Volumetric breast density estimation from full-field digital mammograms
- PMID: 16524084
- DOI: 10.1109/TMI.2005.862741
Volumetric breast density estimation from full-field digital mammograms
Abstract
A method is presented for estimation of dense breast tissue volume from mammograms obtained with full-field digital mammography (FFDM). The thickness of dense tissue mapping to a pixel is determined by using a physical model of image acquisition. This model is based on the assumption that the breast is composed of two types of tissue, fat and parenchyma. Effective linear attenuation coefficients of these tissues are derived from empirical data as a function of tube voltage (kVp), anode material, filtration, and compressed breast thickness. By employing these, tissue composition at a given pixel is computed after performing breast thickness compensation, using a reference value for fatty tissue determined by the maximum pixel value in the breast tissue projection. Validation has been performed using 22 FFDM cases acquired with a GE Senographe 2000D by comparing the volume estimates with volumes obtained by semi-automatic segmentation of breast magnetic resonance imaging (MRI) data. The correlation between MRI and mammography volumes was 0.94 on a per image basis and 0.97 on a per patient basis. Using the dense tissue volumes from MRI data as the gold standard, the average relative error of the volume estimates was 13.6%.
Similar articles
-
Computed-aided diagnosis (CAD) in the detection of breast cancer.Eur J Radiol. 2013 Mar;82(3):417-23. doi: 10.1016/j.ejrad.2012.03.005. Epub 2012 Aug 30. Eur J Radiol. 2013. PMID: 22939365 Review.
-
Unifying framework for multimodal brain MRI segmentation based on Hidden Markov Chains.Med Image Anal. 2008 Dec;12(6):639-52. doi: 10.1016/j.media.2008.03.001. Epub 2008 Mar 17. Med Image Anal. 2008. PMID: 18440268
-
Automatic segmentation of left and right cerebral hemispheres from MRI brain volumes using the graph cuts algorithm.Neuroimage. 2007 Feb 1;34(3):1160-70. doi: 10.1016/j.neuroimage.2006.07.046. Epub 2006 Dec 5. Neuroimage. 2007. PMID: 17150376
-
An adaptive tissue characterization network for model-free visualization of dynamic contrast-enhanced magnetic resonance image data.IEEE Trans Med Imaging. 2005 Oct;24(10):1256-66. doi: 10.1109/TMI.2005.854517. IEEE Trans Med Imaging. 2005. PMID: 16229413 Clinical Trial.
-
Full-field digital mammography. A candid assessment.Diagn Imaging (San Franc). 1999 Sep;21(9):40-5. Diagn Imaging (San Franc). 1999. PMID: 10623316 Review. No abstract available.
Cited by
-
Association of area- and volumetric-mammographic density and breast cancer risk in women of Asian descent: a case control study.Breast Cancer Res. 2024 May 15;26(1):79. doi: 10.1186/s13058-024-01829-2. Breast Cancer Res. 2024. PMID: 38750574 Free PMC article.
-
Anomaly-guided weakly supervised lesion segmentation on retinal OCT images.Med Image Anal. 2024 May;94:103139. doi: 10.1016/j.media.2024.103139. Epub 2024 Mar 12. Med Image Anal. 2024. PMID: 38493532
-
Ionizing radiation and volumetric mammographic density.Int J Occup Med Environ Health. 2022 Oct 3;35(5):635-649. doi: 10.13075/ijomeh.1896.01916. Epub 2022 Aug 1. Int J Occup Med Environ Health. 2022. PMID: 35913368 Free PMC article.
-
Multimodality Imaging of Breast Parenchymal Density and Correlation with Risk Assessment.Curr Breast Cancer Rep. 2019 Mar;11(1):23-33. doi: 10.1007/s12609-019-0302-6. Epub 2019 Jan 17. Curr Breast Cancer Rep. 2019. PMID: 35496471 Free PMC article.
-
Clinical Artificial Intelligence Applications: Breast Imaging.Radiol Clin North Am. 2021 Nov;59(6):1027-1043. doi: 10.1016/j.rcl.2021.07.010. Radiol Clin North Am. 2021. PMID: 34689871 Free PMC article. Review.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical