Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels

Abstract

Purpose: Many radiomics features were originally developed for non-medical imaging applications and therefore original assumptions may need to be reexamined. In this study, we investigated the impact of slice thickness and pixel spacing (or pixel size) on radiomics features extracted from Computed Tomography (CT) phantom images acquired with different scanners as well as different acquisition and reconstruction parameters. The dependence of CT texture features on gray-level discretization was also evaluated.

Methods and materials: A texture phantom composed of 10 different cartridges of different materials was scanned on eight different CT scanners from three different manufacturers. The images were reconstructed for various slice thicknesses. For each slice thickness, the reconstruction Field Of View (FOV) was varied to render pixel sizes ranging from 0.39 to 0.98 mm. A fixed spherical region of interest (ROI) was contoured on the images of the shredded rubber cartridge and the 3D printed, 20% fill, acrylonitrile butadiene styrene plastic cartridge (ABS20) for all phantom imaging sets. Radiomic features were extracted from the ROIs using an in-house program. Features categories were: shape (10), intensity (16), GLCM (24), GLZSM (11), GLRLM (11), and NGTDM (5), fractal dimensions (8) and first-order wavelets (128), for a total of 213 features. Voxel-size resampling was performed to investigate the usefulness of extracting features using a suitably chosen voxel size. Acquired phantom image sets were resampled to a voxel size of 1 × 1 × 2 mm³ using linear interpolation. Image features were therefore extracted from resampled and original datasets and the absolute value of the percent coefficient of variation (%COV) for each feature was calculated. Based on the %COV values, features were classified in 3 groups: (1) features with large variations before and after resampling (%COV >50); (2) features with diminished variation (%COV <30) after resampling; and (3) features that had originally moderate variation (%COV <50%) and were negligibly affected by resampling. Group 2 features were further studied by modifying feature definitions to include voxel size. Original and voxel-size normalized features were used for interscanner comparisons. A subsequent analysis investigated feature dependency on gray-level discretization by extracting 51 texture features from ROIs from each of the 10 different phantom cartridges using 16, 32, 64, 128, and 256 gray levels.

Results: Out of the 213 features extracted, 150 were reproducible across voxel sizes, 42 improved significantly (%COV <30, Group 2) after resampling, and 21 had large variations before and after resampling (Group 1). Ten features improved significantly after definition modification effectively removed their voxel-size dependency. Interscanner comparison indicated that feature variability among scanners nearly vanished for 8 of these 10 features. Furthermore, 17 out of 51 texture features were found to be dependent on the number of gray levels. These features were redefined to include the number of gray levels which greatly reduced this dependency.

Conclusion: Voxel-size resampling is an appropriate pre-processing step for image datasets acquired with variable voxel sizes to obtain more reproducible CT features. We found that some of the radiomics features were voxel size and gray-level discretization-dependent. The introduction of normalizing factors in their definitions greatly reduced or removed these dependencies.

Keywords: computed tomography; features; gray levels; phantom; radiomics; texture; voxel size.

Figure 1

Absolute value of the %COV calculated from 116 original (solid triangles) and resampled (open triangles) image sets for 83 non‐wavelet features. Group 1 features that had %COV >50 after resampling are shown in the insets. Features are ordered (Feature Index) on the x‐axis from largest to lowest %COV value based on the images of the rubber cartridge, same order as in Table 2. The feature order for (a) rubber cartridge was applied to (b) ABS20 cartridge. [Colour figure can be viewed at wileyonlinelibrary.com]

Figure 2

Absolute value of the %COV calculated from 72 original (solid triangles) and resampled (open triangles) image sets for 128 wavelet features. Group 1 features that had %COV >50 after resampling are shown in the insets. Features are ordered (Feature index) on the x‐axis from largest to lowest %COV value. Different feature order was used for (a) rubber cartridge and (b) ABS20 cartridge. [Colour figure can be viewed at wileyonlinelibrary.com]

Figure 3

Scaled features values extracted from original and normalized feature definitions as a function of pixel size and slice thickness. Modified values are shown by box plot. Middle, lower and upper lines in the box indicate median, first quartile, and third quartile respectively. Energy (a) from intensity histogram and GLNU (b) from the GLRLM almost converge to a straight horizontal line after normalization. Coarseness (c) and texture strength (d) from NGTDM exhibit small variations in median values, but with small dependence on slice thickness and pixel spacing after normalization.

Figure 4

Scaled original (solid triangles) and normalized (open triangles) features values across 8 different scanners: Normalized values for energy (a) from intensity histogram, mean (b) from GLCM, GLNU (c) from GLRLM, and coarseness (d) from NGTDM nearly converge into horizontal straight lines for all scanners, while the original feature values for two GE scanners were different because of different slice thickness. [Colour figure can be viewed at wileyonlinelibrary.com]

Figure 5

Scaled original and normalized feature values as function of number of gray levels (Ng) for rubber and ABS20 cartridges: Contrast (a) and dissimilarity (b) from GLCM became independent of Ng after gray‐level normalization as shown by open triangles and circles.

Figure 6

The %COV calculated over 12 different ROIs (10 ROIs of 14 cm³ for each of the 10 cartridges in the phantom and 2 larger ROIs of 50 and 60 cm³ contoured over multiple cartridges, i.e., ABS, wood and shredded rubber before (dark bars) and after (light bars) normalization. The phantom was scanned with a Siemens Definition AS scanner with pixel size of 0.48 mm and slice thickness of 3 mm.