From: [18F]FDG-PET/CT texture analysis in thyroid incidentalomas: preliminary results
Features | Formulas for features resulted significant |
---|---|
Gray-level co-occurrence matrix (GLCM) | |
Homogeneity 1 EnergyGLCM ContrastGLCM CorrelationGLCM EntropyGLCM Dissimilarity | Correlation measures the linear dependency of the gray levels in the GLCM matrix and is defined as the average over the 13 directions of: \( \left(\sum_{i,j}\frac{\left(i-\mu \right)x\left(j-\mu \right) xC\left(i,j\right)}{\sigma_i{\sigma}_j}\right) \) where μi,j correspond to the average on row i or column j and σi,j correspond to the variance on row i or column j. |
Neighborhood gray-level different matrix (NGLDM) | |
ContrastNGTDM Coarseness | Â |
Gray-level run-length matrix (GLRLM) | |
Short-Run Emphasis Long-Run Emphasis Low Gray-level Run Emphasis High Gray-level Run Emphasis Short-Run Low Gray-level Emphasis Short-Run High Gray-level Emphasis Long-Run Low Gray-level Emphasis Long-Run High Gray-level Emphasis Gray-Level Non-Uniformity for run Run Length Non-Uniformity Run Percentage | Â |
Gray-level zone-length matrix (GLZLM) | |
Short-Zone Emphasis Long-Zone Emphasis Low Gray-level Zone Emphasis High Gray-level Zone Emphasis Short-Zone Low Gray-level Emphasis Short-Zone High Gray-level Emphasis Long-Zone Low Gray-level Emphasis Long-Zone High Gray-level Emphasis Gray-Level Non-Uniformity for zone Zone Length Non-Uniformity Zone Percentage | Â |
Shape and Size | |
Sphericity Compacity | Compacity (Shape and size): \( \frac{A^{3/2}}{V} \) where A and V correspond to the area and the volume of the volume of interest from the Delaunay triangulation. |
Histogram | |
Skewness Kurtosis EntropyHist EnergyHist | Skewness \( \frac{a\sum_i{\left(H(i)- Mean\right)}^3}{{\left(\sqrt{a\sum_i{\left(H(i)- Mean\right)}^2}\right)}^3} \) where a is the inverse of the total number of voxels in the volume of interest and mean is the average of the intensity values in the histogram. The sum is extended to all voxels in the volume of interest. Kurtosis \( \frac{a\sum_i{\left(H(i)- Mean\right)}^4}{{\left(a\sum_i{\left(H(i)- Mean\right)}^2\right)}^2} \) |
Conventional parameters | |
SUV minimum, SUV maximum, SUVmean and SUVstandard deviation, SUVpeak within a sphere of 0.5 and 1Â ml volume (mL) Total lesion glycolysis (TLG) | SUVmax maximum of the standardized uptake value in the volume of interest SUVstd standard deviation of the SUV distribution in the volume of interest MTV the metabolic tumor volume was determined as the total number of voxels with SUVÂ >Â 40% TLG is defined as the product of SUVmean times the volume |