Robustness of magnetic resonance radiomic features to pixel size resampling and interpolation in patients with cervical cancer

Abstract

Background Radiomics is a promising field in oncology imaging. However, the implementation of radiomics clinically has been limited because its robustness remains unclear. Previous CT and PET studies suggested that radiomic features were sensitive to variations in pixel size and slice thickness of the images. The purpose of this study was to assess robustness of magnetic resonance (MR) radiomic features to pixel size resampling and interpolation in patients with cervical cancer. Methods This retrospective study included 254 patients with a pathological diagnosis of cervical cancer stages IB to IVA who received definitive chemoradiation at our institution between January 2006 and June 2020. Pretreatment MR scans were analyzed. Each region of cervical cancer was segmented on the axial gadolinium-enhanced T1- and T2-weighted images; 107 radiomic features were extracted. MR scans were interpolated and resampled using various slice thicknesses and pixel spaces. Intraclass correlation coefficients (ICCs) were calculated between the original images and images that underwent pixel size resampling (OP), interpolation (OI), or pixel size resampling and interpolation (OP+I) as well as among processed image sets with various pixel spaces (P), various slice thicknesses (I), and both (P + I). Results After feature standardization, ≥86.0% of features showed good robustness when compared between the original and processed images (OP, OI, and OP+I) and ≥ 88.8% of features showed good robustness when processed images were compared (P, I, and P + I). Although most first-order, shape, and texture features showed good robustness, GLSZM small-area emphasis-related features and NGTDM strength were sensitive to variations in pixel size and slice thickness. Conclusion Most MR radiomic features in patients with cervical cancer were robust after pixel size resampling and interpolation following the feature standardization process. The understanding regarding the robustness of individual features after pixel size resampling and interpolation could help future radiomics research.

Radiomic Based Machine Learning Performance for a Three Class Problem in Neuro-Oncology: Time to Test the Waters?

“…As such, we performed standardized anisotropic resampling for all MRI sequences to ensure reproducibility as also performed in prior MRI radiomic studies [ 19 , 20 ]. Moreover, radiomic features have also been shown to be robust to different levels of pixel spacing and interpolation [ 21 ]. In addition, feature standardization (also performed in our study) has been shown to improve robustness of radiomic features beyond pixel spacing and interpolation [ 21 ].…”

“…Feature selection was performed using the recipes package in R version 4.0.2 [ 34 , 35 ]. All features were standardized using the z-score transformation prior to feature selection [ 21 ]. In patients with any missing mask (absence of necrotic/edema masks), radiomic features were not calculated, and in those, the missing values were imputed using mean imputation.…”

“…Moreover, radiomic features have also been shown to be robust to different levels of pixel spacing and interpolation [21]. In addition, feature standardization (also performed in our study) has been shown to improve robustness of radiomic features beyond pixel spacing and interpolation [21]. All MRI image sequences were mutually registered to the pre-contrast T1W sequence using Advanced Normalization Tools (ANTs) (http://stnava.github.io/ANTs/ (accessed on 05/05/2021) [22] followed by min-max image intensity normalization to 0-255 using the feature scaling method available in the ANTs registration suite (http://stnava.github.io/ANTs/ (accessed on 05/05/2021).…”

Pathologic Complete Response Prediction after Neoadjuvant Chemoradiation Therapy for Rectal Cancer Using Radiomics and Deep Embedding Network of MRI

“…Grayscale normalization improves the robustness of radiomics features [32,33]. As with T2, we applied z-score normalization to the post contrast enhanced MRI during the preprocessing stage.…”

Image Preprocessing and Filtering Effect on the Estimate of Myocardial Radiomic Features From T1 and T2 Mapping in Hypertrophic Cardiomyopathy

“…Indeed, each step of the radiomic work ow (i.e., image acquisition and reconstruction, image segmentation, image preprocessing, image ltering, and feature extraction) could in uence features estimation, thus potentially affecting their discriminative or predictive power 37,38 . Several previous studies have assessed the sensitivity of radiomic features estimation to various elements in computed tomography (CT) [39][40][41] and nuclear medicine (NM) 42,43 imaging, as well as in magnetic resonance imaging (MRI), for various applications [44][45][46][47][48][49][50][51][52][53][54][55] .…”