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
The main challenge with whole slide images (WSI) is that they do not commonly fit into CPU/GPU memory. Thus requires patching when performing inference. Although our WSIReader efficiently handle loading this patches without loading the entire WSI, the outputs also will be patches that usually cannot be merged on the memory so it requires Mergers that can effectively handle these outputs and merge them on the disk. To that end, Zarr is being used in digital pathology, which is a format for the storage of chunked, compressed, N-dimensional arrays.
The text was updated successfully, but these errors were encountered:
Fixes#6006
### Description
This PR implements `ZarrAvgMerger` which can be used for patch
inference. Also a use case is demonstrated
[here](Project-MONAI/tutorials#1433).
### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [x] New tests added to cover the changes.
- [x] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [x] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.
- [x] In-line docstrings updated.
- [x] Documentation updated, tested `make html` command in the `docs/`
folder.
---------
Signed-off-by: Behrooz <[email protected]>
The main challenge with whole slide images (WSI) is that they do not commonly fit into CPU/GPU memory. Thus requires patching when performing inference. Although our WSIReader efficiently handle loading this patches without loading the entire WSI, the outputs also will be patches that usually cannot be merged on the memory so it requires Mergers that can effectively handle these outputs and merge them on the disk. To that end, Zarr is being used in digital pathology, which is a format for the storage of chunked, compressed, N-dimensional arrays.
The text was updated successfully, but these errors were encountered: