CLEAR item#53

“Sharing images along with segmentation data. (Please note that this item is “not essential” but “recommended.”) Provide relevant raw or processed image data considering the regulatory constraints of the institutions involved. Segmentation data can also be shared unless the segmentation is done as part of the workflow. In situations where sharing of the entire dataset is not possible, an end-to-end analysis workflow applied to a representative sample or a public dataset with similar characteristics can facilitate the ability of the readers in reproducing key components of the analysis. Also, specify the reason if the data are not available.” [1] (from the article by Kocak et al.; licensed under CC BY 4.0)

Reporting examples for CLEAR item#53

Example#1. “The iCTCF dataset is publicly available and can be accessed at https://ngdc.cncb.ac.cn/ictcf/. The complete KRI dataset is available on request for research purposes in the frame of the BFS project AZ-1429-20C.” [2] (from the article by Keicher et al.; licensed under CC BY 4.0)

Example#2. “Data reported in this study was not available due to the limitations set by Ethical committee.” [3] (from the article by Shu et al.; licensed under CC BY 4.0)

Example#3. “The Lung2 dataset that support the findings of this study are available by request from the authors […]. This part of data are not publicly available due to the data containing information that could compromise research participant privacy.” [4] (from the article by Shi et al.; licensed under CC BY 4.0)

Explanation and elaboration of CLEAR item#53

This is the first item of the Open Science section from CLEAR, which overall aims to address the issue of data availability, which is a major challenge in radiomics research [5]. The public availability of imaging and segmentation data would certainly increase transparency and allow for replication studies to confirm the original findings, or even advancing the knowledge compared to what previously achieved (e.g., training-testing different models or alternative hypothesis). Unfortunately, despite being also promoted by dedicated scientific journals and perceived as good research practice by the scientific community, data sharing remains rather uncommon in radiomics and the broader field of medicine [6, 7]. Indeed, sharing individual patient data securely is undeniably a demanding endeavor and requires planning in advance. Institutional review board approval and patient’s consent should be obtained. Acknowledging the intricate nature of this crucial task, the checklist item, while deemed “not essential,” is still classified as “recommended” in recognition of its significant importance.

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. Keicher M, Burwinkel H, Bani-Harouni D, et al (2023) Multimodal graph attention network for COVID-19 outcome prediction. Sci Rep 13:19539. https://doi.org/10.1038/s41598-023-46625-8
  3. Shu Z, Fang S, Ding Z, et al (2019) MRI-based Radiomics nomogram to detect primary rectal cancer with synchronous liver metastases. Sci Rep 9:3374. https://doi.org/10.1038/s41598-019-39651-y
  4. Shi Z, Zhovannik I, Traverso A, et al (2019) Distributed radiomics as a signature validation study using the Personal Health Train infrastructure. Sci Data 6:218. https://doi.org/10.1038/s41597-019-0241-0
  5. Namdar K, Wagner MW, Ertl-Wagner BB, Khalvati F (2022) Open-radiomics: A Collection of Standardized Datasets and a Technical Protocol for Reproducible Radiomics Machine Learning Pipelines. In: arXiv.org. https://arxiv.org/abs/2207.14776v2. Accessed 2 Jan 2024
  6. Venkatesh K, Santomartino SM, Sulam J, Yi PH (2022) Code and Data Sharing Practices in the Radiology Artificial Intelligence Literature: A Meta-Research Study. Radiol Artif Intell 4:e220081. https://doi.org/10.1148/ryai.220081
  7. Locher C, Le Goff G, Le Louarn A, et al (2023) Making data sharing the norm in medical research. BMJ 382:1434. https://doi.org/10.1136/bmj.p1434

Back Next