Validation of a new fully automated software for 2D digital mammographic breast density evaluation in predicting breast cancer risk.
Adult
Area Under Curve
Automation
Breast Density
Breast Neoplasms
/ diagnostic imaging
Case-Control Studies
Early Detection of Cancer
/ methods
Female
Humans
Image Processing, Computer-Assisted
/ methods
Mammography
/ methods
Middle Aged
Radiographic Image Interpretation, Computer-Assisted
/ methods
Reproducibility of Results
Risk
Software
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
06 10 2021
06 10 2021
Historique:
received:
25
05
2021
accepted:
22
09
2021
entrez:
7
10
2021
pubmed:
8
10
2021
medline:
29
12
2021
Statut:
epublish
Résumé
We compared accuracy for breast cancer (BC) risk stratification of a new fully automated system (DenSeeMammo-DSM) for breast density (BD) assessment to a non-inferiority threshold based on radiologists' visual assessment. Pooled analysis was performed on 14,267 2D mammograms collected from women aged 48-55 years who underwent BC screening within three studies: RETomo, Florence study and PROCAS. BD was expressed through clinical Breast Imaging Reporting and Data System (BI-RADS) density classification. Women in BI-RADS D category had a 2.6 (95% CI 1.5-4.4) and a 3.6 (95% CI 1.4-9.3) times higher risk of incident and interval cancer, respectively, than women in the two lowest BD categories. The ability of DSM to predict risk of incident cancer was non-inferior to radiologists' visual assessment as both point estimate and lower bound of 95% CI (AUC 0.589; 95% CI 0.580-0.597) were above the predefined visual assessment threshold (AUC 0.571). AUC for interval (AUC 0.631; 95% CI 0.623-0.639) cancers was even higher. BD assessed with new fully automated method is positively associated with BC risk and is not inferior to radiologists' visual assessment. It is an even stronger marker of interval cancer, confirming an appreciable masking effect of BD that reduces mammography sensitivity.
Identifiants
pubmed: 34615978
doi: 10.1038/s41598-021-99433-3
pii: 10.1038/s41598-021-99433-3
pmc: PMC8494838
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
19884Informations de copyright
© 2021. The Author(s).
Références
Breast Cancer Res. 2017 Jun 5;19(1):67
pubmed: 28583146
N Engl J Med. 2019 Nov 28;381(22):2091-2102
pubmed: 31774954
Cancer Epidemiol Biomarkers Prev. 2014 Sep;23(9):1764-72
pubmed: 25012995
Radiology. 2016 Jun;279(3):710-9
pubmed: 26694052
Breast Cancer Res Treat. 2017 Feb;162(1):95-103
pubmed: 28012087
Breast. 2016 Oct;29:49-54
pubmed: 27420382
Ann Intern Med. 2016 Oct 4;165(7):457-464
pubmed: 27428568
Eur Radiol. 2019 Apr;29(4):1762-1777
pubmed: 30255244
Radiology. 2013 May;267(2):328-38
pubmed: 23610094
Breast Cancer Res Treat. 2017 Apr;162(3):541-548
pubmed: 28161786
Breast Cancer (Auckl). 2018 Feb 22;12:1178223418759296
pubmed: 29511356
AJR Am J Roentgenol. 2017 Jan;208(1):222-227
pubmed: 27824483
Radiology. 2018 Aug;288(2):375-385
pubmed: 29869961
Radiology. 2018 Aug;288(2):343-352
pubmed: 29944088
Breast. 2012 Aug;21(4):503-6
pubmed: 22285387
Breast Cancer Res. 2015 Aug 25;17:117
pubmed: 26303303
Eur Radiol. 2019 Jul;29(7):3830-3838
pubmed: 30770972
Breast Cancer Res. 2014 Sep 20;16(5):439
pubmed: 25239205
Eur Radiol. 2016 Dec;26(12):4354-4360
pubmed: 27011371
NPJ Breast Cancer. 2017 Sep 13;3:34
pubmed: 28944288
Breast Cancer Res. 2018 Feb 05;20(1):10
pubmed: 29402289
Radiology. 2017 Feb;282(2):348-355
pubmed: 27598536
Epidemiol Prev. 2013 Jul-Oct;37(4-5):317-27
pubmed: 24293498
Breast Cancer Res. 2018 Aug 9;20(1):95
pubmed: 30092817