Interpretable machine learning model based on MRI radiomics for predicting sentinel lymph node metastasis after neoadjuvant therapy in breast cancer_CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY

Authors：

YANG Aisen ¹ , JIN Mingli ^2,3 , HUANG Deqing ¹ ,  QIN Na ¹ , PENG Yimeng ⁴ ,  LI Jun ¹

1. Institute of System Science and Technology, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, P. R. China;
2. Department of Radiology, Affiliated Hospital of Southwest Medical University, Luzhou, Sichuan 646099, P. R. China;
3. Department of Radiology, The Second Affiliated Hospital of Chengdu Medical College, Nuclear Industry 416 Hospital, Chengdu 610051, P. R. China;
4. Department of Radiology, Suining Central Hospital, Suining, Sichuan 629000, P. R. China;

Corresponding author：

QIN Na, Email: qinna@swjtu.edu.cn; LI Jun, Email: dirk.li@outlook.com

Keywords：

breast cancer; neoadjuvant therapy; sentinel lymph node; magnetic resonance imaging; radiomics

DOI：

10.7507/1007-9424.202505079

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To investigate the value of a predictive model for sentinel lymph node (SLN) metastasis after neoadjuvant therapy (NAT) based on the radiomic features from multi-modality magnetic resonance imaging (MRI) in combination with clinicopathologic data. Methods The clinical data and MRI images of breast cancer patients (initially diagnosed with cN0, all underwent NAT and surgical treatment) from two hospitals (Affiliated Hospital of Southwest Medical University and Suining Central Hospital) from January 2018 to September 2024, were retrospectively collected. The radiomic features from the multi-modality images, including T2-weighted short tau inversion recovery (T2STIR), diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE), were extracted and selected. The predictive models for SLN metastasis after NAT were constructed using four algorithms: LightGBM, XGBoost, support vector machine (SVM), and logistic regression (LR), in combination with clinicopathologic data. The models were evaluated for performance and interpretability using receiver operating characteristic (ROC) curves, calibration curves, decision curve analysis, and Shapley additive explanation (SHAP) analysis. Results A total of 236 breast cancer patients were enrolled in this study. Among them, 216 patients from the Southwest Medical University were subdivided in an 8∶2 ratio into a training set (n=173) and internal validation set (n=43), while 20 patients from the Suining Central Hospital served as the external validation set. The multivariate logistic regression analysis showed that the lymphovascular invasion [OR (95%CI)=21.215 (4.404, 102.202), P ＜0.001] and perineural invasion [OR (95%CI)=25.867 (1.870, 357.790), P=0.002] were the risk factors, while high Ki-67 expression [OR (95%CI)=0.119 (0.035, 0.404), P＜0.001] was the protective factor of SLN metastasis after NAT. The predictive models utilizing multi-modality MRI and clinicopathologic data yielded area under the ROC curve values of the internal and external validation sets of 0.750 [95%CI=(0.395, 1.000)] / 0.625 [95%CI=(0.321, 0.926)] for LightGBM, 0.878 [95%CI=(0.707, 1.000)] / 0.778 [95%CI=(0.525, 0.986)] for XGBoost, 0.641 [95%CI=(0.488, 0.795)] / 0.681 [95%CI=(0.345, 1.000)] for SVM, and 0.667 [95%CI=(0.357, 0.945)] / 0.583 [95%CI=(0.196, 0.969)] for LR. The XGBoost demonstrated the best predictive performance. Further SHAP analysis revealed that the lymphovascular invasion, T2STAR-MRI_FIRSTORDER_Minimum, and platelet were the key features influencing the predictions of the models. Conclusion The findings of this study suggest that XGBoost prediction model based on radiomic features derived from multi-modality MRI (T2STIR, DWI, and DCE) in combination with clinicopathologic data is able to predict SLN metastasis after NAT in patients with breast cancer.

