Comparison of Clinical and Automated Breast Density Measurements: Implications for Risk Prediction and Supplemental Screening

Breast Density: Where Are We Now?

Breast density refers to the amount of fibroglandular tissue relative to fat on mammography and is determined either qualitatively through visual assessment or quantitatively. It is a heritable and dynamic trait associated with age, race/ethnicity, body mass index, and hormonal factors. Increased breast density has important clinical implications including the potential to mask malignancy and as an independent risk factor for the development of breast cancer. Breast density has been incorporated into breast cancer risk models. Given the impact of dense breasts on the interpretation of mammography, supplemental screening may be indicated.

Inter- and intra-observer variability of qualitative visual breast-composition assessment in mammography among Japanese physicians: a first multi-institutional observer performance study in Japan

BACKGROUND

Visual assessment of mammographic breast composition remains the most common worldwide, although subjective variability limits its reproducibility. This study aimed to investigate the inter- and intra-observer variability in qualitative visual assessment of mammographic breast composition through a multi-institutional observer performance study for the first time in Japan.

METHODS

This study enrolled 10 Japanese physicians from five different institutions. They used the new Japanese breast-composition classification system 4th edition to subjectively evaluate the breast composition in 200 pairs of right and left normal mediolateral oblique mammograms (number determined using precise sample size calculations) twice, with a 1-month interval (median patient age: 59 years [range 40-69 years]). The primary endpoint of this study was the inter-observer variability using kappa (κ) value.

RESULTS

Inter-observer variability for the four and two classes of breast-composition assessment revealed moderate agreement (Fleiss' κ: first and second reading = 0.553 and 0.587, respectively) and substantial agreement (Fleiss' κ: first and second reading = 0.689 and 0.70, respectively). Intra-observer variability for the four and two classes of breast-composition assessment demonstrated substantial agreement (Cohen's κ, median = 0.758) and almost perfect agreement (Cohen's κ, median = 0.813). Assessments of consensus between the 10 physicians and the automated software Volpara® revealed slight agreement (Cohen's κ; first and second reading: 0.104 and 0.075, respectively).

CONCLUSIONS

Qualitative visual assessment of mammographic breast composition using the new Japanese classification revealed excellent intra-observer reproducibility. However, persistent inter-observer variability, presenting a challenge in establishing it as the gold standard in Japan.

A publicly available deep learning model and dataset for segmentation of breast, fibroglandular tissue, and vessels in breast MRI

Breast density, or the amount of fibroglandular tissue (FGT) relative to the overall breast volume, increases the risk of developing breast cancer. Although previous studies have utilized deep learning to assess breast density, the limited public availability of data and quantitative tools hinders the development of better assessment tools. Our objective was to (1) create and share a large dataset of pixel-wise annotations according to well-defined criteria, and (2) develop, evaluate, and share an automated segmentation method for breast, FGT, and blood vessels using convolutional neural networks. We used the Duke Breast Cancer MRI dataset to randomly select 100 MRI studies and manually annotated the breast, FGT, and blood vessels for each study. Model performance was evaluated using the Dice similarity coefficient (DSC). The model achieved DSC values of 0.92 for breast, 0.86 for FGT, and 0.65 for blood vessels on the test set. The correlation between our model's predicted breast density and the manually generated masks was 0.95. The correlation between the predicted breast density and qualitative radiologist assessment was 0.75. Our automated models can accurately segment breast, FGT, and blood vessels using pre-contrast breast MRI data. The data and the models were made publicly available.

Factors Associated with Increased Knowledge about Breast Density in South Australian Women Undergoing Breast Cancer Screening

Background: There is growing awareness of breast density in women attending breast cancer screening; however, it is unclear whether this awareness is associated with increased knowledge. This study aims to evaluate breast density knowledge among Australian women attending breast cancer screening. Method: This cross-sectional study was conducted on women undergoing breast cancer screening at The Queen Elizabeth Hospital Breast/Endocrine outpatient department. Participants were provided with a questionnaire to assess knowledge, awareness, and desire to know their own breast density. Result: Of the 350 women who participated, 61% were familiar with 'breast density' and 57% had 'some knowledge'. Prior breast density notification (OR = 4.99, 95% CI = 2.76, 9.03; p = 0.004), awareness (OR = 4.05, 95% CI = 2.57, 6.39; p = 0.004), younger age (OR = 0.97, 95% CI = 0.96, 0.99; p = 0.02), and English as the language spoken at home (OR = 3.29, 95% CI = 1.23, 8.77; p = 0.02) were independent predictors of 'some knowledge' of breast density. A significant proportion of participants (82%) expressed desire to ascertain their individual breast density. Conclusions: While knowledge of breast density in this Australian cohort is generally quite low, we have identified factors associated with increased knowledge. Further research is required to determine optimal interventions to increase breast density knowledge.

Breast density reduction as a predictor for prognosis in premenopausal women with estrogen receptor-positive breast cancer: an exploratory analysis of the updated ASTRRA study

BACKGROUND

While the relationship between mammographic breast density reduction (MDR) and endocrine therapy efficacy has been reported in estrogen receptor (ER)-positive breast cancer, it is still unclear in premenopausal women, especially in the case of adding ovarian function suppression (OFS) to antihormone therapy. The authors investigated the impact of MDR on prognosis stratified by treatment based on the updated results of the ASTRRA trial.

MATERIALS AND METHODS

The ASTRRA trial, a randomized phase III study, showed that adding OFS to tamoxifen (TAM) improved survival in premenopausal women with estrogen receptor-positive breast cancer after chemotherapy. The authors updated survival outcomes and assessed mammography before treatment and the annual follow-up mammography for up to 5 years after treatment initiation. Mammographic density (MD) was classified into four categories based on the Breast Imaging-Reporting and Data System. MDR-positivity was defined as a downgrade in MD grade on follow-up mammography up to 2 years after randomization, with pretreatment MD grade as a reference.

RESULTS

The authors evaluated MDR in 944 of the 1282 patients from the trial, and 813 (86.2%) had grade III or IV MD. There was no difference in the MDR-positivity rate between the two treatment groups [TAM-only group (106/476 (22.3%)) vs. TAM+OFS group (89/468 (19.0%)); P =0.217). MDR-positivity was significantly associated with better disease-free survival (DFS) in the TAM+OFS group (estimated 8-year DFS: 93.1% in MDR-positive vs. 82.0% in MDR-negative patients; HR: 0.37; 95% CI: 0.16-0.85; P =0.019), but not in the TAM-only group ( Pinteraction =0.039). MDR-positive patients who received TAM+OFS had a favorable DFS compared to MDR-negative patients who received only TAM (HR: 0.30; 95% CI: 0.13-0.70; P =0.005).

CONCLUSION

Although the proportion of MDR-positive patients was comparable between both treatment groups, MDR-positivity was independently associated with favorable outcomes only in the TAM+OFS group.

Impact of BMI on Prevalence of Dense Breasts by Race and Ethnicity

BACKGROUND

Density notification laws require notifying women of dense breasts with dense breast prevalence varying by race/ethnicity. We evaluated whether differences in body mass index (BMI) account for differences in dense breasts prevalence by race/ethnicity.

METHODS

Prevalence of dense breasts (heterogeneously or extremely dense) according to Breast Imaging Reporting and Data System and obesity (BMI > 30 kg/m2) were estimated from 2,667,207 mammography examinations among 866,033 women in the Breast Cancer Surveillance Consortium (BCSC) from January 2005 through April 2021. Prevalence ratios (PR) for dense breasts relative to overall prevalence by race/ethnicity were estimated by standardizing race/ethnicity prevalence in the BCSC to the 2020 U.S. population, and adjusting for age, menopausal status, and BMI using logistic regression.

RESULTS

Dense breasts were most prevalent among Asian women (66.0%) followed by non-Hispanic/Latina (NH) White (45.5%), Hispanic/Latina (45.3%), and NH Black (37.0%) women. Obesity was most prevalent in Black women (58.4%) followed by Hispanic/Latina (39.3%), NH White (30.6%), and Asian (8.5%) women. The adjusted prevalence of dense breasts was 19% higher [PR = 1.19; 95% confidence interval (CI), 1.19-1.20] in Asian women, 8% higher (PR = 1.08; 95% CI, 1.07-1.08) in Black women, the same in Hispanic/Latina women (PR = 1.00; 95% CI, 0.99-1.01), and 4% lower (PR = 0.96; 95% CI, 0.96-0.97) in NH White women relative to the overall prevalence.

CONCLUSIONS

Clinically important differences in breast density prevalence are present across racial/ethnic groups after accounting for age, menopausal status, and BMI.

IMPACT

If breast density is the sole criterion used to notify women of dense breasts and discuss supplemental screening it may result in implementing inequitable screening strategies across racial/ethnic groups. See related In the Spotlight, p. 1479.

Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography

OBJECTIVE

We aimed to evaluate the false interpretations between artificial intelligence (AI) and radiologists in screening mammography to get a better understanding of how the distribution of diagnostic mistakes might change when moving from entirely radiologist-driven to AI-integrated breast cancer screening.

METHODS AND MATERIALS

This retrospective case-control study was based on a mammography screening cohort from 2008 to 2015. The final study population included screening examinations for 714 women diagnosed with breast cancer and 8029 randomly selected healthy controls. Oversampling of controls was applied to attain a similar cancer proportion as in the source screening cohort. We examined how false-positive (FP) and false-negative (FN) assessments by AI, the first reader (RAD 1) and the second reader (RAD 2), were associated with age, density, tumor histology and cancer invasiveness in a single- and double-reader setting.

RESULTS

For each reader, the FN assessments were distributed between low- and high-density females with 53 (42%) and 72 (58%) for AI; 59 (36%) and 104 (64%) for RAD 1 and 47 (36%) and 84 (64%) for RAD 2. The corresponding numbers for FP assessments were 1820 (47%) and 2016 (53%) for AI; 1568 (46%) and 1834 (54%) for RAD 1 and 1190 (43%) and 1610 (58%) for RAD 2. For ductal cancer, the FN assessments were 79 (77%) for AI CAD; with 120 (83%) for RAD 1 and with 96 (16%) for RAD 2. For the double-reading simulation, the FP assessments were distributed between younger and older females with 2828 (2.5%) and 1554 (1.4%) for RAD 1 + RAD 2; 3850 (3.4%) and 2940 (2.6%) for AI+RAD 1 and 3430 (3%) and 2772 (2.5%) for AI+RAD 2.

CONCLUSION

The most pronounced decrease in FN assessments was noted for females over the age of 55 and for high density-women. In conclusion, AI could have an important complementary role when combined with radiologists to increase sensitivity for high-density and older females.

ADVANCES IN KNOWLEDGE

Our results highlight the potential impact of integrating AI in breast cancer screening, particularly to improve interpretation accuracy. The use of AI could enhance screening outcomes for high-density and older females.

Local texture statistics augment the power spectrum in modeling radiographic judgments of breast density

Purpose

Anatomical "noise" is an important limitation of full-field digital mammography. Understanding its impact on clinical judgments is made difficult by the complexity of breast parenchyma, which results in image texture not fully captured by the power spectrum. While the number of possible parameters for characterizing anatomical noise is quite large, a specific set of local texture statistics has been shown to be visually salient, and human sensitivity to these statistics corresponds to their informativeness in natural scenes.

Approach

We evaluate these local texture statistics in addition to standard power-spectral measures to determine whether they have additional explanatory value for radiologists' breast density judgments. We analyzed an image database consisting of 111 disease-free mammographic screening exams (4 views each) acquired at the University of Pittsburgh Medical Center. Each exam had a breast density score assigned by the examining radiologist. Power-spectral descriptors and local image statistics were extracted from images of breast parenchyma. Model-selection criteria and accuracy were used to assess the explanatory and predictive value of local image statistics for breast density judgments.

Results

The model selection criteria show that adding local texture statistics to descriptors of the power spectra produce better explanatory and predictive models of radiologists' judgments of breast density. Thus, local texture statistics capture, in some form, non-Gaussian aspects of texture that radiologists are using.

Conclusions

Since these local texture statistics are expected to be impacted by imaging factors like modality, dose, and image processing, they suggest avenues for understanding and optimizing observer performance.

Factors Associated with Longitudinal Changes in Mammographic Density in a Multiethnic Breast Screening Cohort of Postmenopausal Women

Background

Breast density is an important risk factor for breast cancer and is known to be associated with characteristics such as age, race, and hormone levels; however, it is unclear what factors contribute to changes in breast density in postmenopausal women over time. Understanding factors associated with density changes may enable a better understanding of breast cancer risk and facilitate potential strategies for prevention.

Methods

This study investigated potential associations between personal factors and changes in mammographic density in a cohort of 3,392 postmenopausal women with no personal history of breast cancer between 2011 and 2017. Self-reported information on demographics, breast and reproductive history, and lifestyle factors, including body mass index (BMI), alcohol intake, smoking, and physical activity, was collected by an electronic intake form, and breast imaging reporting and database system (BI-RADS) mammographic density scores were obtained from electronic medical records. Factors associated with a longitudinal increase or decrease in mammographic density were identified using Fisher's exact test and multivariate conditional logistic regression.

Results

7.9% of women exhibited a longitudinal decrease in mammographic density, 6.7% exhibited an increase, and 85.4% exhibited no change. Longitudinal changes in mammographic density were correlated with age, race/ethnicity, and age at menopause in the univariate analysis. In the multivariate analysis, Asian women were more likely to exhibit a longitudinal increase in mammographic density and less likely to exhibit a decrease compared to White women. On the other hand, obese women were less likely to exhibit an increase and more likely to exhibit a decrease compared to normal weight women. Women who underwent menopause at age 55 years or older were less likely to exhibit a decrease in mammographic density compared to women who underwent menopause at a younger age. Besides obesity, lifestyle factors (alcohol intake, smoking, and physical activity) were not associated with longitudinal changes in mammographic density.

Conclusions

The associations we observed between Asian race/obesity and longitudinal changes in BI-RADS density in postmenopausal women are paradoxical in that breast cancer risk is lower in Asian women and higher in obese women. However, the association between later age at menopause and a decreased likelihood of decreasing in BI-RADS density over time is consistent with later age at menopause being a risk factor for breast cancer and suggests a potential relationship between greater cumulative lifetime estrogen exposure and relative stability in breast density after menopause. Our findings support the complexity of the relationships between breast density, BMI, hormone exposure, and breast cancer risk.

Breast Cancer in Dense Breasts: Detection Challenges and Supplemental Screening Opportunities

Dense breast tissue at mammography is associated with higher breast cancer incidence and mortality rates, which have prompted new considerations for breast cancer screening in women with dense breasts. The authors review the definition and classification of breast density, density assessment methods, breast cancer risk, current legislation, and future efforts and summarize trials and key studies that have affected the existing guidelines for supplemental screening. Cases of breast cancer in dense breasts are presented, highlighting a variety of modalities and specific imaging findings that can aid in cancer detection and staging. Understanding the current state of breast cancer screening in patients with dense breasts and its challenges is important to shape future considerations for care. Shifting the paradigm of breast cancer detection toward early diagnosis for women with dense breasts may be the answer to reducing the number of deaths from this common disease. ©RSNA, 2023 Online supplemental material is available for this article. Quiz questions for this article are available through the Online Learning Center. See the invited commentary by Yeh in this issue.

Association and Prediction Utilizing Craniocaudal and Mediolateral Oblique View Digital Mammography and Long-Term Breast Cancer Risk

Mammographic percentage of volumetric density is an important risk factor for breast cancer. Epidemiology studies historically used film images often limited to craniocaudal (CC) views to estimate area-based breast density. More recent studies using digital mammography images typically use the averaged density between craniocaudal (CC) and mediolateral oblique (MLO) view mammography for 5- and 10-year risk prediction. The performance in using either and both mammogram views has not been well-investigated. We use 3,804 full-field digital mammograms from the Joanne Knight Breast Health Cohort (294 incident cases and 657 controls), to quantity the association between volumetric percentage of density extracted from either and both mammography views and to assess the 5 and 10-year breast cancer risk prediction performance. Our results show that the association between percent volumetric density from CC, MLO, and the average between the two, retain essentially the same association with breast cancer risk. The 5- and 10-year risk prediction also shows similar prediction accuracy. Thus, one view is sufficient to assess association and predict future risk of breast cancer over a 5 or 10-year interval.

PREVENTION RELEVANCE

Expanding use of digital mammography and repeated screening provides opportunities for risk assessment. To use these images for risk estimates and guide risk management in real time requires efficient processing. Evaluating the contribution of different views to prediction performance can guide future applications for risk management in routine care.

Mammographic Breast Density Model Using Semi-Supervised Learning Reduces Inter-/Intra-Reader Variability

Breast density is an important risk factor for breast cancer development; however, imager inconsistency in density reporting can lead to patient and clinician confusion. A deep learning (DL) model for mammographic density grading was examined in a retrospective multi-reader multi-case study consisting of 928 image pairs and assessed for impact on inter- and intra-reader variability and reading time. Seven readers assigned density categories to the images, then re-read the test set aided by the model after a 4-week washout. To measure intra-reader agreement, 100 image pairs were blindly double read in both sessions. Linear Cohen Kappa (κ) and Student's t-test were used to assess the model and reader performance. The model achieved a κ of 0.87 (95% CI: 0.84, 0.89) for four-class density assessment and a κ of 0.91 (95% CI: 0.88, 0.93) for binary non-dense/dense assessment. Superiority tests showed significant reduction in inter-reader variability (κ improved from 0.70 to 0.88, p ≤ 0.001) and intra-reader variability (κ improved from 0.83 to 0.95, p ≤ 0.01) for four-class density, and significant reduction in inter-reader variability (κ improved from 0.77 to 0.96, p ≤ 0.001) and intra-reader variability (κ improved from 0.89 to 0.97, p ≤ 0.01) for binary non-dense/dense assessment when aided by DL. The average reader mean reading time per image pair also decreased by 30%, 0.86 s (95% CI: 0.01, 1.71), with six of seven readers having reading time reductions.

