MATLAB: Bacterial Cell Segmentation – Ignoring touching bacterial cells

cell segmentationcellsimage analysisimage processingImage Processing Toolboximage segmentation

I’m creating a program that will take in cell images (160810_rpoEdel_13.jpg) and segment the image to identify individual cells’ centroid location and pixel intensity values. So far, by using sobel edge detection and regionprops to filter out things that are too big, my program can remove most clusters and returns an image that is pretty decent. However, there some touching cells that pass through the filters (segmentedImage.jpg).

Is there another / better way to ignore or filter out the touching cells? Or a better way to segment them?

Best Answer

The binary image doesn't even look like it came from the same image. You can check solidity to find out which blobs are touching, assuming one of them is at an angle to the other.

By the way, I don't think I'd use Sobel filter - it already looks kind of like a Sobel filtered image. Anyway, you can get a decent binary image just by taking the red channel and thresholding it at 110.

Related Solutions

MATLAB: Is there a way to get the centroid of a pixel in an image

See my Image Processing Tutorial http://www.mathworks.com/matlabcentral/fileexchange/?term=authorid%3A31862 It goes through all that. It finds centroid of regions and gray level weighted centroids of regions, and a bunch of other stuff too. It has been very instructive for thousands of people.

MATLAB: Plotting bacterial growth using odes

I believe Monod kinetics and curve fitting can help. You are not fitting data, so just use the ODE and ode45 call syntax.

EDIT — (16 Oct 2019 at 17:30)

If you want to plot the differential equations themselves, substitute ‘t’ and ‘y’ back into ‘M’ to get the derivatives:

% Change to First Order%
[V,Sbs] = odeToVectorField([ode1,ode2,ode3])
M = matlabFunction(V,'vars',{'t','Y'})
% Setting Intervals%
interval = [0 1000];
% Initial Conditions%
y0 = [X0 S0 P0];
ysol = ode45(M,interval,y0)
% Graph Plots%
fplot(@(x)deval(ysol,x,1), [0, 35]);
hold on
fplot(@(x)deval(ysol,x,2), [0, 35]);
fplot(@(x)deval(ysol,x,3), [0, 35]);
hold off
legend(string(Sbs))
t = ysol.x;
ys = ysol.y;
for k = 1:numel(t)
    dy(:,k) = M(t(k),ys(:,k));
end
figure
plot(t, dy)
grid
legend(string(Sbs))
xlim([0 35])
title('Derivatives')

Alternatively, you can use the gradient function on the solved values of ‘y’, although you would need to specify ‘interval’ as a vector of more than two elements using the linspace function for best results, since gradient prefers regularly-sampled vectors. It all depends on what you want to do.

EDIT — (16 Oct 2019 at 17:59)

#Plotting bacterial growth using odes.png

The plot image is not appearing when I paste it in, so I attached it as well.

Best Answer

Related Solutions

MATLAB: Is there a way to get the centroid of a pixel in an image

MATLAB: Plotting bacterial growth using odes

Related Question