Citation： YANG Aisen, JIN Mingli, HUANG Deqing, QIN Na, PENG Yimeng, LI Jun. Interpretable machine learning model based on MRI radiomics for predicting sentinel lymph node metastasis after neoadjuvant therapy in breast cancer. CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY, 2025, 32(7): 808-818. doi: 10.7507/1007-9424.202505079 Copy

1.	陈伟玲, 张国君. 乳腺癌新辅助治疗中外指南对比解读. 中国肿瘤外科杂志, 2023, 15(3): 219-224.
2.	Korde LA, Somerfield MR, Carey LA, et al. Neoadjuvant chemotherapy, endocrine therapy, and targeted therapy for breast cancer: ASCO guideline. J Clin Oncol, 2021, 39(13): 1485-1505.
3.	Tjan-Heijnen V, Viale G. The lymph node and the metastasis. N Engl J Med, 2018, 378(21): 2045-2046.
4.	毕钊, 王永胜. 乳腺癌新辅助治疗策略与手术时机. 中国实用外科杂志, 2021, 41(11): 1220-1225.
5.	Brackstone M, Baldassarre FG, Perera FE, et al. Management of the axilla in early-stage breast cancer: Ontario health (Cancer Care Ontario) and ASCO guideline. J Clin Oncol, 2021, 39(27): 3056-3082.
6.	Zarifmahmoudi L, Aghaee A, Treglia G, et al. Sentinel lymph node mapping in breast cancer patients following neoadjuvant chemotherapy: systematic review and meta-analysis about head to head comparison of cN0 and cN⁺ patients. Breast Cancer, 2022, 29(1): 50-64.
7.	Chen M, Kong C, Lin G, et al. Development and validation of convolutional neural network-based model to predict the risk of sentinel or non-sentinel lymph node metastasis in patients with breast cancer: a machine learning study. EClinicalMedicine, 2023, 63: 102176. doi: 10.1016/j.eclinm.2023.102176.
8.	朱娅娣. 基于磁共振多参数影像组学术前预测乳腺癌前哨淋巴结转移的研究. 苏州: 苏州大学, 2024.
9.	张雪丽, 王孟瑶, 杨志豪, 等. 人工智能在乳腺癌磁共振诊断中的研究进展. 磁共振成像, 2025, 16(3): 184-189.
10.	Lin SQ, Vo NP, Yen YC, et al. Outcomes of sentinel node biopsy for women with breast cancer after neoadjuvant therapy: Systematic review and meta-analysis of real-world data. Ann Surg Oncol, 2022, 29(5): 3038-3049.
11.	于理想, 余之刚. 乳腺癌新辅助治疗前哨淋巴结处理原则. 中国实用外科杂志, 2021, 41(11): 1230-1234.
12.	Wang X, Wang X, Zhang Y, et al. Development of the prediction model based on clinical-imaging omics: molecular typing and sentinel lymph node metastasis of breast cancer. Ann Transl Med, 2022, 10(13): 749. doi: 10.21037/atm-22-2844.
13.	Tan YY, Wu CT, Fan YG, et al. Primary tumor characteristics predict sentinel lymph node macrometastasis in breast cancer. Breast J, 2005, 11(5): 338-343.