Impact of Artificial Intelligence System and Volumetric Density on Risk Prediction of Interval, Screen-Detected, and Advanced Breast Cancer

PURPOSE

Artificial intelligence (AI) algorithms improve breast cancer detection on mammography, but their contribution to long-term risk prediction for advanced and interval cancers is unknown.

METHODS

We identified 2,412 women with invasive breast cancer and 4,995 controls matched on age, race, and date of mammogram, from two US mammography cohorts, who had two-dimensional full-field digital mammograms performed 2-5.5 years before cancer diagnosis. We assessed Breast Imaging Reporting and Data System density, an AI malignancy score (1-10), and volumetric density measures. We used conditional logistic regression to estimate odds ratios (ORs), 95% CIs, adjusted for age and BMI, and C-statistics (AUC) to describe the association of AI score with invasive cancer and its contribution to models with breast density measures. Likelihood ratio tests (LRTs) and bootstrapping methods were used to compare model performance.

RESULTS

On mammograms between 2-5.5 years prior to cancer, a one unit increase in AI score was associated with 20% greater odds of invasive breast cancer (OR, 1.20; 95% CI, 1.17 to 1.22; AUC, 0.63; 95% CI, 0.62 to 0.64) and was similarly predictive of interval (OR, 1.20; 95% CI, 1.13 to 1.27; AUC, 0.63) and advanced cancers (OR, 1.23; 95% CI, 1.16 to 1.31; AUC, 0.64) and in dense (OR, 1.18; 95% CI, 1.15 to 1.22; AUC, 0.66) breasts. AI score improved prediction of all cancer types in models with density measures (PLRT values < .001); discrimination improved for advanced cancer (ie, AUC for dense volume increased from 0.624 to 0.679, Δ AUC 0.065, P = .01) but did not reach statistical significance for interval cancer.

CONCLUSION

AI imaging algorithms coupled with breast density independently contribute to long-term risk prediction of invasive breast cancers, in particular, advanced cancer.

Effects of bariatric surgery on breast density in adult obese women: systematic review and meta-analysis

Introduction

Bariatric surgery is one of the most effective methods for treating obesity. It can effectively reduce body weight and reduce the incidence of obesity-related breast cancer. However, there are different conclusions about how bariatric surgery changes breast density. The purpose of this study was to clarify the changes in breast density from before to after bariatric surgery.

Methods

The relevant literature was searched through PubMed and Embase to screen for studies. Meta-analysis was used to clarify the changes in breast density from before to after bariatric surgery.

Results

A total of seven studies were included in this systematic review and meta-analysis, including a total of 535 people. The average body mass index decreased from 45.3 kg/m2 before surgery to 34.4 kg/m2 after surgery. By the Breast Imaging Reporting and Data System score, the proportion of grade A breast density from before to after bariatric surgery decreased by 3.83% (183 vs. 176), grade B (248 vs. 263) increased by 6.05%, grade C (94 vs. 89) decreased by 5.32%, and grade D (1 vs. 4) increased by 300%. There was no significant change in breast density from before to after bariatric surgery (OR=1.27, 95% confidence interval (CI) [0.74, 2.20], P=0.38). By the Volpara density grade score, postoperative volumetric breast density increased (standardized mean difference = -0.68, 95% CI [-1.08, -0.27], P = 0.001).

Discussions

Breast density increased significantly after bariatric surgery, but this depended on the method of detecting breast density. Further randomized controlled studies are needed to validate our conclusions.

Changes in Automated Mammographic Breast Density Can Predict Pathological Response After Neoadjuvant Chemotherapy in Breast Cancer

OBJECTIVE

Mammographic density is an independent risk factor for breast cancer that can change after neoadjuvant chemotherapy (NCT). This study aimed to evaluate percent changes in volumetric breast density (ΔVbd%) before and after NCT measured automatically and determine its value as a predictive marker of pathological response to NCT.

MATERIALS AND METHODS

A total of 357 patients with breast cancer treated between January 2014 and December 2016 were included. An automated volumetric breast density (Vbd) measurement method was used to calculate Vbd on mammography before and after NCT. Patients were divided into three groups according to ΔVbd%, calculated as follows: Vbd (post-NCT - pre-NCT)/pre-NCT Vbd × 100 (%). The stable, decreased, and increased groups were defined as -20% ≤ ΔVbd% ≤ 20%, ΔVbd% < -20%, and ΔVbd% > 20%, respectively. Pathological complete response (pCR) was considered to be achieved after NCT if there was no evidence of invasive carcinoma in the breast or metastatic tumors in the axillary and regional lymph nodes on surgical pathology. The association between ΔVbd% grouping and pCR was analyzed using univariable and multivariable logistic regression analyses.

RESULTS

The interval between the pre-NCT and post-NCT mammograms ranged from 79 to 250 days (median, 170 days). In the multivariable analysis, ΔVbd% grouping (odds ratio for pCR of 0.420 [95% confidence interval, 0.195-0.905; P = 0.027] for the decreased group compared with the stable group), N stage at diagnosis, histologic grade, and breast cancer subtype were significantly associated with pCR. This tendency was more evident in the luminal B-like and triple-negative subtypes.

CONCLUSION

ΔVbd% was associated with pCR in breast cancer after NCT, with the decreased group showing a lower rate of pCR than the stable group. Automated measurement of ΔVbd% may help predict the NCT response and prognosis in breast cancer.

Breast Density Evaluation According to BI-RADS 5th Edition on Digital Breast Tomosynthesis: AI Automated Assessment Versus Human Visual Assessment

Background: The assessment of breast density is one of the main goals of radiologists because the masking effect of dense fibroglandular tissue may affect the mammographic identification of lesions. The BI-RADS 5th Edition has revised the mammographic breast density categories, focusing on a qualitative evaluation rather than a quantitative one. Our purpose is to compare the concordance of the automatic classification of breast density with the visual assessment according to the latest available classification. Methods: A sample of 1075 digital breast tomosynthesis images from women aged between 40 and 86 years (58 ± 7.1) was retrospectively analyzed by three independent readers according to the BI-RADS 5th Edition. Automated breast density assessment was performed on digital breast tomosynthesis images with the Quantra software version 2.2.3. Interobserver agreement was assessed with kappa statistics. The distributions of breast density categories were compared and correlated with age. Results: The agreement on breast density categories was substantial to almost perfect between radiologists (κ = 0.63–0.83), moderate to substantial between radiologists and the Quantra software (κ = 0.44–0.78), and the consensus of radiologists and the Quantra software (κ = 0.60–0.77). Comparing the assessment for dense and non-dense breasts, the agreement was almost perfect in the screening age range without a statistically significant difference between concordant and discordant cases when compared by age. Conclusions: The categorization proposed by the Quantra software has shown a good agreement with the radiological evaluations, even though it did not completely reflect the visual assessment. Thus, clinical decisions regarding supplemental screening should be based on the radiologist’s perceived masking effect rather than the data produced exclusively by the Quantra software.

Validity of computed mean compressed fibroglandular tissue thickness and breast composition for stratification of masking risk in Japanese women

BACKGROUND

The volumetric measurement system for mammographic breast density is a high-precision objective method for evaluating the percentage of fibroglandular tissue volume (FG%). Nonetheless, FG% does not precisely correlate with subjective visual estimation (SVE) and shows poor evaluation performance regarding masking risk in patients with comparatively thin compressed breast thickness (CBT), commonly found in Japanese women. We considered that the mean compressed fibroglandular tissue thickness (mCGT), which incorporates the CBT element into the evaluation of breast density, may better predict masking risk.

METHODS

Volumetric measurements and SVEs were performed on mammograms of 108 breast cancer patients from our center. mCGT was calculated as the product of CBT and FG%. SVE was classified using the Breast Imaging-Reporting and Data System classification, 5th edition. Subsequently, the performance of mCGT, SVE, and FG% in predicting masking risk was estimated using the AUC.

RESULTS

The AUC values of mCGT and SVE were 0.84 (95% confidence interval, 0.71-0.92) and 0.78 (0.66-0.86), respectively (P = 0.16). The AUC of the FG% was 0.65 (0.52-0.77), which was significantly lower than that of mCGT (P < 0.001). The sensitivity and specificity of mCGT in predicting negative detection were 89% and 71%, respectively; of SVE 83% and 61% (versus 72% and 57% with FG%), suggesting that mCGT was superior to FG% in both sensitivity and specificity, and comparable with SVE.

