discretize.RdDiscretizes RIA_image into bins_in number of bins. The equal_prob parameter is used to indicate whether to create bins containing the same number of values. If FALSE then equal sized bins will be created. discretized images will be saved into the $data$modif slot of RIA_image as well as the discretized slot of RIA_image. The name will be automatically created based on the type of dichotomization (ep: equal probability; es: equal size) and the number of bins specified, for example: $dicotomized$es_8 will store the discretized image after equal sized dichotomization into 8 bins. This way many different discretized images using different bin numbers can be saved to the same object for further analysis. The RIA_log will be updated with cut points.
discretize(RIA_data_in, bins_in = 8, equal_prob = FALSE,
use_orig = TRUE, write_orig = FALSE, verbose_in = TRUE)| RIA_data_in | RIA_image. |
|---|---|
| bins_in | integer vector, number of bins specified. |
| equal_prob | logical, indicating to cut data into bins with equal relative frequencies. If FALSE, then equal interval bins will be used. |
| use_orig | logical, indicating to use image present in RIA_data$orig. If FALSE, the modified image will be used stored in RIA_data$modif. |
| write_orig | logical, indicating to write cropped image to RIA_data$orig. If FALSE, the modified image will be used stored in RIA_data$modif. |
| verbose_in | logical, indicating whether to print detailed information.
Most prints can also be suppressed using the |
RIA_image with values discretized to bin values.
Márton KOLOSSVÁRY et al. Radiomic Features Are Superior to Conventional Quantitative Computed Tomographic Metrics to Identify Coronary Plaques With Napkin-Ring Sign Circulation: Cardiovascular Imaging (2017). DOI: 10.1161/circimaging.117.006843 https://www.ncbi.nlm.nih.gov/pubmed/29233836
Márton KOLOSSVÁRY et al. Cardiac Computed Tomography Radiomics: A Comprehensive Review on Radiomic Techniques. Journal of Thoracic Imaging (2018). DOI: 10.1097/RTI.0000000000000268 https://www.ncbi.nlm.nih.gov/pubmed/28346329
if (FALSE) {
#Discretize into 8 bins, each containing equal number of elements
RIA_image <- discretize(RIA_image, bins_in = 8, equal_prob = TRUE,
use_orig = TRUE, write_orig = FALSE)
#Discretize into 6 bins, each with the same width
RIA_image <- discretize(RIA_image, bins_in = 6, equal_prob = FALSE,
use_orig = TRUE, write_orig = FALSE)
#Discretize into 2,4,8,16,32 bins, each containing equal number of elements
RIA_image <- discretize(RIA_image, bins_in = 2^(1:5), equal_prob = FALSE,
use_orig = TRUE, write_orig = FALSE)
#D
}