxhessiannorm(croppedImage);
figure();imshow(C);
croppedImage(croppedImage  == 255) = 233;
figure();imshow(croppedImage);

[mohd akmal masud]

could you attached the image?

[Beren Ac]

I did. @mohd akmal masud

Answer 1

[Image Analyst]

I know from your prior posts that you have the outline of the breasts. So you just need to mask outside of the breast outline before you mask with the circle and crop the circle out of the image.

Actually I don't know why you don't just analyze the image as-is. What is to be gained by circling them and cropping them out. It's not needed.

[Beren Ac]

This is because i'll perform intensity based asymmetry analysis. So that part of area is white color and hot spot which turns my analysis into unreal.

[Beren Ac]

And if you help me to mask outside of the breast outline i'll appriate it. I tried it before with connected component labeling but it didn't work.@Image Analyst

[Image Analyst]

@Beren Ac no, that would be the totally wrong thing to do. Connected component labeling doesn't have anything to do with masking/erasing pixels. You already have the left and right coordinates of the breasts: xl, yr, xl, and yl. So just use those to create a mask and erase it.

% Get mask for left breast
bothBreasts = poly2mask(xl, yl, rows, columns) | poly2mask(xr, yr, rows, columns);
% Erase outside the breasts
grayImage(~bothBreasts) = 0;
% Now do stuff about masking again with the circular mask
% and the cropping out into a smaller sub image.

I don't know why you didn't answer my question. You probably forgot so I'll ask it again so you don't waste time doing unnecessary stuff:

"Actually I don't know why you don't just analyze the image as-is. What is to be gained by circling them and cropping them out? It's not needed."

You can analyze each breast in turn just by using the left and right masks. No need at all to mask with a circle and crop out into a small image of just one breast. You can find hot spots without doing that.

[Beren Ac]

Thaks for your help but this mask didn't get properly breast. If it works, there is no need for circle fitting and cropping image. I used circle fitting because i couldn't get breast with xr,xl,yl and yr coordinates. But I have to seperate it for bileteral asymmerty analysis as left and right. Maybe i can do it by using middle line. @Image Analyst