CONCLUSIONS

Objective mCGT calculated from the volumetric measurement system will highly likely be useful in evaluating breast density and supporting visual assessment for masking risk stratification.

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.

Prediction of breast cancer risk by automated volumetric breast density measurement

PURPOSE

Dense breast (DB) is recognized as a breast cancer (BC) risk factor. Although DB is common in Japanese women, the incidence of BC is lower than in Caucasians. We evaluated whether DB is a risk factor or whether there are other risk factors for BC in Japanese women.

MATERIALS AND METHODS

We retrospectively analyzed 635 BC patients and 999 controls who received a mammography at our hospital between February 2019 and March 2021. Volumetric breast density percentage (VBD%), breast volume (BV), and fibroglandular volume (FGV) were measured using Volpara™, an automated, three-dimensional image analysis program. A VBD% of 7.5% or higher was classified as DB. The association between the VBD%, BV, and FGV, and BC risk were assessed using logistic regression.

RESULTS

Of the BC group and the control group, 77% and 79% had DB. The stratified FGV was positively associated with BC risk (odds ratio: 2.84; 95% confidence interval 1.58-5.12; P < 0.001). No significant association was found between either the VBD% or BV and BC risk.

CONCLUSION

The proportion of Japanese women with DB was high, suggesting that DB might not be significantly associated with BC risk. However, our results also suggested that the FGV may be related to BC risk in Japanese women.

Deep Learning Models for Automated Assessment of Breast Density Using Multiple Mammographic Image Types

Simple Summary

The DL model predictions in automated breast density assessment were independent of the imaging technologies, moderately or substantially agreed with the clinical reader density values, and had improved performance as compared to inclusion of commercial software values.

Abstract

Recently, convolutional neural network (CNN) models have been proposed to automate the assessment of breast density, breast cancer detection or risk stratification using single image modality. However, analysis of breast density using multiple mammographic types using clinical data has not been reported in the literature. In this study, we investigate pre-trained EfficientNetB0 deep learning (DL) models for automated assessment of breast density using multiple mammographic types with and without clinical information to improve reliability and versatility of reporting. 120,000 for-processing and for-presentation full-field digital mammograms (FFDM), digital breast tomosynthesis (DBT), and synthesized 2D images from 5032 women were retrospectively analyzed. Each participant underwent up to 3 screening examinations and completed a questionnaire at each screening encounter. Pre-trained EfficientNetB0 DL models with or without clinical history were optimized. The DL models were evaluated using BI-RADS (fatty, scattered fibroglandular densities, heterogeneously dense, or extremely dense) versus binary (non-dense or dense) density classification. Pre-trained EfficientNetB0 model performances were compared using inter-observer and commercial software (Volpara) variabilities. Results show that the average Fleiss’ Kappa score between-observers ranged from 0.31–0.50 and 0.55–0.69 for the BI-RADS and binary classifications, respectively, showing higher uncertainty among experts. Volpara-observer agreement was 0.33 and 0.54 for BI-RADS and binary classifications, respectively, showing fair to moderate agreement. However, our proposed pre-trained EfficientNetB0 DL models-observer agreement was 0.61–0.66 and 0.70–0.75 for BI-RADS and binary classifications, respectively, showing moderate to substantial agreement. Overall results show that the best breast density estimation was achieved using for-presentation FFDM and DBT images without added clinical information. Pre-trained EfficientNetB0 model can automatically assess breast density from any images modality type, with the best results obtained from for-presentation FFDM and DBT, which are the most common image archived in clinical practice.

Mammographic breast density and the risk of breast cancer: A systematic review and meta-analysis

OBJECTIVES

Mammographic density is a well-defined risk factor for breast cancer and having extremely dense breast tissue is associated with a one-to six-fold increased risk of breast cancer. However, it is questioned whether this increased risk estimate is applicable to current breast density classification methods. Therefore, the aim of this study was to further investigate and clarify the association between mammographic density and breast cancer risk based on current literature.

METHODS

Medline, Embase and Web of Science were systematically searched for articles published since 2013, that used BI-RADS lexicon 5th edition and incorporated data on digital mammography. Crude and maximally confounder-adjusted data were pooled in odds ratios (ORs) using random-effects models. Heterogeneity regarding breast cancer risks were investigated using I² statistic, stratified and sensitivity analyses.

RESULTS

Nine observational studies were included. Having extremely dense breast tissue (BI-RADS density D) resulted in a 2.11-fold (95% CI 1.84-2.42) increased breast cancer risk compared to having scattered dense breast tissue (BI-RADS density B). Sensitivity analysis showed that when only using data that had adjusted for age and BMI, the breast cancer risk was 1.83-fold (95% CI 1.52-2.21) increased. Both results were statistically significant and homogenous.

CONCLUSIONS

Mammographic breast density BI-RADS D is associated with an approximately two-fold increased risk of breast cancer compared to having BI-RADS density B in general population women. This is a novel and lower risk estimate compared to previously reported and might be explained due to the use of digital mammography and BI-RADS lexicon 5th edition.

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.

Exposure to natural vegetation in relation to mammographic density in a Massachusetts-based clinical cohort

Inverse associations between natural vegetation exposure (i.e., greenness) and breast cancer risk have been reported; however, it remains unknown whether greenness affects breast tissue development or operates through other mechanisms (e.g., body mass index [BMI] or physical activity). We examined the association between greenness and mammographic density—a strong breast cancer risk factor—to determine whether greenness influences breast tissue composition independent of lifestyle factors.

Utility of U-Net for the objective segmentation of the fibroglandular tissue region on clinical digital mammograms

This study investigates the equivalence or compatibility between U-Net and visual segmentations of fibroglandular tissue regions by mammography experts for calculating the breast density and mean glandular dose (MGD). A total of 703 mediolateral oblique-view mammograms were used for segmentation. Two region types were set as the ground truth (determined visually): (1) one type included only the region where fibroglandular tissue was identifiable (called the 'dense region'); (2) the other type included the region where the fibroglandular tissue may have existed in the past, provided that apparent adipose-only parts, such as the retromammary space, are excluded (the 'diffuse region'). U-Net was trained to segment the fibroglandular tissue region with an adaptive moment estimation optimiser, five-fold cross-validated with 400 training and 100 validation mammograms, and tested with 203 mammograms. The breast density and MGD were calculated using the van Engeland and Dance formulas, respectively, and compared between U-Net and the ground truth with the Dice similarity coefficient and Bland-Altman analysis. Dice similarity coefficients between U-Net and the ground truth were 0.895 and 0.939 for the dense and diffuse regions, respectively. In the Bland-Altman analysis, no proportional or fixed errors were discovered in either the dense or diffuse region for breast density, whereas a slight proportional error was discovered in both regions for the MGD (the slopes of the regression lines were -0.0299 and -0.0443 for the dense and diffuse regions, respectively). Consequently, the U-Net and ground truth were deemed equivalent (interchangeable) for breast density and compatible (interchangeable following four simple arithmetic operations) for MGD. U-Net-based segmentation of the fibroglandular tissue region was satisfactory for both regions, providing reliable segmentation for breast density and MGD calculations. U-Net will be useful in developing a reliable individualised screening-mammography programme, instead of relying on the visual judgement of mammography experts.

Mammographic breast density and breast cancer risk in the Saudi population: a case-control study using visual and automated methods

OBJECTIVE

This study aims to establish risk of breast cancer based on breast density among Saudi women and to compare cancer prediction using different breast density methods.

METHODS

1140 pseudonymised screening mammograms from Saudi females were retrospectively collected. Breast density was assessed using Breast Imaging Reporting and Data System (BI-RADS) density categories and visual analogue scale (VAS) of 285 cases and 855 controls matched on age and body mass index. In a subset of 160 cases and 480 controls density was estimated by two automated methods, Volpara Density™ and predicted VAS (pVAS). Odds ratios (ORs) between the highest and second categories in BI-RADS and Volpara density grades, and highest vs lowest quartiles in VAS, pVAS and Volpara Density™, were estimated using conditional logistic regression.

RESULTS

For BI-RADS, the OR was 6.69 (95% CI 2.79-16.06) in the highest vs second category and OR = 4.78 (95% CI 3.01-7.58) in the highest vs lowest quartile for VAS. In the subset, VAS was the strongest predictor OR = 7.54 (95% CI 3.86-14.74), followed by pVAS using raw images OR = 5.38 (95% CI 2.68-10.77) and Volpara Density ™ OR = 3.55, (95% CI 1.86-6.75) for highest vs lowest quartiles. The matched concordance index for VAS was 0.70 (95% CI 0.65-0.75) demonstrating better discrimination between cases and controls than all other methods.

