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

The cost-effectiveness of risk-stratified breast cancer screening in the UK

BACKGROUND

There has been growing interest in the UK and internationally of risk-stratified breast screening whereby individualised risk assessment may inform screening frequency, starting age, screening instrument used, or even decisions not to screen. This study evaluates the cost-effectiveness of eight proposals for risk-stratified screening regimens compared to both the current UK screening programme and no national screening.

METHODS

A person-level microsimulation model was developed to estimate health-related quality of life, cancer survival and NHS costs over the lifetime of the female population eligible for screening in the UK.

RESULTS

Compared with both the current screening programme and no screening, risk-stratified regimens generated additional costs and QALYs, and had a larger net health benefit. The likelihood of the current screening programme being the optimal scenario was less than 1%. No screening amongst the lowest risk group, and triannual, biennial and annual screening amongst the three higher risk groups was the optimal screening strategy from those evaluated.

CONCLUSIONS

We found that risk-stratified breast cancer screening has the potential to be beneficial for women at the population level, but the net health benefit will depend on the particular risk-based strategy.

Beyond Breast Density: Risk Measures for Breast Cancer in Multiple Imaging Modalities

Breast density is an independent risk factor for breast cancer. In digital mammography and digital breast tomosynthesis, breast density is assessed visually using the four-category scale developed by the American College of Radiology Breast Imaging Reporting and Data System (5th edition as of November 2022). Epidemiologically based risk models, such as the Tyrer-Cuzick model (version 8), demonstrate superior modeling performance when mammographic density is incorporated. Beyond just density, a separate mammographic measure of breast cancer risk is parenchymal textural complexity. With advancements in radiomics and deep learning, mammographic textural patterns can be assessed quantitatively and incorporated into risk models. Other supplemental screening modalities, such as breast US and MRI, offer independent risk measures complementary to those derived from mammography. Breast US allows the two components of fibroglandular tissue (stromal and glandular) to be visualized separately in a manner that is not possible with mammography. A higher glandular component at screening breast US is associated with higher risk. With MRI, a higher background parenchymal enhancement of the fibroglandular tissue has also emerged as an imaging marker for risk assessment. Imaging markers observed at mammography, US, and MRI are powerful tools in refining breast cancer risk prediction, beyond mammographic density alone.

Understanding mammographic breast density profile in China: A Sino-Australian comparative study of breast density using real-world data from cancer screening programs

AIM

This study aims at understanding mammographic density profile in China by comparing the density between women in China and Australia.

METHODS

Data of 3250 women aged 45-69 were obtained from the Cancer Screening Program in Urban China and data of 1384 Australian counterparts at same age range were gathered from the Lifepool project. Demographic and reproductive details and mammograms for each cohort were collected. Mammographic density was assessed using AutoDensity, and two metrics, percentage density (PD) and dense area (DA), were applied. T-tests were used to compare the means of mammographic density between two populations of all, premenopausal, and postmenopausal women. Two-way ANOVA was conducted to examine interactions of population (Chinese/Australian) and each variable of interest upon mammographic density.

RESULTS

Chinese women had 9.61%, 8.20%, and 9.28% higher PD than their Australian counterparts in all, premenopausal, and postmenopausal women, respectively (all p < 0.001). The mean differences in DA between two population were 1.81 cm² (p < 0.001), 0.55 cm² (p = 0.472), and 1.76 cm² (p = 0.003) for all, premenopausal, and postmenopausal women, respectively. There were significant interactions between population and age (F[4, 4624] = 4.12, p = 0.003), BMI (F[2, 4628] = 3.92, p = 0.020), age at first birth (F[1, 4250] = 11.69, p < 0.001), breastfeeding history (F[1, 4479] = 17.79, p < 0.001), and breastfeeding duration (F[1, 3526] = 66.90, p < 0.001) upon PD. Interaction was only found for breastfeeding history (F[1, 4479] = 4.79, p = 0.029) and breastfeeding duration (F[1, 3526] = 17.72, p < 0.001) for DA.

CONCLUSIONS

Both PD and DA were found to be higher in Chinese women compared to Australian women. The density difference by menopause status was shown and breastfeeding history affected breast density differently in both populations.

Breast Density: Current Knowledge, Assessment Methods, and Clinical Implications

Breast density is an accepted independent risk factor for the future development of breast cancer, and greater breast density has the potential to mask malignancies on mammography, thus lowering the sensitivity of screening mammography. The risk associated with dense breast tissue has been shown to be modifiable with changes in breast density. Numerous studies have sought to identify factors that influence breast density, including age, genetic, racial/ethnic, prepubertal, adolescent, lifestyle, environmental, hormonal, and reproductive history factors. Qualitative, semiquantitative, and quantitative methods of breast density assessment have been developed, but to date there is no consensus assessment method or reference standard for breast density. Breast density has been incorporated into breast cancer risk models, and there is growing consciousness of the clinical implications of dense breast tissue in both the medical community and public arena. Efforts to improve breast cancer screening sensitivity for women with dense breasts have led to increased attention to supplemental screening methods in recent years, prompting the American College of Radiology to publish Appropriateness Criteria for supplemental screening based on breast density.

