Class SpatialCropd

monai/transforms/croppad/dictionary.py:420–595

Dictionary-based wrapper of :py:class:`monai.transforms.SpatialCrop`. General purpose cropper to produce sub-volume region of interest (ROI). If a dimension of the expected ROI size is larger than the input image size, will not crop that dimension. So the cropped result may be small

class SpatialCropd(Cropd):
    """
    Dictionary-based wrapper of :py:class:`monai.transforms.SpatialCrop`.
    General purpose cropper to produce sub-volume region of interest (ROI).
    If a dimension of the expected ROI size is larger than the input image size, will not crop that dimension.
    So the cropped result may be smaller than the expected ROI, and the cropped results of several images may
    not have exactly the same shape.
    It can support to crop ND spatial (channel-first) data.

    The cropped region can be parameterised in various ways:
        - a list of slices for each spatial dimension (allows for use of -ve indexing and `None`)
        - a spatial center and size
        - the start and end coordinates of the ROI

    ROI parameters (``roi_center``, ``roi_size``, ``roi_start``, ``roi_end``) can also be specified as
    string dictionary keys. When a string is provided, the actual coordinate values are read from the
    data dictionary at call time. This enables pipelines where coordinates are computed by earlier
    transforms (e.g., :py:class:`monai.transforms.TransformPointsWorldToImaged`) and stored in the
    data dictionary under the given key.

    Example::

        from monai.transforms import Compose, TransformPointsWorldToImaged, SpatialCropd

        pipeline = Compose([
            TransformPointsWorldToImaged(keys="roi_start", refer_keys="image"),
            TransformPointsWorldToImaged(keys="roi_end", refer_keys="image"),
            SpatialCropd(keys="image", roi_start="roi_start", roi_end="roi_end"),
        ])

    This transform is capable of lazy execution. See the :ref:`Lazy Resampling topic<lazy_resampling>`
    for more information.
    """

    def __init__(
        self,
        keys: KeysCollection,
        roi_center: Sequence[int] | int | str | None = None,
        roi_size: Sequence[int] | int | str | None = None,
        roi_start: Sequence[int] | int | str | None = None,
        roi_end: Sequence[int] | int | str | None = None,
        roi_slices: Sequence[slice] | None = None,
        allow_missing_keys: bool = False,
        lazy: bool = False,
    ) -> None:
        """
        Args:
            keys: keys of the corresponding items to be transformed.
                See also: :py:class:`monai.transforms.compose.MapTransform`
            roi_center: voxel coordinates for center of the crop ROI, or a string key to look up
                the coordinates from the data dictionary.
            roi_size: size of the crop ROI, if a dimension of ROI size is larger than image size,
                will not crop that dimension of the image. Can also be a string key.
            roi_start: voxel coordinates for start of the crop ROI, or a string key to look up
                the coordinates from the data dictionary.
            roi_end: voxel coordinates for end of the crop ROI, if a coordinate is out of image,
                use the end coordinate of image. Can also be a string key.
            roi_slices: list of slices for each of the spatial dimensions.