Examination of fully automated mammographic density measures using LIBRA and breast cancer risk in a cohort of 21,000 non-Hispanic white women.

BACKGROUND: Breast density is strongly associated with breast cancer risk. Fully automated quantitative density assessment methods have recently been developed that could facilitate large-scale studies, although data on associations with long-term breast cancer risk are limited. We examined LIBRA assessments and breast cancer risk and compared results to prior assessments using Cumulus, an established computer-assisted method requiring manual thresholding. METHODS: We conducted a cohort study among 21,150 non-Hispanic white female participants of the Research Program in Genes, Environment and Health of Kaiser Permanente Northern California who were 40-74 years at enrollment, followed for up to 10 years, and had archived processed screening mammograms acquired on Hologic or General Electric full-field digital mammography (FFDM) machines and prior Cumulus density assessments available for analysis. Dense area (DA), non-dense area (NDA), and percent density (PD) were assessed using LIBRA software. Cox regression was used to estimate hazard ratios (HRs) for breast cancer associated with DA, NDA and PD modeled continuously in standard deviation (SD) increments, adjusting for age, mammogram year, body mass index, parity, first-degree family history of breast cancer, and menopausal hormone use. We also examined differences by machine type and breast view. RESULTS: The adjusted HRs for breast cancer associated with each SD increment of DA, NDA and PD were 1.36 (95% confidence interval, 1.18-1.57), 0.85 (0.77-0.93) and 1.44 (1.26-1.66) for LIBRA and 1.44 (1.33-1.55), 0.81 (0.74-0.89) and 1.54 (1.34-1.77) for Cumulus, respectively. LIBRA results were generally similar by machine type and breast view, although associations were strongest for Hologic machines and mediolateral oblique views. Results were also similar during the first 2 years, 2-5 years and 5-10 years after the baseline mammogram. CONCLUSION: Associations with breast cancer risk were generally similar for LIBRA and Cumulus density measures and were sustained for up to 10 years. These findings support the suitability of fully automated LIBRA assessments on processed FFDM images for large-scale research on breast density and cancer risk.

Changes in mammographic density and risk of breast cancer among a diverse cohort of women undergoing mammography screening.

PURPOSE: Mammographic density (MD) is a strong breast cancer risk factor. MD may change over time, with potential implications for breast cancer risk. Few studies have assessed associations between MD change and breast cancer in racially diverse populations. We investigated the relationships between MD and MD change over time and breast cancer risk in a large, diverse screening cohort. MATERIALS AND METHODS: We retrospectively analyzed data from 8462 women who underwent ≥ 2 screening mammograms from Sept. 2010 to Jan. 2015 (N = 20,766 exams); 185 breast cancers were diagnosed 1-7 years after screening. Breast percent density (PD) and dense area (DA) were estimated from raw digital mammograms (Hologic Inc.) using LIBRA (v1.0.4). For each MD measure, we modeled breast density change between two sequential visits as a function of demographic and risk covariates. We used Cox regression to examine whether varying degrees of breast density change were associated with breast cancer risk, accounting for multiple exams per woman. RESULTS: PD at any screen was significantly associated with breast cancer risk (hazard ratio (HR) for PD = 1.03 (95% CI [1.01, 1.05], p < 0.0005), but neither change in breast density nor more extreme than expected changes in breast density were associated with breast cancer risk. We found no evidence of differences in density change or breast cancer risk due to density change by race. Results using DA were essentially identical. CONCLUSIONS: Using a large racially diverse cohort, we found no evidence of association between short-term change in MD and risk of breast cancer, suggesting that short-term MD change is not a strong predictor for risk.

Artificial intelligence in mammographic phenotyping of breast cancer risk: a narrative review.