Algorithms and methods for computerized analysis of mammography images in breast cancer risk assessment

BACKGROUND AND OBJECTIVES

The computerized analysis of mammograms for the development of quantitative biomarkers is a growing field with applications in breast cancer risk assessment. Computerized image analysis offers the possibility of using different methods and algorithms to extract additional information from screening and diagnosis images to aid in the assessment of breast cancer risk. In this work, we review the algorithms and methods for the automated, computerized analysis of mammography images for the task mentioned, and discuss the main challenges that the development and improvement of these methods face today.

METHODS

We review the recent progress in two main branches of mammography-based risk assessment: parenchymal analysis and breast density estimation, including performance indicators of most of the studies considered. Parenchymal analysis methods are divided into feature-based methods and deep learning-based methods; breast density methods are grouped into area-based, volume-based, and breast categorization methods. Additionally, we identify the challenges that these study fields currently face.

RESULTS

Parenchymal analysis using deep learning algorithms are on the rise, with some studies showing high-performance indicators, such as an area under the receiver operating characteristic curve of up to 90. Methods for risk assessment using breast density report a wider variety of performance indicators; however, we can also identify that the approaches using deep learning methods yield high performance in each of the subdivisions considered.

CONCLUSIONS

Both breast density estimation and parenchymal analysis are promising tools for the task of breast cancer risk assessment; deep learning methods have shown performance comparable or superior to the other considered methods. All methods considered face challenges such as the lack of objective comparison between them and the lack of access to datasets from different populations.

Breast Cancer Risk Assessment: A Review on Mammography-Based Approaches

Breast cancer affects thousands of women across the world, every year. Methods to predict risk of breast cancer, or to stratify women in different risk levels, could help to achieve an early diagnosis, and consequently a reduction of mortality. This paper aims to review articles that extracted texture features from mammograms and used those features along with machine learning algorithms to assess breast cancer risk. Besides that, deep learning methodologies that aimed for the same goal were also reviewed. In this work, first, a brief introduction to breast cancer statistics and screening programs is presented; after that, research done in the field of breast cancer risk assessment are analyzed, in terms of both methodologies used and results obtained. Finally, considerations about the analyzed papers are conducted. The results of this review allow to conclude that both machine and deep learning methodologies provide promising results in the field of risk analysis, either in a stratification in risk groups, or in a prediction of a risk score. Although promising, future endeavors in this field should consider the possibility of the implementation of the methodology in clinical practice.

Automated percent mammographic density, mammographic texture variation, and risk of breast cancer: a nested case-control study

Percent mammographic density (PMD) is a strong breast cancer risk factor, however, other mammographic features, such as V, the standard deviation (SD) of pixel intensity, may be associated with risk. We assessed whether PMD, automated PMD (APD), and V, yielded independent associations with breast cancer risk. We included 1900 breast cancer cases and 3921 matched controls from the Nurses' Health Study (NHS) and the NHSII. Using digitized film mammograms, we estimated PMD using a computer-assisted thresholding technique. APD and V were determined using an automated computer algorithm. We used logistic regression to generate odds ratios (ORs) and 95% confidence intervals (CIs). Median time from mammogram to diagnosis was 4.1 years (interquartile range: 1.6-6.8 years). PMD (OR per SD:1.52, 95% CI: 1.42, 1.63), APD (OR per SD:1.32, 95% CI: 1.24, 1.41), and V (OR per SD:1.32, 95% CI: 1.24, 1.40) were positively associated with breast cancer risk. Associations for APD were attenuated but remained statistically significant after mutual adjustment for PMD or V. Women in the highest quartile of both APD and V (OR vs Q1/Q1: 2.49, 95% CI: 2.02, 3.06), or PMD and V (OR vs Q1/Q1: 3.57, 95% CI: 2.79, 4.58) had increased breast cancer risk. An automated method of PMD assessment is feasible and yields similar, but somewhat weaker, estimates to a manual measure. PMD, APD and V are each independently, positively associated with breast cancer risk. Women with dense breasts and greater texture variation are at the highest relative risk of breast cancer.

Fully Automated Breast Density Segmentation and Classification Using Deep Learning

Breast density estimation with visual evaluation is still challenging due to low contrast and significant fluctuations in the mammograms’ fatty tissue background. The primary key to breast density classification is to detect the dense tissues in the mammographic images correctly. Many methods have been proposed for breast density estimation; nevertheless, most of them are not fully automated. Besides, they have been badly affected by low signal-to-noise ratio and variability of density in appearance and texture. This study intends to develop a fully automated and digitalized breast tissue segmentation and classification using advanced deep learning techniques. The conditional Generative Adversarial Networks (cGAN) network is applied to segment the dense tissues in mammograms. To have a complete system for breast density classification, we propose a Convolutional Neural Network (CNN) to classify mammograms based on the standardization of Breast Imaging-Reporting and Data System (BI-RADS). The classification network is fed by the segmented masks of dense tissues generated by the cGAN network. For screening mammography, 410 images of 115 patients from the INbreast dataset were used. The proposed framework can segment the dense regions with an accuracy, Dice coefficient, Jaccard index of 98%, 88%, and 78%, respectively. Furthermore, we obtained precision, sensitivity, and specificity of 97.85%, 97.85%, and 99.28%, respectively, for breast density classification. This study’s findings are promising and show that the proposed deep learning-based techniques can produce a clinically useful computer-aided tool for breast density analysis by digital mammography.

