CLEAR item#49

“Overview of important findings. Provide a summary of the work and an overview of the most important findings. No statistical information is needed. Try to position the study into one of the following categories: proof of concept evaluation, technical task-specific evaluation, clinical evaluation, and post-deployment evaluation. Summarize the contribution to the literature.” [1] (from the article by Kocak et al.; licensed under CC BY 4.0)

Reporting examples for CLEAR item#49

Example#1. “In this proof-of-concept study, we aimed to explore the potential of MRI-derived radiomic features in the non-invasive prediction of tumour hypoxia. Among the routinely-performed magnetic resonance imaging (MRI) scans in the clinical workflow, T2-weighted imaging and DWI have the most profound biological connection to hypoxia. Preclinical studies have also shown that ADC and T2 mapping were helpful in imaging tumour hypoxia in murine models. With this in mind, we decided to focus the scope of our imaging study on T2W and DWI sequences and their derived parameter maps.

In our cohort of baseline colorectal liver metastases, radiomic signatures derived from the ADC map and DWI b200 image were significantly associated with histopathological tumour hypoxia. Imaging markers derived from T2W TE75, DWI b0, and DWI b800 were also predictive of the HIF-1 alpha staining index, albeit narrowly short of statistical significance. In general, lower spin echo times and higher b-value images were able to encode more information regarding the hypoxia status. These findings are in line with our current understanding of hypoxia under MRI.” [2] (from the article by Bodalal et al.; licensed under CC BY 4.0)

Example#2. “In this study, we analyzed the effect of different subsets of radiomic features and the clinical assessment category PI-RADS on the predictive performance of three machine learning algorithms to stratify PCa of the PZ according to its clinical significance. We first demonstrated adequate VOI placement in concordance with the PI-RADS assessment. Our data demonstrates that the integration of radiomic features using machine learning algorithms can positively or negatively influence the prediction performance for clinically significant PCa. The results emphasize the need to be cautious using radiomic machine learning strategies but also the potential of the features SVR, LA, and max3D to improve PI-RADS assessment categories.” [3] (from the article by Bernatz et al.; licensed under CC BY 4.0)

Explanation and elaboration of CLEAR item#49

Item #49 highlights the pivotal role of the discussion section in a radiomics research paper, emphasizing the need to offer a comprehensive overview of key findings without delving into statistical details. This approach allows to focus on the broader conceptual aspects, facilitating a more accessible understanding for a diverse audience [4]. Furthermore, the categorization of the study serves as a structured framework, offering readers a clearer perspective on the nature and goals of the research. Authors should summarize their study’s contribution to the existing literature, elucidating the unique insights and advancements it brings to the field. This approach guarantees a richer and more contextualized understanding of the research findings.

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. Bodalal Z, Bogveradze N, Ter Beek LC, et al (2023) Radiomic signatures from T2W and DWI MRI are predictive of tumour hypoxia in colorectal liver metastases. Insights Imaging 14:133. https://doi.org/10.1186/s13244-023-01474-x
  3. Bernatz S, Ackermann J, Mandel P, et al (2020) Comparison of machine learning algorithms to predict clinically significant prostate cancer of the peripheral zone with multiparametric MRI using clinical assessment categories and radiomic features. Eur Radiol 30:6757–6769. https://doi.org/10.1007/s00330-020-07064-5
  4. van Timmeren JE, Cester D, Tanadini-Lang S, et al (2020) Radiomics in medical imaging—“how-to” guide and critical reflection. Insights Imaging 11:91. https://doi.org/10.1186/s13244-020-00887-2

Back Next