Related Experiment Video
Updated: Apr 16, 2026
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
Reliability of automated breast density measurements
Olivier Alonzo-Proulx1, Gordon E Mawdsley, James T Patrie
1From the Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada (O.A., G.E.M., M.J.Y.); and Department of Public Health Sciences (J.T.P.) and Department of Radiology and Medical Imaging (J.A.H.), University of Virginia, Box 800170, Charlottesville, VA 22908.
Volpara and Quantra showed the lowest variability in repeated breast density measurements, suggesting they are more reliable for risk modeling. Cumulus ABD and CumulusV exhibited higher measurement variability.
Area of Science:
- Radiology
- Medical Imaging
- Biostatistics
Background:
- Accurate breast density measurement is crucial for mammography screening and breast cancer risk assessment.
- Automated methods offer potential for more consistent breast density assessment compared to manual methods.
Purpose of the Study:
- To evaluate the reliability of a two-dimensional area-based breast density method and three automated volumetric methods using repeated measurements.
- To compare the measurement agreement of different breast density algorithms.
Main Methods:
- Thirty women underwent repeat mammography examinations by a second technologist.
- Breast density was measured using Cumulus ABD (area-based), CumulusV, Volpara, and Quantra (volumetric methods).
- Bland-Altman analysis was used to assess limits of agreement for repeated measurements.
Main Results:
- Volpara and Quantra demonstrated significantly lower within-breast density measurement variability compared to Cumulus ABD and CumulusV.
- Standard deviations for repeated measurements were 0.99% for Volpara and 1.64% for Quantra.
- Larger discrepancies in breast density measurements were associated with higher density values for Cumulus ABD and CumulusV, but not for Volpara and Quantra.
Conclusions:
- Volpara and Quantra exhibit superior reliability for repeated breast density measurements.
- These more reliable volumetric methods may be better suited for integration into breast cancer risk models.
