Preoperative prediction of positive margins in breast-conserving surgery using an ensemble model based on DCE-MRI: a multi-center retrospective and prospective study.
A brain-imaging tool predicts risky surgical margins before breast surgery and identifies patients needing closer monitoring after treatment.
This multi-center study (887 patients across three centers) developed a DCE-MRI ensemble model integrating deep learning and radiomics to preoperatively predict positive surgical margins in breast-conserving surgery, validated prospectively. The model's dual role — predicting margin status and stratifying survival risk — provides a clinically actionable decision-support tool for surgical planning in early breast cancer.
What the study was
- Study design
- Multi-center retrospective and prospective cohort study
- Population
- 887 breast cancer patients from three Chinese medical centers undergoing breast-conserving surgery
- Sample size
- 887
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- Breast Cancer Res
Why it surfaced
Multi-center prospective validation with AUC 0.931 and survival stratification establishes clinical readiness for breast margin prediction; directly addresses a major cause of surgical reoperation in breast cancer.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.