CONCLUSION

Increased mammographic density was strongly associated with risk of breast cancer among Saudi women. Radiologists' visual assessment of breast density is superior to automated methods. However, pVAS and Volpara Density ™ also significantly predicted breast cancer risk based on breast density.

ADVANCES IN KNOWLEDGE

Our study established an association between breast density and breast cancer in a Saudi population and compared the performance of automated methods. This provides a stepping-stone towards personalised screening using automated breast density methods.

Breast cancer screening in women with extremely dense breasts recommendations of the European Society of Breast Imaging (EUSOBI)

Breast density is an independent risk factor for the development of breast cancer and also decreases the sensitivity of mammography for screening. Consequently, women with extremely dense breasts face an increased risk of late diagnosis of breast cancer. These women are, therefore, underserved with current mammographic screening programs. The results of recent studies reporting on contrast-enhanced breast MRI as a screening method in women with extremely dense breasts provide compelling evidence that this approach can enable an important reduction in breast cancer mortality for these women and is cost-effective. Because there is now a valid option to improve breast cancer screening, the European Society of Breast Imaging (EUSOBI) recommends that women should be informed about their breast density. EUSOBI thus calls on all providers of mammography screening to share density information with the women being screened. In light of the available evidence, in women aged 50 to 70 years with extremely dense breasts, the EUSOBI now recommends offering screening breast MRI every 2 to 4 years. The EUSOBI acknowledges that it may currently not be possible to offer breast MRI immediately and everywhere and underscores that quality assurance procedures need to be established, but urges radiological societies and policymakers to act on this now. Since the wishes and values of individual women differ, in screening the principles of shared decision-making should be embraced. In particular, women should be counselled on the benefits and risks of mammography and MRI-based screening, so that they are capable of making an informed choice about their preferred screening method. KEY POINTS: • The recommendations in Figure 1 summarize the key points of the manuscript.

Comparison of breast density assessments between synthesized C-View™ & intelligent 2D™ mammography

OBJECTIVE

To compare breast density assessments between C-View™ and Intelligent 2D™, different generations of synthesized mammography (SM) from Hologic.

METHODS

In this retrospective study, we identified a subset of females between March 2017 and December 2019 who underwent screening digital breast tomosynthesis (DBT) with C-View followed by DBT with Intelligent 2D. Clinical Breast Imaging Reporting and Database System breast density was obtained along with volumetric breast density measures (including density grade, breast volume, percentage volumetric density, dense volume) using VolparaTM. Differences in density measures by type of synthesized image were calculated using the pairwise t-test or McNemar's test, as appropriate.

RESULTS

67 patients (avg age 62.7; range 40-84) were included with an average of 13.3 months between the two exams. No difference was found in Breast Imaging Reporting and Database System density between the SM reconstructions (p = 0.74). Similarly, there was no difference in VolparaTM mean density grade (p = 0.71), mean breast volume (p = 0.48), mean dense volume (p = 0.43) or mean percent volumetric density (p = 0.12) between the exams.

CONCLUSION

We found no significant differences in clinical and automated breast density assessments between these two versions of SM.

ADVANCES IN KNOWLEDGE

Lack of differences in density estimates between the two SM reconstructions is important as density assignment impacts risk stratification and adjunct screening recommendations.

Effectiveness of MRI in screening women for breast cancer: a systematic review

Artificial intelligence techniques for the diagnosis of disease continue to develop with rapid pace. This review article systematically determines incremental accuracy and other parameters of current methods, including sensitivity, specificity, positive predictive value and negative predictive value with regard to breast MRI as a screening tool for women under 50 years. Articles were included from the databases of health technology assessment agencies from 2000 to 2019, using various medical subject heading terms. A total of 23 eligible studies were included incorporating a total of 11,688 patients out of which two were multicentered, four were accuracy studies, seven were prospective studies and four were retrospective studies. MRI screening showed an adequate detection of invasive cancers, premalignant lesions and pre-invasive cancers, suggesting that MRI is a powerful surveillance tool to detect cancer in high-risk populations. These findings have indicated that MRI has particular sensitivity and specificity for the diagnosis of breast cancer.

PROSPERO Registration Number: CRD42020158372.

Use of a convolutional neural network-based mammographic evaluation to predict breast cancer recurrence among women with hormone receptor-positive operable breast cancer

PURPOSE

We evaluated whether a novel, fully automated convolutional neural network (CNN)-based mammographic evaluation can predict breast cancer relapse among women with operable hormone receptor (HR)-positive breast cancer.

METHODS

We conducted a retrospective cohort study among women with stage I-III, HR-positive unilateral breast cancer diagnosed at Columbia University Medical Center from 2007 to 2017, who received adjuvant endocrine therapy and had at least two mammograms (baseline, annual follow-up) of the contralateral unaffected breast for CNN analysis. We extracted demographics, clinicopathologic characteristics, breast cancer treatments, and relapse status from the electronic health record. Our primary endpoint was change in CNN risk score (range, 0-1). We used two-sample t-tests to assess for difference in mean CNN scores between patients who relapsed vs. remained in remission, and conducted Cox regression analyses to assess for association between change in CNN score and breast cancer-free interval (BCFI), adjusting for known prognostic factors.

RESULTS

Among 848 women followed for a median of 59 months, there were 67 (7.9%) breast cancer relapses (36 distant, 25 local, 6 new primaries). There was a significant difference in mean absolute change in CNN risk score from baseline to 1-year follow-up between those who relapsed vs. remained in remission (0.001 vs. - 0.022, p = 0.030). After adjustment for prognostic factors, a 0.01 absolute increase in CNN score at 1-year was significantly associated with BCFI, hazard ratio = 1.05 (95% Confidence Interval 1.01-1.09, p = 0.011).

CONCLUSION

Short-term change in the CNN-based breast cancer risk model on adjuvant endocrine therapy predicts breast cancer relapse, and warrants further evaluation in prospective studies.

Spatial Distribution Analysis of Novel Texture Feature Descriptors for Accurate Breast Density Classification

Breast density has been recognised as an important biomarker that indicates the risk of developing breast cancer. Accurate classification of breast density plays a crucial role in developing a computer-aided detection (CADe) system for mammogram interpretation. This paper proposes a novel texture descriptor, namely, rotation invariant uniform local quinary patterns (RIU4-LQP), to describe texture patterns in mammograms and to improve the robustness of image features. In conventional processing schemes, image features are obtained by computing histograms from texture patterns. However, such processes ignore very important spatial information related to the texture features. This study designs a new feature vector, namely, K-spectrum, by using Baddeley's K-inhom function to characterise the spatial distribution information of feature point sets. Texture features extracted by RIU4-LQP and K-spectrum are utilised to classify mammograms into BI-RADS density categories. Three feature selection methods are employed to optimise the feature set. In our experiment, two mammogram datasets, INbreast and MIAS, are used to test the proposed methods, and comparative analyses and statistical tests between different schemes are conducted. Experimental results show that our proposed method outperforms other approaches described in the literature, with the best classification accuracy of 92.76% (INbreast) and 86.96% (MIAS).

Plasma Growth Factor Gene Expression and Mammographic Breast Density in Postmenopausal Women

Mammographic breast density (MBD) is a risk factor for breast cancer, but its molecular basis is poorly understood. Growth factors stimulate cellular and epithelial proliferation and could influence MBD via these mechanisms. Studies investigating the associations of circulating growth factors with MBD have, however, yielded conflicting results especially in postmenopausal women. We, therefore, investigated the associations of plasma growth factor gene expression (IGF-1, IGFBP-3, FGF-1, FGF-12, TGFB-1 and BMP-2) with MBD in postmenopausal women. We used NanoString nCounter platform to quantify plasma growth factor gene expression and Volpara to evaluate volumetric MBD measures. We investigated the associations of growth factor gene expression with MBD using both multiple linear regression (fold change) and multinomial logistic regression models, adjusted for potential confounders. The mean age of the 368 women enrolled was 58 years (range: 50-64). In analyses using linear regression models, one unit increase in IGF-1 gene expression was associated with a 35% higher VPD (1.35, 95%CI 1.13-1.60, p-value=0.001). There were suggestions that TGFB-1 gene expression was positively associated with VPD while BMP gene expression was inversely associated with VPD, but these were not statistically significant. In analyses using multinomial logistic regression, TGFB-1 gene expression was 33% higher (OR=1.33, 95%CI 1.13-1.56, p-value=0.0008) in women with extremely dense breasts than those with almost entirely fatty breasts. There were no associations between growth factor gene expression and dense volume or non-dense volume. Our study provides insights into the associations of growth factors with MBD in postmenopausal women and require confirmation in other study populations.

