Radiomics Results for Adrenal Mass Characterization Are Stable and Reproducible Under Different Software

<i>Background</i>: This study aims to investigate stability and reproducibility of radiomics biomarkers for adrenal lesion characterization across different software packages. <i>Methods</i>: Unenhanced CT images from patients with adrenal tumors were analyzed. Radiomic features were extracted using SOPHIA Radiomics and SIBEX software. The datasets underwent Z-score normalization. Statistical comparisons were made using two-sample <i>t</i>-tests and Spearman correlation coefficients. Three classification models-Logistic Regression, Linear Discriminant Analysis, and Linear Support Vector Machine-were trained on the datasets. Model performance was evaluated using accuracy, precision, recall, F1 score, and ROC curves. Feature importance and the statistical significance of model performance differences were also analyzed. <i>Results</i>: The <i>t</i>-test results showed no significant differences in the radiomic features extracted by SOPHIA and SIBEX (<i>p</i>-values all equal to 1.0). Spearman correlation coefficients were high for most features, suggesting a strong similarity between the two software tools. Classification models generally performed better on the SOPHIA dataset, with higher accuracy and precision. Feature importance analysis identified "Quadratic mean" and "Strength" as consistently influential features. Paired <i>t</i>-tests indicated significant differences in accuracy and precision, while Wilcoxon signed-rank tests did not find significant differences across all performance metrics. <i>Conclusions</i>: Radiomic features extracted by SOPHIA and SIBEX are comparable, but slight variations in model performance highlight the need for standardized extraction protocols and fine-tuning of predictive features. The study underscores the importance of ensuring the stability and reproducibility of radiomics features for reliable clinical application in adrenal lesion characterization.