Area-based breast percentage density estimation in mammograms using weight-adaptive multitask learning.

Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE

Original Publication: London : Nature Publishing Group, copyright 2011-

Breast Density* ; Breast Neoplasms*/diagnostic imaging; Breast/diagnostic imaging ; Female ; Humans ; Image Processing, Computer-Assisted ; Mammography ; Neural Networks, Computer

Breast density, which is a measure of the relative amount of fibroglandular tissue within the breast area, is one of the most important breast cancer risk factors. Accurate segmentation of fibroglandular tissues and breast area is crucial for computing the breast density. Semiautomatic and fully automatic computer-aided design tools have been developed to estimate the percentage of breast density in mammograms. However, the available approaches are usually limited to specific mammogram views and are inadequate for complete delineation of the pectoral muscle. These tools also perform poorly in cases of data variability and often require an experienced radiologist to adjust the segmentation threshold for fibroglandular tissue within the breast area. This study proposes a new deep learning architecture that automatically estimates the area-based breast percentage density from mammograms using a weight-adaptive multitask learning approach. The proposed approach simultaneously segments the breast and dense tissues and further estimates the breast percentage density. We evaluate the performance of the proposed model in both segmentation and density estimation on an independent evaluation set of 7500 craniocaudal and mediolateral oblique-view mammograms from Kuopio University Hospital, Finland. The proposed multitask segmentation approach outperforms and achieves average relative improvements of 2.88% and 9.78% in terms of F-score compared to the multitask U-net and a fully convolutional neural network, respectively. The estimated breast density values using our approach strongly correlate with radiologists' assessments with a Pearson's correlation of [Formula: see text] (95% confidence interval [0.89, 0.91]). We conclude that our approach greatly improves the segmentation accuracy of the breast area and dense tissues; thus, it can play a vital role in accurately computing the breast density. Our density estimation model considerably reduces the time and effort needed to estimate density values from mammograms by radiologists and therefore, decreases inter- and intra-reader variability.
(© 2022. The Author(s).)

IEEE Trans Med Imaging. 2016 May;35(5):1322-1331. (PMID: 26915120)
Med Phys. 2012 Aug;39(8):4903-17. (PMID: 22894417)
Breast Cancer Res. 2007;9(6):217. (PMID: 18190724)
IEEE Trans Pattern Anal Mach Intell. 2017 Apr;39(4):640-651. (PMID: 27244717)
Acad Radiol. 2012 Feb;19(2):236-48. (PMID: 22078258)
Cancer Epidemiol Biomarkers Prev. 2006 Jun;15(6):1159-69. (PMID: 16775176)
Artif Intell Med. 2017 Jun;79:28-41. (PMID: 28606722)
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:2019-2022. (PMID: 33018400)
IEEE Trans Med Imaging. 2016 May;35(5):1273-1284. (PMID: 26886969)
IEEE Trans Image Process. 1998;7(12):1673-83. (PMID: 18276234)
Phys Med Biol. 2018 Jan 09;63(2):025005. (PMID: 29210358)
Breast Cancer Res Treat. 2017 Apr;162(3):541-548. (PMID: 28161786)
AJR Am J Roentgenol. 2017 Jan;208(1):222-227. (PMID: 27824483)
Nature. 2017 Feb 2;542(7639):115-118. (PMID: 28117445)
Acta Radiol Open. 2020 Jul 20;9(7):2058460120937381. (PMID: 32733694)
Breast Cancer Res. 2019 Oct 17;21(1):111. (PMID: 31623646)
Eur J Radiol Open. 2018 Apr 20;5:67-72. (PMID: 29707614)
Radiology. 2019 Jan;290(1):52-58. (PMID: 30325282)
Sci Rep. 2021 Jul 8;11(1):14105. (PMID: 34238940)
Biochem Med (Zagreb). 2015 Jun 05;25(2):141-51. (PMID: 26110027)
Med Phys. 2018 Mar;45(3):1178-1190. (PMID: 29363774)
Phys Med Biol. 1994 Oct;39(10):1629-38. (PMID: 15551535)
Radiologia. 2014 Sep-Oct;56(5):429-34. (PMID: 23489767)
IEEE Trans Pattern Anal Mach Intell. 2018 Apr;40(4):834-848. (PMID: 28463186)
Cancer Causes Control. 2000 Aug;11(7):653-62. (PMID: 10977110)

Date Created: 20220714 Date Completed: 20220718 Latest Revision: 20240831

20250114

PMC9283472

10.1038/s41598-022-16141-2

35835933