Brandt, Kathleen R.

Radiomic parenchymal phenotypes on mammograms were used to predict breast cancer risk among both Black and White women, notably for false-negative findings and symptomatic interval cancer.

Abstract Artificial intelligence (AI) models based on deep learning of mammogram images have been developed for lesion detection and diagnosis as well as breast cancer (BC) risk. We and others have shown that these AI models, coupled with breast density, predict long-term breast cancer risk. Common germline genetic variation, in particular a polygenic risk score (PRS) that captures the cumulative impact of hundreds of common risk variants, has been shown associated with 3-fold increased BC risk. The BC-PRS may complement imaging risk factors to improve identification of women at high BC risk and better target prevention strategies. We evaluated the contribution of a BC-PRS to two imaging-based AI models (Transpara AI cancer detection system and Mirai 5-year risk) and breast density measures to long-term BC risk. We hypothesized that the BC-PRS will improve long-term risk prediction above AI and density measures. We examined this hypothesis within a cohort of 10,271 women enrolled to the Mayo Clinic Biobank between 2009 and 2015. Eligible women had no prior cancer, were ages 35 to 85, had a full-field digital screening mammogram within two years of enrollment and genotyping by Regeneron. Incident invasive and DCIS BC was identified through the Mayo tumor registry and follow-up questionnaires, and person years were calculated from date of mammogram through date of BC, last mammogram at Mayo or last questionnaire. We estimated Transpara AI malignancy score (1-10), 5-year Mirai risk and Volpara volumetric density measures (volumetric percent density, dense volume) on screening mammograms at enrollment and obtained clinical BI-RADS density. We calculated the BC-PRS using 268 SNPs (of the 313-SNP score) and the weighted sum of the SNPs using odds ratios from the largest BC GWAS of European ancestry to date. We performed cox proportional hazards regression adjusting for age and BMI to estimate hazard ratios (HRs), 95% confidence intervals (CI), and C-statistics (AUC) to describe the contribution of BC-PRS (per standard deviation (SD)) to the association of AI scores and breast density with BC risk. Likelihood ratio tests (LRT) and bootstrapping were used to compare model performance with vs. without inclusion of BC-PRS, at 10-years follow-up. Comparisons to the Tyrer-Cuzick model are ongoing. Over a median of 9.1 years (Interquartile range, 6.8 to 10.6), 446 incident BC were identified of which 285 invasive and 103 DCIS were confirmed by pathology report (60 were self-reported); 399 (256 invasive) occurred within 10 years and were used in primary analyses. Transpara score [HR per 1 unit=1.18 (1.14, 1.23), AUC=0.655 (0.628, 0.682)] and Mirai risk [HR per SD log risk=1.54 (1.43, 1.65), AUC=0.681 (0.655, 0.706)] were both associated with BC. All three breast density measures were also significantly associated with BC, including in models with AI scores (Table). Addition of the BC-PRS to models with AI scores and breast density improved both model fit (All PLRT < 0.001; Table) and discrimination, with increases in AUC ranging from 0.033 to 0.034 for models with Transpara and density and 0.025 to 0.026 for models with Mirai and density (all P-values < 0.001; Table). Analyses restricted to invasive BC showed identical results. But, the BC-PRS contribution at 5-year follow-up was attenuated. In this cohort study, we found BC-PRS contributed to long-term risk prediction of BC above imaging AI models and breast density. Imaging and genetic risk factors are complementary and may outperform existing risk models and provide more accurate risk assessment to aid in precision prevention strategies. Citation Format: Celine Vachon, Christopher Scott, Imon Banerjee, Ramon Correa Moderno, Dan Hursh, Matthew Jensen, Yvonne Wang, Kathleen Brandt, Karla Kerlikowske, Sandhya Pruthi, Fergus Couch, Stacey Winham. Contribution of a breast cancer polygenic risk score to mammography artificial intelligence models and breast density for long term breast cancer risk prediction [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PS10-06.

