CLEAR item#55

“Sharing pre-processing scripts or settings. Share the pre-processing and feature extraction parameter scripts or settings (e.g., YAML file in PyRadiomics or complete textual description). If it is not available in a script format, then the parameter configuration as appeared in the software program can be shared as a screenshot.” [1] (from the article by Kocak et al.; licensed under CC BY 4.0)

Reporting examples for CLEAR item#55

Example#1. “The main radiomic features data and radiomics analysis codes are available in https://github.com/JZK00/Ultrasound-Image-Based-Radiomics.” [14] (from the article by Wang et al.; licensed under CC BY-NC-ND 4.0)

Example#2. “The used source codes are available at GitHub (https://github.com/tt1107/wangradiology).” [2] (from the article by Wang et al.; licensed under CC BY 4.0)

Example#3. “The parameter file for the radiomic data extraction is available in a freely accessible online repository (https://github.com/rcuocolo/mri_act_cs2).” [3] (from the article by Gitto et al.; licensed under CC BY-NC-ND 4.0)

Explanation and elaboration of CLEAR item#55

Item#55 highlights the importance of sharing preprocessing scripts or settings. A recent meta-research, the PROPER project, reported that even the most basic parameters, presented in the graphical user interface of radiomic software programs, are poorly reported [4]. Due to their importance on feature values and subsequent models [5–7], a thorough presentation of such settings is crucial to allow methodological assessment as well as study replication and validation. Therefore, the purpose of this open science item is to ensure that no setting is left unreported, independently of the means through which this is achieved (e.g., textual description, configuration file sharing, GUI screenshot image). All of the examples above share their feature extraction parameters, and these files also include instructions for preprocessing the images before extracting the radiomic features, which represents ideal practice.

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. Wang L, Wen D, Yin Y, et al (2023) Musculoskeletal Ultrasound Image-Based Radiomics for the Diagnosis of Achilles Tendinopathy in Skiers. J Ultrasound Med Off J Am Inst Ultrasound Med 42:363–371. https://doi.org/10.1002/jum.16059
  3. Wang T, She Y, Yang Y, et al (2022) Radiomics for Survival Risk Stratification of Clinical and Pathologic Stage IA Pure-Solid Non–Small Cell Lung Cancer. Radiology 302:425–434. https://doi.org/10.1148/radiol.2021210109
  4. Gitto S, Cuocolo R, Langevelde K van, et al (2022) MRI radiomics-based machine learning classification of atypical cartilaginous tumour and grade II chondrosarcoma of long bones. eBioMedicine 75:. https://doi.org/10.1016/j.ebiom.2021.103757
  5. Kocak B, Yuzkan S, Mutlu S, et al (2023) Publications poorly report the essential RadiOmics ParametERs (PROPER): a meta-research on quality of reporting. Eur J Radiol 0: https://doi.org/10.1016/j.ejrad.2023.111088
  6. Demircioğlu A (2022) The effect of preprocessing filters on predictive performance in radiomics. Eur Radiol Exp 6:40. https://doi.org/10.1186/s41747-022-00294-w
  7. Moradmand H, Aghamiri SMR, Ghaderi R (2020) Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma. J Appl Clin Med Phys 21:179–190. https://doi.org/10.1002/acm2.12795
  8. Dewi DEO, Sunoqrot MRS, Nketiah GA, et al (2023) The impact of pre-processing and disease characteristics on reproducibility of T2-weighted MRI radiomics features. Magn Reson Mater Phys Biol Med 36:945–956. https://doi.org/10.1007/s10334-023-01112-z

Back Next