Self-reported barriers to screening breast MRI among women at high risk for breast cancer.

BACKGROUND: Annual screening breast MRI is recommended for women at high (≥ 20% lifetime) breast cancer risk, but is underutilized. Guided by the Health Services Utilization Model (HSUM), we assessed factors associated with screening breast MRI among high-risk women. METHODS: From August 2020-January 2021, we recruited an online convenience sample of high-risk women ages 25-85 (N = 232). High-risk was defined as: pathogenic genetic mutation in self or first-degree relative; history of lobular carcinoma in situ; history of thoracic radiation; or estimated lifetime risk ≥ 20%. Participants self-reported predisposing factors (breast cancer knowledge, health locus of control), enabling factors (health insurance type, social support), need factors (perceived risk, screening-supportive social norms, provider recommendation), and prior receipt of screening breast MRI. Multivariable logistic regression analysis with backward selection identified HSUM factors associated with receipt of screening breast MRI. RESULTS: About half (51%) of participants had received a provider recommendation for screening breast MRI; only 32% had ever received a breast MRI. Breast cancer knowledge (OR = 1.15, 95% CI = 1.04-1.27) and screening-supportive social norms (OR = 2.21, 95% CI = 1.64-2.97) were positively related to breast MRI receipt. No other HSUM variables were associated with breast MRI receipt (all p's > 0.1). CONCLUSIONS: High-risk women reported low uptake of screening breast MRI, indicating a gap in guideline-concordant care. Breast cancer knowledge and screening-supportive social norms are two key areas to target in future interventions. Data were collected during the COVID-19 pandemic and generalizability of results is unclear. Future studies with larger, more heterogeneous samples are needed to replicate these findings.

NCCN Guidelines® Insights: Breast Cancer Screening and Diagnosis, Version 1.2023.

The NCCN Guidelines for Breast Cancer Screening and Diagnosis provide health care providers with a practical, consistent framework for screening and evaluating a spectrum of clinical presentations and breast lesions. The NCCN Breast Cancer Screening and Diagnosis Panel is composed of a multidisciplinary team of experts in the field, including representation from medical oncology, gynecologic oncology, surgical oncology, internal medicine, family practice, preventive medicine, pathology, diagnostic and interventional radiology, as well as patient advocacy. The NCCN Breast Cancer Screening and Diagnosis Panel meets at least annually to review emerging data and comments from reviewers within their institutions to guide updates to existing recommendations. These NCCN Guidelines Insights summarize the panel's decision-making and discussion surrounding the most recent updates to the guideline's screening recommendations.

Breast MRI during Neoadjuvant Chemotherapy: Lack of Background Parenchymal Enhancement Suppression and Inferior Treatment Response.

Background Suppression of background parenchymal enhancement (BPE) is commonly observed after neoadjuvant chemotherapy (NAC) at contrast-enhanced breast MRI. It was hypothesized that nonsuppressed BPE may be associated with inferior response to NAC. Purpose To investigate the relationship between lack of BPE suppression and pathologic response. Materials and Methods A retrospective review was performed for women with menopausal status data who were treated for breast cancer by one of 10 drug arms (standard NAC with or without experimental agents) between May 2010 and November 2016 in the Investigation of Serial Studies to Predict Your Therapeutic Response with Imaging and Molecular Analysis 2, or I-SPY 2 TRIAL (NCT01042379). Patients underwent MRI at four points: before treatment (T0), early treatment (T1), interregimen (T2), and before surgery (T3). BPE was quantitatively measured by using automated fibroglandular tissue segmentation. To test the hypothesis effectively, a subset of examinations with BPE with high-quality segmentation was selected. BPE change from T0 was defined as suppressed or nonsuppressed for each point. The Fisher exact test and the Z tests of proportions with Yates continuity correction were used to examine the relationship between BPE suppression and pathologic complete response (pCR) in hormone receptor (HR)-positive and HR-negative cohorts. Results A total of 3528 MRI scans from 882 patients (mean age, 48 years ± 10 [standard deviation]) were reviewed and the subset of patients with high-quality BPE segmentation was determined (T1, 433 patients; T2, 396 patients; T3, 380 patients). In the HR-positive cohort, an association between lack of BPE suppression and lower pCR rate was detected at T2 (nonsuppressed vs suppressed, 11.8% [six of 51] vs 28.9% [50 of 173]; difference, 17.1% [95% CI: 4.7, 29.5]; P = .02) and T3 (nonsuppressed vs suppressed, 5.3% [two of 38] vs 27.4% [48 of 175]; difference, 22.2% [95% CI: 10.9, 33.5]; P = .003). In the HR-negative cohort, patients with nonsuppressed BPE had lower estimated pCR rate at all points, but the P values for the association were all greater than .05. Conclusions In hormone receptor-positive breast cancer, lack of background parenchymal enhancement suppression may indicate inferior treatment response. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Philpotts in this issue.

Quantitative Measures of Background Parenchymal Enhancement Predict Breast Cancer Risk.