Abstract Artificial intelligence (AI) models applied to mammography have been shown to improve breast cancer (BC) detection and risk estimation. The Transpara AI detection system has been associated with short and longer-term risk of invasive BC. Whether Transpara can identify changes in the breast associated with tamoxifen (TAM) and aromatase inhibitor (AIs) treatment is unknown. We compare changes in the Transpara malignancy score in the unaffected breast of BC cases using TAM or AIs to those of untreated women without cancer. Cases and controls were sampled from the Mayo Clinic Rochester Breast Screening Practice. Eligible cases were women with breast cancer treated with TAM and/or AIs for at least 8 months who had full field digital (FFDM) mammograms within two years prior to start of treatment (pretreatment mammogram). Controls did not have BC, were not using TAM, AIs, or postmenopausal hormones, and had at least two FFDM screening mammograms. Transpara scores (1-10) were calculated for the contralateral breast in cases and a randomly selected side for controls. Two controls were matched to each case on menopausal status at both mammograms, time between mammograms (< 6 months) and baseline Transpara score (±2 units). Conditional logistic regression was used to assess the association of treatment (case (TAM/AIs) vs. control) with change in Transpara score between the pretreatment mammogram and the mammogram taken closest to 13 months later. Change was classified as having a decrease in Transpara score between the two mammograms vs. no change or an increase. Models were adjusted for age and Transpara score at pretreatment mammogram, and time between the two mammograms. We performed analyses on all women combined and stratified by time on treatment, menopausal status, and treatment type (TAM vs. AIs). A total of 134 cases were identified, with 53 on TAM (21 premenopausal and 32 postmenopausal) and 81 on AIs (postmenopausal); 268 controls were matched to the cases. Characteristics of the study population are summarized (Table). Most case mammograms were obtained within six months prior to treatment start [median 2.63 months (interquartile range (IQR), 1.62, 5.72)] and median time on TAM/AIs was 10.9 months (IQR, 8.03, 16.6) at time of second mammogram. The median absolute change in Transpara score between the two mammograms was similar in cases [0 (IQR, -2, 1)] vs. controls [0 (IQR, -1.25, 1)]; 40.3% of cases and 39.2% of controls had any decrease. Conditional logistic models found no evidence for an association between TAM/AIs and decrease in Transpara score [odds ratio (OR) = 1.07; 95% confidence interval (CI), 0.65, 1.78]. When stratified by median time on treatment (10.9 months), there was suggestion of a stronger association for those on treatment for a longer duration (OR = 1.21; 95% CI, 0.61, 2.40 for >10.9 months vs. OR = 0.96; 95% CI, 0.43, 2.13 for < 10.9 months) but these results were not statistically significant. Similarly, odds ratios were stronger in postmenopausal (OR = 1.18; 95% CI, 0.67, 2.07) compared to premenopausal (OR = 0.91; 95% CI, 0.24, 3.45) women, and for AIs (OR = 1.21, 95% CI, 0.64, 2.29) vs. TAM (OR = 0.93; 95% CI, 0.39, 2.22) but none of these results reached statistical significance. In summary, we found no association between treatment with TAM/AIs and change in Transpara score. However, our study had limited power. Also, longer time on treatment as well as investigation of AI-based scores trained directly to assess BC risk may be necessary to identify relevant changes. Citation Format: Yvonne Wang, Christopher Scott, Matthew Jensen, Dan Hursh, Kathleen Brandt, Aaron Norman, Fang Fang Wu, Stacey Winham, Karla Kerlikowske, Celine Vachon. Changes in an artificial intelligence model score for breast cancer detection (Transpara) with tamoxifen and aromatase inhibitor treatment [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-09-04.

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 ( P LRT 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.

