Citations

Objectives: Women with a history of breast cancer are at increased risk of developing subsequent breast cancer, including ipsilateral recurrence and contralateral new primary breast cancer. This study evaluated the discriminatory performance of a mammogram-based artificial intelligence (AI) risk model for predicting subsequent breast cancer within one year after a negative screening mammogram. Methods: This enriched retrospective case–control study included women with a prior history of breast cancer who underwent screening digital breast tomosynthesis between January 2018 and December 2023 at three affiliated academic breast imaging centers. Digital breast tomosynthesis examinations classified as BI-RADS 1 or 2 were retrospectively analyzed using the ProFound AI® Risk model version 1.0 to estimate 1-year breast cancer risk. Patients were classified according to whether they developed subsequent breast cancer within one year of the index screening examination. Model discrimination was evaluated using receiver operating characteristic analysis. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated at an exploratory cutoff selected by maximizing the Youden index. Results: The study included 96 women (mean age, 65.3 ± 8.7 years), of whom 32 developed subsequent breast cancer within one year, and 64 did not. The mean AI risk score was significantly higher in the subsequent breast cancer group than in the control group (1.18 ± 0.59 vs. 0.49 ± 0.41; p < 0.001). The AI model demonstrated an AUC of 0.824 (95% CI: 0.728–0.921). At an exploratory cutoff of 0.39, sensitivity was 81.3%, specificity was 76.6%, PPV was 63.4%, and NPV was 89.1%. In separate exploratory analyses, the AUC was 0.790 (95% CI: 0.641–0.939) for ipsilateral recurrence and 0.860 (95% CI: 0.752–0.974) for contralateral new primary breast cancer. AI risk scores were not significantly correlated with tumor size or age at subsequent breast cancer diagnosis. Conclusions: In this enriched retrospective case–control study, higher mammogram-based AI risk scores were associated with subsequent breast cancer within one year after a negative screening examination. The model demonstrated discriminatory performance for both ipsilateral recurrence and contralateral new primary breast cancer; however, these analyses were exploratory. Because the cohort was enriched for subsequent breast cancer events, the reported predictive values are specific to the study sample and should not be extrapolated to routine surveillance populations. Larger prospective cohorts are needed to validate discrimination, calibration, and clinical utility.

Abstract Objective Current clinical risk models were developed for longer-term breast cancer risk stratification and therefore have limited utility for predicting short-term (1-year) breast cancer risk. This study evaluates the performance of a mammogram-based artificial intelligence (MB-AI) risk model for predicting breast cancer diagnosis within 1 year in high-risk women. Methods This retrospective case-control study included 340 women who underwent supplemental MRI screening within 1 year following a negative mammogram, of whom 101 (29.7%) developed breast cancer and 239 (70.3%) remained cancer-free during the same interval. Artificial-intelligence–assigned absolute 1-year risk scores, Tyrer–Cuzick (TC) lifetime and 10-year scores, and Gail lifetime and 5-year scores were analyzed. Model discrimination was evaluated using receiver operating characteristic (ROC) curves. Sensitivity, specificity, and predictive values were estimated at optimal cutoffs. Subgroup analyses examined model performance across genetic, menopausal, reproductive, and tumor-based strata. Results The MB-AI model demonstrated the highest overall discriminative ability (area under the curve [AUC] = 0.812), with strong performance in extremely dense breasts (AUC = 0.976). By comparison, TC lifetime (AUC = 0.625) and Gail lifetime (AUC = 0.668) models showed modest discrimination, while TC 10-year and Gail 5-year models did not discriminate (AUCs ≤0.49). Subgroup analyses showed consistent performance across clinical and pathological categories. The MB-AI model also showed an AUC comparable to that of previously developed AI models. Conclusions A mammogram-based AI model demonstrated improved performance compared with traditional clinical risk models for predicting breast cancer diagnosis within 1 year in women undergoing supplemental screening. These findings support that AI-based approaches may reflect both short-term risk and early imaging features of occult disease and suggest further investigation of AI as a complement to existing risk stratification strategies.

Breast size changes are common, but the underlying cause may be challenging to diagnose and requires a structured approach combining patient history, physical examination, and multimodality imaging to differentiate benign from malignant causes and improve patient outcomes.

Abstract Patient preferences for communication of breast imaging results are heterogeneous and depend on the clinical context and perceived severity of findings. The 21st Century Cures Act, which mandates immediate electronic release of most medical records, has fundamentally altered result reporting and patient communication in breast imaging. Although this policy enhances transparency and timely access to information, it may conflict with established preferences for how patients receive screening mammography results, diagnostic evaluations, breast biopsy results, and breast cancer risk assessment information. Prior studies—largely conducted before widespread patient portal use—demonstrated that breast imaging patients consistently prioritize timely communication, while preferred delivery methods vary based on result acuity and emotional impact. However, much of this literature pre-dates implementation of the 21st Century Cures Act and widespread use of patient portals. This review examines the current literature to summarize evidence-based patient preferences for breast imaging result communication. As adoption of immediate result release continues to evolve across institutions, understanding contemporary patient preferences is essential to guiding radiologists in optimizing patient-centered communication strategies to inform best practices in breast imaging.

