You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Do you have any advice for running this for 3d volumes instead of 2d images? I could run on each z-slice, but it would lose information across slices and would need to merge classes if it disagrees for the same cell across slices. Curious if you have thoughts about how to adapt this for 3d.
Thanks!
Will Cunningham
The text was updated successfully, but these errors were encountered:
Thank you for your interest in CelloType and your question about 3D volumes. While CelloType currently only supports 2D images, here are a few potential approaches you could consider:
Maximum Intensity Projection:
Project the 3D volume into 2D using maximum intensity projection
Run CelloType on the resulting 2D image
This might work well if your cell features are clearly visible in the projection
Key z-slice selection:
Select representative z-slices (e.g., where cells are in best focus)
Process these key slices with CelloType
This could work if your cells are well-represented in specific z-planes
Hi Minxing Pang,
Do you have any advice for running this for 3d volumes instead of 2d images? I could run on each z-slice, but it would lose information across slices and would need to merge classes if it disagrees for the same cell across slices. Curious if you have thoughts about how to adapt this for 3d.
Thanks!
Will Cunningham
The text was updated successfully, but these errors were encountered: