What question did this study set out to answer?

The study aims to create and validate a model using ultrasound radiomics to distinguish between benign and malignant breast lesions.

June 26, 2026Open Access

Development and validation of an interpretable ultrasound radiomics model for benign and malignant classification of breast lesions: a multicenter large-sample study

Key Points

The study aims to create and validate a model using ultrasound radiomics to distinguish between benign and malignant breast lesions.
Included 3142 patients from eight hospitals in a multicenter retrospective study with additional single-center prospective testing.
Radiomics features were extracted from manually segmented lesions to create multiple machine learning models.
Combined the best radiomics model with clinical features and evaluated performance using AUC metrics across various test sets.
The combined model achieved AUCs of 0.92, 0.90, 0.92, and 0.93 across training and test cohorts.
Logistic regression showed consistent performance with AUC values of 0.83 to 0.82 across different stages.
The combined model indicated a potential to reduce unnecessary biopsies while maintaining diagnostic sensitivity.

Abstract

Abstract Objectives To develop and validate a combined ultrasound-based radiomics-clinical model for differentiating benign and malignant breast lesions. Materials and methods A total of 3142 patients from eight hospitals between February 2012 and September 2024 were included in this multicenter retrospective development and validation study, with an additional single-center prospective test cohort. Lesions were manually segmented, and radiomics features were automatically extracted to construct five machine learning models. The best-performing radiomics model was combined with clinical features to build a combined model. Model performance and its impact on Breast Imaging Reporting and Data System (BI-RADS)-based biopsy decisions were evaluated. Results Logistic regression (LR) showed the best radiomics performance, with area under the curves (AUCs) of 0.83, 0.82, 0.81, and 0.82 across the training, internal test, external test, and prospective test sets. The clinical model achieved AUCs of 0.87, 0.85, 0.87, and 0.86, whereas the combined model achieved AUCs of 0.92, 0.90, 0.92, and 0.93, significantly outperforming both single-modality models (all p < 0.01). Decision curve analysis (DCA) showed that the combined model had a higher net benefit than the other models across a broad range of threshold probabilities (0.05–0.95) in this study. Performance remained stable across lesion size and age subgroups. In the reclassification analysis, the model suggested the potential to influence biopsy recommendations without a significant reduction in sensitivity and to increase the malignancy yield in BI-RADS 4a. Shapley additive explanations (SHAP) analysis provided clinically interpretable feature contributions. Conclusion The interpretable ultrasound-based radiomics model enables reliable, noninvasive breast lesion diagnosis and may reduce unnecessary biopsies. Critical relevance statement This work developed an interpretable radiomics-clinical combined model in a multicenter retrospective development and validation study, with additional testing in a single-center prospective cohort, and may support breast lesion risk stratification and biopsy decision-making after further prospective clinical utility evaluation. Key Points Conventional ultrasound diagnosis of breast cancer shows limited specificity. A multicenter radiomics-clinical combined model showed improved diagnostic performance, with additional validation in a prospective test cohort.

Mark Helpful

Bookmark

Relay

View Full Paper