Prediction of lateral lymph node metastasis with short diameter less than 8 mm in papillary thyroid carcinoma based on radiomics
(1) In this study, among the ensemble learning models established based on clinicopathological features and radiomics features for predicting PTC lateral small lymph node metastasis, the clinical-radiomic CatBoost model has the best performance. (2) SHAP can visualize how the clinical and radiomics features affect the results and realize the interpretation of the model. (3) The combined CatBoost model can improve the diagnostic accuracy of suspicious lymph nodes with short diameter < 8 mm that are difficult to obtain accurate puncture results. The combined application of radiomics features is more accurate and reasonable than the prediction of clinical data alone, which helps to accurately evaluate the surgical scope and provide support for individual clinical decision making.
Authors
- Ziyi Yang (ORCID: https://orcid.org/0000-0001-5883-9552)
- Shiyong Zhang (ORCID: https://orcid.org/0000-0001-7633-358X)
- He Ma (ORCID: https://orcid.org/0000-0002-7704-7419)
- Zhihong Wang (ORCID: https://orcid.org/0000-0003-3196-1739)
- Zijun Yu
- Chen Zhi-guang (ORCID: https://orcid.org/0000-0002-1999-125X)
- Minghui Zhang (ORCID: https://orcid.org/0000-0001-8850-9642)
- Gaosen Zhang (ORCID: https://orcid.org/0000-0003-3136-2453)
- Liang Sang (ORCID: https://orcid.org/0000-0002-9331-0985)
- Xuemei Wang (ORCID: https://orcid.org/0009-0000-7909-3171)
- Yan Wang (ORCID: https://orcid.org/0009-0004-7668-1129)
Institutions
- First Hospital of China Medical University (CN)
- China Medical University (CN)
- Northeastern University (CN)
Publication Details
- Journal
- Cancer Imaging
- Published
- 2024-11-15
- DOI
- https://doi.org/10.1186/s40644-024-00803-7
- Citations
- 7
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 2.50
Funders
- Natural Science Foundation of Liaoning Province