BACKGROUND: Improved breast cancer risk assessment models are needed to enable personalized screening strategies that achieve better harm-to-benefit ratio based on earlier detection and better breast cancer outcomes than existing screening guidelines. Computational mammographic phenotypes have demonstrated a promising role in breast cancer risk prediction. With the recent exponential growth of computational efficiency, the artificial intelligence (AI) revolution, driven by the introduction of deep learning, has expanded the utility of imaging in predictive models. Consequently, AI-based imaging-derived data has led to some of the most promising tools for precision breast cancer screening. MAIN BODY: This review aims to synthesize the current state-of-the-art applications of AI in mammographic phenotyping of breast cancer risk. We discuss the fundamentals of AI and explore the computing advancements that have made AI-based image analysis essential in refining breast cancer risk assessment. Specifically, we discuss the use of data derived from digital mammography as well as digital breast tomosynthesis. Different aspects of breast cancer risk assessment are targeted including (a) robust and reproducible evaluations of breast density, a well-established breast cancer risk factor, (b) assessment of a woman's inherent breast cancer risk, and (c) identification of women who are likely to be diagnosed with breast cancers after a negative or routine screen due to masking or the rapid and aggressive growth of a tumor. Lastly, we discuss AI challenges unique to the computational analysis of mammographic imaging as well as future directions for this promising research field. CONCLUSIONS: We provide a useful reference for AI researchers investigating image-based breast cancer risk assessment while indicating key priorities and challenges that, if properly addressed, could accelerate the implementation of AI-assisted risk stratification to future refine and individualize breast cancer screening strategies.

Artificial Intelligence (AI) for Screening Mammography, From the AJR 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.

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.

Functional 4-D clustering for characterizing intratumor heterogeneity in dynamic imaging: evaluation in FDG PET as a prognostic biomarker for breast cancer.

PURPOSE: Probe-based dynamic (4-D) imaging modalities capture breast intratumor heterogeneity both spatially and kinetically. Characterizing heterogeneity through tumor sub-populations with distinct functional behavior may elucidate tumor biology to improve targeted therapy specificity and enable precision clinical decision making. METHODS: We propose an unsupervised clustering algorithm for 4-D imaging that integrates Markov-Random Field (MRF) image segmentation with time-series analysis to characterize kinetic intratumor heterogeneity. We applied this to dynamic FDG PET scans by identifying distinct time-activity curve (TAC) profiles with spatial proximity constraints. We first evaluated algorithm performance using simulated dynamic data. We then applied our algorithm to a dataset of 50 women with locally advanced breast cancer imaged by dynamic FDG PET prior to treatment and followed to monitor for disease recurrence. A functional tumor heterogeneity (FTH) signature was then extracted from functionally distinct sub-regions within each tumor. Cross-validated time-to-event analysis was performed to assess the prognostic value of FTH signatures compared to established histopathological and kinetic prognostic markers. RESULTS: Adding FTH signatures to a baseline model of known predictors of disease recurrence and established FDG PET uptake and kinetic markers improved the concordance statistic (C-statistic) from 0.59 to 0.74 (p = 0.005). Unsupervised hierarchical clustering of the FTH signatures identified two significant (p < 0.001) phenotypes of tumor heterogeneity corresponding to high and low FTH. Distributions of FDG flux, or Ki, were significantly different (p = 0.04) across the two phenotypes. CONCLUSIONS: Our findings suggest that imaging markers of FTH add independent value beyond standard PET imaging metrics in predicting recurrence-free survival in breast cancer and thus merit further study.

Evaluation of LIBRA Software for Fully Automated Mammographic Density Assessment in Breast Cancer Risk Prediction.

Background The associations of density measures from the publicly available Laboratory for Individualized Breast Radiodensity Assessment (LIBRA) software with breast cancer have primarily focused on estimates from the contralateral breast at the time of diagnosis. Purpose To evaluate LIBRA measures on mammograms obtained before breast cancer diagnosis and compare their performance to established density measures. Materials and Methods For this retrospective case-control study, full-field digital mammograms in for-processing (raw) and for-presentation (processed) formats were obtained (March 2008 to December 2011) in women who developed breast cancer an average of 2 years later and in age-matched control patients. LIBRA measures included absolute dense area and area percent density (PD) from both image formats. For comparison, dense area and PD were assessed by using the research software (Cumulus), and volumetric PD (VPD) and absolute dense volume were estimated with a commercially available software (Volpara). Density measures were compared by using Spearman correlation coefficients (r), and conditional logistic regression (odds ratios [ORs] and 95% confidence intervals [CIs]) was performed to examine the associations of density measures with breast cancer by adjusting for age and body mass index. Results Evaluated were 437 women diagnosed with breast cancer (median age, 62 years ± 17 [standard deviation]) and 1225 matched control patients (median age, 61 years ± 16). LIBRA PD showed strong correlations with Cumulus PD (r = 0.77-0.84) and Volpara VPD (r = 0.85-0.90) (P < .001 for both). For LIBRA, the strongest breast cancer association was observed for PD from processed images (OR, 1.3; 95% CI: 1.1, 1.5), although the PD association from raw images was not significantly different (OR, 1.2; 95% CI: 1.1, 1.4; P = .25). Slightly stronger breast cancer associations were seen for Cumulus PD (OR, 1.5; 95% CI: 1.3, 1.8; processed images; P = .01) and Volpara VPD (OR, 1.4; 95% CI: 1.2, 1.7; raw images; P = .004) compared with LIBRA measures. Conclusion Automated density measures provided by the Laboratory for Individualized Breast Radiodensity Assessment from raw and processed mammograms correlated with established area and volumetric density measures and showed comparable breast cancer associations. © RSNA, 2020 Online supplemental material is available for this article.

