cellmil.datamodels.wsi

Classes

WSI(name, patient, slide_path[, ...])

WSI object

class cellmil.datamodels.wsi.WSI(name: str, patient: str, slide_path: Union[str, Path], patched_slide_path: Optional[Path] = None, embedding_name: Optional[Union[str, Path]] = None, label: Optional[Union[str, int, float, ndarray[Any, Any]]] = None, logger: Optional[Logger] = None)

Bases: object

WSI object

Parameters:

• name (str) – WSI name

• patient (str) – Patient name

• slide_path (Union[str, Path]) – Full path to the WSI file.

• patched_slide_path (Union[str, Path], optional) – Full path to preprocessed WSI files (patches). Defaults to None.

• embedding_name (Union[str, Path], optional) – Defaults to None.

• label (Union[str, int, float, np.ndarray], optional) – Label of the WSI. Defaults to None.

• logger (logging.logger, optional) – Logger module for logging information. Defaults to None.

name: str

patient: str

slide_path: Union[str, Path]

patched_slide_path: Optional[Path] = None

embedding_name: Optional[Union[str, Path]] = None

label: Optional[Union[str, int, float, ndarray[Any, Any]]] = None

logger: Optional[Logger] = None

metadata: dict[str, Any]

all_patch_metadata: dict[str, Any]

patches_list: list[str]

patch_transform: Optional[Callable[[Any], Any]]

__post_init__()

Post-Processing object

_get_metadata() → None

Load metadata yaml file

_get_wsi_patch_metadata() → None

Load patch_metadata json file and convert to dict and lists

load_patch_metadata(patch_name: str) → dict[str, Any]

Return the metadata of a patch with given name (including patch suffix, e.g., wsi_1_1.png)

This function assumes that metadata path is a subpath of the patches dataset path

Parameters:

patch_name (str) – Name of patch

Returns:

metadata

Return type:

dict

set_patch_transform(transform: Callable[[Any], Any]) → None

Set the transformation function to process a patch

Parameters:

transform (Callable) – Transformation function

process_patch_image(patch_name: str, transform: Optional[Compose] = None) → Tuple[Tensor, dict[str, Any]]

Process one patch: Load from disk, apply transformation if needed. ToTensor is applied automatically

Parameters:

• patch_name (Path) – Name of patch to load, including patch suffix, e.g., wsi_1_1.png

• transform (Callable, optional) – Optional Patch-Transformation

Returns:

• torch.Tensor: patch as torch.tensor (:,:,3)

• dict: patch metadata as dictionary

Return type:

Tuple[torch.Tensor, dict]

get_number_patches() → int

Return the number of patches for this WSI

Returns:

number of patches

Return type:

int

get_patches(transform: Callable[[Any], Any]) → Tuple[Tensor, list[dict[str, Any]]]

Get all patches for one image

Parameters:

transform (Callable, optional) – Optional Patch-Transformation

Returns:

• patched image: Shape of torch.Tensor(num_patches, 3, :, :)

• coordinates as list metadata_dictionary

Return type:

Tuple[torch.Tensor, list]

load_embedding() → Tensor

Load embedding from subfolder patched_slide_path/embedding/

Raises:

FileNotFoundError – If embedding is not given

Returns:

WSI embedding

Return type:

torch.Tensor

__init__(name: str, patient: str, slide_path: Union[str, Path], patched_slide_path: Optional[Path] = None, embedding_name: Optional[Union[str, Path]] = None, label: Optional[Union[str, int, float, ndarray[Any, Any]]] = None, logger: Optional[Logger] = None) → None