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

handling more than one image belonging to one patient #2660

Open
dilekozkan opened this issue Dec 28, 2024 · 1 comment
Open

handling more than one image belonging to one patient #2660

dilekozkan opened this issue Dec 28, 2024 · 1 comment
Assignees

Comments

@dilekozkan
Copy link

Hi!
The point I don't understand is that how UNet supports png.
I have more than one png file belonging to a patient. should I leave them separately, or collect all the files of a patient into nii.gz?
which one true? (one modality OCT - duke dataset)

@dilekozkan
Copy link
Author

@FabianIsensee (thanks in advance, happy new years!!)
for the details:
I am using Duke OCT dataset. we have one modality. Actually 61 scans are obtained for each patient. But since there is no significant difference in consecutive images, doctors created a label for every 5 slices. 11 slices are annotated for 10 patients. (so 110 images and 110 labels are shared)
We have separate png slice files for each patient.
Should I convert this to a nii.gz format (not exactly a consecutive CT though?)
or should I let nnUnet treat each slice of each patient as a separate sample

Duke Dataset Reference:
P. P. Srinivasan, L.A. Kim, P.S. Mettu, S.W. Cousins, G.M. Comer, J.A. Izatt, and S. Farsiu,
"Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images",BioMedical Optics Express,5(10), pp. 3568-3577, 2014

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