Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Personalized breast cancer screening with selective addition of digital breast tomosynthesis through artificial intelligence

Dahlblom, Victor LU orcid ; Tingberg, Anders LU ; Zackrisson, Sophia LU and Dustler, Magnus LU (2023) In Journal of Medical Imaging 10(Suppl 2).
Abstract

PURPOSE: Breast cancer screening is predominantly performed using digital mammography (DM), but digital breast tomosynthesis (DBT) has higher sensitivity. DBT demands more resources than DM, and it might be more feasible to reserve DBT for women with a clear benefit from the technique. We explore if artificial intelligence (AI) can select women who would benefit from DBT imaging.

APPROACH: We used data from Malmö Breast Tomosynthesis Screening Trial, where all women prospectively were examined with separately double read DM and DBT. We retrospectively analyzed DM examinations (n=14768) with a breast cancer detection system and used the provided risk score (1 to 10) for risk stratification. We tested how different score thresholds... (More)

PURPOSE: Breast cancer screening is predominantly performed using digital mammography (DM), but digital breast tomosynthesis (DBT) has higher sensitivity. DBT demands more resources than DM, and it might be more feasible to reserve DBT for women with a clear benefit from the technique. We explore if artificial intelligence (AI) can select women who would benefit from DBT imaging.

APPROACH: We used data from Malmö Breast Tomosynthesis Screening Trial, where all women prospectively were examined with separately double read DM and DBT. We retrospectively analyzed DM examinations (n=14768) with a breast cancer detection system and used the provided risk score (1 to 10) for risk stratification. We tested how different score thresholds for adding DBT to an initial DM affects the number of detected cancers, additional DBT examinations needed, detection rate, and false positives.

RESULTS: If using a threshold of 9.0, 25 (26%) more cancers would be detected compared to using DM alone. Of the 41 cancers only detected on DBT, 61% would be detected, with only 1797 (12%) of the women examined with both DM and DBT. The detection rate for the added DBT would be 14/1000 women, whereas the false-positive recalls would be increased with 58 (21%).

CONCLUSION: Using DBT only for selected high gain cases could be an alternative to complete DBT screening. AI can analyze initial DM images to identify high gain cases where DBT can be added during the same visit. There might be logistical challenges, and further studies in a prospective setting are necessary.

(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
in
Journal of Medical Imaging
volume
10
issue
Suppl 2
article number
S22408
publisher
SPIE
external identifiers
  • scopus:85173208730
  • pmid:37274777
ISSN
2329-4302
DOI
10.1117/1.JMI.10.S2.S22408
language
English
LU publication?
yes
additional info
© 2023 The Authors.
id
d4614cfe-3f26-4cfe-9adb-24d6feb2db28
date added to LUP
2023-08-31 09:39:58
date last changed
2024-04-15 15:21:22
@article{d4614cfe-3f26-4cfe-9adb-24d6feb2db28,
  abstract     = {{<p>PURPOSE: Breast cancer screening is predominantly performed using digital mammography (DM), but digital breast tomosynthesis (DBT) has higher sensitivity. DBT demands more resources than DM, and it might be more feasible to reserve DBT for women with a clear benefit from the technique. We explore if artificial intelligence (AI) can select women who would benefit from DBT imaging.</p><p>APPROACH: We used data from Malmö Breast Tomosynthesis Screening Trial, where all women prospectively were examined with separately double read DM and DBT. We retrospectively analyzed DM examinations (n=14768) with a breast cancer detection system and used the provided risk score (1 to 10) for risk stratification. We tested how different score thresholds for adding DBT to an initial DM affects the number of detected cancers, additional DBT examinations needed, detection rate, and false positives.</p><p>RESULTS: If using a threshold of 9.0, 25 (26%) more cancers would be detected compared to using DM alone. Of the 41 cancers only detected on DBT, 61% would be detected, with only 1797 (12%) of the women examined with both DM and DBT. The detection rate for the added DBT would be 14/1000 women, whereas the false-positive recalls would be increased with 58 (21%).</p><p>CONCLUSION: Using DBT only for selected high gain cases could be an alternative to complete DBT screening. AI can analyze initial DM images to identify high gain cases where DBT can be added during the same visit. There might be logistical challenges, and further studies in a prospective setting are necessary.</p>}},
  author       = {{Dahlblom, Victor and Tingberg, Anders and Zackrisson, Sophia and Dustler, Magnus}},
  issn         = {{2329-4302}},
  language     = {{eng}},
  number       = {{Suppl 2}},
  publisher    = {{SPIE}},
  series       = {{Journal of Medical Imaging}},
  title        = {{Personalized breast cancer screening with selective addition of digital breast tomosynthesis through artificial intelligence}},
  url          = {{http://dx.doi.org/10.1117/1.JMI.10.S2.S22408}},
  doi          = {{10.1117/1.JMI.10.S2.S22408}},
  volume       = {{10}},
  year         = {{2023}},
}