===== Lab 02 : MATLAB: Segmentation =====

Topics:
  * Simple cell segmentation
  * Count the total number of cells and mean size

==== HW02 Assignment ====

For the homework (HW02), follow the emphasized links to get to the detailed description.

    * **[5 pts]** - [[# Cell segmentation]], build an image processing pipeline for cell segmentation in microscopy images (see detailed description).

Upload your report in PDF format to [[https://cw.felk.cvut.cz/brute/student/course/962|BRUTE]] to the assignment ''L02-segmentation''. Please name the PDF file as ''hw01_<your_fel_id>.pdf''. Zip both the MATLAB code and pdf report in a single file and upload to Brute.

==== 1. Cell segmentation ====
{{ :courses:zsl:cv1_segmentation.png?300|}}

//Segmentation// is the task of describing image areas by some context information, like finding cells in microscopy images. We want to construct an automated detection procedure. //A cell// is typically  a //roundish// dark object, so we first need to separate cell-like pixels from background and other structures by thresholding with a suitable threshold ''level''. After reading (//imopen//) and converting to grayscale image //rgb2gray//,<code matlab>
I = imread('5830.png');
Ig = rgb2gray(I);
figure;
imshow(I,[],'InitialMagnification','fit');
</code> we can attempt to find optimal threshold via<code matlab>
level = graythresh(I_gray);
Ibw = im2bw(I_gray, level);
</code>


  * If the automatic thresholding fails, we may need to set the threshold ''level'' manually. 
  * Image filtering like //imgaussfilt// prior to thresholding may give us better result.
  * //Binary morphology// filters and //filling holes// may help reduce artifacts in the binarized image.
  * To select the threshold level manually, a look at the histogram can be useful (as below)

<code matlab>
[pixelCount grayLevels] = imhist(I_gray);
bar(pixelCount);
</code>
  
We then search isolated (connected) areas in the binarized image and use //regionprops// to retrieve properties of each region: <code matlab>
[B, L] = bwboundaries(Ibw, 'noholes');
stats = regionprops('table',L,'Area');
</code>

  * we can specify multiple measures in  //regionprops// as ''Area'' may not be sufficient to distinguish between false and true detection. Consider ''Eccentricity'' and ''Solidity'' measures
  * to view labels as a colored image, use <code matlab>imshow(label2rgb(L, @jet, [.5 .5 .5]))</code>
  * (optional) if multiple cells are labeled as one blob, a //watershed// filter can sometimes separate them. <code matlab>
% Watershed - first compute distances for each pixel to the boundary 
% but since bwdist computes distances to non-zero pixels, we need to 
% logicaly revert the segmentation (~Ibw)
D = bwdist(~Ibw);

% If the watershed produces too many splits, try to smooth the distance image
D = imgaussfilt(-D, 1.5);
% Set distance to Infinity for places, where our binary image is zero
D(~Ibw) = Inf;

% Get labels by watershed transform
Lw = watershed(D, 8);
Lw(~Ibw) = 0;
</code>
  
  
Finally, we want to filter the detected cell regions by the retrieved measures and plot their boundary in the original input image ''I''<code matlab>
imshow(I);
hold on
for k = 1:length(B)
    if stats.Area(k) > ?? 
        boundary = B{k};
        plot(boundary(:,2), boundary(:,1), 'y', 'LineWidth', 2)
    end
end
</code>


**Task** Find suitable criterion on region properties (like ''Area'', ''Solidity'' etc.) to select cell-regions for each of the following data: {{ :courses:zsl:5140.png?linkonly|}} {{ :courses:zsl:5830.png?linkonly |}} {{ :courses:zsl:histopato1.png?linkonly |}}  {{ :courses:zsl:histopato2.png?linkonly |}}

==== 2. Some useful commands ====
 
<code Matlab>
help, rand, meshgrid, surf, imread, rgb2gray, imshow, lookfor, edit, path, addpath, format,
end, reshape, inf, nan, isempty, floor, ceil, round, abs, sign, ops,
length, linspace, sort, det, rank, load, save, fprintf, axis, title, 
contour, mesh, surf, colormap, print, for, if, while, function
</code>

Plot the resulting segmentation as boundary contour over the original image, like shown in the last picture.


** MATLAB Help**
  * documentation of useful MATLAB functions: [[https://uk.mathworks.com/help/images/ref/regionprops.html|properties of labeled regions]], [[https://uk.mathworks.com/help/images/ref/imgaussfilt.html|gaussian filtering]], [[https://www.mathworks.com/help/images/ref/bwmorph.html|binary morphology]],[[https://uk.mathworks.com/help/images/ref/watershed.html|watershed filter]], [[https://www.mathworks.com/help/images/ref/imfill.html|filling holes]]
  * [[https://www.youtube.com/watch?v=NSSTkkKRabI&ab_channel=DerekBanas]]
  
** Python Help** 

  * use the [[https://pypi.org/project/opencv-python|OpenCV]] library for image processing tasks. There are nice tutorials that cover many topics of [[https://docs.opencv.org/master/d2/d96/tutorial_py_table_of_contents_imgproc.html|image processing]], including 
    * [[https://docs.opencv.org/master/d7/d4d/tutorial_py_thresholding.html|Image thresholding]], 
    * [[https://docs.opencv.org/master/d9/d61/tutorial_py_morphological_ops.html|Binary morphology]] and 
    * [[https://docs.opencv.org/master/dd/d49/tutorial_py_contour_features.html|Labeling and contour features]].