Radiomics-based signature of breast cancer on preoperative contrast-enhanced MRI to predict axillary metastasis

被引:2
作者
Chen, Danxiang [1 ]
Liu, Xia [2 ]
Hu, Chunlei [1 ]
Hao, Rutian [1 ]
Wang, Ouchen [1 ]
Xiao, Yanling [1 ]
机构
[1] Wenzhou Med Univ, Dept Breast Surg, Affiliated Hosp 1, Wenzhou 325000, Zhejiang, Peoples R China
[2] Wenzhou Med Univ, Dept Anesthesia, Affiliated Hosp 1, Wenzhou 325000, Zhejiang, Peoples R China
关键词
breast neoplasms; DCE-MRI; lymph node metastasis; machine-learning algorithm; radiomics; LYMPH-NODE BIOPSY; DISSECTION; ESTROGEN;
D O I
10.2217/fon-2022-0333
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Aim: This study aimed to predict axillary metastasis using radiology features in dynamic contrast-enhanced MRI. Methods: This study included 243 breast lesions confirmed as malignant based on axillary status. Most outcome-predictive features were selected using four machine-learning algorithms. Receiver operating characteristic analysis was used to reflect diagnostic performance. Results: Least absolute shrinkage and selection operator was used to dimensionally reduce 1137 radiomics features to three features. Three optimal radiomics features were used to model construction. The logistic regression model achieved an accuracy of 97% and 85% in the training and test groups. Clinical utility was evaluated using decision curve analysis. Conclusion: The novel combination of radiomics analysis and machine-learning algorithm could predict axillary metastasis and prevent invasive manipulation.
引用
收藏
页数:14
相关论文
empty
未找到相关数据