Development of a Nomogram for Predicting Malignancy in BI-RADS 4 Breast Lesions Using Contrast-Enhanced Ultrasound and Shear Wave Elastography Parameters

Abstract

Background This study aimed to construct a Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression (LR) model using Shear Wave Elastography (SWE) and Contrast-Enhanced Ultrasound (CEUS) quantitative imaging features to accurately assess the malignant probability of Breast Imaging Reporting and Data System (BI-RADS) 4 breast lesions (BLs). Methods Female patients (n = 111) with BI-RADS 4 BLs detected via routine ultrasound at Ma'anshan People's Hospital underwent SWE, CEUS, and histopathological examinations. Histopathological results served as the benchmark. LASSO LR analysis with 10-fold cross-validation identified significant imaging features for malignancy prediction. A predictive nomogram was developed and validated with bootstrap sampling. Performance was assessed using calibration curves, Receiver Operating Characteristic (ROC) analysis, and decision curve analysis (DCA). Results Histopathological analysis revealed 35 malignant and 76 benign BLs. Significant features included peak intensity (PI) from CEUS (odds ratio [OR] = 5.788, p < 0.05), the area under the curve (AUC) from CEUS (OR = 6.920, p < 0.05), and Maximum Young’s Modulus (SWE_Max) from SWE (OR = 10.802, p < 0.05). The nomogram showed an AUC of 0.875 (95% CI: 0.805–0.945), sensitivity of 0.886, and specificity of 0.684, with good calibration and clinical utility. Conclusion The nomogram outperformed traditional BI-RADS methods, providing excellent predictive performance for distinguishing malignant from benign BI-RADS 4 BLs and reducing unnecessary biopsies.