Effect of Mammographic Screening Modality on Breast Density Assessment: Digital Mammography versus Digital Breast Tomosynthesis.

Background Breast Imaging Reporting and Data System (BI-RADS) breast density categories assigned by interpreting radiologists often influence decisions surrounding supplemental breast cancer screening and risk assessment. The landscape of mammographic screening continuously evolves, and different mammographic screening modalities may result in different perception of density, reflected in different assignment of BI-RADS density categories. Purpose To investigate the effect of screening mammography modality on BI-RADS breast density assessments. Materials and Methods Data were retrospectively analyzed from 24 736 individual women (42.3% [10 455 of 24 736] white women, 57.7% [14 281 of 24 736] black women; mean age, 56.3 years; age range, 40.0-74.9 years) who underwent from one to seven mammographic screening examinations from September 2010 through February 2017 (60 766 examinations). Three screening modalities were used: digital mammography alone (8935 examinations); digital mammography with digital breast tomosynthesis (DBT; 30 779 examinations); and synthetic mammography with DBT (21 052 examinations). Random-effects logistic regression analysis was performed to estimate the likelihood of assignment to high versus low BI-RADS density category according to each modality, adjusted for ethnicity, age, body mass index (BMI), and radiologist. The interactions of modality with ethnicity and BMI on density categorization were also tested with the model. Results Women screened with DBT versus digital mammography alone had lower likelihood regarding categorization of high density breasts (digital mammography and DBT vs digital mammography: odds ratio, 0.69 [95% confidence interval: 0.61, 0.80], P < .001; synthetic mammography and DBT vs digital mammography: odds ratio, 0.43 [95% confidence interval: 0.37, 0.50], P < .001). Lower likelihood of high density was also observed at synthetic mammography and DBT compared with digital mammography and DBT (odds ratio, 0.62; 95% confidence interval: 0.56, 0.69; P < .001). There were interactions of modality with ethnicity (P = .007) and BMI (P = .003) on breast density assessment, with greater differences in density categorization according to modality observed for black women than for white women and groups with higher BMI. Conclusion Breast density categorization may vary by screening mammographic modality, and this effect appears to vary by ethnicity and body mass index. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Philpotts in this issue.

Radiomic Phenotypes of Mammographic Parenchymal Complexity: Toward Augmenting Breast Density in Breast Cancer Risk Assessment.

Purpose To identify phenotypes of mammographic parenchymal complexity by using radiomic features and to evaluate their associations with breast density and other breast cancer risk factors. Materials and Methods Computerized image analysis was used to quantify breast density and extract parenchymal texture features in a cross-sectional sample of women screened with digital mammography from September 1, 2012, to February 28, 2013 (n = 2029; age range, 35-75 years; mean age, 55.9 years). Unsupervised clustering was applied to identify and reproduce phenotypes of parenchymal complexity in separate training (n = 1339) and test sets (n = 690). Differences across phenotypes by age, body mass index, breast density, and estimated breast cancer risk were assessed by using Fisher exact, χ2, and Kruskal-Wallis tests. Conditional logistic regression was used to evaluate preliminary associations between the detected phenotypes and breast cancer in an independent case-control sample (76 women diagnosed with breast cancer and 158 control participants) matched on age. Results Unsupervised clustering in the screening sample identified four phenotypes with increasing parenchymal complexity that were reproducible between training and test sets (P = .001). Breast density was not strongly correlated with phenotype category (R2 = 0.24 for linear trend). The low- to intermediate-complexity phenotype (prevalence, 390 of 2029 [19%]) had the lowest proportion of dense breasts (eight of 390 [2.1%]), whereas similar proportions were observed across other phenotypes (from 140 of 291 [48.1%] in the high-complexity phenotype to 275 of 511 [53.8%] in the low-complexity phenotype). In the independent case-control sample, phenotypes showed a significant association with breast cancer (P = .001), resulting in higher discriminatory capacity when added to a model with breast density and body mass index (area under the curve, 0.84 vs 0.80; P = .03 for comparison). Conclusion Radiomic phenotypes capture mammographic parenchymal complexity beyond conventional breast density measures and established breast cancer risk factors. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Pinker in this issue.

