Assessing the multi-software robustness of radiomic biomarkers: a three-tool evaluation

To assess the cross-software reproducibility of Computed Tomography (CT) radiomic features extracted using three widely adopted platforms (Siemens syngo.via Frontier, 3D Slicer/PyRadiomics, and mint Lesion) and to identify a subset of highly robust features suitable for multi-platform and multi-center radiomics applications.

A retrospective cohort of 97 lesions (primary colorectal cancer, colorectal liver metastases, and hepatocellular carcinoma) who underwent contrast-enhanced Computed Tomography (CT) in the portal venous phase was analyzed. Semi-automatic 3D lesion segmentations were exported for radiomic extraction across the three platforms. Shared radiomic features among tools were harmonized and z-score normalized. Cross-platform similarity was assessed using distribution distance metrics, hierarchical clustering, and the Adjusted Rand Index (ARI). A novel Composite Robustness Index (CI) integrating Pearson correlation, Kolmogorov-Smirnov statistics, and mean fold-difference was developed to quantify feature-level reproducibility.

First-order intensity features and key GLCM descriptors (e.g., Correlation, Joint Average, Sum Entropy) demonstrated the highest cross-software stability, with nearly superimposable distributions and strong concordance in clustering structure. Siemens syngo.via Frontier and 3D Slicer/PyRadiomics showed the highest agreement (mean ARI >0.85), while mint Lesion™-which lacks higher-order texture families-showed moderate deviations (mean ARI ≈ 0.70-0.75). High-order features, particularly GLDM and GLRLM metrics, exhibited substantial variability across platforms. The CI ranking enabled identification of a reproducible set of "highly reproducible features, " including glcm_Correlation, firstorder_Mean, firstorder_RMS, firstorder_90Percentile, and shape axis-length descriptors.

Despite intrinsic software differences, a consistent subset of radiomic features remains reproducible across heterogeneous extraction tools. The combined use of distribution analysis, hierarchical clustering, and the Composite Robustness Index offers a rigorous framework for evaluating cross-platform reliability. These findings support the feasibility of multi-tool radiomics and provide a validated feature set for harmonized quantitative imaging pipelines.