Thymoma habitat segmentation and risk prediction model using CT imaging and K‐means clustering
This study successfully identified distinct habitat zones within thymomas through CT imaging feature analysis and developed an efficient predictive model that significantly improved diagnostic accuracy. This model offers a novel tool for risk assessment of thymomas and can aid in guiding clinical decision-making.
Authors
- Chun‐Yuan Chen (ORCID: https://orcid.org/0000-0002-6244-8455)
- Rongtai Cai (ORCID: https://orcid.org/0000-0003-4505-7927)
- Yan Zhang (ORCID: https://orcid.org/0000-0002-2168-9674)
- Shuyan He
- Siyuan Li (ORCID: https://orcid.org/0000-0002-2354-4233)
- Zhu Liang (ORCID: https://orcid.org/0000-0001-8223-5003)
- Yanxia Wu (ORCID: https://orcid.org/0009-0006-2226-5757)
- Biao Deng
- Jiamin Li (ORCID: https://orcid.org/0009-0009-0232-2138)
Institutions
- Guangzhou University of Chinese Medicine (CN)
- Guangdong Medical College (CN)
- Longgang Central Hospital (CN)
- ShenZhen People’s Hospital (CN)
- Affiliated Hospital of Guangdong Medical College Hospital (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-05-19
- DOI
- https://doi.org/10.1002/mp.17892
- Citations
- 4
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 5.44