Persistent inter-observer variability of breast density assessment using BI-RADS® 5th edition guidelines

OBJECTIVES

Due to most states' legislation, mammographic density categorization has potentially far-reaching implications, but remains subjective based on BIRADS® guidelines. We aimed to determine 1) effect of BI-RADS® 5th edition (5th-ed) vs 4th-edition (4th-ed) guidelines on reader agreement regarding density assessment; 2) 5th-ed vs 4th-ed density distribution, and visual vs quantitative assessment agreement; 3) agreement between experienced vs less experienced readers.

METHODS

In a retrospective review, six breast imaging radiologists (BIR) (23-30 years' experience) visually assessed density of 200 screening mammograms performed September 2012-January 2013 using 5th-ed guidelines. Results were compared to 2016 data of the same readers evaluating the same mammograms using 4th-ed guidelines after a training module. 5th-ed density categorization by seven junior BIR (1-5 years' experience) was compared to eight experienced BIR. Nelson et al.'s kappas (κ_m, κ_w), Fleiss' κ_F, and Cohen's κ were calculated. Quantitative density using Volpara was compared with reader assessments.

RESULTS

Inter-reader weighted agreement using 5th-ed is moderately strong, 0.73 (κ_w, s.e. = 0.01), similar to 4th-ed, 0.71 (κ_w, s.e. = 0.03). Intra-reader Cohen's κ is 0.23-0.34, similar to 4th-ed. Binary not-dense vs dense categorization, using 5th-ed results in higher dense categorization vs 4th-ed (p < 0.001). 5th-ed density distribution results in higher numbers in categories B/C vs 4th-ed (p < 0.001). Distribution for 5th-ed does not differ based on reader experience (p = 0.09). Reader vs quantitative weighted agreement is similar (5th-ed, Cohen's κ = 0.76-0.85; 4th-ed, Cohen's κ = 0.68-0.83).

CONCLUSION

There is persistent subjectivity of visually assessed mammographic density using 5th-ed guidelines; experience does not correlate with better inter-reader agreement.

Development and Validation of an AI-driven Mammographic Breast Density Classification Tool Based on Radiologist Consensus

Mammographic breast density (BD) is commonly visually assessed using the Breast Imaging Reporting and Data System (BI-RADS) four-category scale. To overcome inter- and intraobserver variability of visual assessment, the authors retrospectively developed and externally validated a software for BD classification based on convolutional neural networks from mammograms obtained between 2017 and 2020. The tool was trained using the majority BD category determined by seven board-certified radiologists who independently visually assessed 760 mediolateral oblique (MLO) images in 380 women (mean age, 57 years ± 6 [SD]) from center 1; this process mimicked training from a consensus of several human readers. External validation of the model was performed by the three radiologists whose BD assessment was closest to the majority (consensus) of the initial seven on a dataset of 384 MLO images in 197 women (mean age, 56 years ± 13) obtained from center 2. The model achieved an accuracy of 89.3% in distinguishing BI-RADS a or b (nondense breasts) versus c or d (dense breasts) categories, with an agreement of 90.4% (178 of 197 mammograms) and a reliability of 0.807 (Cohen κ) compared with the mode of the three readers. This study demonstrates accuracy and reliability of a fully automated software for BD classification. Keywords: Mammography, Breast, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2022.

Family History of Breast Cancer and Mammographic Breast Density in Premenopausal Women

Importance

Family history of breast cancer (FHBC) and mammographic breast density are independent risk factors for breast cancer, but the association of FHBC and mammographic breast density in premenopausal women is not well understood.

Objectives

To investigate the association of FHBC and mammographic breast density in premenopausal women using both quantitative and qualitative measurements.

Design, Setting, and Participants

This single-center cohort study examined 2 retrospective cohorts: a discovery set of 375 premenopausal women and a validation set of 14 040 premenopausal women. Data from women in the discovery set was collected between December 2015 and October 2016, whereas data from women in the validation set was collected between June 2010 and December 2015. Data analysis was performed between June 2018 and June 2020.

Exposures

Family history of breast cancer (FHBC).

Main Outcomes and Measures

The primary outcomes were mammographic breast density measured quantitatively as volumetric percent density using Volpara (discovery set) and qualitatively using BI-RADS (Breast Imaging Reporting and Data System) breast density (validation set). Multivariable regressions were performed using a log-transformed normal distribution for the discovery set and a logistic distribution for the validation set.

Results

Of 14 415 premenopausal women included in the study, the discovery set and validation set had similar characteristics (discovery set with FHBC: mean [SD] age, 47.1 [5.6] years; 15 [17.2%] were Black or African American women and 64 [73.6%] were non-Hispanic White women; discovery set with no FHBC: mean [SD] age, 47.7 [4.5] years; 87 [31.6%] were Black or African American women and 178 [64.7%] were non-Hispanic White women; validation set with FHBC: mean [SD] age, 46.8 [7.3] years; 720 [33.4%] were Black or African American women and 1378 [64.0%] were non-Hispanic White women]; validation set with no FHBC: mean [SD] age, 47.5 [6.1] years; 4572 [38.5%] were Black or African American women and 6632 [55.8%] were non-Hispanic White women]). In the discovery set, participants who had FHBC were more likely to have a higher mean volumetric percent density compared with participants with no FHBC (11.1% vs 9.0%). In the multivariable-adjusted model, volumetric percent density was 25% higher (odds ratio [OR], 1.25 ;95% CI, 1.12-1.41) in women with FHBC compared with women without FHBC; and 24% higher (OR, 1.24; 95% CI, 1.10-1.40) in women who had 1 affected relative, but not significantly higher in women who had at least 2 affected relatives (OR, 1.40; 95% CI, 0.95-2.07) compared with women with no relatives affected. In the validation set, women with a positive FHBC were more likely to have dense breasts (BI-RADS 3-4) compared with women with no FHBC (BI-RADS 3: 41.1% vs 38.8%; BI-RADS 4: 10.5% vs 7.7%). In the multivariable-adjusted model, the odds of having dense breasts (BI-RADS 3-4) were 30% higher (OR, 1.30; 95% CI, 1.17-1.45) in women with FHBC compared with women without FHBC; and 29% higher (OR, 1.29; 95% CI, 1.14-1.45) in women who had 1 affected relative, but not significantly higher in women who had at least 2 affected relatives (OR, 1.38; 95% CI, 0.85-2.23) compared with women with no relatives affected.

Conclusions and Relevance

In this cohort study, having an FHBC was positively associated with mammographic breast density in premenopausal women. Our findings highlight the heritable component of mammographic breast density and underscore the need to begin annual screening early in premenopausal women with a family history of breast cancer.

Artificial Intelligence (AI) for Screening Mammography, From the AI Special Series on AI Applications

Artificial intelligence (AI) applications for screening mammography are being marketed for clinical use in the interpretative domains of lesion detection and diagnosis, triage, and breast density assessment, and in the noninterpretive domains of breast cancer risk assessment, image quality control, image acquisition, and dose reduction. Evidence in support of these nascent applications, particularly for lesion detection and diagnosis, is largely based on multireader studies with cancer-enriched datasets rather than rigorous clinical evaluation aligned with the application's specific intended clinical use. This article reviews commercial AI algorithms for screening mammography that are currently available for clinical practice, their use, and evidence supporting their performance. Clinical implementation considerations, such as workflow integration, governance, and ethical issues, are also described. In addition, the future of AI for screening mammography is discussed, including the development of interpretive and noninterpretive AI applications and strategic priorities for research and development.

Mammographic Density Assessment by Artificial Intelligence-Based Computer-Assisted Diagnosis: A Comparison with Automated Volumetric Assessment

We evaluated and compared the mammographic density assessment of an artificial intelligence-based computer-assisted diagnosis (AI-CAD) program using inter-rater agreements between radiologists and an automated density assessment program. Between March and May 2020, 488 consecutive mammograms of 488 patients (56.2 ± 10.9 years) were collected from a single institution. We assigned four classes of mammographic density based on BI-RADS (Breast Imaging Reporting and Data System) using commercial AI-CAD (Lunit INSIGHT MMG), and compared inter-rater agreements between radiologists, AI-CAD, and another commercial automated density assessment program (Volpara®). The inter-rater agreement between AI-CAD and the reader consensus was 0.52 with a matched rate of 68.2% (333/488). The inter-rater agreement between Volpara® and the reader consensus was similar to AI-CAD at 0.50 with a matched rate of 62.7% (306/488). The inter-rater agreement between AI-CAD and Volpara® was 0.54 with a matched rate of 61.5% (300/488). In conclusion, density assessments by AI-CAD showed fair agreement with those of radiologists, similar to the agreement between the commercial automated density assessment program and radiologists.

Proton density water fraction as a reproducible MR-based measurement of breast density

PURPOSE

To introduce proton density water fraction (PDWF) as a confounder-corrected (CC) MR-based biomarker of mammographic breast density, a known risk factor for breast cancer.

