wsireg.parameter_maps package

Submodules

wsireg.parameter_maps.preprocessing module

class wsireg.parameter_maps.preprocessing.BoundingBox(X: int, Y: int, WIDTH: int, HEIGHT: int)

Bases: NamedTuple

Bounding box named tuple.

HEIGHT: int

Alias for field number 3

WIDTH: int

Alias for field number 2

X: int

Alias for field number 0

Y: int

Alias for field number 1

class wsireg.parameter_maps.preprocessing.CoordinateFlip(value)

Bases: str, Enum

Coordinate flip options * “h” : horizontal flip * “v” : vertical flip

HORIZONTAL = 'h'

VERTIAL = 'v'

class wsireg.parameter_maps.preprocessing.ImagePreproParams(*, image_type: ImageType = ImageType.DARK, max_int_proj: bool = True, ch_indices: List[int] | None = None, as_uint8: bool = True, contrast_enhance: bool = False, invert_intensity: bool = False, custom_processing: Dict[str, Callable] | None = None, rot_cc: int | float = 0, flip: CoordinateFlip | None = None, crop_to_mask_bbox: bool = False, mask_bbox: BoundingBox | None = None, downsampling: int = 1, use_mask: bool = True)

Bases: BaseModel

Preprocessing parameter model

image_type

Whether image is dark or light background. Light background images are intensity inverted by default

Type:

ImageType

max_int_proj

Perform max intensity projection number of channels > 1.

Type:

bool

contrast_enhance

Enhance contrast of image

Type:

bool

ch_indices

Channel indicies to use for registartion, 0-index, so ch_indices = 0, pulls the first channel

Type:

list of int or int

as_uint8

Whether to byte scale registration image data for memory saving

Type:

bool

invert_intensity

invert the intensity of an image

Type:

bool

rot_cc

Rotate image counter-clockwise by degrees, can be positive or negative (cw rot)

Type:

int, float

flip

flip coordinates, “v” = vertical flip, “h” = horizontal flip

Type:

CoordinateFlip, default: None

crop_to_mask_bbox

Convert a binary mask to a bounding box and crop to this area

Type:

bool

mask_bbox

supply a pre-computed list of bbox info of form x,y,width,height

Type:

tuple or list of 4 ints

downsampling

Downsampling by integer factor, i.e., downsampling = 3, downsamples image 3x

Type:

int

use_mask

Whether to use mask in elastix registration. At times it is better to use the mask to find a cropping area then use the mask during the registration process as errors are frequent

Type:

bool

custom_processing

Custom intensity preprocessing functions in a dict like {“my_custom_process: custom_func} that will be applied to the image. Must take in an sitk.Image and return an sitk.Image

Type:

callable

class Config

Bases: object

use_enum_names = True

as_uint8: bool

ch_indices: List[int] | None

contrast_enhance: bool

crop_to_mask_bbox: bool

custom_processing: Dict[str, Callable] | None

dict(**kwargs)

downsampling: int

flip: CoordinateFlip | None

image_type: ImageType

invert_intensity: bool

mask_bbox: BoundingBox | None

max_int_proj: bool

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

model_config: ClassVar[ConfigDict] = {'use_enum_names': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_fields: ClassVar[dict[str, FieldInfo]] = {'as_uint8': FieldInfo(annotation=bool, required=False, default=True), 'ch_indices': FieldInfo(annotation=Union[List[int], NoneType], required=False), 'contrast_enhance': FieldInfo(annotation=bool, required=False, default=False), 'crop_to_mask_bbox': FieldInfo(annotation=bool, required=False, default=False), 'custom_processing': FieldInfo(annotation=Union[Dict[str, Callable], NoneType], required=False), 'downsampling': FieldInfo(annotation=int, required=False, default=1), 'flip': FieldInfo(annotation=Union[CoordinateFlip, NoneType], required=False), 'image_type': FieldInfo(annotation=ImageType, required=False, default=<ImageType.DARK: 'FL'>), 'invert_intensity': FieldInfo(annotation=bool, required=False, default=False), 'mask_bbox': FieldInfo(annotation=Union[BoundingBox, NoneType], required=False), 'max_int_proj': FieldInfo(annotation=bool, required=False, default=True), 'rot_cc': FieldInfo(annotation=Union[int, float], required=False, default=0), 'use_mask': FieldInfo(annotation=bool, required=False, default=True)}

Metadata about the fields defined on the model, mapping of field names to [FieldInfo][pydantic.fields.FieldInfo].

This replaces Model.__fields__ from Pydantic V1.

rot_cc: int | float

use_mask: bool

class wsireg.parameter_maps.preprocessing.ImageType(value)

Bases: str, Enum

Set the photometric interpretation of the image * “FL”: background is black (fluorescence) * “BF”: Background is white (brightfield)

DARK = 'FL'

LIGHT = 'BF'

wsireg.parameter_maps.reg_model module

wsireg.parameter_maps.reg_params module

wsireg.parameter_maps.transformations module

Module contents

Parameter maps.