AutoDensity: an automated method to measure mammographic breast density that predicts breast cancer risk and screening outcomes

Abstract

IntroductionWhile Cumulus – a semi-automated method for measuring breast density – is utilised extensively in research, it is labour-intensive and unsuitable for screening programmes that require an efficient and valid measure on which to base screening recommendations. We develop an automated method to measure breast density (AutoDensity) and compare it to Cumulus in terms of association with breast cancer risk and breast cancer screening outcomes.MethodsAutoDensity automatically identifies the breast area in the mammogram and classifies breast density in a similar way to Cumulus, through a fast, stand-alone Windows or Linux program. Our sample comprised 985 women with screen-detected cancers, 367 women with interval cancers and 4,975 controls (women who did not have cancer), sampled from first and subsequent screening rounds of a film mammography screening programme. To test the validity of AutoDensity, we compared the effect estimates using AutoDensity with those using Cumulus from logistic regression models that tested the association between breast density and breast cancer risk, risk of small and large screen-detected cancers and interval cancers, and screening programme sensitivity (the proportion of cancers that are screen-detected). As a secondary analysis, we report on correlation between AutoDensity and Cumulus measures.ResultsAutoDensity performed similarly to Cumulus in all associations tested. For example, using AutoDensity, the odds ratios for women in the highest decile of breast density compared to women in the lowest quintile for invasive breast cancer, interval cancers, large and small screen-detected cancers were 3.2 (95% CI 2.5 to 4.1), 4.7 (95% CI 3.0 to 7.4), 6.4 (95% CI 3.7 to 11.1) and 2.2 (95% CI 1.6 to 3.0) respectively. For Cumulus the corresponding odds ratios were: 2.4 (95% CI 1.9 to 3.1), 4.1 (95% CI 2.6 to 6.3), 6.6 (95% CI 3.7 to 11.7) and 1.3 (95% CI 0.9 to 1.8). Correlation between Cumulus and AutoDensity measures was 0.63 (P < 0.001).ConclusionsBased on the similarity of the effect estimates for AutoDensity and Cumulus in models of breast density and breast cancer risk and screening outcomes, we conclude that AutoDensity is a valid automated method for measuring breast density from digitised film mammograms.

Impact of errors in recorded compressed breast thickness measurements on volumetric density classification using volpara v1.5.0 software

“…16 Automation of this process removes human variability. Several automated systems exist, including AutoDensity 11 , Quantra 12 and Volpara 13 . The latter two use volumetric breast 75 density assessment and has been cleared by the Food and Drug Administrative (FDA) as adjunctive supporting tools.…”

“…3 Women with high MD might benefit from additional imaging, such as ultrasound (US) or magnetic resonance imaging (MRI), or more frequent 65 screening compared with women with low MD. [4][5][6][7] There are several methods to measure MD [8][9][10][11][12][13] , the most common of which is visual assessment by radiologists using the Breast Imaging Reporting and Data System (BIRADS) scale. 8 This system is prone to inter and intra-reader variability 14,15 and thus several 70 computer-assisted methods have been developed including Cumulus 9 and Madena 10 .…”

Breast composition: Measurement and clinical use

“…99 The first of these separates the image of the breast from the background, and aggregation of the pixels over the intensity range gives the Cumulus has demonstrated good association between breast density and cancer risk in multiple global studies. 3,101,102 AutoDensity has been shown to be comparable to Cumulus for risk assessment 24 .…”

“…28,108 However, quantum and anatomical noise reduce the reliability of AutoDensity and MedDensity. 24,109 Image quality may limit accurate outlining of the dense area with semi-automated methods. 110 Although semi-automated thresholding methods have better reproducibility than visual approaches, they are labour-intensive, time-…”

“…3,5 Women with dense breasts are 4.7 to 17.8 times at risk of interval breast cancer relative to those with non-dense breasts. 3,[23][24][25] Mammographic breast density also reduces mammographic sensitivity and limits earlier detection of breast cancer with 2-dimensional mammography through masking effects. 23,26 Therefore, it is increasingly important to assess breast density of women undergoing screening mammography and inform women of their density.…”