Correlation Analysis and Construction of a Predictive Model Between Contrast-Enhanced Ultrasound Features and the Risk of Recurrence in Granulomatous Mastitis

Abstract

Background

Granulomatous mastitis (GM) is an inflammatory breast condition with high recurrence risk, often complicating management. Existing imaging techniques provide limited predictive insight. This study aims to analyze the correlation between contrast-enhanced ultrasound (CEUS) features and the risk of GM recurrence, developing a predictive model.

Methods

A retrospective review included 510 patients diagnosed with GM from 2017 to 2022, divided into non-recurrence (non-recurrence, n = 389) and recurrence (recurrence, n = 121) groups. CEUS was conducted to assess lesion perfusion and enhancement patterns. Key features such as isoenhancement and perfusion defects were analyzed. Correlation analyses, ROC, univariate, and multivariate analyses informed the predictive model construction using XGBoost. External validation was performed to confirm model reliability.

Results

CEUS features like homogeneous (rho = 0.137, P = 0.002) and heterogeneous isoenhancement (rho = 0.134, P = 0.002) showed significant correlations with recurrence risk. Perfusion defects (rho = 0.127, P = 0.004) and not smooth edge lines of defects (rho = 0.234, P < 0.001) were also associated. The predictive model, integrating CEUS patterns, achieved an area under the curve (AUC) of 0.822, indicating strong predictive validity. External validation confirmed the model's efficacy (AUC = 0.808).

Conclusion

CEUS imaging reveals specific vascular and enhancement patterns that correlate with the risk of GM recurrence, providing critical diagnostic and prognostic value.