Evaluation and optimization of radiomics features stability to respiratory motion in ¹⁸F‐FDG 3D PET imaging

Abstract

Purpose To evaluate the impact of respiratory motion on radiomics features in 18F‐fluoro‐2‐deoxy‐D‐glucose three dimensional positron emission tomography (18F‐FDG 3D PET) imaging and optimize feature stability by combining preprocessing configurations and aggregation strategies. Methods An in‐house developed respiratory motion phantom was imaged in 3D PET scanner under nine respiratory patterns including one reference pattern. In total, 487 radiomics features were extracted for each respiratory pattern. Feature stability to respiratory motion was first evaluated by metrics of coefficient of variation (COV) and relative difference (RD) in a fixed preprocessing configuration. Further, one‐way ANOVA and trend analysis were performed to evaluate the impact of preprocessing configuration (voxel size, discretization scheme) and aggregation strategy on feature stability. Finally, an optimization framework was proposed by selected feature‐specific configurations with minimum COV value, and the diagnostic performance was validated in stable versus unstable features and fixed versus optimal features by a set of 46 patients with lung disease. Results PET radiomics features were sensitive to respiratory motion, only 79/487 (16%) features were identified to be very stable in the fixed configuration. Preprocessing configuration and aggregation strategy had an impact on feature stability. For different voxel size, bin number, bin size and aggregation strategy, 188/487 (39%), 70/487 (15%), 148/487 (30%), and 38/95 (29%) features appeared significant changes in feature stability. The optimized configuration had the potential to improve feature stability compared to fixed configuration, with the COV decreased from 22% ±24% to 16% ±20%. Regarding the diagnostic performance, the stable and optimal configuration features outperformed the unstable and fixed configuration features, respectively (AUC 0.88, 0.87 vs. 0.83, 0.85). Conclusions Respiratory motion shows considerable impact on feature stability in 3D PET imaging, while optimizing preprocessing configuration may improve feature stability and diagnostic performance.

The combined tumor-nodal glycolytic entropy improves survival stratification in nonsmall cell lung cancer with locoregional disease

“…Our findings were supported by other studies showing a positive association between 18 F-FDG PET-derived heterogeneity features and survival outcomes in patients with lung cancer and small tumor size [5,33,34], indicating that the functional relationship between glycolytic heterogeneity and prognosis can be maintained despite analyzing a small volume. Furthermore, the entropy we used in our study is one of the most reproducible image features in different image processing methods and in the presence of respiratory motion [16,17]. Therefore, combined entropy may reliably stratify the survival outcomes in patients with NSCLC with locoregional disease.…”

Synergistic impact of motion and acquisition/reconstruction parameters on18F‐FDG PET radiomic features in non‐small cell lung cancer: Phantom and clinical studies

“…In a recent study, 33 the effect of respiratory motion on radiomic features was investigated. To date, experimental studies evaluating the synergistic impact of motion and acquisition or reconstruction parameters on moving targets from PET images are lacking.…”

Reproducibility of lung cancer radiomics features extracted from data-driven respiratory gating and free-breathing flow imaging in [18F]-FDG PET/CT

“…To our knowledge, other studies have evaluated radiomics features behaviour under different image segmentation, discretisation and reconstruction methods but have not focused on their reproducibility. Xu et al ( 2021 ) measured respiratory motion influence on radiomics features stability with phantom simulation of different respiratory patterns. Based on the different radiomics values distribution, the stability of the features was evaluated calculating the coefficient of variation and the relative difference.…”