preprocessing.py

from monai.transforms import MapTransform, Transform
import numpy as np 
from monai.config import KeysCollection
from typing import Dict, Hashable, Mapping, Optional, Type, Union, Sequence
import sys
from pathlib import Path
from monai.config import DtypeLike, KeysCollection
from monai.data.image_reader import ImageReader
from monai.transforms.transform import MapTransform
from monai.utils import ensure_tuple, ensure_tuple_rep
from monai.utils.enums import PostFix
from monai.data.meta_tensor import MetaTensor
from monai.transforms.utility.array import EnsureChannelFirst
from monai.utils import ImageMetaKey as Key
from monai.utils import ensure_tuple, ensure_tuple_rep, convert_to_dst_type
from monai.data import NibabelReader
from monai.config import DtypeLike, KeysCollection, PathLike, NdarrayOrTensor

DEFAULT_POST_FIX = PostFix.meta()

class LoadImaged(MapTransform):
    """
    Dictionary-based wrapper of :py:class:`monai.transforms.LoadImage`,
    It can load both image data and metadata. When loading a list of files in one key,
    the arrays will be stacked and a new dimension will be added as the first dimension
    In this case, the metadata of the first image will be used to represent the stacked result.
    The affine transform of all the stacked images should be same.
    The output metadata field will be created as ``meta_keys`` or ``key_{meta_key_postfix}``.

    If reader is not specified, this class automatically chooses readers
    based on the supported suffixes and in the following order:

        - User-specified reader at runtime when calling this loader.
        - User-specified reader in the constructor of `LoadImage`.
        - Readers from the last to the first in the registered list.
        - Current default readers: (nii, nii.gz -> NibabelReader), (png, jpg, bmp -> PILReader),
          (npz, npy -> NumpyReader), (dcm, DICOM series and others -> ITKReader).

    Please note that for png, jpg, bmp, and other 2D formats, readers often swap axis 0 and 1 after
    loading the array because the `HW` definition for non-medical specific file formats is different
    from other common medical packages.

    Note:

        - If `reader` is specified, the loader will attempt to use the specified readers and the default supported
          readers. This might introduce overheads when handling the exceptions of trying the incompatible loaders.
          In this case, it is therefore recommended setting the most appropriate reader as
          the last item of the `reader` parameter.

    See also:

        - tutorial: https://github.com/Project-MONAI/tutorials/blob/master/modules/load_medical_images.ipynb

    """

    def __init__(
        self,
        keys: KeysCollection,
        reader: Optional[Union[ImageReader, str]] = None,
        patientname: str='',
        dtype: DtypeLike = np.float32,
        meta_keys: Optional[KeysCollection] = None,
        meta_key_postfix: str = DEFAULT_POST_FIX,
        overwriting: bool = False,
        image_only: bool = False,
        ensure_channel_first: bool = False,
        simple_keys: bool = False,
        prune_meta_pattern: Optional[str] = None,
        prune_meta_sep: str = ".",
        allow_missing_keys: bool = False,
        *args,
        **kwargs,
    ) -> None:
        """
        Args:
            keys: keys of the corresponding items to be transformed.
                See also: :py:class:`monai.transforms.compose.MapTransform`
            reader: reader to load image file and metadata
                - if `reader` is None, a default set of `SUPPORTED_READERS` will be used.
                - if `reader` is a string, it's treated as a class name or dotted path
                (such as ``"monai.data.ITKReader"``), the supported built-in reader classes are
                ``"ITKReader"``, ``"NibabelReader"``, ``"NumpyReader"``.
                a reader instance will be constructed with the `*args` and `**kwargs` parameters.
                - if `reader` is a reader class/instance, it will be registered to this loader accordingly.
            patientname: the patient name.
            dtype: if not None, convert the loaded image data to this data type.
            meta_keys: explicitly indicate the key to store the corresponding metadata dictionary.
                the metadata is a dictionary object which contains: filename, original_shape, etc.
                it can be a sequence of string, map to the `keys`.
                if None, will try to construct meta_keys by `key_{meta_key_postfix}`.
            meta_key_postfix: if meta_keys is None, use `key_{postfix}` to store the metadata of the nifti image,
                default is `meta_dict`. The metadata is a dictionary object.
                For example, load nifti file for `image`, store the metadata into `image_meta_dict`.
            overwriting: whether allow overwriting existing metadata of same key.
                default is False, which will raise exception if encountering existing key.
            image_only: if True return dictionary containing just only the image volumes, otherwise return
                dictionary containing image data array and header dict per input key.
            ensure_channel_first: if `True` and loaded both image array and metadata, automatically convert
                the image array shape to `channel first`. default to `False`.
            simple_keys: whether to remove redundant metadata keys, default to False for backward compatibility.
            prune_meta_pattern: combined with `prune_meta_sep`, a regular expression used to match and prune keys
                in the metadata (nested dictionary), default to None, no key deletion.
            prune_meta_sep: combined with `prune_meta_pattern`, used to match and prune keys
                in the metadata (nested dictionary). default is ".", see also :py:class:`monai.transforms.DeleteItemsd`.
                e.g. ``prune_meta_pattern=".*_code$", prune_meta_sep=" "`` removes meta keys that ends with ``"_code"``.
            allow_missing_keys: don't raise exception if key is missing.
            args: additional parameters for reader if providing a reader name.
            kwargs: additional parameters for reader if providing a reader name.
        """
        super().__init__(keys, allow_missing_keys)
                
