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

Spacing for TIF files #2304

Open
serg-bg opened this issue Jun 18, 2024 · 2 comments
Open

Spacing for TIF files #2304

serg-bg opened this issue Jun 18, 2024 · 2 comments
Assignees

Comments

@serg-bg
Copy link

serg-bg commented Jun 18, 2024

Hi! I've been having amazing success with your models! However I have bene ignoring the spacing component a bit in the tif images I am using. I would like to compare the performance of my models if I specify the spacing in the .json file. I understand how to generate the spacing .json file per image but wanted to make sure how the spacing is being read. If I have a TIF file with spacing XY=0.102 um and Z= 1um, does the spacing file need to know it is in microns or do I need to convert to some other unit, such a nanometers or meters? Thanks!

@serg-bg
Copy link
Author

serg-bg commented Aug 13, 2024

Hi just wanted to follow up on this if there is a recommendation on how to specify spacing for tif files? Thanks!

@TaWald
Copy link
Member

TaWald commented Nov 5, 2024

Generally spacings are entered in millimeters, but in principle there is nothin stopping you from choosing a consistent other scale. (But I would not recommend since it is bad practice)

If you'd ignore the recommendations and choose another scale you can run into issues:
Imagine you have your model developed and then apply it to another dataset where the scale is not in um but in mm --> your model will try to resample to the original spacing and this will end up breaking your model (either 1 voxel becomes about 1k repeats and your images will blow up, or your images will shrink to a single point 1000 -> 1).
So the gist is that you need to be consistent. There are no hard constraints but I'd recommend sticking to the mm standard.

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