Different radiomics annotation methods comparison in rectal cancer characterisation and prognosis prediction: a two-centre study
There is currently a lack of discussion on whether different annotation efforts in radiomics are predictively representative. No significant differences were observed in radiomics and combined models regardless of the annotations (2D, 3D, detailed, or bounding box). Prioritise selecting the more time and effort-saving 2D maximum area bounding box annotation.
Authors
- Ying Zhu (ORCID: https://orcid.org/0000-0002-5502-3571)
- Xiang Li (ORCID: https://orcid.org/0000-0002-4122-0654)
- Meihao Wang (ORCID: https://orcid.org/0000-0002-7055-993X)
- Zhongwei Chen (ORCID: https://orcid.org/0000-0002-0782-0648)
- Guoquan Cao (ORCID: https://orcid.org/0000-0001-9450-2690)
- Shiwei Zhang (ORCID: https://orcid.org/0000-0001-5840-6888)
- Yaru Wei
- Jiejie Zhou
- Caiyun Wen (ORCID: https://orcid.org/0000-0002-3937-6596)
Institutions
- Wenzhou Medical University (CN)
- First Affiliated Hospital of Wenzhou Medical University (CN)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2024-08-26
- DOI
- https://doi.org/10.1186/s13244-024-01795-5
- Citations
- 4
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.62
Funders
- Wenzhou Medical University
- Wenzhou Municipal Science and Technology Bureau
- Natural Science Foundation of Zhejiang Province