Skip to main content

Table 2 Summary of feature groups in proposed Radiomics-Driven Feature Model (RD-FM) [21]

From: MPCaD: a multi-scale radiomics-driven framework for automated prostate cancer localization and detection

Feature group

Number of features

Description

Morphology

3

Area regularity (1), Perimeter regularity (2)

Asymmetry

4

Region bilateral symmetry (4)

Physiology

26

 

Textural (1st-order)

7

Mean, median, standard deviation, minimum, maximum, kurtosis, skewness

  

Energy, contrast, correlation, variance, inverse difference moment normalized, sum average,

Textural (2nd-order)

19

Sum variance, entropy, sum entropy, difference entropy, normalized entropy,

  

Information measure of correlation, homogeneity, difference variance,

  

Autocorrelation, dissimilarity, cluster shade, cluster prominence, maximum probability

Size

1

Size of region

Total

34

All features