        self._loader = LoadImage(
            reader,
            patientname,
            image_only,
            dtype,
            ensure_channel_first,
            simple_keys,
            prune_meta_pattern,
            prune_meta_sep,
            *args,
            **kwargs,
        )
                
        if not isinstance(meta_key_postfix, str):
            raise TypeError(f"meta_key_postfix must be a str but is {type(meta_key_postfix).__name__}.")
        self.meta_keys = ensure_tuple_rep(None, len(self.keys)) if meta_keys is None else ensure_tuple(meta_keys)
        if len(self.keys) != len(self.meta_keys):
            raise ValueError("meta_keys should have the same length as keys.")
        self.meta_key_postfix = ensure_tuple_rep(meta_key_postfix, len(self.keys))
        self.overwriting = overwriting
        
        # Check patient name
        if (len(patientname)==0):
            raise ValueError("Patient name should not be empty.")

    def register(self, reader: ImageReader):
        self._loader.register(reader)


    def __call__(self, data, reader: Optional[ImageReader] = None):
        """
        Raises:
            KeyError: When not ``self.overwriting`` and key already exists in ``data``.

        """
        d = dict(data)
        for key, meta_key, meta_key_postfix in self.key_iterator(d, self.meta_keys, self.meta_key_postfix):
            data = self._loader(d[key], reader)
            if self._loader.image_only:
                d[key] = data
            else:
                if not isinstance(data, (tuple, list)):
                    raise ValueError("loader must return a tuple or list (because image_only=False was used).")
                d[key] = data[0]
                if not isinstance(data[1], dict):
                    raise ValueError("metadata must be a dict.")
                meta_key = meta_key or f"{key}_{meta_key_postfix}"
                if meta_key in d and not self.overwriting:
                    raise KeyError(f"Metadata with key {meta_key} already exists and overwriting=False.")
                d[meta_key] = data[1]
                
        return d

def switch_endianness(data, new="<"):
    """
    Convert the input `data` endianness to `new`.

    Args:
        data: input to be converted.
        new: the target endianness, currently support "<" or ">".
    """
    if isinstance(data, np.ndarray):
        # default to system endian
        sys_native = "<" if (sys.byteorder == "little") else ">"
        current_ = sys_native if data.dtype.byteorder not in ("<", ">") else data.dtype.byteorder
        if new not in ("<", ">"):
            raise NotImplementedError(f"Not implemented option new={new}.")
        if current_ != new:
            data = data.byteswap().newbyteorder(new)
    elif isinstance(data, tuple):
        data = tuple(switch_endianness(x, new) for x in data)
    elif isinstance(data, list):
        data = [switch_endianness(x, new) for x in data]
    elif isinstance(data, dict):
        data = {k: switch_endianness(v, new) for k, v in data.items()}
    elif not isinstance(data, (bool, str, float, int, type(None))):
        raise RuntimeError(f"Unknown type: {type(data).__name__}")
    return data

class LoadImage(Transform):
    """
    Load image file or files from provided path based on reader.
    If reader is not specified, this class automatically chooses readers
    based on the supported suffixes and in the following order:

        - User-specified reader at runtime when calling this loader.
        - User-specified reader in the constructor of `LoadImage`.
        - Readers from the last to the first in the registered list.
        - Current default readers: (nii, nii.gz -> NibabelReader), (png, jpg, bmp -> PILReader),
          (npz, npy -> NumpyReader), (nrrd -> NrrdReader), (DICOM file -> ITKReader).

    Please note that for png, jpg, bmp, and other 2D formats, readers often swap axis 0 and 1 after
    loading the array because the `HW` definition for non-medical specific file formats is different
    from other common medical packages.