Abstract High-risk breast lesions (HRLs) encompass a heterogeneous group of pathologies that coexist with an adjacent or synchronous malignancy, confer an increased risk of future breast cancer, or warrant surgical consideration because of upgrade potential or local behavior. Despite their clinical importance, management of HRLs remains variable. The American Society of Breast Surgeons (ASBrS) and the Society of Breast Imaging are collaborating to establish unified, evidence-based guidelines for managing these lesions. While these recommendations are currently in development, this review summarizes the existing literature and current guidance, including ASBrS recommendations, to provide context for multidisciplinary management. The article reviews the histopathologic features, imaging appearance, and management strategies for HRLs, including atypical ductal hyperplasia (ADH), atypical lobular hyperplasia (ALH), lobular carcinoma in situ (LCIS), flat epithelial atypia (FEA), papillomas with and without atypia, radial scar/complex sclerosing lesion (RS/CSL), mucocele-like lesion (MLL), desmoid tumor, and pseudoangiomatous stromal hyperplasia (PASH). Recent literature supports nonoperative management for specific radiologic-pathologic concordant lesions, particularly limited ADH, pure FEA, and pure RS, highlighting the important role of multidisciplinary discussion for personalized care. Lesions such as LCIS subtypes, papilloma with atypia, and MLL with atypia continue to warrant excision due to higher reported upgrade rates to malignancy. Beyond short-term management, HRLs such as ADH, ALH, and LCIS serve as biomarkers of long-term breast cancer risk, informing recommendations for surveillance, risk assessment, and chemoprevention counseling. Achieving a consensus among radiology, pathology, and surgical disciplines is essential to ensure oncologic safety while minimizing overtreatment in the era of precision breast care.

Background: The current guidelines recommend that women at elevated risk for breast cancer (BC), defined as lifetime BC risk ≥ 20%, undergo annual screening with breast magnetic resonance imaging (MRI) and mammogram. However, limited evidence exists in the literature to guide the optimal timing of the MRI relative to the mammogram. Our study evaluated women undergoing high-risk BC screenings to determine the impact of timing for supplemental MRI on BC detection. Methods: Patients who completed high-risk screening MRI at a single institution from January 2019 through June 2022 were included. Baseline characteristics and clinical outcomes were collected through retrospective chart review. MRI exams were divided into two groups based on timing of MRI: concurrent (<90 days from mammogram) and staggered (≥90 days from mammogram). Results: Of 1115 patients initially identified, 770 met inclusion criteria, with a total of 3707 screening exams performed (2073 mammograms and 1634 MRIs). The final analysis included 1355 MRI exams for 712 patients, where a prior mammogram and MRI were available. Of the MRIs included, 784 (57.9%) were concurrent and 571 (42.1%) were staggered. Additional imaging was performed for 12.5% (98/784) of concurrent MRIs and 9.6% (55/571) of staggered MRIs. Biopsy rates were 9.8% (77/784) for concurrent and 7.0% (40/571) for staggered MRIs. In this high-risk population, there were surprisingly low BC detection rates, with a BC incremental detection rate of 0.5% in both the concurrent and staggered groups (p = 1.0), with the median size of detected invasive BCs equaling 5 mm in the concurrent group and 4 mm in the staggered group (p = 0.72). Conclusions: When comparing concurrent and staggered MRI regimens, there were no significant differences in incremental cancer detection rate, tumor size, rates of additional imaging, or negative biopsies. Further investigation with prospective analysis is needed to validate these findings.

Abstract Women with a personal history of breast cancer (PHBC) remain at risk for ipsilateral breast tumor recurrence or a second primary tumor, with a cumulative incidence of 14.3% and reported annual risk of approximately 1–2%. Post-treatment changes can obscure imaging findings, making early recognition of recurrence a challenging, but critical skill for breast radiologists. Detection of early breast cancer recurrence, before it becomes symptomatic, is linked to improved survival, highlighting the need for multimodality surveillance imaging. This review summarizes key prognostic factors that influence recurrence risk and should inform imaging interpretation. Incorporating these prognostic factors into practice can aid imaging interpretation by heightening the attention to subtle changes that may reflect early recurrence. Illustrative cases are used to demonstrate the imaging spectrum of locoregional recurrence in post-lumpectomy and post-mastectomy patients. Recurrences often resemble the imaging features of the primary tumor but may also present subtly. The distinction between recurrence and benign post-treatment change is emphasized, with attention to imaging findings that warrant further evaluation. Finally, emerging evidence-based recommendations for risk-adapted surveillance incorporating tumor biology, receptor status, and stage are reviewed to support early detection and improved outcomes