The TP53 mutation rate differs in breast cancers that arise in women with high or low mammographic density

Mammographic density (MD) influences breast cancer risk, but how this is mediated is unknown. Molecular differences between breast cancers arising in the context of the lowest and highest quintiles of mammographic density may identify the mechanism through which MD drives breast cancer development. Women diagnosed with invasive or in situ breast cancer where MD measurement was also available (n = 842) were identified from the Lifepool cohort of >54,000 women participating in population-based mammographic screening. This group included 142 carcinomas in the lowest quintile of MD and 119 carcinomas in the highest quintile. Clinico-pathological and family history information were recorded. Tumor DNA was collected where available (n = 56) and sequenced for breast cancer predisposition and driver gene mutations, including copy number alterations. Compared to carcinomas from low-MD breasts, those from high-MD breasts were significantly associated with a younger age at diagnosis and features associated with poor prognosis. Low- and high-MD carcinomas matched for grade, histological subtype, and hormone receptor status were compared for somatic genetic features. Low-MD carcinomas had a significantly increased frequency of TP53 mutations, higher homologous recombination deficiency, higher fraction of the genome altered, and more copy number gains on chromosome 1q and losses on 17p. While high-MD carcinomas showed enrichment of tumor-infiltrating lymphocytes in the stroma. The data demonstrate that when tumors were matched for confounding clinico-pathological features, a proportion in the lowest quintile of MD appear biologically distinct, reflective of microenvironment differences between the lowest and highest quintiles of MD.

Measurement challenge: protocol for international case-control comparison of mammographic measures that predict breast cancer risk

INTRODUCTION

For women of the same age and body mass index, increased mammographic density is one of the strongest predictors of breast cancer risk. There are multiple methods of measuring mammographic density and other features in a mammogram that could potentially be used in a screening setting to identify and target women at high risk of developing breast cancer. However, it is unclear which measurement method provides the strongest predictor of breast cancer risk.

METHODS AND ANALYSIS

The measurement challenge has been established as an international resource to offer a common set of anonymised mammogram images for measurement and analysis. To date, full field digital mammogram images and core data from 1650 cases and 1929 controls from five countries have been collated. The measurement challenge is an ongoing collaboration and we are continuing to expand the resource to include additional image sets across different populations (from contributors) and to compare additional measurement methods (by challengers). The intended use of the measurement challenge resource is for refinement and validation of new and existing mammographic measurement methods. The measurement challenge resource provides a standardised dataset of mammographic images and core data that enables investigators to directly compare methods of measuring mammographic density or other mammographic features in case/control sets of both raw and processed images, for the purposes of the comparing their predictions of breast cancer risk.

ETHICS AND DISSEMINATION

Challengers and contributors are required to enter a Research Collaboration Agreement with the University of Melbourne prior to participation in the measurement challenge. The Challenge database of collated data and images are stored in a secure data repository at the University of Melbourne. Ethics approval for the measurement challenge is held at University of Melbourne (HREC ID 0931343.3).

Does Breast Density Increase the Risk of Re-excision for Women with Breast Cancer Having Breast-Conservation Therapy?

BACKGROUND

Women with dense breasts may have less-accurate preoperative evaluation of extent of disease, potentially affecting the achievement of negative margins. The goal of this study is to examine the association between breast density and re-excision rates in women having breast-conserving surgery for invasive breast cancer.

PATIENTS AND METHODS

Women with stage I/II invasive breast cancer treated with breast-conserving surgery between 1/1/2014 and 10/31/2014 were included. Breast density was assessed by two radiologists. The association between breast density and re-excision was examined using logistic regression.

RESULTS

Seven hundred and one women were included. Overall, 106 (15.1%) women had at least one re-excision. Younger age at diagnosis was associated with increased breast density (p < 0.001). On univariable analysis, increased breast density was associated with significantly increased odds of re-excision (odds ratio [OR] 1.38, 95% confidence interval [CI] 1.04-1.83), as was multifocal disease, human epidermal growth factor receptor 2 (HER2) positive status, and extensive intraductal component (EIC) (all p < 0.05). On multivariable analysis, breast density remained significantly associated with increased odds of re-excision (OR 1.37, 95% CI 1.00-1.86), as did multifocality and EIC. HER2 positive status was not significantly associated with re-excision on multivariable analysis.

CONCLUSIONS

Women with dense breasts are more likely to need additional surgery (re-excision after breast-conserving surgery), but increased breast density did not adversely affect disease-free survival in our study. Our findings support the need for further study in developing techniques that can help decrease re-excisions for women with dense breasts who undergo breast-conserving surgery.

Long-term excess risk of breast cancer after a single breast density measurement

AIM

Breast density is a risk factor for breast cancer. As density changes across a woman's life span, we studied for how long a single density measurement taken in (post-)menopausal women remains informative.

METHODS

We used data from Singaporean women who underwent a single mammography screen at age 50-64 years. For each case with breast cancer diagnosed at screening or in the subsequent 10 years, whether screen detected or diagnosed following symptoms, two age-matched controls were selected. We studied the excess risk of breast cancer, calculated as an odds ratio (OR) with conditional logistic regression and adjusted for body mass index, associated with 26-50% and with 51-100% density compared with ≤25% density by time since screening.