    See also:

        - tutorial: https://github.com/Project-MONAI/tutorials/blob/master/modules/load_medical_images.ipynb

    """

    def __init__(
        self,
        reader="NibabelReader",
        patientname:str="",
        image_only: bool = False,
        dtype: DtypeLike = np.float32,
        ensure_channel_first: bool = False,
        simple_keys: bool = False,
        prune_meta_pattern: Optional[str] = None,
        prune_meta_sep: str = ".",
        *args,
        **kwargs,
    ) -> None:
        """
        Args:
            reader: reader to load image file and metadata
                - if `reader` is None, a default set of `SUPPORTED_READERS` will be used.
                - if `reader` is a string, it's treated as a class name or dotted path
                (such as ``"monai.data.ITKReader"``), the supported built-in reader classes are
                ``"ITKReader"``, ``"NibabelReader"``, ``"NumpyReader"``, ``"PydicomReader"``.
                a reader instance will be constructed with the `*args` and `**kwargs` parameters.
                - if `reader` is a reader class/instance, it will be registered to this loader accordingly.
            image_only: if True return only the image MetaTensor, otherwise return image and header dict.
            dtype: if not None convert the loaded image to this data type.
            ensure_channel_first: if `True` and loaded both image array and metadata, automatically convert
                the image array shape to `channel first`. default to `False`.
            simple_keys: whether to remove redundant metadata keys, default to False for backward compatibility.
            prune_meta_pattern: combined with `prune_meta_sep`, a regular expression used to match and prune keys
                in the metadata (nested dictionary), default to None, no key deletion.
            prune_meta_sep: combined with `prune_meta_pattern`, used to match and prune keys
                in the metadata (nested dictionary). default is ".", see also :py:class:`monai.transforms.DeleteItemsd`.
                e.g. ``prune_meta_pattern=".*_code$", prune_meta_sep=" "`` removes meta keys that ends with ``"_code"``.
            args: additional parameters for reader if providing a reader name.
            kwargs: additional parameters for reader if providing a reader name.

        Note:

            - The transform returns a MetaTensor, unless `set_track_meta(False)` has been used, in which case, a
              `torch.Tensor` will be returned.
            - If `reader` is specified, the loader will attempt to use the specified readers and the default supported
              readers. This might introduce overheads when handling the exceptions of trying the incompatible loaders.
              In this case, it is therefore recommended setting the most appropriate reader as
              the last item of the `reader` parameter.

        """

        self.auto_select = reader is None
        self.image_only = image_only
        self.dtype = dtype
        self.ensure_channel_first = ensure_channel_first
        self.simple_keys = simple_keys
        self.pattern = prune_meta_pattern
        self.sep = prune_meta_sep
        self.patientname = patientname
        return
    
    def __call__(self, filename: Union[Sequence[PathLike], PathLike], reader: Optional[ImageReader] = NibabelReader):
        """
        Load image file and metadata from the given filename(s).
        If `reader` is not specified, this class automatically chooses readers based on the
        reversed order of registered readers `self.readers`.

        Args:
            filename: path file or file-like object or a list of files.
                will save the filename to meta_data with key `filename_or_obj`.
                if provided a list of files, use the filename of first file to save,
                and will stack them together as multi-channels data.
                if provided directory path instead of file path, will treat it as
                DICOM images series and read.
            reader: runtime reader to load image file and metadata.

        """  
        filename = tuple(f"{Path(s).expanduser()}" for s in ensure_tuple(filename))  # allow Path objects
        img, err = None, []
        # if reader is not None:
        reader=NibabelReader()
        img = reader.read(filename)  # runtime specified reader
        header = img.header
        img_array = img.get_fdata()
        img_array: NdarrayOrTensor
        img_array, meta_data = reader.get_data(img)
        img_array = convert_to_dst_type(img_array, dst=img_array, dtype=self.dtype)[0]
        if not isinstance(meta_data, dict):
            raise ValueError("`meta_data` must be a dict.")
        # make sure all elements in metadata are little endian
        meta_data = switch_endianness(meta_data, "<")        
        # meta_data["patient_name"]=filename[0].split('/')[-3]
        meta_data["patient_name"]=self.patientname
        meta_data[Key.FILENAME_OR_OBJ] = f"{ensure_tuple(filename)[0]}"  # Path obj should be strings for data loader        
        img = MetaTensor.ensure_torch_and_prune_meta(
            img_array, meta_data, self.simple_keys, pattern=self.pattern, sep=self.sep
        )
        if self.ensure_channel_first:
            img = EnsureChannelFirst()(img)
        if self.image_only:
            return img
        return img, img.meta, header if isinstance(img, MetaTensor) else meta_data