Radiomics Model for Evaluating the Level of Tumor-Infiltrating Lymphocytes in Breast Cancer Based on Dynamic Contrast-Enhanced MRI
| Autor: | Zhifang Pan, Nina Xu, Meihao Wang, Jiejie Zhou, Huiru Liu, Shuxin Ye, Zhongwei Chen, Xiaxia He, Haiwei Miao, Youfan Zhao |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Oncology Cancer Research medicine.medical_specialty Breast Neoplasms Correlation 03 medical and health sciences Lymphocytes Tumor-Infiltrating 0302 clinical medicine Breast cancer Internal medicine Image Interpretation Computer-Assisted medicine Humans Neoplasm Staging Retrospective Studies business.industry Area under the curve Retrospective cohort study Nomogram medicine.disease Magnetic Resonance Imaging Confidence interval 030104 developmental biology 030220 oncology & carcinogenesis Dynamic contrast-enhanced MRI Biomarker (medicine) Female Lymph Nodes business |
| Zdroj: | Clinical Breast Cancer. 21:440-449.e1 |
| ISSN: | 1526-8209 |
| DOI: | 10.1016/j.clbc.2020.12.008 |
| Popis: | Background To help identify potential breast cancer (BC) candidates for immunotherapies, we aimed to develop and validate a radiology-based biomarker (radiomic score) to predict the level of tumor-infiltrating lymphocytes (TILs) in patients with BC. Patients and Methods This retrospective study enrolled 172 patients with histopathology-confirmed BC assigned to the training (n = 121) or testing (n = 51) cohorts. Radiomic features were extracted and selected using Analysis-Kit software. The correlation between TIL levels and clinical features and radiomic features was evaluated. The clinical features model, radiomic signature model, and combined prediction model were constructed and compared. Predictive performance was assessed by receiver operating characteristic analysis and clinical utility by implementing a nomogram. Results Seven radiomic features were selected as the best discriminators to construct the radiomic signature model, the performance of which was good in both the training and validation data sets, with an area under the curve (AUC) of 0.742 (95% confidence interval [CI], 0.642-0.843) and 0.718 (95% CI, 0.558-0.878), respectively. Estrogen receptor status and tumor diameter were confirmed to be significant features for building the clinical feature model, which had an AUC of 0.739 (95% CI, 0.632-0.846) and 0.824 (95% CI, 0.692-0.957), respectively. The combined prediction model had an AUC of 0.800 (95% CI, 0.709-0.892) and 0.842 (95% CI, 0.730-0.954), respectively. Conclusion The radiomic signature could be an important predictor of the TIL level in BC, which, when validated, could be useful in identifying BC patients who can benefit from immunotherapies. The nomogram may help clinicians make decisions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect