Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Enhancing the Prediction of Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Routine Full-Breast Mammograms

Zhang, Daqu LU ; Dihge, Looket LU ; Bendahl, Pär-Ola LU ; Arvidsson, Ida LU orcid ; Dustler, Magnus LU orcid ; Ellbrant, Julia LU ; Gulis, Kim LU orcid ; Hjärtström, Malin LU orcid ; Ohlsson, Mattias LU orcid and Rejmer, Cornelia LU orcid , et al. (2025) In Breast Cancer Research
Abstract
Background: With a trend toward de-escalation of axillary surgery in breast cancer, prediction models incorporating imaging modalities can help reassess the need for surgical axillary staging. Although mammography is routinely performed for breast cancer imaging, its potential in nodal staging remains underutilized. This study aims to employ advancements in deep learning (DL) to comprehensively evaluate the potential of routine mammograms for predicting lymph node metastasis (LNM) in preoperative clinical settings.

Methods: This retrospective study included 1,265 cN0 T1-T2 breast cancer patients, comprising 368 node-positive and 897 node-negative cases, diagnosed from 2009-2017 at three Swedish institutions. Patients diagnosed in... (More)
Background: With a trend toward de-escalation of axillary surgery in breast cancer, prediction models incorporating imaging modalities can help reassess the need for surgical axillary staging. Although mammography is routinely performed for breast cancer imaging, its potential in nodal staging remains underutilized. This study aims to employ advancements in deep learning (DL) to comprehensively evaluate the potential of routine mammograms for predicting lymph node metastasis (LNM) in preoperative clinical settings.

Methods: This retrospective study included 1,265 cN0 T1-T2 breast cancer patients, comprising 368 node-positive and 897 node-negative cases, diagnosed from 2009-2017 at three Swedish institutions. Patients diagnosed in 2017 were assigned to the independent test set (n=123, site 2) and the external test set (n=103, site 3), while the remaining patients (n=1,039, site 1 and 2) were used for model development and double cross-validation. A neck module, in conjunction with a ResNet backbone pretrained on unlabeled mammograms, was developed to extract global information from full-breast or region-of-interest (ROI) mammograms by predicting five cancer outcomes. Clinicopathological characteristics were combined with the learned mammogram features to predict LNM collaboratively. The models were evaluated using area under the receiver operating characteristic (ROC) curve (AUC), calibration, and decision curve analysis.

Results: Compared to models using only clinical variables, incorporating full-breast mammograms with preoperative clinical variables improved the ROC AUC from 0.690 ± 0.063 (SD) to 0.774 ± 0.057 in the independent test set and from 0.584 ± 0.068 to 0.637 ± 0.063 in the external test set. The combined model showed good calibration and, at sensitivity ≥ 90%, achieved a better net benefit, and a higher sentinel lymph node biopsy reduction rate of 41.7% in the independent test set. Full-breast mammograms showed comparable ability to tumor ROIs in predicting LNM.

Conclusion: Our findings underscore that routine mammograms, particularly full-breast images, can enhance preoperative nodal status prediction. They may substitute key postoperative predictors such as pathological tumor size and multifocality, aiding patient stratification before surgery. Interestingly, the added predictive value of mammography was consistent across all sites, whereas the overall performance varied over time periods and sites, likely due to advancements in equipment and procedures. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Working paper/Preprint
publication status
submitted
subject
keywords
Artifical Intelligence, Machine learning, Breast cancer, Axillary lymph node metastasis, Mammography, Self-supervised learning, Multimodality
in
Breast Cancer Research
publisher
Research Square
ISSN
1465-5411
DOI
10.21203/rs.3.rs-5728087/v1
language
English
LU publication?
yes
id
19633b07-b09a-43ab-9bf5-3d0498c64d3c
date added to LUP
2025-01-14 10:07:22
date last changed
2025-04-04 14:04:23
@misc{19633b07-b09a-43ab-9bf5-3d0498c64d3c,
  abstract     = {{Background: With a trend toward de-escalation of axillary surgery in breast cancer, prediction models incorporating imaging modalities can help reassess the need for surgical axillary staging. Although mammography is routinely performed for breast cancer imaging, its potential in nodal staging remains underutilized. This study aims to employ advancements in deep learning (DL) to comprehensively evaluate the potential of routine mammograms for predicting lymph node metastasis (LNM) in preoperative clinical settings.<br/><br/>Methods: This retrospective study included 1,265 cN0 T1-T2 breast cancer patients, comprising 368 node-positive and 897 node-negative cases, diagnosed from 2009-2017 at three Swedish institutions. Patients diagnosed in 2017 were assigned to the independent test set (n=123, site 2) and the external test set (n=103, site 3), while the remaining patients (n=1,039, site 1 and 2) were used for model development and double cross-validation. A neck module, in conjunction with a ResNet backbone pretrained on unlabeled mammograms, was developed to extract global information from full-breast or region-of-interest (ROI) mammograms by predicting five cancer outcomes. Clinicopathological characteristics were combined with the learned mammogram features to predict LNM collaboratively. The models were evaluated using area under the receiver operating characteristic (ROC) curve (AUC), calibration, and decision curve analysis.<br/><br/>Results: Compared to models using only clinical variables,  incorporating full-breast mammograms with preoperative clinical variables improved the ROC AUC from 0.690 ± 0.063 (SD) to 0.774 ± 0.057 in the independent test set and from 0.584 ± 0.068 to 0.637 ± 0.063 in the external test set. The combined model showed good calibration and, at sensitivity ≥ 90%, achieved a better net benefit, and a higher sentinel lymph node biopsy reduction rate of 41.7% in the independent test set. Full-breast mammograms showed comparable ability to tumor ROIs in predicting LNM.<br/><br/>Conclusion: Our findings underscore that routine mammograms, particularly full-breast images, can enhance preoperative nodal status prediction. They may substitute key postoperative predictors such as pathological tumor size and multifocality, aiding patient stratification before surgery. Interestingly, the added predictive value of mammography was consistent across all sites, whereas the overall performance varied over time periods and sites, likely due to advancements in equipment and procedures.}},
  author       = {{Zhang, Daqu and Dihge, Looket and Bendahl, Pär-Ola and Arvidsson, Ida and Dustler, Magnus and Ellbrant, Julia and Gulis, Kim and Hjärtström, Malin and Ohlsson, Mattias and Rejmer, Cornelia and Schmidt, David and Zackrisson, Sophia and Edén, Patrik and Ryden, Lisa}},
  issn         = {{1465-5411}},
  keywords     = {{Artifical Intelligence; Machine learning; Breast cancer; Axillary lymph node metastasis; Mammography; Self-supervised learning; Multimodality}},
  language     = {{eng}},
  month        = {{01}},
  note         = {{Preprint}},
  publisher    = {{Research Square}},
  series       = {{Breast Cancer Research}},
  title        = {{Enhancing the Prediction of Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Routine Full-Breast Mammograms}},
  url          = {{http://dx.doi.org/10.21203/rs.3.rs-5728087/v1}},
  doi          = {{10.21203/rs.3.rs-5728087/v1}},
  year         = {{2025}},
}