Long-Term Predictive Value of MRI Radiomics in Identifying Patients with Metastasis-Free Breast Cancer Over a 100-Month Follow-Up Period: A retrospective, observational study.
Authors
Affiliations (2)
Affiliations (2)
- Department of Breast Imaging, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Breast Cancer Prevention and Therapy, Tianjin Medical University, Ministry of Education, Tianjin 300060, China.
- Hangzhou Smart Intelligent Co., Ltd., Hangzhou, 311121, China.
Abstract
Postoperative distant metastasis remains a major challenge in breast cancer management, which significantly affects long-term survival among patients. Standard follow-up protocols rely on frequent imaging and clinical evaluations to detect recurrence early. However, such intensive surveillance imposes a financial and psychological burden on both patients and healthcare systems. Recent advances in breast magnetic resonance imaging (MRI)-based radiomics provide new opportunities to capture tumor heterogeneity and may enhance individualized risk prediction. This study aims to assess the long-term predictive value of MRI-based radiomics combined with clinicopathological features in identifying patients with breast cancer and to investigate the potential of this approach in guiding individualized follow-up strategies. This retrospective study included 388 women with breast cancer who underwent breast MRI between February 2015 and October 2017 at the Tianjin Medical University Cancer Institute & Hospital. Radiomic features were extracted from tumor segmentations on second-phase dynamic contrast-enhanced MRI (DCE-MRI) images using semiautomated and deep learning-based segmentation algorithms. The radiomic signature was constructed using the least absolute shrinkage and selection operator (LASSO) method and further integrated with clinical features, including tumor size, estrogen receptor (ER) status, and histological type, to develop ensemble machine learning models. Model performance was assessed using the area under the receiver operating characteristic curve (AUC-ROC) and additional metrics. The combined radiomics-clinical model yielded an AUC of 0.686 for predicting distant metastasis over a 100-month follow-up period in the validation cohort. A predicted probability of 0.22-the lowest value observed among metastatic cases-was used as the risk threshold. Approximately one-third of nonmetastatic patients (n = 32) fell below this cutoff, and all remained metastasis-free during follow-up. ER and Progesterone Receptor (PR) positivity were significantly more common in this subgroup compared to those with a higher predicted risk or confirmed metastasis (ER, p < .005; PR, p < .005). Radiomics-based modeling using DCE-MRI and clinical data demonstrated potential in effectively predicting long-term metastatic risk in patients with breast cancer and identifying a subset of metastatic-free patients with favorable profiles who may benefit from less intensive surveillance.