RESULTS

In total, 490 women had breast cancer, of which 361 were diagnosed because of symptoms after screening. Women with 51-100% breast density had an excess risk of breast cancer that did not seem to attenuate with time. In 1-3 years after screening, the OR was 2.22 (95% confidence interval [CI]: 1.07-4.61); in 4-6 years after screening, the OR was 4.09 (95% CI: 2.21-7.58), and in 7-10 years after screening, the OR was 5.35 (95% CI: 2.57-11.15). Excess risk with a stable OR of about 2 was also observed for women with 26-50% breast density. These patterns were robust when the analyses were limited to post-menopausal women, non-users of hormonal replacement therapy and after stratification by age at density measurement.

CONCLUSION

A single breast density measurement identifies women with an excess risk of breast cancer during at least the subsequent 10 years.

A review of the influence of mammographic density on breast cancer clinical and pathological phenotype

PURPOSE

It is well established that high mammographic density (MD), when adjusted for age and body mass index, is one of the strongest known risk factors for breast cancer (BC), and also associates with higher incidence of interval cancers in screening due to the masking of early mammographic abnormalities. Increasing research is being undertaken to determine the underlying histological and biochemical determinants of MD and their consequences for BC pathogenesis, anticipating that improved mechanistic insights may lead to novel preventative or treatment interventions. At the same time, technological advances in digital and contrast mammography are such that the validity of well-established relationships needs to be re-examined in this context.

METHODS

With attention to old versus new technologies, we conducted a literature review to summarise the relationships between clinicopathologic features of BC and the density of the surrounding breast tissue on mammography, including the associations with BC biological features inclusive of subtype, and implications for the clinical disease course encompassing relapse, progression, treatment response and survival.

RESULTS AND CONCLUSIONS

There is reasonable evidence to support positive relationships between high MD (HMD) and tumour size, lymph node positivity and local relapse in the absence of radiotherapy, but not between HMD and LVI, regional relapse or distant metastasis. Conflicting data exist for associations of HMD with tumour location, grade, intrinsic subtype, receptor status, second primary incidence and survival, which need further confirmatory studies. We did not identify any relationships that did not hold up when data involving newer imaging techniques were employed in analysis.

Characteristics of Mammographic Breast Density and Associated Factors for Chinese Women: Results from an Automated Measurement

Background

Characteristics of mammographic density for Chinese women are understudied. This study aims to identify factors associated with mammographic density in China using a quantitative method.

Methods

Mammographic density was measured for a total of 1071 (84 with and 987 without breast cancer) women using an automatic algorithm AutoDensity. Pearson tests examined relationships between density and continuous variables and t-tests compared differences of mean density values between groupings of categorical variables. Linear models were built using multiple regression.

Results

Percentage density and dense area were positively associated with each other for cancer-free (r=0.487, p<0.001) and cancer groups (r=0.446, p<0.001), respectively. For women without breast cancer, weight and BMI (p<0.001) were found to be negatively associated (r=-0.237, r=-0.272) with percentage density whereas they were found to be positively associated (r=0.110, r=0.099) with dense area; age at mammography was found to be associated with percentage density (r=-0.202, p<0.001) and dense area (r=-0.086, p<0.001) but did not add any prediction within multivariate models; lower percentage density was found within women with secondary education background or below compared to women with tertiary education. For women with breast cancer, percentage density demonstrated similar relationships with that of cancer-free women whilst breast area was the only factor associated with dense area (r=0.739, p<0.001).

Conclusion

This is the first time that mammographic density was measured by a quantitative method for women in China and identified associations should be useful to health policy makers who are responsible for introducing effective models of breast cancer prevention and diagnosis.

Cirrus: An Automated Mammography-Based Measure of Breast Cancer Risk Based on Textural Features

Background

We applied machine learning to find a novel breast cancer predictor based on information in a mammogram.

Methods

Using image-processing techniques, we automatically processed 46 158 analog mammograms for 1345 cases and 4235 controls from a cohort and case–control study of Australian women, and a cohort study of Japanese American women, extracting 20 textural features not based on pixel brightness threshold. We used Bayesian lasso regression to create individual- and mammogram-specific measures of breast cancer risk, Cirrus. We trained and tested measures across studies. We fitted Cirrus with conventional mammographic density measures using logistic regression, and computed odds ratios (OR) per standard deviation adjusted for age and body mass index.

Results

Combining studies, almost all textural features were associated with case–control status. The ORs for Cirrus measures trained on one study and tested on another study ranged from 1.56 to 1.78 (all P < 10⁻⁶). For the Cirrus measure derived from combining studies, the OR was 1.90 (95% confidence interval [CI] = 1.73 to 2.09), equivalent to a fourfold interquartile risk ratio, and was little attenuated after adjusting for conventional measures. In contrast, the OR for the conventional measure was 1.34 (95% CI = 1.25 to 1.43), and after adjusting for Cirrus it became 1.16 (95% CI = 1.08 to 1.24; P = 4 × 10⁻⁵).

Conclusions

A fully automated personal risk measure created from combining textural image features performs better at predicting breast cancer risk than conventional mammographic density risk measures, capturing half the risk-predicting ability of the latter measures. In terms of differentiating affected and unaffected women on a population basis, Cirrus could be one of the strongest known risk factors for breast cancer.

Exploring the prediction performance for breast cancer risk based on volumetric mammographic density at different thresholds

BACKGROUND

The percentage of mammographic dense tissue (PD) defined by pixel value threshold is a well-established risk factor for breast cancer. Recently there has been some evidence to suggest that an increased threshold based on visual assessment could improve risk prediction. It is unknown, however, whether this also applies to volumetric density using digital raw mammograms.

