Research Article: Assessing the multi-software robustness of radiomic biomarkers: a three-tool evaluation
Abstract:
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 color ectal cancer , color ectal liver metastases, and hepatocellular carcinoma) who underwent contrast-enhanced Computed Tomography (CT) in the portal venous phase was analyze d. 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.
Introduction:
Radiomics has emerged as a powerful quantitative imaging methodology capable of capturing spatial and intensity-based tissue characteristics beyond visual interpretation ( 1 – 8 ). Despite its increasing relevance in oncologic imaging, the lack of standardization in feature extraction pipelines remains one of the major barriers to clinical translation. Differences in software implementation, interpolation, discretization, and feature definitions can lead to substantial inconsistencies in radiomic values, even when…
Read more