Related Experiment Video
Updated: Jul 14, 2026
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
Published on: October 2, 2020
Multiparametric MRI-Based Prediction Model for Sentinel Lymph Node Metastasis in Breast Cancer: Integrating
Yao Zhang1, Zipei Wang1, Zhichao Li1
1Department of Radiology, Jingzhou No.1 People's Hospital, The First Affiliated Hospital of Yangtze University, Jingzhou, Hubei, 434000, People's Republic of China.
Background:
Sentinel lymph node metastasis (SLNM) status guides axillary staging and treatment planning in breast cancer, but conventional imaging has limited preoperative predictive accuracy.
Methods:
This retrospective study included 125 consecutive women with pathologically confirmed invasive breast cancer who underwent preoperative multiparametric MRI and sentinel lymph node biopsy between January 2022 and December 2024. Candidate predictors were assessed by univariate analysis and selected with least absolute shrinkage and selection operator regression using 5-fold cross-validation. A multivariable logistic regression model was evaluated for discrimination, calibration, and clinical utility, with internal validation by 1000 bootstrap resamples.
Results:
SLNM was present in 57 of 125 patients (45.6%). The final model retained ADC, T1 Map_post, T2* Map, and parity. The model showed excellent discrimination (AUC, 0.960; 95% CI, 0.927-0.985), good calibration (Brier score, 0.082), and positive net clinical benefit across threshold probabilities of approximately 10%-80%. Bootstrap validation yielded an optimism-corrected AUC of 0.956.
Conclusion:
A multiparametric MRI-based model incorporating ADC, T1 Map_post, T2* Map, and parity showed strong performance for preoperative SLNM prediction and may support individualized surgical planning after external validation.