Abstract Background: Artificial intelligence (AI) algorithms based on deep learning approaches show promise in improving breast cancer (BC) detection on mammography and may also improve prediction of future BC risk compared with clinical risk prediction models. Historical clinical risk prediction models underperform among women with BBD; however, AI models for BC detection on mammography have not been tested among women at elevated BC risk due to benign breast disease (BBD). We evaluated if an AI cancer detection algorithm can aid BC risk prediction among women with BBD. Methods: We examined women without a prior BC who had an initial BBD biopsy at Mayo Clinic, Rochester, between 2002 and 2013. Incident BC occurring after BBD was identified using the Mayo Tumor Registry and supplemented by follow-up questionnaires. Only women with a full field digital mammogram at least 2 years prior to BC diagnosis were eligible. A breast pathologist evaluated BBD according to increasing severity, as non-proliferative (NP), proliferative disease without atypia (PDWA) or atypical hyperplasia (AH). AI malignancy scores derived from the Transpara detection algorithm (1-10) and volumetric percent density (VPD) from Volpara (per one standard deviation, SD) were assessed from mammograms close to BBD diagnosis. Cox proportional hazards regression models were applied to estimate hazard ratios (HRs) with 95% Confidence Intervals (CIs), adjusted for age and BMI. C-statistics were estimated to assess the contribution of each factor to BC risk prediction. Likelihood ratio tests (LRTs) and bootstrapping methods were used to compare model performance with the addition of AI malignancy score. Results: The BBD cohort with mammography consisted of 3,125 women followed for a median 12.9 years, with 250 incident BC. Of these, 221 BC occurred at least two years after the mammogram and were used in analyses. As expected, increased BC risk was associated with BBD severity [for AH HR=3.18 (95%CI: 2.04, 4.95) and for PDWA HR=1.59 (95%CI: 1.17, 2.14) compared to NP] and with higher VPD [HR=1.24 per SD (95% CI: 1.05, 1.45)] (Table ). The AI-malignancy score alone was also associated with BC risk [HR=1.16 per 1 unit score (95%CI: 1.09,1.23)] and showed similar discriminatory accuracy [C-statistic=0.626 (95%CI: 0.586, 0.665)] as the model with BBD severity and VPD combined [C-statistic=0.627, (95%CI: 0.585, 0.669)] (Table ). In models with BBD severity and VPD, the AI-malignancy score was an independent risk factor for BC [HR=1.14 (95%CI: 1.07, 1.21); PLRT&lt;0.001] but only achieved a marginally significant improvement in discriminatory accuracy [C-statistic=0.651 (0.609, 0.693), ΔC-statistic=0.024 (95% CI: 0.000, 0.047)]. Conclusion: In this preliminary study, an AI BC detection algorithm achieved similar performance in predicting future BC risk compared to established risk factors. Citation Format: C. M. Vachon, S. Winham, M. Jensen, D. Hursh, L. Pacheco-Spann, A. Norman, J. Fischer, S. Schrup, L. Seymour, D. Gehling, S. Nyante, M. Troester, N. Karssemeijer, R. Vierkant, D. Radisky, C. Scott, S. I. Maimone, A. Degnim, M. Sherman. An AI algorithm for breast cancer detection improves future BC risk prediction among women with benign breast disease [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-02.

Abstract Objective To compare the pathology outcomes of image-guided breast biopsies across a multistate health care enterprise by the method of detection (MOD), including the positive predictive value (PPV3) and histological types. Methods Biopsies from October 31, 2017, to July 6, 2023, across 18 imaging sites in 4 states were extracted. Radiologists prospectively assigned MODs, including symptomatic presentations (self-examination, clinical examination) and imaging modalities (mammogram, tomosynthesis, US, MRI, contrast-enhanced mammogram, molecular breast imaging, other imaging). For each MOD, the rates of malignancy and cancer subtypes were calculated. Univariate and multivariate logistic regression analyses were performed. Results In 26 932 biopsies on 22 582 patients (mean age 57.6 years ± 14.2 [SD]; 22 416 women), 6068 (81.1%) cancers were detected by screening, and 1144 (15.3%) were detected by symptoms. Symptomatic presentation MODs had a higher PPV3 (43.0% vs 25.6%; P &lt; .001), larger cancer lesion sizes (x̄ = 27.5 mm vs x̄ = 17.8 mm; P &lt; 001), and a higher association with invasive carcinoma (96.7% vs 76.8%; P &lt;.001) compared with screening imaging-based MODs. Methods of detection with higher PPV3s also tended to have higher rates of invasive carcinoma (Spearman’s ρ = 0.83). Conclusion Compared with breast cancers detected after symptomatic presentations, those identified via image-based screening were smaller and less often invasive, confirming the value of screening in early detection. Positive predictive value and the rate of invasive carcinoma varied in parallel across MODs.