Development of a nomogram for predicting malignancy in BI-RADS 4 breast lesions using contrast-enhanced ultrasound and shear wave elastography parameters

• Published in: Scientific reports Vol. 15; no. 1; pp. 1356 - 11
• Main Authors: Ren, Tiantian, Gao, Zhenzhen, Yang, Lufeng, Cheng, Weibo, Luo, Xiao
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 08.01.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 692/308; 692/4028; Adult; Aged; BI-RADS classification; Biopsy; Breast; Breast - diagnostic imaging; Breast - pathology; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Calibration; Contrast Media; Contrast-enhanced ultrasound quantitative parameters; Elasticity Imaging Techniques - methods; Female; Humanities and Social Sciences; Humans; LASSO regression; Lesions; Malignancy; Mechanical properties; Middle Aged; multidisciplinary; Nomogram; Nomograms; ROC Curve; Science; Science (multidisciplinary); Shear wave elastography parameters; Ultrasonic imaging; Ultrasonography, Mammary - methods; Ultrasound; LASSO regression; Contrast-enhanced ultrasound quantitative parameters; BI-RADS classification; Shear wave elastography parameters; Nomogram
• DOI: 10.1038/s41598-025-85862-x
• ISSN: 2045-2322

This study aimed to develop a Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression (LR) model using quantitative imaging features from Shear Wave Elastography (SWE) and Contrast-Enhanced Ultrasound (CEUS) to assess the malignancy risk of BI-RADS 4 breast lesions (BLs). The features predictive of malignancy in the LASSO analysis were used to construct a nomogram. 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 were enrolled in this study. The histopathological results served as the gold standard. A time-intensity curve (TIC) was used to analyze the peak intensity (PI), area under the curve (AUC), and other CEUS parameters. The Young’s modulus was used for the SWE analysis. Bootstrap sampling was used to validate the nomogram. The performance of the model was evaluated using calibration curves, receiver operator characteristics curve (ROC) analysis, and decision curve analysis (DCA). The histopathological analysis revealed 35 malignant and 76 benign BLs. The multivariate LR analysis identified PI (odds ratio [OR] = 5.788, p  < 0.05), AUC (OR = 6.920, p  < 0.05), and SWE_Max (OR = 10.802, p  < 0.05) as predictive of malignancy. The nomogram based on these features demonstrated an AUC of 0.875 (95% CI 0.805–0.945), sensitivity of 88.6%, specificity of 68.4%, good calibration, and excellent clinical utility. The nomogram could be used to improve the classification of BI-RADS 4 BLs and hence reduce the need for invasive biopsies to confirm malignancy.