Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

thresholding value for clothing and patient bed removal #14

Open
gokceay opened this issue Jul 11, 2020 · 3 comments
Open

thresholding value for clothing and patient bed removal #14

gokceay opened this issue Jul 11, 2020 · 3 comments

Comments

@gokceay
Copy link

gokceay commented Jul 11, 2020

Hi,

By using your code is it possible to remove clothing, patient bed etc. removal by changing HU threshold values or trying something else? I tried a few threshold value for skin extraction and soft tissue but could not get a clean stl.
Thanks in advance,
Kind regards
Gokce

@dave3d
Copy link
Owner

dave3d commented Jul 13, 2020

I'm afraid there's no way to remove those thing simply based on a threshold. I think the Hounsfield units of cloth and the bed are similar to soft tissue, so you can't just pick a value. You really need some sort of model based segmentation approach.

@gokceay
Copy link
Author

gokceay commented Jul 17, 2020

Thanks a lot, I segmented the patient bed and clothing using another code, is it possible to convert to stl directly without selecting the bone skin soft tissue part specifically? I want to convert my segmented dicom to stl directly. Thanks in advance

@dave3d
Copy link
Owner

dave3d commented Jul 17, 2020

If you can select a good iso-value, then you can use my script to create a STL mesh of that iso-value. Examine the pixel intensities of the thing you're trying to extract, and pick a number somewhere in the middle range of those intensities.

Let's say you thing 200 is a reasonable iso-value. Then you'd run the script like this:

dicom2stl.py -i 200 dicom.zip

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants