The value of clinical-CT radiomics model in predicting cervical lymph node metastasis of papillary thyroid carcinoma
10.3969/j.issn.1002-1671.2023.12.004
- VernacularTitle:临床-CT影像组学模型预测甲状腺乳头状癌颈部淋巴结转移的价值
- Author:
Haiming ZHANG
1
;
Fengtao ZHANG
;
Liheng MA
;
Hengguo LI
;
Zhenyu LI
Author Information
1. 广东药科大学附属第一医院医学影像科,广东 广州 518100
- Keywords:
radiomics;
papillary thyroid carcinoma;
cervical lymph node metastasis;
computed tomography
- From:
Journal of Practical Radiology
2023;39(12):1926-1930
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the value of a clinical-CT radiomics model in predicting cervical lymph node metastasis(CLNM)of papillary thyroid carcinoma(PTC).Methods A total of 262 cases with PTC confirmed by pathology after surgery were selected.On CT arterial phase images,the PTC was outlined layer by layer via software 3D-slicer to extract CT radiomics features.The least absolute shrinkage and selection operator(LASSO)algorithm was used for dimensionality reduction and feature screening in relation to CLNM.The Mann-Whitney U test or Chi square test was performed to identify clinical parameters significantly associated with CLNM.The statistically significant CT radiomics features and clinical parameters were all selected for the multivariate logistic regression analysis to construct the clinical-CT radiomics model.The predictive efficiency of model was evaluated via the receiver operating characteristic(ROC)curve.Results The clinical-CT radiomics model demonstrated favorable predictive performance in both the training group[area under the curve(AUC)0.804,sensitivity 68.7％,specificity 82.4％]and the validation group(AUC 0.782,sensitivity 84.4％,specificity 61.8％).Conclusion The clinical-CT radiomics model demonstrates significant value in predicting CLNM of PTC,thereby,aiding in the development of personalized clinical plans for cervical lymph node(CLN)dissection.
