A Nomogram Combined Radiomics and Kinetic Curve Pattern as Imaging Biomarker for Detecting Metastatic Axillary Lymph Node in Invasive Breast Cancer
Yanna Shan, Wen Xu, Rong Wang, Wei Wang, Peipei Pang, Qijun Shen
Abstract
Objective: To construct and validate a nomogram model integrated the MRI radiomic features and the kinetic curve pattern for detecting metastatic axillary lymph node (ALN) in invasive breast cancer preoperatively. Material and Methods: A total of 145 ALNs from two institutions were classified into negative and positive groups according to the pathologic or surgical results. The kinetic curve was computed using dynamic contrast-enhanced MR imaging (DCE-MRI) software. The preprocessed images were used for radiomic feature extraction. The LASSO regression was applied to identify optimal radiomic features and construct the Radscore. A nomogram model was constructed combining the Radscore and the kinetic curve pattern. The discriminative performance was evaluated by ROC analysis and calibration curve. Result: Five optimal features were ultimately selected and contributed to the Radscore construction. The kinetic curve pattern was significant different between negative and positive lymph nodes. The nomogram model showed a better performance in both training cohort (AUC=0.91, 95%CI 0.83-0.96) and external validation cohort (AUC=0.86, 95%CI 0.72-0.94), the calibration curve indicated a better accuracy of the nomogram model for detecting metastatic ALN than either Radscore or kinetic curve pattern alone. Conclusion: A nomogram model integrated the Radscore and the kinetic curve pattern could serve as a biomarker for detecting metastatic ALN in patients with invasive breast cancer.