Blood vessel identification from an OCT image

Hello,

I have an image that I want to identify blood vessels in (marked with arrows)

Does anyone have an idea how to do this? Basically, I need the borders of the blood vessels.

The original image:

Answer 1

[Mathieu NOE]

let's try something with edge approach : nice but how do you then isolate the black thicker line as the identified blood vessel ?

% Read the input image
image = imread('image.jpg');
grayImage = rgb2gray(image); % Convert to grayscale if it's a color image

% Enhance contrast using adaptive histogram equalization
enhancedImage = adapthisteq(grayImage);

% Apply a median filter to reduce noise
filteredImage = medfilt2(enhancedImage, [3 3]);

% Use edge detection to highlight blood vessels
edges = edge(filteredImage, 'log');

% Perform morphological operations to refine the segmentation
se = strel('disk', 4); % Structuring element
dilatedEdges = imdilate(edges, se); % Dilate edges
cleanedEdges = imerode(dilatedEdges, se); % Erode to clean up

% Display the results
% figure, imshow(enhancedImage), title('Enhanced Image');
% figure, imshow(filteredImage), title('Filtered Image');
figure, imshow(edges), title('Edge Detection');

●

figure, imshow(cleanedEdges), title('Final Segmentation');

[Mathieu NOE]

then this my suggestion, not anything fancy based on image processing tbx

as per my understanding the blood vessel is within the two magenta curves

% Read the input image
A = imread('image.jpg');
A = rgb2gray(A); % Convert to grayscale if it's a color image
A = double(A);
A = flipud(A); % to have image displayed with correct y direction
[y,x] = find(A>50); 
[xtop,ytop,xbottom,ybottom,] = top_bottom_boundary(x,y);
figure(1)
imagesc(A);
colorbar('vert');
set(gca,'YDir','normal');
colormap('gray');
hold on
plot(xtop, ytop, '--r', xbottom, ybottom, '--g','linewidth',2)

% first find the blood vessel center line ("valey")
for k = 1:numel(xtop)
    s = A(:,k);
    [minS,ind] = min(s(ybottom(k):ytop(k)));
    xline(k) = k;
    yline(k) = ind+ybottom(k);
    zline(k) = minS;
end

% smooth zline profile before moving on
zline = smoothdata(zline,'gaussian',50);
% smooth yline profile before moving on
yline = round(smoothdata(yline,'gaussian',50))'; % nb : must be rounded because after used as an index

% now find top and bottom envelope of blood vessel
for k = 1:numel(xtop)
    s = A(:,k);
    % find upper line with threshold factor with zline
    thres = 1.25;
    [valU,indU] = min(abs(s(yline(k):ytop(k))-thres*zline(k)));
    yu(k) = yline(k)+indU;
    % find lower line with threshold factor with zline
    thres = 1.5;
    [valL,indL] = min(abs(s(yline(k):-1:ybottom(k))-thres*zline(k)));
    yl(k) = yline(k)-indL;
    
end

%smooth it a bit
N = 50;
yu = smoothdata(yu,'gaussian',N);
yl = smoothdata(yl,'gaussian',N);

% remove incorrect start and stop because of YTicks in image
n = 16;
yline(1:n) = NaN;
yline(end-n:end) = NaN;
yu(1:n) = NaN;
yu(end-n:end) = NaN;
yl(1:n) = NaN;
yl(end-n:end) = NaN;


% final plot 
plot(xline,yline,'--c')
plot(xline,yu,'m')
plot(xline,yl,'m')
legend('top boundary','bottom boundary','bv center line','bv top','bv bottom');

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function [x3,y3,x4,y4] = top_bottom_boundary(x,y)
% based on FEX : https://fr.mathworks.com/matlabcentral/answers/299796-tight-boundary-around-a-set-of-points
    %split data into classes and find max/min for each class
    class_label = unique(x);
    upper_boundary = zeros(size(class_label));
    lower_boundary = zeros(size(class_label));
    for idx = 1:numel(class_label)
        class = y(x == class_label(idx));
        upper_boundary(idx) = max(class);
        lower_boundary(idx) = min(class);
    end
%     left_boundary = y(x == class_label(1));
%     right_boundary = y(x == class_label(end));
% 
%     % left_boundary
%     x1 = class_label(1)*ones(size(left_boundary));
%     y1 = left_boundary;
% 
%     % right_boundary
%     x2 = class_label(end)*ones(size(right_boundary));
%     y2 = right_boundary;
    % top boundary
    x3 = class_label;
    y3 = upper_boundary;
    % bottom boundary
    x4 = class_label;
    y4 = lower_boundary;
end

[Mathieu NOE]

hello

problem solved ?