METHODS

Chemical shift encoded (CSE) MR images were acquired using a low flip angle to provide proton density contrast from multiple echo times. Fat and water images, corrected for known biases, were produced by a six-echo CC CSE-MRI algorithm. Fibroglandular tissue (FGT) volume was calculated from whole-breast segmented PDWF maps at 1.5T and 3T. The method was evaluated in (1) a physical fat-water phantom and (2) normal volunteers. Results from two- and three-echo CSE-MRI methods were included for comparison.

RESULTS

Six-echo CC-CSE-MRI produced unbiased estimates of the total water volume in the phantom (mean bias 3.3%) and was reproducible across protocol changes (repeatability coefficient [RC] = 14.8 cm³ and 13.97 cm³ at 1.5T and 3.0T, respectively) and field strengths (RC = 51.7 cm³ ) in volunteers, while the two- and three-echo CSE-MRI approaches produced biased results in phantoms (mean bias 30.7% and 10.4%) that was less reproducible across field strengths in volunteers (RC = 82.3 cm³ and 126.3 cm³ ). Significant differences in measured FGT volume were found between the six-echo CC-CSE-MRI and the two- and three-echo CSE-MRI approaches (p = 0.002 and p = 0.001, respectively).

CONCLUSION

The use of six-echo CC-CSE-MRI to create unbiased PDWF maps that reproducibly quantify FGT in the breast is demonstrated. Further studies are needed to correlate this quantitative MR biomarker for breast density with mammography and overall risk for breast cancer.

Does circulating progesterone mediate the associations of single nucleotide polymorphisms in progesterone receptor (PGR)-related genes with mammographic breast density in premenopausal women?

Progesterone is a proliferative hormone in the breast but the associations of genetic variations in progesterone-regulated pathways with mammographic breast density (MD) in premenopausal women and whether these associations are mediated through circulating progesterone are not clearly defined. We, therefore, investigated these associations in 364 premenopausal women with a median age of 44 years. We sequenced 179 progesterone receptor (PGR)-related single nucleotide polymorphisms (SNPs). We measured volumetric percent density (VPD) and non-dense volume (NDV) using Volpara. Linear regression models were fit on circulating progesterone or VPD/NDV separately. We performed mediation analysis to evaluate whether the effect of a SNP on VPD/NDV is mediated through circulating progesterone. All analyses were adjusted for confounders, phase of menstrual cycle and the Benjamini-Hochberg false discovery (FDR) adjusted p-value was applied to correct for multiple testing. In multivariable analyses, only PGR rs657516 had a direct effect on VPD (averaged direct effect estimate = - 0.20, 95%CI = - 0.38 ~ - 0.04, p-value = 0.02) but this was not statistically significant after FDR correction and the effect was not mediated by circulating progesterone (mediation effect averaged across the two genotypes = 0.01, 95%CI = - 0.02 ~ 0.03, p-value = 0.70). Five SNPs (PGR rs11571241, rs11571239, rs1824128, rs11571150, PGRMC1 rs41294894) were associated with circulating progesterone but these were not statistically significant after FDR correction. SNPs in PGR-related genes were not associated with VPD, NDV and circulating progesterone did not mediate the associations, suggesting that the effects, if any, of these SNPs on MD are independent of circulating progesterone.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s12672-021-00438-1.

Coffee, Tea, and Mammographic Breast Density in Premenopausal Women

Studies have investigated the associations of coffee and tea with mammographic breast density (MBD) in premenopausal women with inconsistent results. We analyzed data from 375 premenopausal women who attended a screening mammogram at Washington University School of Medicine, St. Louis, MO in 2016, and stratified the analyses by race (non-Hispanic White (NHW) vs. Black/African American). Participants self-reported the number of servings of coffee, caffeinated tea, and decaffeinated tea they consumed. Volpara software was used to determine volumetric percent density (VPD), dense volume (DV), and non-dense volume (NDV). We used generalized linear regression models to quantify the associations of coffee and tea intake with MBD measures. Coffee: ≥1 time/day (β = 1.06; 95% CI = 0.93–1.21; p-trend = 0.61) and caffeinated tea: ≥1 time/day (β = 1.01; 95% CI = 0.88–1.17; p-trend = 0.61) were not associated with VPD. Decaffeinated tea (≥1 time/week) was positively associated with VPD in NHW women (β = 1.22; 95% CI = 1.06–1.39) but not in African American women (β = 0.93; 95% CI = 0.73–1.17; p-interaction = 0.02). Coffee (≥1 time/day) was positively associated with DV in African American women (β = 1.52; 95% CI = 1.11–2.07) but not in NHW women (β = 1.10; 95% CI = 0.95–1.29; p-interaction = 0.02). Our findings do not support associations of coffee and caffeinated tea intake with VPD in premenopausal women. Positive associations of decaffeinated tea with VPD, with suggestions of effect modification by race, require confirmation in larger studies with diverse study populations.

The Effect of Breast Size and Density in Turkish Women on Radiation Dose in Full-Field Digital Mammography

Objective

The purpose of this study was to look into the relationship between breast size and mammographic breast density in women and breast radiation dose on full-field digital mammography (FFDM), as well as the factors that influence radiation dose.

Materials and Methods

The study included a total of 2,060 FFDM images from 515 consecutive participants. The participants were divided into two groups: those exposed to high doses (>3 mGy) and those exposed to low doses (<3 mGy). Moreover, the researchers analyzed the relationship between mean glandular dose (MGD) of the breast and patient age, compressed breast thickness, compression force, mammographic breast composition, and mammographic breast size.

Results

The mean mammographic breast volume was 936.2 ± 425.2 (114.5-3,018) mL, and the mean compressed breast tissue thickness was 56.75 ± 10.44 mm. Moreover, the mean MGD in the high-dose group was 3.51 ± 0.48 mGy and 1.92 ± 0.56 mGy in the low-dose group. The high-dose group had greater breast thickness, diameters, volume, compression pressure, and surgical rate. However, the high-dose group was younger and had less dense breasts. In multivariate logistic regression analysis, the most important predictors of dose determination were breast thickness [odds ratio (OR): 1.178, 95% confidence interval (CI): 1.156-1.200, p<0.001], history of previous surgery (OR: 2.210, 95% CI: 1.417-3.447, p<0.001), compression force (OR: 1.008, 95% CI: 1.004-1.013, p<0.001), and breast density (OR: 1.873, 95% CI: 1.359-2.580, p<0.001).

Conclusion

Women with larger breast volumes are subjected to higher doses of radiation. Therefore, breast-screening programs can be individualized to young women with larger breast volumes and women who have had breast-conserving surgery.

Validation of a new fully automated software for 2D digital mammographic breast density evaluation in predicting breast cancer risk

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.

Deep-LIBRA: An artificial-intelligence method for robust quantification of breast density with independent validation in breast cancer risk assessment

Breast density is an important risk factor for breast cancer that also affects the specificity and sensitivity of screening mammography. Current federal legislation mandates reporting of breast density for all women undergoing breast cancer screening. Clinically, breast density is assessed visually using the American College of Radiology Breast Imaging Reporting And Data System (BI-RADS) scale. Here, we introduce an artificial intelligence (AI) method to estimate breast density from digital mammograms. Our method leverages deep learning using two convolutional neural network architectures to accurately segment the breast area. An AI algorithm combining superpixel generation and radiomic machine learning is then applied to differentiate dense from non-dense tissue regions within the breast, from which breast density is estimated. Our method was trained and validated on a multi-racial, multi-institutional dataset of 15,661 images (4,437 women), and then tested on an independent matched case-control dataset of 6368 digital mammograms (414 cases; 1178 controls) for both breast density estimation and case-control discrimination. On the independent dataset, breast percent density (PD) estimates from Deep-LIBRA and an expert reader were strongly correlated (Spearman correlation coefficient = 0.90). Moreover, in a model adjusted for age and BMI, Deep-LIBRA yielded a higher case-control discrimination performance (area under the ROC curve, AUC = 0.612 [95% confidence interval (CI): 0.584, 0.640]) compared to four other widely-used research and commercial breast density assessment methods (AUCs = 0.528 to 0.599). Our results suggest a strong agreement of breast density estimates between Deep-LIBRA and gold-standard assessment by an expert reader, as well as improved performance in breast cancer risk assessment over state-of-the-art open-source and commercial methods.