Agreement between Breast Percentage Density Estimations from Standard-Dose versus Synthetic Digital Mammograms: Results from a Large Screening Cohort Using Automated Measures.

Purpose To evaluate agreement between automated estimates of breast density made from standard-dose versus synthetic digital mammograms in a large cohort of women undergoing screening. Materials and Methods This study received institutional review board approval with waiver of consent. A total of 3668 negative (Breast Imaging Reporting and Data System category 1 or 2) digital breast tomosynthesis (DBT) screening examinations consecutively performed over a 4-month period at one institution for which both standard-dose and synthetic mammograms were available for analysis were retrospectively analyzed. All mammograms were acquired with a Selenia Dimensions system (Hologic, Bedford, Mass), and synthetic mammograms were generated by using the U.S. Food and Drug Administration-approved "C-View" software module. The "For Presentation" standard-dose mammograms and synthetic images were analyzed by using a fully automated algorithm. Agreement between density estimates was assessed by using Pearson correlation, linear regression, and Bland-Altman analysis. Differences were evaluated by using the paired Student t test. Results Breast percentage density (PD) estimates from synthetic and standard-dose mammograms were highly correlated (r = 0.92, P < .001), and the 95% Bland-Altman limits of agreement between PD estimates were -6.4% to 9.9%. Synthetic mammograms had PD estimates by an average of 1.7% higher than standard-dose mammograms (P < .001), with a larger disagreement by 1.56% in women with highly dense breast tissue (P < .0001). Conclusion Fully automated estimates of breast density made from synthetic mammograms are generally comparable to those made from standard-dose mammograms. This may be important, as standard two-dimensional mammographic images are increasingly being replaced by synthetic mammograms in DBT screening in an attempt to reduce radiation dose. © RSNA, 2017 Online supplemental material is available for this article.

Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment.

BACKGROUND: The assessment of a woman's risk for developing breast cancer has become increasingly important for establishing personalized screening recommendations and forming preventive strategies. Studies have consistently shown a strong relationship between breast cancer risk and mammographic parenchymal patterns, typically assessed by percent mammographic density. This paper will review the advancing role of mammographic texture analysis as a potential novel approach to characterize the breast parenchymal tissue to augment conventional density assessment in breast cancer risk estimation. MAIN TEXT: The analysis of mammographic texture provides refined, localized descriptors of parenchymal tissue complexity. Currently, there is growing evidence in support of textural features having the potential to augment the typically dichotomized descriptors (dense or not dense) of area or volumetric measures of breast density in breast cancer risk assessment. Therefore, a substantial research effort has been devoted to automate mammographic texture analysis, with the aim of ultimately incorporating such quantitative measures into breast cancer risk assessment models. In this paper, we review current and emerging approaches in this field, summarizing key methodological details and related studies using novel computerized approaches. We also discuss research challenges for advancing the role of parenchymal texture analysis in breast cancer risk stratification and accelerating its clinical translation. CONCLUSIONS: The objective is to provide a comprehensive reference for researchers in the field of parenchymal pattern analysis in breast cancer risk assessment, while indicating key directions for future research.

Impact of multi-source data augmentation on performance of convolutional neural networks for abnormality classification in mammography.

