Radiomics of Patients with Locally Advanced Rectal Cancer: Effect of Preprocessing on Features Estimation from Computed Tomography Imaging

Abstract

The purpose of this study was to investigate the effect of image preprocessing on radiomic features estimation from computed tomography (CT) imaging of locally advanced rectal cancer (LARC). CT images of 20 patients with LARC were used to estimate 105 radiomic features of 7 classes (shape, first-order, GLCM, GLDM, GLRLM, GLSZM, and NGTDM). Radiomic features were estimated for 6 different isotropic resampling voxel sizes, using 10 interpolation algorithms (at fixed bin width) and 6 different bin widths (at fixed interpolation algorithm). The intraclass correlation coefficient (ICC) and the coefficient of variation (CV) were calculated to assess the variability in radiomic features estimation due to preprocessing. A repeated measures correlation analysis was performed to assess any linear correlation between radiomic feature estimate and resampling voxel size or bin width. Reproducibility of radiomic feature estimate, when assessed through ICC analysis, was nominally excellent ( ICC > 0.9 ) for shape features, good ( 0.75 < ICC ≤ 0.9 ) or moderate ( 0.5 < ICC ≤ 0.75 ) for first-order features, and moderate or poor ( 0 ≤ ICC ≤ 0.5 ) for textural features. A number of radiomic features characterized by good or excellent reproducibility in terms of ICC showed however median CV values greater than 15%. For most textural features, a significant ( p < 0.05 ) correlation between their estimate and resampling voxel size or bin width was found. In CT imaging of patients with LARC, the estimate of textural features, as well as of first-order features to a lesser extent, is appreciably biased by preprocessing. Accordingly, this should be taken into account when planning clinical or research studies, as well as when comparing results from different studies and performing multicenter studies.

Effect of Gray Value Discretization and Image Filtration on Texture Features of the Pancreas Derived from Magnetic Resonance Imaging at 3T

“…This is because, while the number of significant first-order texture features was not affected by absolute versus relative discretization, the number of second-order texture features differed markedly. Interestingly, similar inference was drawn from the findings of a radiomics of computed tomography images in individuals with locally advanced rectal cancer [ 41 ]. In the present study, relative discretization (using fixed bin number of 16) yielded a total of 42 significant second-order features whereas absolute discretization at most yielded only 26 significant second-order features (using fixed bin width of 42).…”

A novel radiomics approach for predicting TACE outcomes in hepatocellular carcinoma patients using deep learning for multi-organ segmentation

“…It must be clearly stated that no CT image normalization or filtering was applied prior to segmentation and feature extraction in our study. This may be particularly important for the reliability of gray-level feature estimates and, to a lesser extent, shape-based and first-order features 48 , 49 . However, given the preliminary nature of our study and the lack of standardization in preprocessing steps, we opted for a straightforward exploratory analysis.…”

Clinical features combined with ultrasound-based radiomics nomogram for discrimination between benign and malignant lesions in ultrasound suspected supraclavicular lymphadenectasis

“…Second-order statistics refer to the spatial relationship between the intensities of each voxel. Higher-order statistics are used for feature extraction and image preprocessing such as wavelet decomposition, Fourier transform and other filtering ( 15 ). The software automatically extracts radiomics features to compensate for errors introduced by manual and subjective measurements.…”