Development and evaluation of artificial intelligence tools to estimate volumetric breast density from processed 2D mammograms
BJR|Artificial Intelligence · 23.01.2026 · 3 (1)
DOI: 10.1093/bjrai/ubag009 ↗Kurz gefasst
Fachartikel in der Zeitschrift BJR|Artificial Intelligence, online erschienen am 28.04.2026. Verfasst von Sam Ellis und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Scientific Computing, Royal Surrey NHS Foundation Trust, Guildford GU2 7XX, United Kingdom. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cancer Research UK, Million Women Study.
Abstract (Originalsprache)
Objectives
Artificial intelligence (AI) has shown promise for estimating volumetric breast density values from processed, “for presentation,” mammograms. However, previous evaluations have typically used small datasets or focused on a single vendor. In this study, we aimed to improve volumetric breast density estimation from processed mammograms for the three main UK vendors with a combination of improved training methods and the utilization of up-to-date data from the large OPTIMAM Mammography Image Database (OMI-DB).
Methods
Paired processed/unprocessed mammograms were obtained from OMI-DB. Ground-truth, image-level density values were calculated by passing unprocessed images through a commercial density estimation tool. AI tools, comprising feed-forward convolution neural networks, were then trained to reproduce these values from the corresponding processed mammograms.
Results
Patient-level AI predictions for volumetric breast density demonstrated strong correlation with ground-truth values derived from unprocessed image counterparts (r = 0.954-0.976). Models trained on less prevalent manufacturers performed worse (r = 0.954 compared to 0.976 for the most prevalent manufacturer), highlighting the importance of collecting larger training datasets in future. Error levels were higher in patients with dense breasts. Model performance was generally consistent across screening sites but correlated with patient age, possibly due to the correlation of age and breast density.
Conclusions
The presented models demonstrated good performance overall and were generally consistent across screening sites. Advances in knowledge The presented AI tools provide a means of estimating breast density from processed mammograms, enabling further research into breast cancer epidemiology and risk where only processed mammograms are available.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Scientific Computing, Royal Surrey NHS Foundation Trust, Guildford GU2 7XX, United Kingdom.
- Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford GU2 7XH, United Kingdom.
- National Co-ordinating Centre for the Physics of Mammography, Royal Surrey NHS Foundation Trust, Guildford GU2 7XX, United Kingdom.
- Department of Physics, University of Surrey, Guildford GU2 7XH, United Kingdom.
ORCID-Profile: Sam Ellis
Förderung
- Cancer Research UK
- Million Women Study
Zitieren
APA
Ellis, S., Gomes, S., Halling-Brown, M. D., Young, K. C., & Warren, L. M. (2026). Development and evaluation of artificial intelligence tools to estimate volumetric breast density from processed 2D mammograms. BJR|Artificial Intelligence, 3(1). https://doi.org/10.1093/bjrai/ubag009
Vancouver
Ellis S, Gomes S, Halling-Brown MD, Young KC, Warren LM. Development and evaluation of artificial intelligence tools to estimate volumetric breast density from processed 2D mammograms. BJR|Artificial Intelligence. 2026;3(1). doi:10.1093/bjrai/ubag009
BibTeX
@article{Ellis2026,
author = {Ellis, Sam and Gomes, Sandra and Halling-Brown, Mark D and Young, Kenneth C and Warren, Lucy M},
title = {Development and evaluation of artificial intelligence tools to estimate volumetric breast density from processed 2D mammograms},
journal = {BJR|Artificial Intelligence},
year = {2026},
volume = {3},
number = {1},
doi = {10.1093/bjrai/ubag009}
}
EUVIMED