-
Notifications
You must be signed in to change notification settings - Fork 366
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
Upgrade file reader to tifffile #118
Comments
I am not familiar with tifffile - does that handle all common wsi formats such as .svs, .ndpi, etc.? |
Yes - it is quite robust to source scanners. I have not tested it with all scanner data structures, but it appears to be much more reliable than openslide. Additionally, you can then work with custom levels by just using cv2 in your pipeline and resizing your arrays. Or you can load metadata if you wish with tifffile so that it mimics what you are doing with openslide (although I think that could make your code sensitive to different scanners, I dont encourage it). You can see my fork here. Keep in mind I have not yet tested it for anything other than patch, segmask, and stitch generation. It is also not optimized. |
i haven't used tifffile, but i've had an excellent experience with |
Hi pcicales, |
Yes I did. You can load it in parts or use ROIs to load a section only. I
can share a piece of code I used to do that later today.
On Tue, Oct 18, 2022 at 1:03 AM vcantter ***@***.***> wrote:
Hi there,
Ive found openslide to be quite problematic when dealing with high mag
WSIs. Your code can be upgraded to use tifffile, which would eliminate the
image size limitations of your system. I have used it in your code
successfully.
Hi pcicales,
I try to use your upgraded code to process my datasets. But for a big wsi,
such as 106067Pixel×86371Pixel, the system memory (32G) can not support to
read such a big image. Did you encounter this problem?
—
Reply to this email directly, view it on GitHub
<#118 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ACLFIMNE25XESVRIHX4FHN3WDY4U7ANCNFSM5S2RUXDQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
--
Kind Regards,
*Pietro Antonio Cicalese*
*Personal Cell: *(713)-689-4852
*Joint BIOE/EE PhD Candidate*
*Dr. Chandra Mohan <http://mohanlab.bme.uh.edu/> (BIOE), Dr. Hien Nguyen
<https://www.hvnguyen.com/> (EE)*
*BS, Biomedical Engineering, University of Houston*
*Former President and Co-Founder* - The Global Humanitarian Student
Initiative (GHSI)
<https://www.egr.uh.edu/news/201705/cullen-college-student-spreads-international-compassion-and-kindness-needy>
*Former Vice-President* - Friends of Haiti (FOH)
<https://uhhonorsabroad.wordpress.com/2016/04/20/becoming-a-global-humanitarian-a-student-perspective/>
*Former Webmaster *- Tau Beta Pi, Texas Epsilon
<http://www2.egr.uh.edu/~tbp/>
*Connect with me on LinkedIn <https://www.linkedin.com/in/pacicalese/>*
|
Hi pcicale, |
Hi, likewise would you mind sharing the code you used to load it in parts? |
Hi there,
Ive found openslide to be quite problematic when dealing with high mag WSIs. Your code can be upgraded to use tifffile, which would eliminate the image size limitations of your system. I have used it in your code successfully.
The text was updated successfully, but these errors were encountered: