# Effect of a Real-Time Artificial Intelligence-Assisted Ultrasound System on BI-RADS C4 Breast Lesions Based on Breast Density

## TL;DR

An AI-assisted ultrasound system performs better in dense breasts, potentially reducing unnecessary biopsies for suspicious breast lesions.

## Contribution

The study demonstrates that AI-assisted ultrasound systems have higher diagnostic accuracy in dense breasts, particularly for BI-RADS C4 lesions.

## Key findings

- AI-assisted ultrasound showed higher sensitivity, specificity, and accuracy in extremely dense breasts.
- Diagnostic performance metrics improved with increasing breast density, with the highest accuracy in density D category.
- Non-benign lesions consistently had higher probability of malignancy values across all density groups.

## Abstract

Breast ultrasound is widely used to evaluate suspicious breast lesions, particularly in women with dense breasts, but many BI-RADS C4 lesions ultimately prove to be benign and still undergo biopsy. Artificial intelligence (AI)-assisted ultrasound systems have been developed to support diagnostic decision-making, yet their performance may vary according to breast density. In this study, we evaluated an AI-based ultrasound system in 110 BI-RADS C4 breast lesions and analyzed its diagnostic performance across different mammographic breast density categories. The AI system showed higher sensitivity, specificity, and overall accuracy as breast density increased, with the best performance observed in extremely dense breasts. Conversely, lower-density breasts showed more false-positive results, likely due to heterogeneous background tissue. These findings suggest that breast density is an important factor influencing AI performance in breast ultrasound. AI-assisted ultrasound is useful as a decision-support tool for reducing unnecessary biopsies in women with dense breasts.

Background: Artificial intelligence-based computer-aided diagnosis (AI-CAD) systems are increasingly used in breast ultrasonography; however, their diagnostic performance may vary with breast density. Given that dense breasts are highly prevalent among Asian women, understanding this relationship is essential for optimizing AI-assisted imaging strategies. Therefore, this study aims to evaluate the effect of breast density on the diagnostic accuracy of an AI-CAD ultrasound system in BI-RADS category 4 (C4) breast lesions. Methods: Overall, 110 consecutive BI-RADS C4 lesions were reviewed between January and December 2023. An AI-CAD ultrasound system automatically assigned BI-RADS categories and calculated the probability of malignancy (POM) using static ultrasound images. Histopathology served as the reference standard, with atypia and malignancy combined into a non-benign category. Diagnostic performance—including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and overall accuracy—was analyzed based on breast density (BI-RADS B–D), determined using AI-assisted mammography. Results: Overall, the sensitivity and NPV were 81.3% and 87.5%, respectively, while the specificity and PPV were lower at 53.8% and 41.9%. All diagnostic performance metrics improved with increasing breast density. In the density D category, sensitivity (92.3%), specificity (61.5%), NPV (96.0%), and accuracy (69.2%) were highest. Additionally, concordance between AI-assigned BI-RADS categories and histopathologic diagnoses increased with density (B: 50.0%, C: 57.5%, D: 67.3%). Across all density groups, non-benign lesions consistently demonstrated higher POM values. Conclusions: Breast density significantly affects the diagnostic performance of AI-CAD ultrasound in BI-RADS C4 lesions. The AI system demonstrates higher accuracy and concordance in dense breasts, suggesting more consistent lesion interpretation in high-density environments. These findings highlight the potential utility of AI-assisted ultrasound as a diagnostic adjunct, particularly for Asian women, who commonly have dense breast composition. Further multicenter, real-time validation studies are warranted to validate these findings.