Evaluation of diagnostic efficacy of multimode ultrasound in BI-RADS 4 breast neoplasms and establishment of a predictive model

Abstract

Objectives: To explore the diagnostic efficacy of ultrasound (US), two-dimensional and three-dimensional shear-wave elastography (2D-SWE and 3D-SWE), and contrast-enhanced ultrasound (CEUS) in breast neoplasms in category 4 based on the Breast Imaging Reporting and Data System (BI-RADS) from the American College of Radiology (ACR) and to develop a risk-prediction nomogram based on the optimal combination to provide a reference for the clinical management of BI-RADS 4 breast neoplasms.

Methods: From September 2021 to April 2022, a total of 104 breast neoplasms categorized as BI-RADS 4 by US were included in this prospective study. There were 78 breast neoplasms randomly assigned to the training cohort; the area under the receiver-operating characteristic curve (AUC), 95% confidence interval (95% CI), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 2D-SWE, 3D-SWE, CEUS, and their combination were analyzed and compared. The optimal combination was selected to develop a risk-prediction nomogram. The performance of the nomogram was assessed by a validation cohort of 26 neoplasms.

Results: Of the 78 neoplasms in the training cohort, 16 were malignant and 62 were benign. Among the 26 neoplasms in the validation cohort, 6 were malignant and 20 were benign. The AUC values of 2D-SWE, 3D-SWE, and CEUS were not significantly different. After a comparison of the different combinations, 2D-SWE+CEUS showed the optimal performance. Least absolute shrinkage and selection operator (LASSO) regression was used to filter the variables in this combination, and the variables included Emax, Eratio, enhancement mode, perfusion defect, and area ratio. Then, a risk-prediction nomogram with BI-RADS was built. The performance of the nomogram was better than that of the radiologists in the training cohort (AUC: 0.974 vs. 0.863). In the validation cohort, there was no significant difference in diagnostic accuracy between the nomogram and the experienced radiologists (AUC: 0.946 vs. 0.842).

Conclusions: US, 2D-SWE, 3D-SWE, CEUS, and their combination could improve the diagnostic efficiency of BI-RADS 4 breast neoplasms. The diagnostic efficacy of US+3D-SWE was not better than US+2D-SWE. US+2D-SWE+CEUS showed the optimal diagnostic performance. The nomogram based on US+2D-SWE+CEUS performs well.

Keywords: breast neoplasms; contrast media; elastography; nomograms; ultrasound.

Figure 1

The flowchart of this study.

Figure 2

ROC curve of the multimode ultrasound combination.

Figure 3

Ultrasonographic feature selection using the least absolute shrinkage and selection operator (LASSO) regression in the training cohort. (A) Lambda (λ) selection in the LASSO model used 10-fold cross-validation via minimum criteria. The value of λ was used to select features. Vertical lines were drawn at the optimal values using the minimum criteria and the 1-SE criteria. The optimal value of 0.0034 was selected. (B) Coefficient profiles of the 13 features.

Figure 4

(A) Nomogram with selected ultrasonographic feature and the BI-RADS category incorporated. Performance and clinical usefulness evaluation of the nomogram. (B) Calibration curves for the nomogram in the training cohort. (C) Decision curve analysis (DCA) derived from the training cohort.

Figure 5

ROC curves of the nomogram and the radiologist’s diagnosis derived from the training cohort (A) and the validation cohort (B).

Figure 6

In a 72-year-old woman, lesion size was 0.8 x 0.4 cm in the duct on B-mode imaging (A), considered to be BI-RADS category 4A. The lesion was homogeneously soft (blue color) in 2D-SWE (B) and 3D-SWE (C), indicating that it was benign. In CEUS (D), an inhomogeneous hyperenhancement of the lesion was noted, the boundary between the lesion and the surrounding gland was not clear, and the scope was larger than that of the B-mode, indicating malignancy. The risk degree of the nomogram (E) was less than 0.3, indicating a benign neoplasm. Pathology (F) showed that the lesion was intraductal papilloma.

Figure 7

In a 48-year-old woman, B-mode imaging (A) showed a 2.0 × 1.1-cm hypoechoic lesion below the nipple, considered to be BI-RADS category 4A. In 2D-SWE (B) and 3D-SWE (C), the lesion showed a polychrome or partly hard ring sign, indicating malignancy. In CEUS (D), the lesion showed inhomogeneous low–no enhancement and a well-defined margin, indicating a benign lesion. The risk degree of the nomogram (E) was less than 0.2, indicating a benign neoplasm. Pathology (F) showed that the lesion was a fibroadenoma.