METHOD

Two case-control studies nested within a screening cohort (ages of participants 46-73 years) from Manchester UK were used. In the first study (317 cases and 947 controls) cases were detected at the first screen; whereas in the second study (318 cases and 935 controls), cases were diagnosed after the initial mammogram. Volpara software was used to estimate dense tissue height at each pixel point, and from these, volumetric and area-based PD were computed at a range of thresholds. Volumetric and area-based PDs were evaluated using conditional logistic regression, and their predictive ability was assessed using the Akaike information criterion (AIC) and matched concordance index (mC).

RESULTS

The best performing volumetric PD was based on a threshold of 5 mm of dense tissue height (which we refer to as VPD5), and the best areal PD was at a threshold level of 6 mm (which we refer to as APD6), using pooled data and in both studies separately. VPD5 showed a modest improvement in prediction performance compared to the original volumetric PD by Volpara with ΔAIC = 5.90 for the pooled data. APD6, on the other hand, shows much stronger evidence for better prediction performance, with ΔAIC = 14.52 for the pooled data, and mC increased slightly from 0.567 to 0.577.

CONCLUSION

These results suggest that imposing a 5 mm threshold on dense tissue height for volumetric PD could result in better prediction of cancer risk. There is stronger evidence that area-based density with a 6 mm threshold gives better prediction than the original volumetric density metric.

Automatic Estimation of Volumetric Breast Density Using Artificial Neural Network-Based Calibration of Full-Field Digital Mammography: Feasibility on Japanese Women With and Without Breast Cancer

Breast cancer is the most common invasive cancer among women and its incidence is increasing. Risk assessment is valuable and recent methods are incorporating novel biomarkers such as mammographic density. Artificial neural networks (ANN) are adaptive algorithms capable of performing pattern-to-pattern learning and are well suited for medical applications. They are potentially useful for calibrating full-field digital mammography (FFDM) for quantitative analysis. This study uses ANN modeling to estimate volumetric breast density (VBD) from FFDM on Japanese women with and without breast cancer. ANN calibration of VBD was performed using phantom data for one FFDM system. Mammograms of 46 Japanese women diagnosed with invasive carcinoma and 53 with negative findings were analyzed using ANN models learned. ANN-estimated VBD was validated against phantom data, compared intra-patient, with qualitative composition scoring, with MRI VBD, and inter-patient with classical risk factors of breast cancer as well as cancer status. Phantom validations reached an R ² of 0.993. Intra-patient validations ranged from R ² of 0.789 with VBD to 0.908 with breast volume. ANN VBD agreed well with BI-RADS scoring and MRI VBD with R ² ranging from 0.665 with VBD to 0.852 with breast volume. VBD was significantly higher in women with cancer. Associations with age, BMI, menopause, and cancer status previously reported were also confirmed. ANN modeling appears to produce reasonable measures of mammographic density validated with phantoms, with existing measures of breast density, and with classical biomarkers of breast cancer. FFDM VBD is significantly higher in Japanese women with cancer.

Qualitative Versus Quantitative Mammographic Breast Density Assessment: Applications for the US and Abroad

Mammographic breast density (MBD) has been proven to be an important risk factor for breast cancer and an important determinant of mammographic screening performance. The measurement of density has changed dramatically since its inception. Initial qualitative measurement methods have been found to have limited consistency between readers, and in regards to breast cancer risk. Following the introduction of full-field digital mammography, more sophisticated measurement methodology is now possible. Automated computer-based density measurements can provide consistent, reproducible, and objective results. In this review paper, we describe various methods currently available to assess MBD, and provide a discussion on the clinical utility of such methods for breast cancer screening.

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

PURPOSE

Mammographic density has been demonstrated to predict breast cancer risk. It has been proposed that it could be used for stratifying screening pathways and recommending additional imaging. Volumetric density tools use the recorded compressed breast thickness (CBT) of the breast measured at the x-ray unit in their calculation; however, the accuracy of the recorded thickness can vary. The aim of this study was to investigate whether inaccuracies in recorded CBT impact upon volumetric density classification and to examine whether the current quality control (QC) standard is sufficient for assessing mammographic density.

METHODS

Raw data from 52 digital screening mammograms were included in the study. For each image, the clinically recorded CBT was artificially increased and decreased in increments of 1 mm to simulate measurement error, until ±15% from the recorded CBT was reached. New images were created for each 1 mm step in thickness resulting in a total of 974 images which then had volpara density grade (VDG) and volumetric density percentage assigned.

RESULTS

A change in VDG was observed in 38.5% (n = 20) of mammograms when applying ±15% error to the recorded CBT and 11.5% (n = 6) was within the QC standard prescribed error of ±5 mm.

CONCLUSIONS

The current QC standard of ±5 mm error in recorded CBT creates the potential for error in mammographic density measurement. This may lead to inaccurate classification of mammographic density. The current QC standard for assessing mammographic density should be reconsidered.

Mammographic density assessed on paired raw and processed digital images and on paired screen-film and digital images across three mammography systems

BACKGROUND

Inter-women and intra-women comparisons of mammographic density (MD) are needed in research, clinical and screening applications; however, MD measurements are influenced by mammography modality (screen film/digital) and digital image format (raw/processed). We aimed to examine differences in MD assessed on these image types.

