Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

The effect of breast density on the performance of deep learning-based breast cancer detection methods for mammography

Dustler, Magnus LU ; Dahlblom, Victor LU orcid ; Tingberg, Anders LU and Zackrisson, Sophia LU (2020) 15th International Workshop on Breast Imaging, IWBI 2020 In Proceedings of SPIE - The International Society for Optical Engineering 11513.
Abstract

Mammographic sensitivity in breasts with higher density has been questioned. Higher breast density is also linked to an increased risk for breast cancer. Even though digital breast tomosynthesis (DBT) offers an attractive solution, for varied reasons it has not yet been widely adopted in screening. An alternative could be to boost the performance of standard mammography by using computer-aided detection based on deep learning, but it remains to be proven how such methods are affected by density. A deep-learning based computer-aided detection program was used to score the suspicion of cancer on a scale of 1 to 10. A set of 13838 mammography screening exams were used. All cases had BIRADS density values available. The set included 2304... (More)

Mammographic sensitivity in breasts with higher density has been questioned. Higher breast density is also linked to an increased risk for breast cancer. Even though digital breast tomosynthesis (DBT) offers an attractive solution, for varied reasons it has not yet been widely adopted in screening. An alternative could be to boost the performance of standard mammography by using computer-aided detection based on deep learning, but it remains to be proven how such methods are affected by density. A deep-learning based computer-aided detection program was used to score the suspicion of cancer on a scale of 1 to 10. A set of 13838 mammography screening exams were used. All cases had BIRADS density values available. The set included 2304 exams (11 cancers) in BIRADS 1, 5310 (51 cancers) in BIRADS 2, 4844 (73 cancers) in BIRADS 3 and 1223 (22 cancers) in BIRADS 4. A Kruskal-Wallis analysis of variance showed no statistically significant differences between the cancer risk scores of the density categories for cases diagnosed with cancer (P=0.9225). An identical analysis for cases without cancer, showed significant differences between the density categories (P<0.0001). The results suggest that the risk categorization of the deep-learning software is not affected by density, as though some density categories receive higher risk assessments in general, this does not hold for cancer cases, which show uniformly high risk values despite density. This shows the potential for deep-learning to improve screening sensitivity even for women with high density breasts.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Breast, Breast density, Computer aided detection, Deep learning, Mammography, Screening
host publication
15th International Workshop on Breast Imaging, IWBI 2020
series title
Proceedings of SPIE - The International Society for Optical Engineering
editor
Bosmans, Hilde ; Marshall, Nicholas and Van Ongeval, Chantal
volume
11513
article number
1151324
publisher
SPIE
conference name
15th International Workshop on Breast Imaging, IWBI 2020
conference location
Leuven, Belgium
conference dates
2020-05-25 - 2020-05-27
external identifiers
  • scopus:85086140472
ISSN
1996-756X
0277-786X
ISBN
9781510638310
DOI
10.1117/12.2564328
project
Can breast cancer screening be improved with artificial intelligence?
language
English
LU publication?
yes
id
1a1d83d8-a05c-41da-a365-9e2ff9995a6e
date added to LUP
2021-01-11 12:10:57
date last changed
2024-03-20 23:09:04
@inproceedings{1a1d83d8-a05c-41da-a365-9e2ff9995a6e,
  abstract     = {{<p>Mammographic sensitivity in breasts with higher density has been questioned. Higher breast density is also linked to an increased risk for breast cancer. Even though digital breast tomosynthesis (DBT) offers an attractive solution, for varied reasons it has not yet been widely adopted in screening. An alternative could be to boost the performance of standard mammography by using computer-aided detection based on deep learning, but it remains to be proven how such methods are affected by density. A deep-learning based computer-aided detection program was used to score the suspicion of cancer on a scale of 1 to 10. A set of 13838 mammography screening exams were used. All cases had BIRADS density values available. The set included 2304 exams (11 cancers) in BIRADS 1, 5310 (51 cancers) in BIRADS 2, 4844 (73 cancers) in BIRADS 3 and 1223 (22 cancers) in BIRADS 4. A Kruskal-Wallis analysis of variance showed no statistically significant differences between the cancer risk scores of the density categories for cases diagnosed with cancer (P=0.9225). An identical analysis for cases without cancer, showed significant differences between the density categories (P&lt;0.0001). The results suggest that the risk categorization of the deep-learning software is not affected by density, as though some density categories receive higher risk assessments in general, this does not hold for cancer cases, which show uniformly high risk values despite density. This shows the potential for deep-learning to improve screening sensitivity even for women with high density breasts.</p>}},
  author       = {{Dustler, Magnus and Dahlblom, Victor and Tingberg, Anders and Zackrisson, Sophia}},
  booktitle    = {{15th International Workshop on Breast Imaging, IWBI 2020}},
  editor       = {{Bosmans, Hilde and Marshall, Nicholas and Van Ongeval, Chantal}},
  isbn         = {{9781510638310}},
  issn         = {{1996-756X}},
  keywords     = {{Breast; Breast density; Computer aided detection; Deep learning; Mammography; Screening}},
  language     = {{eng}},
  publisher    = {{SPIE}},
  series       = {{Proceedings of SPIE - The International Society for Optical Engineering}},
  title        = {{The effect of breast density on the performance of deep learning-based breast cancer detection methods for mammography}},
  url          = {{http://dx.doi.org/10.1117/12.2564328}},
  doi          = {{10.1117/12.2564328}},
  volume       = {{11513}},
  year         = {{2020}},
}