Add OMEZarr reader support based on changes in mahmoodlab#163

Author: HarveySouth

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",

trident/wsi_objects/WSIFactory.py

@@ -6,19 +6,21 @@
 from trident.wsi_objects.ImageWSI import ImageWSI
 from trident.wsi_objects.CuCIMWSI import CuCIMWSI
 from trident.wsi_objects.SDPCWSI import SDPCWSI
-WSIReaderType = Literal['openslide', 'image', 'cucim', 'sdpc']
+from trident.wsi_objects.OMEZarrWSI import OMEZarrWSI
+WSIReaderType = Literal['openslide', 'image', 'cucim', 'sdpc', 'omezarr']
 OPENSLIDE_EXTENSIONS = {'.svs', '.tif', '.tiff', '.ndpi', '.vms', '.vmu', '.scn', '.mrxs'}
 CUCIM_EXTENSIONS = {'.svs', '.tif', '.tiff'}
 SDPC_EXTENSIONS = {'.sdpc'}
 PIL_EXTENSIONS = {'.png', '.jpg', '.jpeg'}
+OMEZARR_EXTENSIONS = {'.ome.zarr'}
 
 
 def load_wsi(
     slide_path: str,
     reader_type: Optional[WSIReaderType] = None,
     lazy_init: bool = False,
     **kwargs
-) -> Union[OpenSlideWSI, ImageWSI, CuCIMWSI, SDPCWSI]:
+) -> Union[OpenSlideWSI, ImageWSI, CuCIMWSI, SDPCWSI, OMEZarrWSI]:
     """
     Load a whole-slide image (WSI) using the appropriate backend.
 
@@ -30,7 +32,7 @@ def load_wsi(
     ----------
     slide_path : str
         Path to the whole-slide image.
-    reader_type : {'openslide', 'image', 'cucim', 'sdpc'}, optional
+    reader_type : {'openslide', 'image', 'cucim', 'sdpc', 'omezarr'}, optional
         Manually specify the WSI reader to use. If None (default), selection
         is automatic based on file extension.
     lazy_init : bool, optional
@@ -41,7 +43,7 @@ def load_wsi(
 
     Returns
     -------
-    Union[OpenSlideWSI, ImageWSI, CuCIMWSI, SDPCWSI]
+    Union[OpenSlideWSI, ImageWSI, CuCIMWSI, SDPCWSI, OMEZarrWSI]
         An instance of the appropriate WSI reader.
 
     Raises
@@ -78,11 +80,22 @@ def load_wsi(
                 f"Unsupported file format '{ext}' for CuCIM. "
                 f"Supported whole-slide image formats are: {', '.join(CUCIM_EXTENSIONS)}."
             )
- 
+    
+    elif reader_type == 'omezarr':
+        if ext in OMEZARR_EXTENSIONS:
+            return OMEZarrWSI(slide_path=slide_path, lazy_init=lazy_init, **kwargs)
+        else:
+            raise ValueError(
+                f"Unsupported file format '{ext}' for Ome-Zarr. "
+                f"Supported whole-slide image formats are: {', '.join(OMEZARR_EXTENSIONS)}."
+            )
+        
     elif reader_type is None:
         if ext in OPENSLIDE_EXTENSIONS:
             return OpenSlideWSI(slide_path=slide_path, lazy_init=lazy_init, **kwargs)
         elif ext in SDPC_EXTENSIONS:
             return SDPCWSI(slide_path=slide_path, lazy_init=lazy_init, **kwargs)
+        elif ext in OMEZARR_EXTENSIONS:
+            return OMEZarrWSI(slide_path=slide_path, lazy_init=lazy_init, **kwargs)
         else:
             return ImageWSI(slide_path=slide_path, lazy_init=lazy_init, **kwargs)