Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Assessing mammographic density change within individuals across screening rounds using deep learning–based software

Olinder, Jakob LU ; Förnvik, Daniel LU orcid ; Dahlblom, Victor LU orcid ; Lu, Viktor LU ; Åkesson, Anna LU ; Johnson, Kristin LU orcid and Zackrisson, Sophia LU (2025) In Journal of Medical Imaging 12.
Abstract

Purpose: The purposes are to evaluate the change in mammographic density within individuals across screening rounds using automatic density software, to evaluate whether a change in breast density is associated with a future breast cancer diagnosis, and to provide insight into breast density evolution. Approach: Mammographic breast density was analyzed in women screened in Malmö, Sweden, between 2010 and 2015 who had undergone at least two consecutive screening rounds <30 months apart. The volumetric and area-based densities were measured with deep learning–based software and fully automated software, respectively. The change in volumetric breast density percentage (VBD%) between two consecutive screening examinations was determined.... (More)

Purpose: The purposes are to evaluate the change in mammographic density within individuals across screening rounds using automatic density software, to evaluate whether a change in breast density is associated with a future breast cancer diagnosis, and to provide insight into breast density evolution. Approach: Mammographic breast density was analyzed in women screened in Malmö, Sweden, between 2010 and 2015 who had undergone at least two consecutive screening rounds <30 months apart. The volumetric and area-based densities were measured with deep learning–based software and fully automated software, respectively. The change in volumetric breast density percentage (VBD%) between two consecutive screening examinations was determined. Multiple linear regression was used to investigate the association between VBD% change in percentage points and future breast cancer, as well as the initial VBD%, adjusting for age group and the time between examinations. Examinations with potential positioning issues were removed in a sensitivity analysis. Results: In 26,056 included women, the mean VBD% decreased from 10.7% [95% confidence interval (CI) 10.6 to 10.8] to 10.3% (95% CI: 10.2 to 10.3) (p < 0.001) between the two examinations. The decline in VBD% was more pronounced in women with initially denser breasts (adjusted β ¼ −0.10, p < 0.001) and less pronounced in women with a future breast cancer diagnosis (adjusted β ¼ 0.16, p ¼ 0.02). Conclusions: The demonstrated density changes over time support the potential of using breast density change in risk assessment tools and provide insights for future risk-based screening.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
breast cancer risk, breast cancer screening, breast density, deep learning, longitudinal trends, mammography
in
Journal of Medical Imaging
volume
12
article number
S22017
publisher
SPIE
external identifiers
  • pmid:40823522
  • scopus:105015380487
ISSN
2329-4302
DOI
10.1117/1.JMI.12.S2.S22017
language
English
LU publication?
yes
id
8a19f04a-07f9-4c03-9fc0-74d405315af3
date added to LUP
2025-10-03 13:30:54
date last changed
2025-10-04 03:00:10
@article{8a19f04a-07f9-4c03-9fc0-74d405315af3,
  abstract     = {{<p>Purpose: The purposes are to evaluate the change in mammographic density within individuals across screening rounds using automatic density software, to evaluate whether a change in breast density is associated with a future breast cancer diagnosis, and to provide insight into breast density evolution. Approach: Mammographic breast density was analyzed in women screened in Malmö, Sweden, between 2010 and 2015 who had undergone at least two consecutive screening rounds &lt;30 months apart. The volumetric and area-based densities were measured with deep learning–based software and fully automated software, respectively. The change in volumetric breast density percentage (VBD%) between two consecutive screening examinations was determined. Multiple linear regression was used to investigate the association between VBD% change in percentage points and future breast cancer, as well as the initial VBD%, adjusting for age group and the time between examinations. Examinations with potential positioning issues were removed in a sensitivity analysis. Results: In 26,056 included women, the mean VBD% decreased from 10.7% [95% confidence interval (CI) 10.6 to 10.8] to 10.3% (95% CI: 10.2 to 10.3) (p &lt; 0.001) between the two examinations. The decline in VBD% was more pronounced in women with initially denser breasts (adjusted β ¼ −0.10, p &lt; 0.001) and less pronounced in women with a future breast cancer diagnosis (adjusted β ¼ 0.16, p ¼ 0.02). Conclusions: The demonstrated density changes over time support the potential of using breast density change in risk assessment tools and provide insights for future risk-based screening.</p>}},
  author       = {{Olinder, Jakob and Förnvik, Daniel and Dahlblom, Victor and Lu, Viktor and Åkesson, Anna and Johnson, Kristin and Zackrisson, Sophia}},
  issn         = {{2329-4302}},
  keywords     = {{breast cancer risk; breast cancer screening; breast density; deep learning; longitudinal trends; mammography}},
  language     = {{eng}},
  publisher    = {{SPIE}},
  series       = {{Journal of Medical Imaging}},
  title        = {{Assessing mammographic density change within individuals across screening rounds using deep learning–based software}},
  url          = {{http://dx.doi.org/10.1117/1.JMI.12.S2.S22017}},
  doi          = {{10.1117/1.JMI.12.S2.S22017}},
  volume       = {{12}},
  year         = {{2025}},
}