METHODS

We obtained 1294 pairs of images saved in both raw and processed formats from Hologic and General Electric (GE) direct digital systems and a Fuji computed radiography (CR) system, and 128 screen-film and processed CR-digital pairs from consecutive screening rounds. Four readers performed Cumulus-based MD measurements (n = 3441), with each image pair read by the same reader. Multi-level models of square-root percent MD were fitted, with a random intercept for woman, to estimate processed-raw MD differences.

RESULTS

Breast area did not differ in processed images compared with that in raw images, but the percent MD was higher, due to a larger dense area (median 28.5 and 25.4 cm2 respectively, mean √dense area difference 0.44 cm (95% CI: 0.36, 0.52)). This difference in √dense area was significant for direct digital systems (Hologic 0.50 cm (95% CI: 0.39, 0.61), GE 0.56 cm (95% CI: 0.42, 0.69)) but not for Fuji CR (0.06 cm (95% CI: -0.10, 0.23)). Additionally, within each system, reader-specific differences varied in magnitude and direction (p < 0.001). Conversion equations revealed differences converged to zero with increasing dense area. MD differences between screen-film and processed digital on the subsequent screening round were consistent with expected time-related MD declines.

CONCLUSIONS

MD was slightly higher when measured on processed than on raw direct digital mammograms. Comparisons of MD on these image formats should ideally control for this non-constant and reader-specific difference.

Mammographic density and risk of breast cancer by mode of detection and tumor size: a case-control study

BACKGROUND

Risk of screen-detected breast cancer mostly reflects inherent risk, while risk of interval cancer reflects inherent risk and risk of masking (risk of the tumor not being detected due to increased dense tissue). Therefore the predictors of whether a breast cancer is interval or screen-detected include those that predict masking. Our aim was to investigate the associations between mammographic measures and (1) inherent risk, and (2) masking.

METHODS

We conducted a case-control study nested within the Melbourne collaborative cohort study of 244 screen-detected cases (192 small tumors (<2 cm)) matched to 700 controls and 148 interval cases (76 small tumors) matched to 446 controls. Dense area (DA), percent dense area (PDA), and non-dense area (NDA) were measured using the Cumulus software. Conditional and unconditional logistic regression were applied as appropriate to estimate the odds per adjusted standard deviation (OPERA) adjusted for age and body mass index (BMI), allowing for the association with BMI to be a function of age at diagnosis. Tests of fit were performed using the Bayesian information criterion (BIC) and the area under the receiver operating characteristic curve.

RESULTS

For screen-detected cancer, the association with BMI had a marginally significant dependence on age at diagnosis, and after adjustment both DA and PDA were associated with risk (OPERA approximately 1.2) and gave a similar fit. NDA was not associated with risk. For interval cancer, the BMI risk association was not dependent on age at diagnosis and the best fitting model was PDA alone (OPERA = 2.24, 95 % confidence interval 1.75, 2.86). Prediction of interval versus screen-detected cancer was best achieved by PDA alone (OPERA = 1.76, 95 % confidence interval 1.39, 2.22) with no association with BMI. When the analysis was restricted to small tumors to reduce the influence of tumor growth, we obtained similar results.

CONCLUSIONS

Inherent breast cancer risk is predicted by BMI and DA or PDA, but not NDA. Masking is predicted by PDA, and not by BMI. Understanding risk and masking could help tailor mammographic screening.

Reliability of Computer-Assisted Breast Density Estimation: Comparison of Interactive Thresholding, Semiautomated, and Fully Automated Methods

OBJECTIVE

The purpose of this study was to investigate the reliability of computer-assisted methods of estimating breast density.

MATERIALS AND METHODS

Craniocaudal mammograms of 100 healthy subjects were collected from a screening mammography database. Three expert readers independently assessed mammographic breast density twice in a 1-month period using interactive thresholding and semiautomated methods. In addition, fully automated breast density estimation software was used to generate objective breast density estimates. The reliability of the computer-assisted breast density estimation was assessed in terms of concordance correlation coefficients, limits of agreement, systematic difference, and reader variability.

RESULTS

Statistically significant systematic bias (paired t test, p < 0.01) and variability (4.75-10.91) were found within and between readers for both the interactive thresholding and the semiautomated methods. Using the semiautomated method significantly reduced the within-reader bias of one reader (p < 0.02) and the between-reader variability of all three readers (p < 0.05). The breast density estimates obtained with the fully automated method had excellent agreement with those of the reference standard (concordance correlation coefficient, 0.93) without a significant systematic difference.

CONCLUSION

Reader-dependent variability and systematic bias exist in breast density estimates obtained with the interactive thresholding method, but they may be reduced in part by use of the semiautomated method. Assessing reader performance may be necessary for more reliable breast density estimation, especially for surveillance of breast density over time. The fully automated method has the potential to provide reliable breast density estimates nearly free from reader-dependent systematic bias and reader variability.

Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring

Mammographic risk scoring has commonly been automated by extracting a set of handcrafted features from mammograms, and relating the responses directly or indirectly to breast cancer risk. We present a method that learns a feature hierarchy from unlabeled data. When the learned features are used as the input to a simple classifier, two different tasks can be addressed: i) breast density segmentation, and ii) scoring of mammographic texture. The proposed model learns features at multiple scales. To control the models capacity a novel sparsity regularizer is introduced that incorporates both lifetime and population sparsity. We evaluated our method on three different clinical datasets. Our state-of-the-art results show that the learned breast density scores have a very strong positive relationship with manual ones, and that the learned texture scores are predictive of breast cancer. The model is easy to apply and generalizes to many other segmentation and scoring problems.

