Effect of reconstruction settings on radiomics feature robustness in positron emission tomography images: a clinical study
These findings suggest that certain radiomic features exhibit high robustness across reconstruction algorithms, parameter settings, acquisition durations, and count statistics. Joint consideration of reconstruction, segmentation, and feature selection is essential to ensuring reproducibility in radiomics workflows. Certain features hold promise for robust tumor quantification in multicenter studies, longitudinal monitoring, and prospective trials, where imaging protocols may vary, making them strong candidates for standardized imaging biomarkers in routine clinical workflows and research settings.
Authors
- Guolin Wang (ORCID: https://orcid.org/0000-0002-5393-9500)
- Shuye Yang
- Yinuo Liu (ORCID: https://orcid.org/0009-0008-7124-9328)
- Zhenfeng Liu (ORCID: https://orcid.org/0000-0002-1808-9352)
- Tian‐Cheng Li (ORCID: https://orcid.org/0000-0002-6047-8482)
- Shuming Zhang (ORCID: https://orcid.org/0009-0008-2594-2877)
- Xinhui Su (ORCID: https://orcid.org/0000-0002-4782-3982)
- Huatao Wang (ORCID: https://orcid.org/0009-0008-0889-7779)
- Xiaofang Yan
Institutions
- United Imaging Healthcare (China) (CN)
- First Affiliated Hospital Zhejiang University (CN)
Publication Details
- Journal
- Quantitative Imaging in Medicine and Surgery
- Published
- 2025-09-24
- DOI
- https://doi.org/10.21037/qims-2025-958
- Citations
- 1
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.36