Fully Automated Volumetric Breast Density Estimation from Digital Breast Tomosynthesis

Background While digital breast tomosynthesis (DBT) is rapidly replacing digital mammography (DM) in breast cancer screening, the potential of DBT density measures for breast cancer risk assessment remains largely unexplored. Purpose To compare associations of breast density estimates from DBT and DM with breast cancer. Materials and Methods This retrospective case-control study used contralateral DM/DBT studies from women with unilateral breast cancer and age- and ethnicity-matched controls (September 19, 2011-January 6, 2015). Volumetric percent density (VPD%) was estimated from DBT using previously validated software. For comparison, the publicly available Laboratory for Individualized Breast Radiodensity Assessment software package, or LIBRA, was used to estimate area-based percent density (APD%) from raw and processed DM images. The commercial Quantra and Volpara software packages were applied to raw DM images to estimate VPD% with use of physics-based models. Density measures were compared by using Spearman correlation coefficients (r), and conditional logistic regression was performed to examine density associations (odds ratios [OR]) with breast cancer, adjusting for age and body mass index. Results A total of 132 women diagnosed with breast cancer (mean age ± standard deviation [SD], 60 years ± 11) and 528 controls (mean age, 60 years ± 11) were included. Moderate correlations between DBT and DM density measures (r = 0.32-0.75; all P < .001) were observed. Volumetric density estimates calculated from DBT (OR, 2.3 [95% CI: 1.6, 3.4] per SD for VPD%_DBT) were more strongly associated with breast cancer than DM-derived density for both APD% (OR, 1.3 [95% CI: 0.9, 1.9] [P < .001] and 1.7 [95% CI: 1.2, 2.3] [P = .004] per SD for LIBRA raw and processed data, respectively) and VPD% (OR, 1.6 [95% CI: 1.1, 2.4] [P = .01] and 1.7 [95% CI: 1.2, 2.6] [P = .04] per SD for Volpara and Quantra, respectively). Conclusion The associations between quantitative breast density estimates and breast cancer risk are stronger for digital breast tomosynthesis compared with digital mammography. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Yaffe in this issue.

Deep Learning Predicts Interval and Screening-detected Cancer from Screening Mammograms: A Case-Case-Control Study in 6369 Women

Background The ability of deep learning (DL) models to classify women as at risk for either screening mammography-detected or interval cancer (not detected at mammography) has not yet been explored in the literature. Purpose To examine the ability of DL models to estimate the risk of interval and screening-detected breast cancers with and without clinical risk factors. Materials and Methods This study was performed on 25 096 digital screening mammograms obtained from January 2006 to December 2013. The mammograms were obtained in 6369 women without breast cancer, 1609 of whom developed screening-detected breast cancer and 351 of whom developed interval invasive breast cancer. A DL model was trained on the negative mammograms to classify women into those who did not develop cancer and those who developed screening-detected cancer or interval invasive cancer. Model effectiveness was evaluated as a matched concordance statistic (C statistic) in a held-out 26% (1669 of 6369) test set of the mammograms. Results The C statistics and odds ratios for comparing patients with screening-detected cancer versus matched controls were 0.66 (95% CI: 0.63, 0.69) and 1.25 (95% CI: 1.17, 1.33), respectively, for the DL model, 0.62 (95% CI: 0.59, 0.65) and 2.14 (95% CI: 1.32, 3.45) for the clinical risk factors with the Breast Imaging Reporting and Data System (BI-RADS) density model, and 0.66 (95% CI: 0.63, 0.69) and 1.21 (95% CI: 1.13, 1.30) for the combined DL and clinical risk factors model. For comparing patients with interval cancer versus controls, the C statistics and odds ratios were 0.64 (95% CI: 0.58, 0.71) and 1.26 (95% CI: 1.10, 1.45), respectively, for the DL model, 0.71 (95% CI: 0.65, 0.77) and 7.25 (95% CI: 2.94, 17.9) for the risk factors with BI-RADS density (b rated vs non-b rated) model, and 0.72 (95% CI: 0.66, 0.78) and 1.10 (95% CI: 0.94, 1.29) for the combined DL and clinical risk factors model. The P values between the DL, BI-RADS, and combined model's ability to detect screen and interval cancer were .99, .002, and .03, respectively. Conclusion The deep learning model outperformed in determining screening-detected cancer risk but underperformed for interval cancer risk when compared with clinical risk factors including breast density. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Bae and Kim in this issue.

Fully automated measurements of volumetric breast density adapted for BIRADS 5th edition: a comparison with visual assessment

BACKGROUND

Since the 5th edition of BI-RADS was released, prior studies have compared BI-RADS and quantitative fully automated volumetric assessment, but with software packages that were not recalibrated according to the 5th edition.

PURPOSE

To investigate mammographic density assessment of automated volumetric measurements recalibrated according to the BI-RADS 5th edition compared with visual assessment.

MATERIAL AND METHODS

A total of 4000 full-field digital mammographic examinations were reviewed by three radiologists for the BI-RADS 5th edition density category by consensus after individual assessments. Volumetric density data obtained using Quantra and Volpara software were collected. The comparison of visual and volumetric density assessments was performed in total and according to the presence of cancer.

RESULTS

Among 4000 examinations, 129 were mammograms of breast cancer. Compared to visual assessment, volumetric measurements showed higher category B (40.6% vs. 19.8%) in Quantra, and higher category D (40.4% vs. 14.7%) and lower category A (0.2% vs. 5.0%) in Volpara (P < 0.0001). All volumetric data showed a difference according to visually assessed categories and were correlated between the two volumetric measurements (P < 0.0001). The group with cancer showed a lower proportion of fatty breast than that without cancer: 17.8% vs. 46.9% for Quantra (P < 0.0001) and 9.3% vs. 21.5% for Volpara (P = 0.003). Both measurements showed significantly higher mean density data in the group with cancer than without cancer (P < 0.005 for all).

CONCLUSION

Automated volumetric measurements adapted for the BI-RADS 5th edition showed different but correlated results with visual assessment and each other. Recalibration of volumetric measurement has not completely reflected the visual assessment.

Medication use and mammographic breast density

PURPOSE

A dense breast on mammogram is a strong risk factor for breast cancer. Identifying factors that reduce mammographic breast density could thus provide insight into breast cancer prevention. Due to the limited number of studies and conflicting findings, we investigated the associations of medication use (specifically statins, aspirin, and ibuprofen) with mammographic breast density.

METHODS

We evaluated these associations in 775 women who were recruited during an annual screening mammogram at Washington University School of Medicine, St. Louis. We measured mammographic breast density using Volpara. We used multivariable-adjusted linear regressions to determine the associations of medication use (statins, aspirin, and ibuprofen) with mammographic breast density. Least squared means were generated and back-transformed for easier interpretation.

RESULTS

The mean age of study participants was 52.9 years. Statin use in the prior 12 months was not associated with volumetric percent density or dense volume, but was positively associated with non-dense volume. The mean volumetric percent density was 8.6% among statin non-users, 7.2% among women who used statins 1-3 days/week, and 7.3% among women who used statins ≥ 4 days/week (p trend = 0.07). The non-dense volume was 1297.1 cm³ among statin non-users, 1368.7 cm³ among women who used statins 1-3 days/week, and 1408.4 cm³ among those who used statins ≥ 4 days/week (p trend = 0.02). We did not observe statistically significant differences in mammographic breast density by aspirin or ibuprofen use.

CONCLUSION

Statin, aspirin, and ibuprofen use was not associated with volumetric percent density and dense volume, but statin use was positively associated with non-dense volume. Any potential associations of these medications with breast cancer risk are unlikely to be mediated through an effect on volumetric percent density.

Mammographic Variation Measures, Breast Density, and Breast Cancer Risk

OBJECTIVE. Our previous work showed that variation measures, which represent breast architecture derived from mammograms, were significantly associated with breast cancer. For replication purposes, we examined the association of three variation measures (variation [V], which is measured in the image domain, and P₁ and p₁ [a normalized version of P₁], which are derived from restricted regions in the Fourier domain) with breast cancer risk in an independent population. We also compared these measures to volumetric density measures (volumetric percent density [VPD] and dense volume [DV]) from a commercial product. MATERIALS AND METHODS. We examined 514 patients with breast cancer and 1377 control patients from a screening practice who were matched for age, date of examination, mammography unit, facility, and state of residence. Spearman rank-order correlation was used to evaluate the monotonic association between measures. Breast cancer associations were estimated using conditional logistic regression, after adjustment for age and body mass index. Odds ratios were calculated per SD increment in mammographic measure. RESULTS. These variation measures were strongly correlated with VPD (correlation, 0.68-0.80) but not with DV (correlation, 0.31-0.48). Similar to previous findings, all variation measures were significantly associated with breast cancer (odds ratio per SD: 1.30 [95% CI, 1.16-1.46] for V, 1.55 [95% CI, 1.35-1.77] for P₁, and 1.51 [95% CI, 1.33-1.72] for p₁). Associations of volumetric density measures with breast cancer were similar (odds ratio per SD: 1.54 [95% CI, 1.33-1.78] for VPD and 1.34 [95% CI, 1.20-1.50] for DV). When DV was included with each variation measure in the same model, all measures retained significance. CONCLUSION. Variation measures were significantly associated with breast cancer risk (comparable to the volumetric density measures) but were independent of the DV.

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.