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 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 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.

e12615 Background: Breast MRI after completion of neoadjuvant chemotherapy (NAC) has demonstrated high sensitivity and positive predictive value in evaluating response to NAC. It is widely recognized as the most accurate imaging technique for assessing tumor response, outperforming mammography and ultrasound. However, there remains a knowledge gap in its potential as an early predictor of pathological response, when performed at the midpoint of NAC. Here, we investigated the correlation between MRI findings at the midpoint of NAC and subsequent pathological response at definitive surgery. Methods: A retrospective study was performed of patients with breast cancer who received NAC at Mayo Clinic, Florida and had at least 2 breast MRIs, one at midpoint and one either pre- or post-treatment. Patients with prior ipsilateral breast cancer were excluded. Participants were stratified into three molecular subtypes: hormone receptor-positive (HR+), HER2-positive (HER2+), and triple-negative breast cancer (TNBC). All MRIs were re-reviewed by dedicated breast radiologists, with tumor response classified as complete response (CR), partial response (PR), stable disease (SD), or progressive disease (PD) based on RECIST criteria. Pathological outcomes, including pathologic complete response (pCR) and residual cancer burden (RCB), were extracted from pathology reports and confirmed by a single breast pathologist, as indicated. pCR was defined as the absence of residual invasive tumor in both the breast and axillary lymph nodes. Results: A total of 154 patients met inclusion criteria from 2012 to 2022. Similar to previous studies, the positive predictive value for the post-treatment MRI was high at 82.4%, with 14 of 17 patients with imaging complete responses (iCR) achieving pCR. For the midpoint MRI, the positive predictive value for patients with iCR was 100%, with 8 out of 8 patients achieving pCR. Patients with certain subtypes of breast cancer with at least PR in both breast and axillary lymph nodes at midpoint MRI had numerically higher pCR rate, specifically HER2+ (22/37, 59.5%) and TNBC (8/13, 61.5%) but not HR+ tumors (12/45, 26.7%). In contrast, patients with less than PR in either breast or axillary lymph nodes showed numerically lower rate pCR in TNBC (7/18, 38.9%) and HR+ tumors (3/18, 16.7%). However, 15/23 (65.2%) patients with HER2+ tumors achieved pCR despite having less than PR at midpoint MRI. Conclusions: Midpoint breast MRI may serve as an early predictor of pathological response, particularly in patients with iCR. Patients with less than PR, especially those with HR+ and TNBC, have lower chances of achieving pCR. These findings highlight the importance of considering additional therapies for these subgroups of patients to improve the treatment outcomes, as they are less likely to achieve pCR with the current standard neoadjuvant chemotherapy regimen.

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.

Abstract Unlike many other subspecialties in radiology, breast radiologists practice in a patient-facing and interdisciplinary environment where team building, communication, and leadership skills are critical. Although breast radiologists can improve these skills over time, strong mentorship can accelerate this process, leading to a more successful and satisfying career. In addition to providing advice, insight, feedback, and encouragement to mentees, mentors help advance the field of breast radiology by contributing to the development of the next generation of leaders. During the mentorship process, mentors continue to hone their listening, problem-solving, and networking skills, which in turn creates a more supportive and nurturing work environment for the entire breast care team. This article reviews important mentorship skills that are essential for all breast radiologists. Although some of the principles apply to all mentoring relationships, ensuring that every breast radiologist has the skills to be both an effective mentor and mentee is key to the future of the profession.

Abstract Objective The purpose of this study is to assess the “real-world” impact of an artificial intelligence (AI) tool designed to detect breast cancer in digital breast tomosynthesis (DBT) screening exams following 12 months of utilization in a subspecialized academic breast center. Methods Following IRB approval, mammography audit reports, as specified in the BI-RADS atlas, were retrospectively generated for five radiologists reading at three locations during a 12-month time frame. One location had the AI tool (iCAD ProFound AI v2.0), and the other two locations did not. The co-primary endpoints were cancer detection rate (CDR) and abnormal interpretation rate (AIR). Secondary endpoints included positive predictive values (PPVs) for cancer among screenings with abnormal interpretations (PPV1) and for biopsies performed (PPV3). Odds ratios (OR) with two-sided 95% confidence intervals (CIs) summarized the impact of AI across radiologists using generalized estimating equations. Results Nonsignificant differences were observed in CDR, AIR, and PPVs. The CDR was 7.3 with AI and 5.9 without AI (OR 1.3, 95% CI: 0.9–1.7). The AIR was 11.7% with AI and 11.8% without AI (OR 1.0, 95% CI: 0.8–1.3). The PPV1 was 6.2% with AI and 5.0% without AI (OR 1.3, 95% CI: 0.97–1.7). The PPV3 was 33.3% with AI and 32.0% without AI (OR 1.1, 95% CI: 0.8–1.5). Conclusion Although we are unable to show statistically significant changes in CDR and AIR outcomes in the two groups, the results are consistent with prior reader studies. There is a nonsignificant trend toward improvement in CDR with AI, without significant increases in AIR.

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.