Study on CT Radiomics for the Preoperative Prediction of
Axillary Lymph Node Metastasis in Breast Cancer
LIU Qinfeng1a，LIU Weijun1a，YANG Jingbo2，YU Bin1a，ZHANG Xuan1a，MA Liang1a，LIU Hui1b，WANG Tao1b
1. a. Department of Medical Equipment Management| b. Department of Radiology, Shannxi Provincial People’s Hospital, Xi’an
Shannxi 710068, China| 2. School of Life Science and Technology, Xidian University, Xi’an Shannxi 710071, China
Abstract：Objective To explore the application value of CT imaging in predicting axillary lymph node metastasis of breast cancer. Methods A total of 112 patients with breast cancer confirmed by pathology in our hospital from January 2018 to May 2019 were randomly assigned to training set (75 cases) and test set (37 cases). Features were extracted from breast CT images, and lasso algorithm was used to select features, and image omics feature tags were established. Then, a multivariate logistic regression model was established and validated by the characteristic tags and clinical risk factors. Finally, the nomogram diagram was developed and the calibration curve was drawn to evaluate the performance of the model. Results The C-index value obtained by constructing the model with the training set was 0.727 (95%CI: 0.719~0.736), while the C-index obtained with the test set verification was 0.711 (95%CI: 0.703~0.718). The mean square error of the prediction model calculated from the prediction probability of axillary lymph node metastasis and the actual metastasis probability was 0.072. Conclusion The prediction model based on the image omics features extracted from preoperative CT images of breast cancer patients can predict the status of axillary lymph node metastasis in breast cancer patients.
刘沁峰1a，刘伟军1a，杨静波2，于斌1a，张旋1a，马良1a，刘辉1b，王涛1b. CT影像组学术前预测乳腺癌腋窝淋巴结转[J]. 中国医疗设备, 2020, 35(9): 88-92.
LIU Qinfeng1a，LIU Weijun1a，YANG Jingbo2，YU Bin1a，ZHANG Xuan1a，MA Liang1a，LIU Hui1b，WANG Tao1b. Study on CT Radiomics for the Preoperative Prediction of
Axillary Lymph Node Metastasis in Breast Cancer. China Medical Devices, 2020, 35(9): 88-92.
Freddie B,Jacques F,Isabelle S,et al.Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J].CA Cancer J Clin,2018,68:394-424.