Introduction: To date, most mammography-related AI models have been trained using either film or digital mammogram datasets with little overlap. We investigated whether or not combining film and digital mammography during training will help or hinder modern models designed for use on digital mammograms. Methods: To this end, a total of six binary classifiers were trained for comparison. The first three classifiers were trained using images only from Emory Breast Imaging Dataset (EMBED) using ResNet50, ResNet101, and ResNet152 architectures. The next three classifiers were trained using images from EMBED, Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM), and Digital Database for Screening Mammography (DDSM) datasets. All six models were tested only on digital mammograms from EMBED. Results: The results showed that performance degradation to the customized ResNet models was statistically significant overall when EMBED dataset was augmented with CBIS-DDSM/DDSM. While the performance degradation was observed in all racial subgroups, some races are subject to more severe performance drop as compared to other races. Discussion: The degradation may potentially be due to ( 1) a mismatch in features between film-based and digital mammograms ( 2) a mismatch in pathologic and radiological information. In conclusion, use of both film and digital mammography during training may hinder modern models designed for breast cancer screening. Caution is required when combining film-based and digital mammograms or when utilizing pathologic and radiological information simultaneously.

Genome-Wide Association Study of Breast Density among Women of African Ancestry.

Breast density, the amount of fibroglandular versus fatty tissue in the breast, is a strong breast cancer risk factor. Understanding genetic factors associated with breast density may help in clarifying mechanisms by which breast density increases cancer risk. To date, 50 genetic loci have been associated with breast density, however, these studies were performed among predominantly European ancestry populations. We utilized a cohort of women aged 40-85 years who underwent screening mammography and had genetic information available from the Penn Medicine BioBank to conduct a Genome-Wide Association Study (GWAS) of breast density among 1323 women of African ancestry. For each mammogram, the publicly available "LIBRA" software was used to quantify dense area and area percent density. We identified 34 significant loci associated with dense area and area percent density, with the strongest signals in GACAT3, CTNNA3, HSD17B6, UGDH, TAAR8, ARHGAP10, BOD1L2, and NR3C2. There was significant overlap between previously identified breast cancer SNPs and SNPs identified as associated with breast density. Our results highlight the importance of breast density GWAS among diverse populations, including African ancestry populations. They may provide novel insights into genetic factors associated with breast density and help in elucidating mechanisms by which density increases breast cancer risk.

External Validation of a Mammography-Derived AI-Based Risk Model in a U.S. Breast Cancer Screening Cohort of White and Black Women.

Despite the demonstrated potential of artificial intelligence (AI) in breast cancer risk assessment for personalizing screening recommendations, further validation is required regarding AI model bias and generalizability. We performed external validation on a U.S. screening cohort of a mammography-derived AI breast cancer risk model originally developed for European screening cohorts. We retrospectively identified 176 breast cancers with exams 3 months to 2 years prior to cancer diagnosis and a random sample of 4963 controls from women with at least one-year negative follow-up. A risk score for each woman was calculated via the AI risk model. Age-adjusted areas under the ROC curves (AUCs) were estimated for the entire cohort and separately for White and Black women. The Gail 5-year risk model was also evaluated for comparison. The overall AUC was 0.68 (95% CIs 0.64−0.72) for all women, 0.67 (0.61−0.72) for White women, and 0.70 (0.65−0.76) for Black women. The AI risk model significantly outperformed the Gail risk model for all women p < 0.01 and for Black women p < 0.01, but not for White women p = 0.38. The performance of the mammography-derived AI risk model was comparable to previously reported European validation results; non-significantly different when comparing White and Black women; and overall, significantly higher than that of the Gail model.

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.

Incorporating Robustness to Imaging Physics into Radiomic Feature Selection for Breast Cancer Risk Estimation.

Digital mammography has seen an explosion in the number of radiomic features used for risk-assessment modeling. However, having more features is not necessarily beneficial, as some features may be overly sensitive to imaging physics (contrast, noise, and image sharpness). To measure the effects of imaging physics, we analyzed the feature variation across imaging acquisition settings (kV, mAs) using an anthropomorphic phantom. We also analyzed the intra-woman variation (IWV), a measure of how much a feature varies between breasts with similar parenchymal patterns-a woman's left and right breasts. From 341 features, we identified "robust" features that minimized the effects of imaging physics and IWV. We also investigated whether robust features offered better case-control classification in an independent data set of 575 images, all with an overall BI-RADS® assessment of 1 (negative) or 2 (benign); 115 images (cases) were of women who developed cancer at least one year after that screening image, matched to 460 controls. We modeled cancer occurrence via logistic regression, using cross-validated area under the receiver-operating-characteristic curve (AUC) to measure model performance. Models using features from the most-robust quartile of features yielded an AUC = 0.59, versus 0.54 for the least-robust, with p < 0.005 for the difference among the quartiles.