Robust cross-vendor mammographic texture models using augmentation-based domain adaptation for long-term breast cancer risk
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Robust cross-vendor mammographic texture models using augmentation-based domain adaptation for long-term breast cancer risk. / Lauritzen, Andreas D.; Von Euler-Chelpin, My Catarina; Lynge, Elsebeth; Vejborg, Ilse; Nielsen, Mads; Karssemeijer, Nico; Lillholm, Martin.
In: Journal of Medical Imaging, Vol. 10, No. 5, 054003, 2023, p. 1-16.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Robust cross-vendor mammographic texture models using augmentation-based domain adaptation for long-term breast cancer risk
AU - Lauritzen, Andreas D.
AU - Von Euler-Chelpin, My Catarina
AU - Lynge, Elsebeth
AU - Vejborg, Ilse
AU - Nielsen, Mads
AU - Karssemeijer, Nico
AU - Lillholm, Martin
N1 - Publisher Copyright: © 2023 Society of Photo-Optical Instrumentation Engineers (SPIE).
PY - 2023
Y1 - 2023
N2 - Purpose: Risk-stratified breast cancer screening might improve early detection and efficiency without comprising quality. However, modern mammography-based risk models do not ensure adaptation across vendor-domains and rely on cancer precursors, associated with short-term risk, which might limit long-term risk assessment. We report a cross-vendor mammographic texture model for long-term risk. Approach: The texture model was robustly trained using two systematically designed case-control datasets. Textural features, indicative of future breast cancer, were learned by excluding samples with diagnosed/potential malignancies from training. An augmentation-based domain adaption technique, based on flavorization of mammographic views, ensured generalization across vendor-domains. The model was validated in 66,607 consecutively screened Danish women with flavorized Siemens views and 25,706 Dutch women with Hologic-processed views. Performances were evaluated for interval cancers (IC) within 2 years from screening and long-term cancers (LTC) from 2 years after screening. The texture model was combined with established risk factors to flag 10% of women with the highest risk. Results: In Danish women, the texture model achieved an area under the receiver operating characteristic curve (AUC) of 0.71 and 0.65 for ICs and LTCs, respectively. In Dutch women with Hologic-processed views, the AUCs were not different from AUCs in Danish women with flavorized views. The AUC for texture combined with established risk factors increased to 0.68 for LTCs. The 10% of women flagged as high-risk accounted for 25.5% of ICs and 24.8% of LTCs. Conclusions: The texture model robustly estimated long-term breast cancer risk while adapting to an unseen processed vendor-domain and identified a clinically relevant high-risk subgroup.
AB - Purpose: Risk-stratified breast cancer screening might improve early detection and efficiency without comprising quality. However, modern mammography-based risk models do not ensure adaptation across vendor-domains and rely on cancer precursors, associated with short-term risk, which might limit long-term risk assessment. We report a cross-vendor mammographic texture model for long-term risk. Approach: The texture model was robustly trained using two systematically designed case-control datasets. Textural features, indicative of future breast cancer, were learned by excluding samples with diagnosed/potential malignancies from training. An augmentation-based domain adaption technique, based on flavorization of mammographic views, ensured generalization across vendor-domains. The model was validated in 66,607 consecutively screened Danish women with flavorized Siemens views and 25,706 Dutch women with Hologic-processed views. Performances were evaluated for interval cancers (IC) within 2 years from screening and long-term cancers (LTC) from 2 years after screening. The texture model was combined with established risk factors to flag 10% of women with the highest risk. Results: In Danish women, the texture model achieved an area under the receiver operating characteristic curve (AUC) of 0.71 and 0.65 for ICs and LTCs, respectively. In Dutch women with Hologic-processed views, the AUCs were not different from AUCs in Danish women with flavorized views. The AUC for texture combined with established risk factors increased to 0.68 for LTCs. The 10% of women flagged as high-risk accounted for 25.5% of ICs and 24.8% of LTCs. Conclusions: The texture model robustly estimated long-term breast cancer risk while adapting to an unseen processed vendor-domain and identified a clinically relevant high-risk subgroup.
KW - breast cancer risk
KW - data augmentation
KW - domain adaptation
KW - mammography
KW - noisy labels
U2 - 10.1117/1.JMI.10.5.054003
DO - 10.1117/1.JMI.10.5.054003
M3 - Journal article
C2 - 37780685
AN - SCOPUS:85176135611
VL - 10
SP - 1
EP - 16
JO - Journal of Medical Imaging
JF - Journal of Medical Imaging
SN - 2329-4302
IS - 5
M1 - 054003
ER -
ID: 374119555