Purpose: Radiomic texture calculation requires discretizing image intensities within the region-of-interest. FBN (fixed-bin-number), FBS (fixed-bin-size) and FBN and FBS with intensity equalization (FBNequal, FBSequal) are four discretization approaches. A crucial choice is the voxel intensity (Hounsfield units, or HU) binning range. We assessed the effect of this choice on radiomic features. Methods: The dataset comprised 95 patients with head-and-neck squamous-cell-carcinoma. Dual energy CT data was reconstructed at 21 electron energies (40, 45,... 140 keV). Each of 94 texture features were calculated with 64 extraction parameters. All features were calculated five times: original choice, left shift (-10/-20 HU), right shift (+10/+20 HU). For each feature, Spearman correlation between nominal and four variants were calculated to determine feature stability. This was done for six texture feature types (GLCM, GLRLM, GLSZM, GLDZM, NGTDM, and NGLDM) separately. This analysis was repeated for the four binning algorithms. Effect of feature instability on predictive ability was studied for lymphadenopathy as endpoint. Results: FBN and FBNequal algorithms showed good stability (correlation values consistently >0.9). For FBS and FBSequal algorithms, while median values exceeded 0.9, the 95% lower bound decreased as a function of energy, with poor performance over the entire spectrum. FBNequal was the most stable algorithm, and FBS the least. Conclusions: We believe this is the first multi-energy systematic study of the impact of CT HU range used during intensity discretization for radiomic feature extraction. Future analyses should account for this source of un-certainty when evaluating the robustness of their radiomic signature.
|Number of pages||6|
|Journal||Physica Medica: European journal of medical physics|
|Publication status||Published - 1 Aug 2021|
- Feature stability