Research Article

[Retracted] Retinal OCT Texture Analysis for Differentiating Healthy Controls from Multiple Sclerosis (MS) with/without Optic Neuritis

Table 1

List of utilized features.

Texture analysis methodFeaturesDescriptionTexture analysis methodFeaturesDescription

GLCMEnergyProvides the sum of squared elements in the GLCM. It has values between 0 and 1GLCMDifference varianceMeasures the dispersion (with regard to the mean) of the grey-level difference distribution of the image
EntropyMeasure of randomness that can be used to characterize the texture of an imageDifference entropyMeasures the disorder related to the grey-level difference distribution of the image
ContrastA measure of intensity contrast between a pixel and its neighbor over the whole imageMaximum probabilityMeasures the maximum likelihood of producing the pixels of interest
HomogeneityMeasures the closeness of the distribution of elements in the GLCM to the GLCM diagonalIMC1Measure of dependency between two random variables
CorrelationA measure of how correlated a pixel is to its neighbor over the whole imageIMC2
Sum of squaresMeasures the dispersion (with regard to the mean) of the grey-level distributionLBP
LDP
LOOP
MeanMeasures mean and standard deviation of histograms
Cluster shadeCharacterizes the tendency of clustering of the pixels in the region of interest
Cluster prominenceStandard deviation
DissimilarityA measure of distance between pairs of pixels in the region of interestDynamic rangeMeasures the ratio between the largest and smallest values
AutocorrelationRepresents the degree of similarity between a given time series and a lagged version of itKurtosisMeasure of the “tailedness” of the probability distribution
Sum averageMeasures the mean of the grey-level sum distribution of the imageSkewnessMeasure of the asymmetry of the probability distribution
Sum entropyMeasures the disorder related to the grey-level sum distribution of the imageFractal dimensionMeanMeasures mean and standard deviation of the box-counting method
Sum varianceMeasures the dispersion (with regard to the mean) of the grey-level sum distribution of the imageStandard deviation
Inverse differenceA measure of local homogeneity of an image