The reproducibility and predictivity of radiomic features extracted from dynamic contrast-enhanced computed tomography of hepatocellular carcinoma
The reproducibility of many RFs was significantly impacted by inter-observer variability, and a larger number of RFs were impacted by the difference in the time of acquisition after contrast injection. Our findings highlight the need for quality assessment to ensure that scans are analyzed in the same physiologic imaging phase in quantitative imaging studies, or that phase-wide reproducible RFs are selected. Overall, the study emphasizes the importance of reproducibility and quality control when using RFs as biomarkers for clinical applications.
Authors
- Hao Yang (ORCID: https://orcid.org/0000-0003-4172-012X)
- Chuanmiao Xie (ORCID: https://orcid.org/0000-0001-8533-623X)
- Lawrence H. Schwartz
- Qian Wu (ORCID: https://orcid.org/0000-0001-5746-2677)
- Peng Geng (ORCID: https://orcid.org/0009-0006-5046-8527)
- Abdalla Ibrahim (ORCID: https://orcid.org/0000-0003-4138-5755)
- Siddharth Guha (ORCID: https://orcid.org/0009-0002-2326-4482)
- Lin Lu (ORCID: https://orcid.org/0000-0002-7171-9704)
- Delin Wang (ORCID: https://orcid.org/0000-0003-0689-3199)
- Yen Chou (ORCID: https://orcid.org/0000-0003-2388-194X)
- Binsheng Zhao (ORCID: https://orcid.org/0009-0009-9934-9141)
Institutions
- Fu Jen Catholic University (TW)
- Memorial Sloan Kettering Cancer Center (US)
- Sun Yat-sen University (CN)
- Columbia University Irving Medical Center (US)
- Sun Yat-sen University Cancer Center (CN)
- Nanjing Medical University (CN)
Publication Details
- Journal
- PLoS ONE
- Published
- 2024-09-13
- DOI
- https://doi.org/10.1371/journal.pone.0310486
- Citations
- 3
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.21