14.	Chen M, Palleschi S, Khoynezhad A, et al. Role of primary breast cancer characteristics in predicting positive sentinel lymph node biopsy results: a multivariate analysis. Arch Surg, 2002, 137(5): 606-609.
15.	Yoshida A, Kojima Y, Tazo M, et al. Can sentinel node biopsy after neoadjuvant systemic chemotherapy (NAC) be safely omitted in selected patients with early breast cancer? J Clin Oncol, 2020, 38(15_suppl): 564. doi: 10.1200/JCO.2020.38.15_suppl.564.
16.	Yuan J, Xiong J, Yang J, et al. Machine learning-based 28-day mortality prediction model for elderly neurocritically ill patients. Comput Methods Programs Biomed, 2025, 260: 108589. doi: 10.1016/j.cmpb.2025.108589.
17.	Li L, Cui X, Yang J, et al. Using feature optimization and LightGBM algorithm to predict the clinical pregnancy outcomes after in vitro fertilization. Front Endocrinol (Lausanne), 2023, 14: 1305473. doi: 10.3389/fendo.2023.1305473.
18.	Rakha EA, Martin S, Lee AH, et al. The prognostic significance of lymphovascular invasion in invasive breast carcinoma. Cancer, 2012, 118(15): 3670-3680.Rakha EA, Martin S, Lee AH, et al. The prognostic significance of lymphovascular invasion in invasive breast carcinoma. Cancer, 2012, 118(15): 3670-3680.
19.	Edge SB, Compton CC. The American Joint Committee on cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM. Ann Surg Oncol, 2010, 17(6): 1471-1474.Edge SB, Compton CC. The American Joint Committee on cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM. Ann Surg Oncol, 2010, 17(6): 1471-1474.
20.	Dong Y, Feng Q, Yang W, et al. Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI. Eur Radiol, 2018, 28(2): 582-591.Dong Y, Feng Q, Yang W, et al. Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI. Eur Radiol, 2018, 28(2): 582-591.
21.	Wang L, Zhang K, Feng J, et al. The progress of platelets in breast cancer. Cancer Manag Res, 2023, 15: 811-821.
22.	Zha HL, Zong M, Liu XP, et al. Preoperative ultrasound-based radiomics score can improve the accuracy of the Memorial Sloan Kettering Cancer Center nomogram for predicting sentinel lymph node metastasis in breast cancer. Eur J Radiol, 2021, 135: 109512. doi: 10.1016/j.ejrad.2020.109512.
23.	江宁祥, 曹迪, 李振宇, 等. 肿瘤恶性增殖及侵袭相关基因在乳腺癌组织中表达水平与前哨淋巴结阳性数相关性分析. 中国医药, 2021, 16(8): 1236-1240.

