CLEAR item#28

“Default configuration statement for remaining parameters. After providing all modified parameters of pre-processing and radiomic feature extraction, state clearly that all other parameters remained as a default configuration.” [1] (from the article by Kocak et al.; licensed under CC BY 4.0)

Reporting examples for CLEAR item#28

Example#1. “After providing all modified parameters of pre-processing and radiomic feature extraction, all other parameters remained as a default configuration.” [2] (from the article by Jo et al.; licensed under CC BY 4.0)

Example#2. “Radiomics features parameters were set to their default values.” [3] (from the article by Flouris et al.; licensed under CC BY 4.0)

Explanation and elaboration of CLEAR item#28

After detailing the modified parameters for pre-processing and radiomic feature extraction, it is essential to explicitly mention that all remaining parameters were maintained at their default configuration. This statement serves as a critical point of reference, ensuring transparency and reproducibility in research methodologies. Additionally, features may show different correlation with imaging parameters, with different preprocessing techniques [4]. By specifying that default settings were preserved for all other parameters, researchers convey a standardized baseline for their study. Clarity in reporting default configurations is particularly important when utilizing complex software or algorithms for pre-processing and feature extraction. It reduces ambiguity and potential sources of variation, fostering a clearer understanding of the methods used.

References

  1. Kocak B, Baessler B, Bakas S, et al (2023) CheckList for EvaluAtion of Radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII. Insights Imaging 14:75. https://doi.org/10.1186/s13244-023-01415-8
  2. Jo SW, Kim ES, Yoon DY, Kwon MJ (2023) Changes in radiomic and radiologic features in meningiomas after radiation therapy. BMC Med Imaging 23:164. https://doi.org/10.1186/s12880-023-01116-0
  3. Flouris K, Jimenez-del-Toro O, Aberle C, et al (2022) Assessing radiomics feature stability with simulated CT acquisitions. Sci Rep 12:4732. https://doi.org/10.1038/s41598-022-08301-1
  4. Fave X, Zhang L, Yang J, et al (2016) Impact of image preprocessing on the volume dependence and prognostic potential of radiomics features in non-small cell lung cancer. Transl Cancer Res 5:. https://doi.org/10.21037/tcr.2016.07.11

Back Next