McCarthy, Anne Marie

Abstract Background Artificial intelligence (AI)–based, mammography breast cancer risk prediction models show improved discriminatory accuracy relative to clinical risk models. However, data on their calibration are limited. This study compared model performance of 3 clinical breast cancer risk models: Gail, Tyrer–Cuzick v8, and Breast Cancer Surveillance Consortium v3 with the MIRAI AI-risk model. Methods Digital mammograms were ascertained from a screening mammography cohort of 12 308 women within the Mayo Clinic Biobank with 250 incident breast cancers (176 invasive) within 5 years. We predicted 5-year breast cancer risk, estimated discriminatory accuracy (C-index), and calibration (observed-to-expected ratio) of both overall and invasive breast cancer and compared estimates using bootstrapping approaches. Results MIRAI demonstrated similar or improved discriminatory accuracy of overall breast cancer (C-index = 0.71, 95% confidence interval [CI] = 0.68 to 0.74) and invasive breast cancer (C-index = 0.71, 95% CI = 0.67 to 0.75) compared with clinical models (overall breast cancer: C-index = 0.59-0.68; invasive breast cancer: C-index = 0.60-0.68). MIRAI’s calibration for risk of overall breast cancer (observed-to-expected ratio = 0.96, 95% CI = 0.85 to 1.08) was improved compared with Gail (observed-to-expected ratio = 1.22, 95% CI = 1.07 to 1.38) and Breast Cancer Surveillance Consortium (observed-to-expected ratio = 1.38, 95% CI = 1.22 to 1.56) but similar to TC with volumetric percent density and polygenic risk score (observed-to-expected ratio = 0.99, 95% CI = 0.87 to 1.13). However, for low-risk women (approximately 50%), MIRAI overestimated risk of overall breast cancer. MIRAI also overestimated risk of invasive breast cancer across the risk spectrum (observed-to-expected ratio = 0.68, 95% CI = 0.58 to 0.78), whereas clinical models had good calibration (observed-to-expected ratio = 0.86–0.99). Conclusion MIRAI demonstrated stronger discriminatory accuracy than clinical models for 5-year overall and invasive breast cancer risk prediction but overestimated risk for both breast cancer endpoints. AI-based risk models should consider discriminatory accuracy and calibration for invasive cancer before implementation.

Three-dimensional radiomic analysis of digital breast tomosynthesis outperformed two-dimensional measures in breast cancer risk assessment.

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 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< 0.001) and six PCs (P< 0.001) were both associated with invasive BC, including after adjusting for age, BMI, and density (cluster P=0.004; PCs P< 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< 0.001) and clusters (P< 0.001) were significantly associated with FN overall and for symptomatic IC (PCs P< 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 Introduction: Mammographic breast density is among the strongest risk factors for breast cancer. However, breast density is typically assessed subjectively by the radiologist according to the Breast Imaging Reporting and Data System (BI-RADS) based on 2 dimensional (2D) digital mammography (DM) images. Digital breast tomosynthesis (DBT) is quickly replacing DM and allows more detailed volumetric imaging of the breast. Advances in radiomics, the high-throughput extraction of radiologic features, has enabled characterization of breast parenchymal complexity beyond breast density alone. The purpose of this study was to compare the performance of volumetric parenchymal pattern analysis from DBT and DM with conventional breast density measurement with respect to breast cancer risk estimation. Methods: We performed a case control study among women with concurrent DM and DBT screening (Selenia Dimensions, Hologic Inc.) at our institution between 3/2011-12/2014. Cases were diagnosed with breast cancer within 1 year of screening; controls were confirmed negative or benign at 1 year follow-up, matched on race (Black, White, other/unknown) and age (5-year bins). After exclusions for imaging artifacts, craniocaudal (CC) and mediolateral oblique (MLO) views for 187 cases and 737 controls, in six image formats were assessed: 1) raw (“FOR PROCESSING”) DM; 2) processed (“FOR PRESENTATION”) DM; 3) raw DBT central projection; 4) processed DBT central projection; 5) DBT central reconstructed slice; and 6) DBT reconstructed stack. For cases, we analyzed the breast contralateral to cancer diagnosis; for controls the same breast as the matched case. We extracted radiomic features using a lattice-based approach with the publicly available CaPTk software, averaging features for each breast over CC and MLO views. We examined 3 lattice window sizes (6.4, 12.8, and 25.6 mm) and 23 resolutions for image resampling (0.075 - 2mm). We performed PCA on the resulting 487 features for each combination of window size and resolution and built conditional logistic regression models to assess the association of the first 7 principal components with breast cancer, with models including age, BMI, and BI-RADS density. For each image type we calculated the model C-statistic at all window sizes and resolutions, for a total of 2304 experimental conditions. Results: Features from reconstructed DBT scans had on average higher C-statistics across all experimental conditions. A model using only age, BMI, and BI-RADS density had a C-statistic of 0.61. Models using radiomic features plus age, BMI, and BI-RADS density had mean C-statistic of 0.68 (IQR 0.68, 0.69) for reconstructed DBT scans; for all other image types, the mean C-statistic ranged from 0.64 to 0.66. Conclusions: Incorporating volumetric breast parenchymal patterns from DBT improves breast cancer risk estimation beyond markers derived from DM and beyond conventional BI-RADS density. Citation Format: Eric A. Cohen, Omid Haji Maghsoudi, Raymond Acciavatti, Lauren Pantalone, Walter Mankowski, Alex A Nguyen, Christopher G. Scott, Stacey Winham, Andrew D. Maidment, Anne Marie McCarthy, Celine M Vachon, Emily F Conant, Despina Kontos. Volumetric parenchymal pattern analysis for breast cancer risk estimation. [abstract]. In: Proceedings of the AACR Special Conference: Precision Prevention, Early Detection, and Interception of Cancer; 2022 Nov 17-19; Austin, TX. Philadelphia (PA): AACR; Can Prev Res 2023;16(1 Suppl): Abstract nr P070.