Add OMEZarrWSI slide reader

README.md

@@ -40,6 +40,7 @@ This project was developed by the [Mahmood Lab](https://faisal.ai/) at Harvard M
 Optional install profiles:
 - `pip install -e ".[patch-encoders]"` for CONCH/MUSK/CTransPath-related extras.
 - `pip install -e ".[slide-encoders]"` for PRISM/GigaPath/Madeleine-related extras.
+- `pip install -e ".[omezarr]"` for OME Zarr WSI reader support
 - `pip install -e ".[convert]"` for slide conversion dependencies.
 - `pip install -e ".[full]"` to install all pip-installable optional dependencies.
 
@@ -232,7 +233,7 @@ main()
    - **A**: Yes using the `--custom_list_of_wsis` argument. Provide a list of WSI names in a CSV (with slide extension, `wsi`). Optionally, provide the mpp (field `mpp`)
 
  - **Q**: Do I need to install any additional packages to use Trident?
-   - **A**: `pip install -e .` installs core dependencies. Some optional components still require extra installs. Use profiles (`.[patch-encoders]`, `.[slide-encoders]`, `.[convert]`, or `.[full]`) and run `trident-doctor` for preflight checks.
+   - **A**: `pip install -e .` installs core dependencies. Some optional components still require extra installs. Use profiles (`.[patch-encoders]`, `.[slide-encoders]`, `.[convert]`, `.[omezarr]` or `.[full]`) and run `trident-doctor` for preflight checks.
 
 ## License and Terms of Use
 

docs/quickstart.rst

@@ -123,7 +123,7 @@ WSI discovery and reading
 - ``--search_nested``: recursively discover slides in nested subfolders.
 - ``--custom_list_of_wsis``: CSV subset list to process selected slides only.
 - ``--custom_mpp_keys``: metadata keys to read MPP from non-standard slide headers.
-- ``--reader_type``: force backend reader (``openslide``, ``cucim``, ``image``, ``sdpc``).
+- ``--reader_type``: force backend reader (``openslide``, ``cucim``, ``image``, ``sdpc``, ``omezarr``).
 
 When to change:
 

pyproject.toml

@@ -51,6 +51,10 @@ musk = { git = "https://github.com/lilab-stanford/MUSK", optional = true }
 gigapath = { git = "https://github.com/prov-gigapath/prov-gigapath.git", optional = true }
 madeleine = { git = "https://github.com/mahmoodlab/MADELEINE.git", optional = true }
 pylibCZIrw = { version = "*", optional = true }
+cf-units = { version = ">=3.1", optional = true }
+ngff-zarr = { version = ">=0.12", optional = true }
+zarr = { version = ">=3.0.0a0", optional = true }
+dask = { version = ">=2024.10", optional = true }
 
 [tool.poetry.extras]
 patch-encoders = [
@@ -82,6 +86,12 @@ full = [
     "madeleine",
     "pylibCZIrw",
 ]
+omezarr = [
+    "ngff-zarr",
+    "dask",
+    "cf-units",
+    "zarr"
+]
 
 [tool.poetry.dev-dependencies]
 # Optional development dependencies 

run_batch_of_slides.py

@@ -59,8 +59,8 @@ def build_parser() -> argparse.ArgumentParser:
                     help='Custom keys used to store the resolution as MPP (micron per pixel) in your list of whole-slide image.')
     parser.add_argument('--custom_list_of_wsis', type=str, default=None,
                     help='Custom list of WSIs specified in a csv file.')
-    parser.add_argument('--reader_type', type=str, choices=['openslide', 'image', 'cucim', 'sdpc'], default=None,
-                    help='Force the use of a specific WSI image reader. Options are ["openslide", "image", "cucim", "sdpc"]. Defaults to None (auto-determine which reader to use).')
+    parser.add_argument('--reader_type', type=str, choices=['openslide', 'image', 'cucim', 'sdpc', 'omezarr'], default=None,
+                    help='Force the use of a specific WSI image reader. Options are ["openslide", "image", "cucim", "sdpc", "omezarr"]. Defaults to None (auto-determine which reader to use).')
     parser.add_argument("--search_nested", action="store_true",
                         help=("If set, recursively search for whole-slide images (WSIs) within all subdirectories of "
                               "`wsi_source`. Uses `os.walk` to include slides from nested folders. "

trident/Processor.py

@@ -11,7 +11,7 @@
 from trident import load_wsi, WSIReaderType
 from trident.IO import create_lock, remove_lock, is_locked, update_log, collect_valid_slides, splitext
 from trident.Maintenance import deprecated
-from trident.wsi_objects.WSIFactory import OPENSLIDE_EXTENSIONS, PIL_EXTENSIONS, SDPC_EXTENSIONS
+from trident.wsi_objects.WSIFactory import OPENSLIDE_EXTENSIONS, PIL_EXTENSIONS, SDPC_EXTENSIONS, OMEZARR_EXTENSIONS
 
 
 class Processor:
@@ -74,7 +74,7 @@ def __init__(
                 Maximum number of workers for data loading. If None, the default behavior will be used.
                 Defaults to None.
             reader_type (WSIReaderType, optional):
-                Force the image reader engine to use. Options are are ["openslide", "image", "cucim"]. Defaults to None
+                Force the image reader engine to use. Options are are ["openslide", "image", "cucim", "sdpc", "omezarr"]. Defaults to None
                 (auto-determine the right engine based on image extension).
             search_nested (bool, optional):  
                 If True, the processor will recursively search for WSIs within all subdirectories of `wsi_source`.
@@ -108,7 +108,7 @@ def __init__(
 
         self.job_dir = job_dir
         self.wsi_source = wsi_source
-        self.wsi_ext = wsi_ext or (list(PIL_EXTENSIONS) + list(OPENSLIDE_EXTENSIONS) + list(SDPC_EXTENSIONS))
+        self.wsi_ext = wsi_ext or (list(PIL_EXTENSIONS) + list(OPENSLIDE_EXTENSIONS) + list(SDPC_EXTENSIONS) + list(OMEZARR_EXTENSIONS))
         self.skip_errors = skip_errors
         self.custom_mpp_keys = custom_mpp_keys
         self.max_workers = max_workers

trident/__init__.py

@@ -9,6 +9,7 @@
 from trident.wsi_objects.CuCIMWSI import CuCIMWSI
 from trident.wsi_objects.ImageWSI import ImageWSI
 from trident.wsi_objects.SDPCWSI import SDPCWSI
+from trident.wsi_objects.OMEZarrWSI import OMEZarrWSI
 from trident.wsi_objects.WSIFactory import load_wsi, WSIReaderType
 from trident.wsi_objects.WSIPatcher import OpenSlideWSIPatcher, WSIPatcher
 from trident.wsi_objects.WSIPatcherDataset import WSIPatcherDataset
@@ -28,6 +29,7 @@
     "ImageWSI",
     "CuCIMWSI",
     "SDPCWSI",
+    "OMEZarrWSI",
     "WSIPatcher",
     "OpenSlideWSIPatcher",
     "WSIPatcherDataset",