1. 陈伟玲, 张国君. 乳腺癌新辅助治疗中外指南对比解读. 中国肿瘤外科杂志, 2023, 15(3): 219-224.
2. Korde LA, Somerfield MR, Carey LA, et al. Neoadjuvant chemotherapy, endocrine therapy, and targeted therapy for breast cancer: ASCO guideline. J Clin Oncol, 2021, 39(13): 1485-1505.
3. Tjan-Heijnen V, Viale G. The lymph node and the metastasis. N Engl J Med, 2018, 378(21): 2045-2046.
4. 毕钊, 王永胜. 乳腺癌新辅助治疗策略与手术时机. 中国实用外科杂志, 2021, 41(11): 1220-1225.
5. Brackstone M, Baldassarre FG, Perera FE, et al. Management of the axilla in early-stage breast cancer: Ontario health (Cancer Care Ontario) and ASCO guideline. J Clin Oncol, 2021, 39(27): 3056-3082.
6. Zarifmahmoudi L, Aghaee A, Treglia G, et al. Sentinel lymph node mapping in breast cancer patients following neoadjuvant chemotherapy: systematic review and meta-analysis about head to head comparison of cN0 and cN⁺ patients. Breast Cancer, 2022, 29(1): 50-64.
7. Chen M, Kong C, Lin G, et al. Development and validation of convolutional neural network-based model to predict the risk of sentinel or non-sentinel lymph node metastasis in patients with breast cancer: a machine learning study. EClinicalMedicine, 2023, 63: 102176. doi: 10.1016/j.eclinm.2023.102176.
8. 朱娅娣. 基于磁共振多参数影像组学术前预测乳腺癌前哨淋巴结转移的研究. 苏州: 苏州大学, 2024.
9. 张雪丽, 王孟瑶, 杨志豪, 等. 人工智能在乳腺癌磁共振诊断中的研究进展. 磁共振成像, 2025, 16(3): 184-189.
10. Lin SQ, Vo NP, Yen YC, et al. Outcomes of sentinel node biopsy for women with breast cancer after neoadjuvant therapy: Systematic review and meta-analysis of real-world data. Ann Surg Oncol, 2022, 29(5): 3038-3049.
11. 于理想, 余之刚. 乳腺癌新辅助治疗前哨淋巴结处理原则. 中国实用外科杂志, 2021, 41(11): 1230-1234.
12. Wang X, Wang X, Zhang Y, et al. Development of the prediction model based on clinical-imaging omics: molecular typing and sentinel lymph node metastasis of breast cancer. Ann Transl Med, 2022, 10(13): 749. doi: 10.21037/atm-22-2844.
13. Tan YY, Wu CT, Fan YG, et al. Primary tumor characteristics predict sentinel lymph node macrometastasis in breast cancer. Breast J, 2005, 11(5): 338-343.
14. Chen M, Palleschi S, Khoynezhad A, et al. Role of primary breast cancer characteristics in predicting positive sentinel lymph node biopsy results: a multivariate analysis. Arch Surg, 2002, 137(5): 606-609.
15. Yoshida A, Kojima Y, Tazo M, et al. Can sentinel node biopsy after neoadjuvant systemic chemotherapy (NAC) be safely omitted in selected patients with early breast cancer? J Clin Oncol, 2020, 38(15_suppl): 564. doi: 10.1200/JCO.2020.38.15_suppl.564.
16. Yuan J, Xiong J, Yang J, et al. Machine learning-based 28-day mortality prediction model for elderly neurocritically ill patients. Comput Methods Programs Biomed, 2025, 260: 108589. doi: 10.1016/j.cmpb.2025.108589.
17. Li L, Cui X, Yang J, et al. Using feature optimization and LightGBM algorithm to predict the clinical pregnancy outcomes after in vitro fertilization. Front Endocrinol (Lausanne), 2023, 14: 1305473. doi: 10.3389/fendo.2023.1305473.
18. Rakha EA, Martin S, Lee AH, et al. The prognostic significance of lymphovascular invasion in invasive breast carcinoma. Cancer, 2012, 118(15): 3670-3680.Rakha EA, Martin S, Lee AH, et al. The prognostic significance of lymphovascular invasion in invasive breast carcinoma. Cancer, 2012, 118(15): 3670-3680.
19. Edge SB, Compton CC. The American Joint Committee on cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM. Ann Surg Oncol, 2010, 17(6): 1471-1474.Edge SB, Compton CC. The American Joint Committee on cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM. Ann Surg Oncol, 2010, 17(6): 1471-1474.
20. Dong Y, Feng Q, Yang W, et al. Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI. Eur Radiol, 2018, 28(2): 582-591.Dong Y, Feng Q, Yang W, et al. Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI. Eur Radiol, 2018, 28(2): 582-591.
21. Wang L, Zhang K, Feng J, et al. The progress of platelets in breast cancer. Cancer Manag Res, 2023, 15: 811-821.
22. Zha HL, Zong M, Liu XP, et al. Preoperative ultrasound-based radiomics score can improve the accuracy of the Memorial Sloan Kettering Cancer Center nomogram for predicting sentinel lymph node metastasis in breast cancer. Eur J Radiol, 2021, 135: 109512. doi: 10.1016/j.ejrad.2020.109512.
23. 江宁祥, 曹迪, 李振宇, 等. 肿瘤恶性增殖及侵袭相关基因在乳腺癌组织中表达水平与前哨淋巴结阳性数相关性分析. 中国医药, 2021, 16(8): 1236-1240.

CHINESE JOURNAL OF BASES AND CLINICS IN GENERAL SURGERY

Interpretable machine learning model based on MRI radiomics for predicting sentinel lymph node metastasis after neoadjuvant therapy in breast cancer

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content