Robinson, Kristin A.

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.

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 The practice of formally documenting radiologic and pathologic concordance after percutaneous breast biopsies was instituted more than 20 years ago. There are several ways in which this can be done, but in many practices the performing radiologist independently compares the imaging findings with the pathology report to determine concordance. However, some studies show that a multidisciplinary review of breast biopsy results can maximize cancer detection, identify discordant cases in a timely manner, decrease imaging follow-up, and avoid unnecessary surgical intervention. This article will propose a practical method to establish a formal radiology-pathology conference in which percutaneous breast biopsies are reviewed with multidisciplinary input to increase efficiency and improve patient care. With the wide implementation of digital radiologic imaging and digital pathology evaluation plus the recent adoption of virtual meeting platforms, a successful radiology-pathology conference can be implemented in nearly any practice setting. Case examples will be presented demonstrating the utility of such a conference.

Abstract Objective Peri-implant enhancement can be seen on contrast-enhanced breast MRI, but its association with malignancy has not been described, leading to considerable variability in assessment and recommendations by radiologists. This study evaluated imaging features, management, and outcomes of implant-related enhancement. Methods This multisite IRB-approved retrospective review queried all breast MRI reports for keywords describing peri-implant enhancement, fluid, and/or masses (plus synonymous descriptions) and implant-associated malignancies, with subsequent imaging and chart review. Peri-implant enhancement and implant features were characterized. Assessments and outcomes were evaluated via clinical and imaging follow-up, aspiration/biopsy, and/or capsulectomy to evaluate for association of peri-implant enhancement with implant-related malignancy. Results A total of 100 patients had peri-implant enhancement. Uniform thin peripheral enhancement was most common (79/100, 79%). Capsulectomy was performed in 31/100 (31%), with benign capsular fibrosis/inflammation discovered in 26/31 (83.9%). Breast implant–associated anaplastic large cell lymphoma was present in 2/100 (2%), both with textured implants, while 98/100 (98%) had no implant-related malignancy. MRI recommendations varied: resume routine imaging (26/100, 26%), clinical management (18/100, 18%), follow-up MRI (17/100, 17%), MRI-directed US (17/100, 17%), aspiration/biopsy (11/100, 11%), and surgical consultation (10/100, 10%). Conclusion Peri-implant enhancement is a nonspecific imaging finding with a low malignant association, especially when seen in isolation (no associated effusion, mass, or adenopathy). Implant surface texture should be considered in management recommendations; diagnostic capsulectomy is not recommended in patients with smooth implants. Additional studies are encouraged to validate nonoperative management recommendations.

Papillary carcinoma of the breast is a rare histologic subtype of invasive breast cancer. In contrast, ductal carcinoma in situ (DCIS) is a noninvasive, nonobligate precursor to invasive mammary carcinoma, confined within the terminal duct lobular unit of the breast and surrounded by an intact myoepithelial cell layer at the stromal/epithelial interface. We present an unusual case in which a patient with only DCIS of the breast exhibited papillary carcinoma within a sentinel lymph node, leading to questions about the origin of the lymph node lesion—whether it represents a true metastasis or iatrogenic displacement during diagnostic procedures. This case underscores the diagnostic challenges and clinical implications associated with such rare presentations.

Abstract Objective Establish a radiologist-run consultation clinic to review breast density and supplemental screening exams (SSEs) directly with patients in response to breast density reporting laws. Methods Breast radiologists opened and staffed a clinic for formal patient consultations regarding breast density and SSEs. An IRB-approved questionnaire assessed patient knowledge of breast density, SSEs, and encounter satisfaction. Comparative statistical analyses were performed on knowledge-based questions. Results From February 2019 to February 2021, 294 reimbursable consultations were performed with 215 patients completing pre- and post-consultation questionnaires (survey response rate, 73%). Median patient age was 58 years (range, 34–86 years) and 9% (19/210) had a personal history of breast cancer. An increase in patient knowledge of breast density and SSEs was observed as follows: breast density categories (9% correct pre-consultation (20/215), 86% correct post-consultation (185/215), P &lt; 0.001), dense breast effects on cancer risk (39% correct pre-consultation (83/215), 84% post-consultation (180/215)), mammogram sensitivity (90% correct pre-consultation (193/215), 94% post-consultation (201/215)), and increased cancer detection with SSEs (82% correct pre-consultation (177/215), 95% post-consultation (205/215)) (P &lt; 0.001). Post-consultation, 96% (200/209) were satisfied with the usefulness of information, 89% (186/209) strongly agreed they had sufficient knowledge of SSEs, and 81% (167/205) agreed they would like future opportunities to meet with a breast radiologist. Conclusion A consultation clinic staffed by breast radiologists focused on breast density and supplemental breast cancer screening can provide personalized patient counseling, engage patients in shared decision making, assist referring clinicians, and support high quality patient-centered care.