Abstract Breast parenchymal patterns on radiologic images are associated with breast cancer risk. Radiomic features have been proposed as quantitative measures of parenchymal patterns. We defined intrinsic imaging phenotypes of breast parenchymal patterns based on radiomic features extracted from full field digital mammography (FFDM) in breast screening populations and assessed whether these phenotypes are associated with breast cancer risk and masking. We selected 30,000 women with 4-view FFDM exams from Hologic machines from three institutions (Hospital of the University of Pennsylvania, Mayo Clinic, and San Francisco Mammography Registry), randomly split into a training (20,000 women) and test set (10,000 women). In total, 390 radiomic features were automatically extracted from each image using a validated software pipeline, standardized, and adjusted for site differences using ComBat. We used two methods, hierarchical clustering and Principal Components (PCs) analysis, to classify significant variation among the features in the training set and replicate among the test set. Next, we applied the replicated clusters and PCs to an independent nested case-control set [1082 invasive breast cancer (BC) cases (of which 151 were Black and 893 White women, 38 other race) matched to 2837 controls (411 Black and 2345 White women, 81 other race) on age, race, timing of images, and site]. We examined associations of the clusters and PCs with invasive breast cancer risk, as well as masking [defined as a false-negative (FN) screen (124 cases and 319 matched controls) and additionally the subset with symptomatic interval cancer (IC) within 12 months of negative screen (88 cases and 223 matched controls)] using conditional logistic regression. We evaluated their association with breast cancer alone, and with adjustment for age, body mass index (BMI) and breast density assessed by Breast Imaging Reporting and Data System (BI-RADS) using likelihood ratio tests. We estimated discrimination using area under the curve (AUC) and compared AUCs for models that included the radiomic clusters and PCs with the model that included only age, BMI and density. We also stratified analyses by race (Black/White). From hierarchical clustering, we defined six statistically significant phenotype clusters (each of at least 1000 women) in the training set which were replicated in the test set. For PC Analysis, we identified six PCs in the training set, explaining 85% of the variation in texture features and reproduced these in the test set. The six radiomic phenotype clusters (P&lt; 0.001) and six PCs (P&lt; 0.001) were both associated with invasive BC, including after adjusting for age, BMI, and density (cluster P=0.004; PCs P&lt; 0.001). Improvements in discrimination of invasive BC with inclusion of PCs or clusters were more pronounced among Black women (Table). Further, the PCs (P&lt; 0.001) and clusters (P&lt; 0.001) were significantly associated with FN overall and for symptomatic IC (PCs P&lt; 0.001; clusters P=0.001), but only PCs remained significant after adjusting for age, BMI and density (PCs P=0.004 for FN; PCs P=0.007 for symptomatic IC). Discrimination of masking also improved with inclusion of both clusters and PCs (Table). We identified reproducible radiomic phenotypes that are associated with invasive BC risk, above and beyond breast density with the strongest associations for invasive BC among Black women and symptomatic interval cancers. Citation Format: Stacey Winham, Anne Marie McCarthy, Aimilia Gastounioti, Christopher Scott, Aaron Norman, Walter C. Mankowski, Lauren Pantalone, Matthew Jensen, Eric A. Cohen, Hannah Horng, Kathleen Brandt, Emily F. Conant, Karla Kerlikowske, Despina Kontos, Celine Vachon. Radiomic phenotypes of breast texture and association with breast cancer risk and masking [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr GS4-06.

Abstract To facilitate the delivery of accurate and timely care to patients in complex environments, process improvement methodologies such as Lean can be very effective. Lean is a quality improvement methodology that seeks to add value for patients and employees by continuously improving processes and eliminating waste. At our institution, Lean principles were applied to improve efficiency and minimize waste in the diagnostic breast imaging reading room. This paper describes how we applied Lean principles, including plan-do-study-act testing, level-loading (heijunka), and visual management, to level the workload of the diagnostic radiologists in our practice. Implementation of these principles to improve the diagnostic workflow in breast imaging is described along with examples from our practice, including challenges and future opportunities.

Abstract High alcohol intake and breast density increase breast cancer (BC) risk, but their interrelationship is unknown. We examined whether volumetric density modifies and/or mediates the alcohol-BC association. BC cases (n = 2233) diagnosed from 2006 to 2013 in the San Francisco Bay area had screening mammograms 6 or more months before diagnosis; controls (n = 4562) were matched on age, mammogram date, race or ethnicity, facility, and mammography machine. Logistic regression was used to estimate alcohol-BC associations adjusted for age, body mass index, and menopause; interaction terms assessed modification. Percent mediation was quantified as the ratio of log (odds ratios [ORs]) from models with and without density measures. Alcohol consumption was associated with increased BC risk (2-sided Ptrend = .004), as were volumetric percent density (OR = 1.45 per SD, 95% confidence interval [CI] = 1.36 to 1.56) and dense volume (OR = 1.30, 95% CI = 1.24 to 1.37). Breast density did not modify the alcohol-BC association (2-sided P &gt; .10 for all). Dense volume mediated 25.0% (95% CI = 5.5% to 44.4%) of the alcohol-BC association (2-sided P = .01), suggesting alcohol may partially increase BC risk by increasing fibroglandular tissue.