Mammographic Breast Density in Chinese Women: Spatial Distribution and Autocorrelation Patterns

Mammographic breast density (MBD) is a strong risk factor for breast cancer. The spatial distribution of MBD in the breast is variable and dependent on physiological, genetic, environmental and pathological factors. This pilot study aims to define the spatial distribution and autocorrelation patterns of MBD in Chinese women aged 40–60. By analyzing their digital mammographic images using a public domain Java image processing program for segmentation and quantification of MBD, we found their left and right breasts were symmetric to each other in regard to their breast size (Total Breast Area), the amount of BMD (overall PD) and Moran's I values. Their MBD was also spatially autocorrelated together in the anterior part of the breast in those with a smaller breast size, while those with a larger breast size tend to have their MBD clustered near the posterior part of the breast. Finally, we observed that the autocorrelation pattern of MBD was dispersed after a 3-year observation period.

Preliminary evaluation of the publicly available Laboratory for Breast Radiodensity Assessment (LIBRA) software tool: comparison of fully automated area and volumetric density measures in a case-control study with digital mammography

INTRODUCTION

Breast density, commonly quantified as the percentage of mammographically dense tissue area, is a strong breast cancer risk factor. We investigated associations between breast cancer and fully automated measures of breast density made by a new publicly available software tool, the Laboratory for Individualized Breast Radiodensity Assessment (LIBRA).

METHODS

Digital mammograms from 106 invasive breast cancer cases and 318 age-matched controls were retrospectively analyzed. Density estimates acquired by LIBRA were compared with commercially available software and standard Breast Imaging-Reporting and Data System (BI-RADS) density estimates. Associations between the different density measures and breast cancer were evaluated by using logistic regression after adjustment for Gail risk factors and body mass index (BMI). Area under the curve (AUC) of the receiver operating characteristic (ROC) was used to assess discriminatory capacity, and odds ratios (ORs) for each density measure are provided.

RESULTS

All automated density measures had a significant association with breast cancer (OR = 1.47-2.23, AUC = 0.59-0.71, P < 0.01) which was strengthened after adjustment for Gail risk factors and BMI (OR = 1.96-2.64, AUC = 0.82-0.85, P < 0.001). In multivariable analysis, absolute dense area (OR = 1.84, P < 0.001) and absolute dense volume (OR = 1.67, P = 0.003) were jointly associated with breast cancer (AUC = 0.77, P < 0.01), having a larger discriminatory capacity than models considering the Gail risk factors alone (AUC = 0.64, P < 0.001) or the Gail risk factors plus standard area percent density (AUC = 0.68, P = 0.01). After BMI was further adjusted for, absolute dense area retained significance (OR = 2.18, P < 0.001) and volume percent density approached significance (OR = 1.47, P = 0.06). This combined area-volume density model also had a significantly (P < 0.001) improved discriminatory capacity (AUC = 0.86) relative to a model considering the Gail risk factors plus BMI (AUC = 0.80).

CONCLUSIONS

Our study suggests that new automated density measures may ultimately augment the current standard breast cancer risk factors. In addition, the ability to fully automate density estimation with digital mammography, particularly through the use of publically available breast density estimation software, could accelerate the translation of density reporting in routine breast cancer screening and surveillance protocols and facilitate broader research into the use of breast density as a risk factor for breast cancer.

A Review on Automatic Mammographic Density and Parenchymal Segmentation

Breast cancer is the most frequently diagnosed cancer in women. However, the exact cause(s) of breast cancer still remains unknown. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective way to tackle breast cancer. There are more than 70 common genetic susceptibility factors included in the current non-image-based risk prediction models (e.g., the Gail and the Tyrer-Cuzick models). Image-based risk factors, such as mammographic densities and parenchymal patterns, have been established as biomarkers but have not been fully incorporated in the risk prediction models used for risk stratification in screening and/or measuring responsiveness to preventive approaches. Within computer aided mammography, automatic mammographic tissue segmentation methods have been developed for estimation of breast tissue composition to facilitate mammographic risk assessment. This paper presents a comprehensive review of automatic mammographic tissue segmentation methodologies developed over the past two decades and the evidence for risk assessment/density classification using segmentation. The aim of this review is to analyse how engineering advances have progressed and the impact automatic mammographic tissue segmentation has in a clinical environment, as well as to understand the current research gaps with respect to the incorporation of image-based risk factors in non-image-based risk prediction models.

Associations between breast density and a panel of single nucleotide polymorphisms linked to breast cancer risk: a cohort study with digital mammography

Background

Breast density and single-nucleotide polymorphisms (SNPs) have both been associated with breast cancer risk. To determine the extent to which these two breast cancer risk factors are associated, we investigate the association between a panel of validated SNPs related to breast cancer and quantitative measures of mammographic density in a cohort of Caucasian and African-American women.

Methods

In this IRB-approved, HIPAA-compliant study, we analyzed a screening population of 639 women (250 African American and 389 Caucasian) who were tested with a validated panel assay of 12 SNPs previously associated to breast cancer risk. Each woman underwent digital mammography as part of routine screening and all were interpreted as negative. Both absolute and percent estimates of area and volumetric density were quantified on a per-woman basis using validated software. Associations between the number of risk alleles in each SNP and the density measures were assessed through a race-stratified linear regression analysis, adjusted for age, BMI, and Gail lifetime risk.

