Manipulating CytoImageList objects

Description

Methods to change pixel values in CytoImageList objects. In the following sections, object is a CytoImageList object containing one or multiple channels.

Value

A CytoImageList object containing the manipulated Images

Image scaling

In some cases, images need to be scaled by a constant (e.g. 2^16-1 = 65535) value to revert them back to the original pixel values after reading them in.

scaleImages(object, value):

Scales all images in the CytoImageList object object by value.

Image normalization

Linear scaling of the intensity values of each Image contained in a CytoImageList object to a specific range. Images can either be scaled to the minimum/maximum value per channel or across all channels (default separateChannels = TRUE). Also, Images can be scaled to the minimum/maximum value per image or across all images (default separateImages = FALSE). The latter allows the visual comparison of intensity values across images.

To clip the images before normalization, the inputRange can be set. Explain in more detail...

normalize(object, separateChannels = TRUE, separateImages = FALSE, ft = c(0, 1), inputRange = NULL):

object:

A CytoImageList object

separateChannels:

Logical if pixel values should be normalized per channel (default) or across all channels.

separateImages:

Logical if pixel values should be normalized per image or across all images (default).

ft:

Numeric vector of 2 values, target minimum and maximum intensity values after normalization (see normalize).

inputRange:

Numeric vector of 2 values, sets the absolute clipping range of the input intensity values (see normalize).

Author(s)

Nils Eling nils.eling@dqbm.uzh.ch

See Also

normalize for details on Image normalization

Examples

data(pancreasImages)

# Scale images to create segmentation masks
cur_files <- list.files(system.file("extdata", package = "cytomapper"),
                        pattern = "mask.tiff", full.names = TRUE)
x <- loadImages(cur_files)
# Error when running plotCells(x)
# Therefore scale to account for 16 bit encoding
x <- scaleImages(x, 2^16 - 1)
plotCells(x)

# Default normalization
x <- normalize(pancreasImages)
plotPixels(x, colour_by = c("H3", "CD99"))

# Setting the clipping range
x <- normalize(x, inputRange = c(0, 0.9))
plotPixels(x, colour_by = c("H3", "CD99"))

# Normalizing per image
x <- normalize(pancreasImages, separateImages = TRUE)
plotPixels(x, colour_by = c("H3", "CD99"))