Preoperative prediction of positive margins in breast-conserving surgery using an ensemble model based on DCE-MRI: a multi-center retrospective and prospective study.
9 affiliations
- 1The Breast Center and the Cancer Institute, Yunnan Key Laboratory of Molecular Imaging in Oncology, Yunnan International Joint Laboratory on Cancer Molecular Imaging, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Peking University Cancer Hospital Yunnan, 519 Kunzhou Rd, Xishan District, Kunming, 650118, China.
- 2National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China.
- 3Department of Rehabilitation and Palliative Medicine, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Peking University Cancer Hospital Yunnan, Kunming, China.
- 4School of Software, Yunnan University, Kunming, China.
- 5Department of Radiology, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Peking University Cancer Hospital Yunnan, Kunming, China.
- 6Department of Artificial Intelligence, Xiamen University, Xiamen, China.
- 7Department of Radiology, Cancer Hospital of Shantou University Medical College, Shantou, China.
- 8The Breast Center and the Cancer Institute, Yunnan Key Laboratory of Molecular Imaging in Oncology, Yunnan International Joint Laboratory on Cancer Molecular Imaging, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Peking University Cancer Hospital Yunnan, 519 Kunzhou Rd, Xishan District, Kunming, 650118, China. [email protected].
- 9National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China. [email protected].
Abstract
Background
Breast-conserving surgery (BCS) is the standard care for early breast cancer. However, positive surgical margins lead to high recurrence and require reoperation, remaining a clinical challenge. This study aims to develop an ensemble model to preoperatively predict positive margins using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).Methods
A total of 887 patients from three Chinese medical centers were included. Patients from the Yunnan (581 patients) and Fujian (51 patients) provinces were used for model development, with external testing on 188 patients from Guangdong and prospective testing on 67 patients from Yunnan. Three base models were developed: the clinical model based on 32 features, the deep learning (DL) model using ResNet-34, and the radiomics model utilizing radiomics features. The ensemble model combined predictions from these three base models using weighted voting. Performance metrics (accuracy, AUC, sensitivity, specificity) were computed, and prognostic analyses were conducted with a public dataset.Results
The ensemble model outperformed each of the three base models, with the AUC of 0.931, accuracy of 0.872, sensitivity of 0.871, and specificity of 0.880 in the validation set. Robustness was further confirmed in independent test cohorts, yielding AUCs of 0.762 and 0.861. Furthermore, patients identified at high-risk by the model exhibited poor recurrence-free survival (RFS, HR = 8.117, p < 0.0001) and overall survival (OS, HR = 5.748, p < 0.0001), underscoring its prognostic value.Conclusions
The ensemble model based on DCE-MRI effectively predicts positive margins and prognosis for BCS patients, facilitating the clinical decision-making on the surgery. Trial registration This study was approved by the Ethics Committee of the Yunnan Cancer Hospital (KYLX2023-134), Xiang'an Hospital of Xiamen University (XDYX202305K26), and Cancer Hospital of Shantou University Medical College (2024059). The study was also registered with the Chinese Clinical Trial Registry (ChiCTR2400083298, Registered 19 April 2024, https://www.chictr.org.cn/showproj.html?%20proj=207948 ).
Related
- Foundation Model-Enabled Pathology-Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study.
- Development of a nomogram for preoperative prediction of malignant risk in thyroid follicular tumors based on multimodal ultrasound and clinical features: A retrospective observational study
- Multiparametric MRI radiomics and clinical features for preoperative prediction of high-grade meningioma: a two-centre retrospective study
- Development and external validation of a preoperative prediction model for in-hospital major adverse cardiovascular events after hip fracture surgery in older adults: a retrospective two-center study.
- Preoperative ovarian vascular parameters and perioperative factors associated with ovarian reserve marker decline after laparoscopic endometrioma cystectomy: a retrospective prediction study
BibTeX
@article{zhao2026preoperative,
title = {{Preoperative prediction of positive margins in breast-conserving surgery using an ensemble model based on DCE-MRI: a multi-center retrospective and prospective study.}},
author = {Xue Zhao and Jing-Wen Bai and Li-Ang Dong and Zhen-Hui Li and Jie-Zhou He and Yi-Xin Chen and Yong Liu and Wen-Tai Hou and Ze-Yan Xu and Zhi-Cheng Du and Sen Jiang and Shao-Zi Li and Guo-Jun Zhang},
journal = {Breast cancer research : BCR},
year = {2026},
month = jul,
doi = {10.1186/s13058-026-02354-0},
url = {https://europepmc.org/article/MED/42902311},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Preoperative prediction of positive margins in breast-conserving surgery using an ensemble model based on DCE-MRI: a multi-center retrospective and prospective study.
AU - Xue Zhao
AU - Jing-Wen Bai
AU - Li-Ang Dong
AU - Zhen-Hui Li
AU - Jie-Zhou He
AU - Yi-Xin Chen
AU - Yong Liu
AU - Wen-Tai Hou
AU - Ze-Yan Xu
AU - Zhi-Cheng Du
AU - Sen Jiang
AU - Shao-Zi Li
AU - Guo-Jun Zhang
PY - 2026
DA - 2026/07/01
JO - Breast cancer research : BCR
DO - 10.1186/s13058-026-02354-0
UR - https://europepmc.org/article/MED/42902311
AB - Background Breast-conserving surgery (BCS) is the standard care for early breast cancer. However, positive surgical margins lead to high recurrence and require reoperation, remaining a clinical challenge. This study aims to develop an ensemble model to preoperatively predict positive margins using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).Methods A total of 887 patients from three Chinese medical centers were included. Patients from the Yunnan (581 patients) and Fujian (51 patients) provinces were used for model development, with external testing on 188 patients from Guangdong and prospective testing on 67 patients from Yunnan. Three base models were developed: the clinical model based on 32 features, the deep learning (DL) model using ResNet-34, and the radiomics model utilizing radiomics features. The ensemble model combined predictions from these three base models using weighted voting. Performance metrics (accuracy, AUC, sensitivity, specificity) were computed, and prognostic analyses were conducted with a public dataset.Results The ensemble model outperformed each of the three base models, with the AUC of 0.931, accuracy of 0.872, sensitivity of 0.871, and specificity of 0.880 in the validation set. Robustness was further confirmed in independent test cohorts, yielding AUCs of 0.762 and 0.861. Furthermore, patients identified at high-risk by the model exhibited poor recurrence-free survival (RFS, HR = 8.117, p < 0.0001) and overall survival (OS, HR = 5.748, p < 0.0001), underscoring its prognostic value.Conclusions The ensemble model based on DCE-MRI effectively predicts positive margins and prognosis for BCS patients, facilitating the clinical decision-making on the surgery. Trial registration This study was approved by the Ethics Committee of the Yunnan Cancer Hospital (KYLX2023-134), Xiang'an Hospital of Xiamen University (XDYX202305K26), and Cancer Hospital of Shantou University Medical College (2024059). The study was also registered with the Chinese Clinical Trial Registry (ChiCTR2400083298, Registered 19 April 2024, https://www.chictr.org.cn/showproj.html?%20proj=207948 ).
SN - 1465-5411
SN - 1465-542X
ER -