Abstract Objective Molecular breast imaging (MBI) is a supplemental screening modality consistently demonstrating incremental cancer detection over mammography alone; however, its lengthy duration may limit widespread utilization. The study purpose was to assess feasibility of an abbreviated MBI protocol, providing readers with mediolateral oblique (MLO) projections only and assessing performance in lesion detection and localization. Methods Retrospective IRB-exempt blinded reader study administered to 5 fellowship-trained breast imaging radiologists. Independent reads performed for 124 screening MBI cases, half abnormal and half negative/normal. Readers determined whether an abnormality was present, side of abnormality, and location of abnormality (medial/lateral). Abnormal cases had confirmatory biopsy or surgical pathology; normal cases had imaging follow-up ensuring true negative results. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated to assess performance. A false negative result indicated that a reader failed to detect abnormal uptake; a false positive result indicated a reader incorrectly called an abnormality for a negative case. Tests for association included chi-square, Fisher-exact, and analysis of variance. Results Mean reader performance for detecting abnormal uptake: sensitivity 96.8%, specificity 98.7%, PPV 98.8%, and NPV 96.9%. Accuracy in localizing lesions to the medial or lateral breast was 100%. There were no associations in reader performance with reader experience, reader technique, lesion morphology, or lesion pathology. Median lesion size was 1.0 cm (range: 0.4–8.0 cm). All readers correctly identified 97.7% (42/43) of lesions with malignant or elevated risk pathology. Conclusion An abbreviated MBI protocol (MLO images only) maintained high accuracy in lesion detection and localization.

Abstract Background: This study reports incidence, timing, characteristics, and surveillance imaging of mammographic axillary adenopathy following COVID-19 vaccination. As COVID-19 immunizations continue, with possible booster vaccines upcoming, this study offers timing considerations and potential follow-up recommendations for breast imaging after vaccination. Methods: Retrospective analysis of patients (pts) who received at least one COVID-19 vaccine prior to screening (SM) or diagnostic mammography (DM) at Mayo Clinic Florida between January 15 to May 31, 2021. Vaccine-related information was queried by mammography technologists. Adenopathy was assessed by interpreting radiologists and follow-up studies were collated. Mammogram adenopathy included single enlarged node, multiple enlarged nodes, and adenopathy with soft tissue stranding. Ultrasound adenopathy included mildly prominent nodes with preserved fatty hila to rounded nodes with apparent loss of a fatty hilum. Wilcoxon rank-sum test and Fisher’s exact test were used to compare continuous and categorical variables, respectively. Multivariable logistic regression model was used to evaluate the association between days from vaccine and adenopathy. Results: Of 2349 pts, 34 (1.4%) had adenopathy (DM=6; SM=28) and 3 (0.1%) were symptomatic. Presence of axillary symptoms was associated with abnormal imaging (p&lt;0.001) with an odds ratio of 33 in multivariable model. Median time after vaccine for pts with adenopathy was significantly shorter at 14 days compared to 33 days for pts without adenopathy (p&lt;0.001). Incidence of adenopathy decreased as days from vaccine increased (3.4% for 0-14 days, 2.1% for 15-28 days, and 0.4% for &gt; 28 days, p&lt;0.001). After adjusting for being symptomatic, days from vaccine still had a significant impact on finding mammographic adenopathy (for each day after vaccine, OR=0.96, p&lt;0.001). No significant difference was seen based on age (p=0.66), vaccine brand (p=0.66), vaccine dose (p=0.18). ROC analysis to identify a cutoff value for presence/absence of adenopathy was 0.74 (95% CI 0.67-0.81) at 22.5 days following vaccination. Additional imaging with mammogram and/or ultrasound was requested for 31 pts. These included no follow-up (n=4, 12.9%), repeat ultrasound with or without mammogram in 1-3 months (n=26, 83.9%), and biopsy (n=1, 3.2%, pt with ipsilateral breast cancer with negative results, presumably vaccine induced). To date, all pts who underwent surveillance imaging demonstrated normalization of lymph node appearance. The median time for abnormal imaging related to adenopathy to return to BI-RADS 1 or 2 was 84 (range 13-157) days. Conclusion: The incidence of COVID-19 vaccine-induced adenopathy in this study (1.4%) appeared to be lower than self-reported axillary swelling in COVID-19 vaccine trials (16%) but is still higher than the reported incidence of adenopathy on an otherwise normal SM (0.02-0.04%). The incidence of adenopathy decreased significantly over time and was not present in most pts 28 days after the vaccine. In patients with abnormal adenopathy, followup imaging showed resolution of vaccine-induced adenopathy in most patients by 3 months. Adenopathy(N=34)No Adenopathy (N=2315)P valueAge0.66N342314Median (Range)63.5 (35.0, 83.0)64.0 (30.0, 94.0)Q1, Q351.5, 72.555.0, 71.0Exam type&lt;0.001DM6 (13.3%)39 (86.7%)SM28 (1.2%)2276 (98.8%)Symptomatic&lt;0.001Missing032Yes3 (23.1%)10 (76.9%)No31 (1.3%)2273 (98.7%)Vaccine brand0.66Missing119mRNA-127319 (1.7%)1117 (98.3%)BNT162b214 (1.2%)1138 (98.8%)Other0 (0.0%)41 (100.0%)Vaccine dose0.18Missing0181st9 (2.2%)409 (97.8%)2nd25 (1.3%)1888 (98.7%)Days from vaccine&lt;0.001Median (Range)14.0 (1.0, 91.0)33.0 (0.0, 239.0)Q1, Q38.2, 20.816.0, 61.0Days from Vaccine&lt;0.0010-1418 (3.4%)519 (96.6%)15-2811 (2.1%)513 (97.9%)&gt;285 (0.4%)1283 (99.6%) Citation Format: Kristin Robinson, Santo Maimone, Pooja P Advani, Zhuo Li, Denise Gococo-Benore, Neda Qosja, Ashita Mummareddy, Ahmed M Ashai, Annamaria Wilhelm, Robert Maxwell, Martha Wasserman, Neema Patel, Andrey Morozov, Saranya Chumsri. Incidence and time to resolution of axillary adenopathy on mammography after COVID-19 vaccination [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P3-03-19.