Results

The majority of SNPs were not found to be associated with any measure of breast density. SNP rs3817198 (in LSP1) was significantly associated with both absolute area (p = 0.004) and volumetric (p = 0.019) breast density in Caucasian women. In African-American women, SNPs rs3803662 (in TNRC9/TOX3) and rs4973768 (in NEK10) were significantly associated with absolute (p = 0.042) and percent (p = 0.028) volume density respectively.

Conclusions

The majority of SNPs investigated in our study were not found to be significantly associated with breast density, even when accounting for age, BMI, and Gail risk, suggesting that these two different risk factors contain potentially independent information regarding a woman’s risk to develop breast cancer. Additionally, the few statistically significant associations between breast density and SNPs were different for Caucasian versus African American women. Larger prospective studies are warranted to validate our findings and determine potential implications for breast cancer risk assessment.

Electronic supplementary material

The online version of this article (doi:10.1186/s12885-015-1159-3) contains supplementary material, which is available to authorized users.

Risk determination and prevention of breast cancer

Breast cancer is an increasing public health problem. Substantial advances have been made in the treatment of breast cancer, but the introduction of methods to predict women at elevated risk and prevent the disease has been less successful. Here, we summarize recent data on newer approaches to risk prediction, available approaches to prevention, how new approaches may be made, and the difficult problem of using what we already know to prevent breast cancer in populations. During 2012, the Breast Cancer Campaign facilitated a series of workshops, each covering a specialty area of breast cancer to identify gaps in our knowledge. The risk-and-prevention panel involved in this exercise was asked to expand and update its report and review recent relevant peer-reviewed literature. The enlarged position paper presented here highlights the key gaps in risk-and-prevention research that were identified, together with recommendations for action. The panel estimated from the relevant literature that potentially 50% of breast cancer could be prevented in the subgroup of women at high and moderate risk of breast cancer by using current chemoprevention (tamoxifen, raloxifene, exemestane, and anastrozole) and that, in all women, lifestyle measures, including weight control, exercise, and moderating alcohol intake, could reduce breast cancer risk by about 30%. Risk may be estimated by standard models potentially with the addition of, for example, mammographic density and appropriate single-nucleotide polymorphisms. This review expands on four areas: (a) the prediction of breast cancer risk, (b) the evidence for the effectiveness of preventive therapy and lifestyle approaches to prevention, (c) how understanding the biology of the breast may lead to new targets for prevention, and (d) a summary of published guidelines for preventive approaches and measures required for their implementation. We hope that efforts to fill these and other gaps will lead to considerable advances in our efforts to predict risk and prevent breast cancer over the next 10 years.

Measurement of breast density with digital breast tomosynthesis--a systematic review

Digital breast tomosynthesis (DBT) has gained acceptance as an adjunct to digital mammography in screening. Now that breast density reporting is mandated in several states in the USA, it is increasingly important that the methods of breast density measurement be robust, reliable and consistent. Breast density assessment with DBT needs some consideration since quantitative methods are modelled for two-dimensional (2D) mammography. A review of methods used for breast density assessment with DBT was performed. Existing evidence shows Cumulus has better reproducibility than that of the breast imaging reporting and data system (BI-RADS®) but still suffers from subjective variability; MedDensity is limited by image noise, whilst Volpara and Quantra are robust and consistent. The reported BI-RADs inter-reader breast density agreement (k) ranged from 0.65 to 0.91, with inter-reader correlation (r) ranging from 0.70 to 0.93. The correlation (r) between BI-RADS and Cumulus ranged from 0.54-0.94, whilst that of BI-RADs and MedDensity ranged from 0.48-0.78. The reported agreement (k) between BI-RADs and Volpara is 0.953. Breast density correlation between DBT and 2D mammography ranged from 0.73 to 0.97, with agreement (k) ranging from 0.56 to 0.96. To avoid variability and provide more reliable breast density information for clinicians, automated volumetric methods are preferred.

Mammographic density-a review on the current understanding of its association with breast cancer

There has been considerable recent interest in the genetic, biological and epidemiological basis of mammographic density (MD), and the search for causative links between MD and breast cancer (BC) risk. This report will critically review the current literature on MD and summarize the current evidence for its association with BC. Keywords 'mammographic dens*', 'dense mammary tissue' or 'percent dens*' were used to search the existing literature in English on PubMed and Medline. All reports were critically analyzed. The data were assigned to one of the following aspects of MD: general association with BC, its relationship with the breast hormonal milieu, the cellular basis of MD, the generic variations of MD, and its significance in the clinical setting. MD adjusted for age, and BMI is associated with increased risk of BC diagnosis, advanced tumour stage at diagnosis and increased risk of both local recurrence and second primary cancers. The MD measures that predict BC risk have high heritability, and to date several genetic markers associated with BC risk have been found to also be associated with these MD risk predictors. Change in MD could be a predictor of the extent of chemoprevention with tamoxifen. Although the biological and genetic pathways that determine and perhaps modulate MD remain largely unresolved, significant inroads are being made into the understanding of MD, which may lead to benefits in clinical screening, assessment and treatment strategies. This review provides a timely update on the current understanding of MD's association with BC risk.