Related Experiment Video
Updated: May 8, 2026
Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis
Published on: February 6, 2020
Radiologist assessment of breast density by BI-RADS categories versus fully automated volumetric assessment
Hye Mi Gweon1, Ji Hyun Youk, Jeong-Ah Kim
1Department of Radiology, Gangnam Severance Hospital, Yonsei University College of Medicine, 211 Eonju-ro, Dogok-Dong, Gangnam-Gu, Seoul 135-720, South Korea.
Objective:
The objective of our study was to estimate mammographic breast density using a fully automated volumetric breast density measurement method in comparison with BI-RADS breast density categories determined by radiologists.
Materials And Methods:
A total of 791 full-field digital mammography examinations with standard views were evaluated by three blinded radiologists as BI-RADS density categories 1-4. For fully automated volumetric analysis, volumetric breast density was calculated with fully automated software. The volume of fibroglandular tissue, the volume of the breast, and the volumetric percentage density were provided.
Results:
The weighted overall kappa was 0.48 (moderate agreement) for the three radiologists' estimates of BI-RADS density. Pairwise comparisons of the radiologists' measurements of BI-RADS density revealed moderate to substantial agreement, with kappa values ranging from 0.51 to 0.64. There was a significant difference in mean volumetric breast density among the BI-RADS density categories, and the mean volumetric breast density increased as the BI-RADS density category increased (p<0.001). A significant positive correlation was found between BI-RADS categories and fully automated volumetric breast density (ρ=0.765, p<0.001).
Conclusion:
Our study showed good correlation of the fully automated volumetric method with radiologist-assigned BI-RADS density categories. Mammographic density assessment with the fully automated volumetric method may be used to assign BI-RADS density categories.