Abstract Background: Alcohol intake and breast density are established risk factors for breast cancer (BC). A few studies suggest breast density is on the causal pathway between alcohol and BC but the literature is not consistent. We examine the interrelationship between alcohol, volumetric breast density and BC risk, specifically whether there is a stronger alcohol and BC association among women with dense breasts and/or whether breast density mediates the alcohol and BC association. Methods: We conducted a nested case-control study within the San Francisco Mammography Registry consisting of four breast screening centers. From 2006-2013, through linkages with the California cancer registry, we identified 2572 women diagnosed with BC who had screening mammograms performed at least six months prior to diagnosis. Controls (5119) were matched to cases on age, date of earliest mammogram, race/ethnicity, facility, and mammography machine. We obtained the raw format of digital mammograms on average 3.1 (standard deviation (SD) =1.7) years prior to diagnosis or corresponding date for controls. We ascertained usual daily alcohol intake and other risk factors from a clinical questionnaire at time of mammography. We obtained BI-RADS density from clinical records and used VolparaTM to assess volumetric percent density, dense volume and non-dense volume from the mammogram. We examined the associations of daily alcohol intake (none, one or less, two or more drinks per day) and volumetric density phenotypes (per 1 SD) with BC risk using logistic regression (odds ratios, OR; 95% confidence intervals, CI; and trend tests). We examined deviation from multiplicative interaction using chi-squared tests. We evaluated mediation of the alcohol and BC association by volumetric density measures using logistic regression to estimate the association between alcohol use and BC with and without adjustment for density measures. Percent mediation was estimated using the differences in the log OR estimates from the two models. All models were adjusted for age, 1/BMI and menopause and matching factors. Analyses were also stratified by menopausal status. Results: Alcohol intake was available on 2233 cases and 4562 controls, 88% of those eligible. BC cases and controls had similar age (57.2 years (SD=11.5) vs. 57.1 years (SD=11.5)), BMI (25.3 kg/m2 (SD=5.3) vs. 24.9 kg/ m2 (SD=5.1)) and race (69.0% vs. 68.2% Caucasian). Cases were more likely to drink alcohol daily than controls (52.1% vs. 49.0%), in particular two or more drinks per day (14.8% vs. 13.2%). Alcohol was associated with increased BC risk (OR=1.14, 95% CI:1.02-1.27, for one or less drinks per day and OR=1.22, 95% CI:1.05-1.42 for 2 or more drinks per day) compared to non-drinkers (p-trend=0.004). Percent volumetric density (OR=1.45 per SD, 95%CI: 1.36-1.56,) and dense volume (OR=1.30, 95% CI: 1.24-1.37) were also positively associated with BC risk; non-dense volume was inversely associated (OR=0.93, 95%CI: 0.86-1.01). Associations were similar by menopausal subgroup. There was no evidence for a differential association of alcohol and breast cancer risk by dense breasts assessed using any of the density phenotypes examined (all P’s&gt;0.1). However, the association between alcohol and overall risk of BC was partially mediated by dense volume among all women (percent mediated=25%, P=0.01) and postmenopausal women (percent mediated=19%, P=0.03). Conclusions: The association of daily alcohol intake and breast cancer risk was similar among women with dense and non-dense breasts. However, dense volume partially mediated the association between alcohol and risk of breast cancer, particularly among postmenopausal women, suggesting that alcohol partially influences breast cancer risk through changes in breast tissue composition. Citation Format: Celine Marie Vachon, Christopher G. Scott, Stacey J Winham, John A Shepherd, Kathleen R Brandt, Matthew R Jensen, Carrie B Hruska, John J Heine, V. Shane Pankratz, Karla Kerlikowske. Association of daily alcohol intake, volumetric density and breast cancer risk [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P5-08-02.

Abstract Background: Mammographic breast density declines during menopause. We assessed changes in volumetric breast density across the menopausal transition and factors that influence these changes. Methods: Women without a history of breast cancer, who had full field digital mammograms during both pre- and postmenopausal periods, at least 2 years apart, were sampled from four facilities within the San Francisco Mammography Registry from 2007 to 2013. Dense breast volume (DV) was assessed using Volpara on mammograms across the time period. Annualized change in DV from pre- to postmenopause was estimated using linear mixed models adjusted for covariates and per-woman random effects. Multiplicative interactions were evaluated between premenopausal risk factors and time to determine whether these covariates modified the annualized changes. Results: Among the 2,586 eligible women, 1,802 had one premenopausal and one postmenopausal mammogram, 628 had an additional perimenopausal mammogram, and 156 had two perimenopausal mammograms. Women experienced an annualized decrease in DV [−2.2 cm3 (95% confidence interval, −2.7 to −1.7)] over the menopausal transition. Declines were greater among women with a premenopausal DV above the median (54 cm3) versus below (DV, −3.5 cm3 vs. −1.0 cm3; P &lt; 0.0001). Other breast cancer risk factors, including race, body mass index, family history, alcohol, and postmenopausal hormone therapy, had no effect on change in DV over the menopausal transition. Conclusions: High premenopausal DV was a strong predictor of greater reductions in DV across the menopausal transition. Impact: We found that few factors other than premenopausal density influence changes in DV across the menopausal transition, limiting targeted prevention efforts.