Prediction of mammographic breast density based on clinical breast ultrasound images using deep learning: a retrospective analysis.
Authors
Affiliations (5)
Affiliations (5)
- Department of Information and Computer Sciences, University of Hawai'i at Mānoa, POST Bldg, 1860 East-West Rd, Honolulu, HI, 96822, USA.
- University of Hawai'i Cancer Center, 701 Ilalo St, Honolulu, HI, 96813, USA.
- The Queen's Medical Center, 1301 Punchbowl Street, Honolulu, HI, 96813, USA.
- Hawai'i Pacific Health, 55 Merchant St., Honolulu, HI, 96813, USA.
- Hawai'i Diagnostic Radiology Services (St. Francis), 2230 Liliha Street, Suite 106, Honolulu, HI, 96817, USA.
Abstract
Breast density, as derived from mammographic images and defined by the Breast Imaging Reporting & Data System (BI-RADS), is one of the strongest risk factors for breast cancer. Breast ultrasound is an alternative breast cancer screening modality, particularly useful in low-resource, rural contexts. To date, breast ultrasound has not been used to inform risk models that need breast density. The purpose of this study is to explore the use of artificial intelligence (AI) to predict BI-RADS breast density category from clinical breast ultrasound imaging. We compared deep learning methods for predicting breast density directly from breast ultrasound imaging, as well as machine learning models from breast ultrasound image gray-level histograms alone. The use of AI-derived breast ultrasound breast density as a breast cancer risk factor was compared to clinical BI-RADS breast density. Retrospective (2009-2022) breast ultrasound data were split by individual into 70/20/10% groups for training, validation, and held-out testing for reporting results. 405,120 clinical breast ultrasound images from 14,066 women (mean age 53 years, range 18-99 years) with clinical breast ultrasound exams were retrospectively selected for inclusion from three institutions: 10,393 training (302,574 images), 2593 validation (69,842), and 1074 testing (28,616). The AI model achieves AUROC 0.854 in breast density classification and statistically significantly outperforms all image statistic-based methods. In an existing clinical 5-year breast cancer risk model, breast ultrasound AI and clinical breast density predict 5-year breast cancer risk with 0.606 and 0.599 AUROC (DeLong's test p-value: 0.67), respectively. BI-RADS breast density can be estimated from breast ultrasound imaging with high accuracy. The AI model provided superior estimates to other machine learning approaches. Furthermore, we demonstrate that age-adjusted, AI-derived breast ultrasound breast density provides similar predictive power to mammographic breast density in our population. Estimated breast density from ultrasound may be useful in performing breast cancer risk assessment in areas where mammography may not be available. National Cancer Institute.