Creating lung volume from CAT scan?

2021 1 8
1 个回答
回答已采纳
更新时间：2021 1 10
3 次查看（30 天）

0 个投票

https://www.mathworks.com/help/images/segment-lungs-from-3-d-chest-mri-data.html
It's going to work amazing in that imageset, but when i try to use mine, i dont know what should i do?
I'm working with DICOM format but also i can work with the jpeg format, if its going to be problem.
This is the code from i get the link but im not sure how to change this for my imageset(link)
Edit: I solved the importing issue, now i can use my own imageset. But now i have another issue on Image Segmentation.
Im going to use this segmentation on volume segmentation as a slice mask.
I thresolded, inverted and cleaned borders and filled holes. But still the base of tomography showing here. Any possibilities to using that mask in that red rectangle region?
And any possibilities have we to export this into a 3D object?
[V,spatial,dim] = dicomreadVolume(fullfile("Seri2"));
V = squeeze(V);
whos V
V = im2single(V);
XY = V(:,:,180);
XZ = squeeze(V(256,:,:));
figure
imshow(XY,[],'Border','tight');
figure
imshow(XZ,[],'Border','tight');
%%
BW = XY > 7.647100e-01;
BW = imcomplement(BW);
BW = imclearborder(BW);
BW = imfill(BW, 'holes');
radius = 3;
decomposition = 0;
se = strel('disk',radius,decomposition);
BW = imerode(BW, se);
maskedImageXY = XY;
maskedImageXY(~BW) = 0;
imshow(maskedImageXY)
%%
BW = XZ > 7.647100e-01;
BW = imcomplement(BW);
BW = imclearborder(BW);
BW = imfill(BW, 'holes');
radius = 3;
decomposition = 0;
se = strel('disk',radius,decomposition);
BW = imerode(BW, se);
maskedImageXZ = XZ;
maskedImageXZ(~BW) = 0;
imshow(maskedImageXZ)
%%
mask = false(size(V));
mask(:,:,160) = maskedImageXY;
mask(256,:,:) = mask(256,:,:)|reshape(maskedImageXZ,[1,512,212]);
V = histeq(V);
%%
BW = activecontour(V,mask,100,'Chan-Vese');
segmentedImage = V.*single(BW);
volumeViewer(segmentedImage)
%%
volLungsPixels = regionprops3(logical(BW),'volume');
spacingx = 0.938;
spacingy = 0.938;
spacingz = 1.26*le-6;
unitvol = spacingx*spacingy*spacingz;
volLungs1 = volLungsPixels.Volume(1)*unitvol;
volLungs2 = volLungsPixels.Volume(2)*unitvol;
volLungsLiters = volLungs1 + volLungs2
%%

请先登录，再回答此问题。

 采纳的回答

Image Analyst
Image Analyst 2021-1-9

1 个投票

If you have row1, row2, col1, and col2 of your red box, then you can erase the 2-D binary image outside that like this:
mask(1:row1, :) = false;
mask(row2:end, :) = false;
mask(:, 1:col1) = false;
mask(:, col2:end) = false;

4 个评论
显示 2更早的评论 隐藏 2更早的评论

Mr. Image Analyst im really sorry to disturb you, but im stuck again.
[128:132]
[400:132]
[128:315]
[400:315]
These are the 4 corners of the red rectangle on pixel region, im making the rows and cols like this but im giving error. What should i do?
row1 = maskedImageXY((128:132),(400:132));
row2 = maskedImageXY((128:315),(400:315));
col1 = maskedImageXY((128:132),(128:315));
col2 = maskedImageXY((400:132),(400:315));
mask = false(size(V));
mask(:,:,160) = maskedImageXY;
mask(256,:,:) = mask(256,:,:)|reshape(maskedImageXZ,[1,512,212]);
mask(1:row1, :) = false;
mask(row2:end, :) = false;
mask(:, 1:col1) = false;
mask(:, col2:end) = false;
V = histeq(V);
Image Analyst
Image Analyst 2021-1-9
row1, etc. are single numbers, not images. So
row1 = 128
row2 = 400
col1 = 132
col2 = 315
Works like a charm! Thank you so much! I think it is not possible but, could have any chance to exporting this volume as .stl or .obj format?
Image Analyst
Image Analyst 2021-1-10
I don't use those formats, so I don't know. You'll have to figure it out on your own. If my main answer worked, could you please "Accept this Answer". Thanks in advance.

请先登录，再进行评论。

更多回答（0 个）

类别

在 帮助中心 和 File Exchange 中查找有关 Image Segmentation 的更多信息

产品

版本

R2020b

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by