Calculates all radiomic statistics on supplied RIA_image

Calculates specified radiomic statistics on RIA_image. Parameters of radiomic functions may be set. By default the the images are discretized to 2, 8, 32 and 128 bins using equally sized binning. First-order statistics are calculated on the original image and if asked then on all discretizations. Symmetric GLCMs are calculated for all directions at a distance of 1, 2 and 3 for all discretizations. GLRLMs are also calculated for all discretizations. Geometry-based statistics are calculated for the original image as well as all discretizations is requested.

radiomics_all(RIA_data_in, bins_in = c(2, 8, 32, 128),
  equal_prob = FALSE, fo_discretized = FALSE, distance = c(1, 2, 3),
  statistic = "mean(X, na.rm = TRUE)", geometry_discretized = FALSE,
  verbose_in = TRUE)

Arguments

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.
fo_discretized

logical, indicating whether to calculate first-order statistics on discretized images.
distance

integer, distance between the voxels being compared.
statistic

string, defining the statistic to be calculated on the array of GLCM statistics. By default, statistic is set to "mean", however any function may be provided. The proper syntax is: function(X, attributes). The supplied string must contain a "X", which will be replaced with the array of the GLCM statistics value. Further attributes of the function may also be given. For example, if you wish to calculate the median of all GLCMs calculated in different directions, then it must be supplied as: median(X, na.rm = TRUE).
geometry_discretized

logical, indicating whether to calculate geometry-based statistics on discretized images.
verbose_in

logical, indicating whether to print detailed information. Most prints can also be suppressed using the suppressMessages function.

Value

RIA_image containing the statistical information.

References

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

Examples

if (FALSE) {
#Discretize loaded image and then calculate all radiomic statistics
RIA_image <- radiomics_all(RIA_image, equal_prob = FALSE, bins_in= c(2,8,32,128), distance = c(1:3))
RIA_image <- radiomics_all(RIA_image, equal_prob = TRUE, bins_in= c(2,8,32,128), distance = c(1:3))
}