BACKGROUND. Higher categories of background parenchymal enhancement (BPE) increase breast cancer risk. However, current clinical BPE categorization is subjective. OBJECTIVE. Using a semiautomated segmentation algorithm, we calculated quantitative BPE measures and investigated the utility of individual features and feature pairs in significantly predicting subsequent breast cancer risk compared with radiologist-assigned BPE category. METHODS. In this retrospective case-control study, we identified 95 women at high risk of breast cancer but without a personal history of breast cancer who underwent breast MRI. Of these women, 19 subsequently developed breast cancer and were included as cases. Each case was age matched to four control patients (76 control patients total). Sociodemographic characteristics were compared between the cases and matched control patients using the Mann-Whitney U test. From each dynamic contrast-enhanced MRI examination, quantitative fibroglandular tissue and BPE measures were computed by averaging enhancing voxels above enhancement ratio thresholds (0-100%), totaling the enhancing volume above thresholds (BPE volume in cm3), and estimating the percentage of enhancing tissue above thresholds relative to total breast volume (BPE%) on each gadolinium-enhanced phase. For the 91 imaging features generated, we compared predictive performance using conditional logistic regression with 80:20 hold-out cross validation and ROC curve analysis. ROC AUC was the figure of merit. Sensitivity, specificity, PPV, and NPV were also computed. All feature pairs were exhaustively searched to identify those with the highest AUC and Youden index. A DeLong test was used to compare predictive performance (AUCs). RESULTS. Women subsequently diagnosed with breast cancer were more likely to have mild, moderate, or marked BPE (odds ratio, 3.0; 95% CI, 0.9-10.0; p = .07). According to ROC curve analysis, a BPE category threshold greater than minimal resulted in a maximized AUC (0.62) in distinguishing cases from control patients. Compared with BPE category, the first gadolinium-enhanced (phase 1) BPE% at the 30% and 40% enhancement ratio thresholds yielded significantly higher AUC values of 0.85 (p = .0007) and 0.84 (p = .0004), respectively. Feature combinations showed similar AUC values with improved sensitivity. CONCLUSION. Preliminary data indicate that quantitative BPE measures may outperform radiologist-assigned category in breast cancer risk prediction. CLINICAL IMPACT. Future risk prediction models that incorporate quantitative measures warrant additional investigation.

Distribution of Estimated Lifetime Breast Cancer Risk Among Women Undergoing Screening Mammography.

OBJECTIVE. Supplemental screening breast MRI is recommended for women with an estimated lifetime risk of breast cancer of greater than 20-25%. The performance of risk prediction models varies for each individual and across groups of women. The present study investigates the concordance of three breast cancer risk prediction models among women presenting for screening mammography. SUBJECTS AND METHODS. In this prospective study, we calculated the estimated lifetime risk of breast cancer using the modified Gail, Tyrer-Cuzick version 7, and BRCAPRO models for each woman who presented for screening mammography. Per American Cancer Society guidelines, for each woman the risk was categorized as less than 20% or 20% or greater as well as less than 25% or 25% or greater with use of each model. Venn diagrams were constructed to evaluate concordance across models. The McNemar test was used to test differences in risk group allocations between models, with p ≤ .05 considered to denote statistical significance. RESULTS. Of 3503 screening mammography patients who underwent risk stratification, 3219 (91.9%) were eligible for risk estimation using all three models. Using at least one model, 440 (13.7%) women had a lifetime risk of 20% or greater, including 390 women (12.1%) according to the Tyrer-Cuzick version 7 model, 18 (0.6%) according to the BRCAPRO model, and 141 (4.4%) according to the modified Gail model. Six women (0.2%) had a risk of 20% or greater according to all three models. Women were significantly more likely to be classified as having a high lifetime breast cancer risk by the Tyrer-Cuzick version 7 model compared with the modified Gail model, with thresholds of 20% or greater (odds ratio, 6.4; 95% CI, 4.7-8.7) or 25% or greater (odds ratio, 7.4; 95% CI, 4.7-11.9) used for both models. CONCLUSION. To identify women with a high lifetime breast cancer risk, practices should use estimates of lifetime breast cancer risk derived from multiple risk prediction models.

Tissue marker migration after MRI-guided breast biopsy: Migration frequency and associated factors.

The purpose of this study was to determine the frequency and associated risk factors contributing to immediate tissue marker migration in patients undergoing MRI-guided breast biopsy and to evaluate how often tissue marker migration altered clinical management. Between July 2010 and May 2015, we retrospectively reviewed all MRI-guided breast biopsies at our institution for tissue marker migration. Migration was defined as final position of the tissue marker >10 mm from the target site based on the expected location of the MRI finding on postprocedure mammogram. Factors associated with migration were analyzed using Fisher's exact test and Chi-squared test, with P < .05 considered statistically significant. A total of 278 patients underwent 298 MRI-guided biopsies. Migration occurred in 42/298 biopsies (14%). Almost entirely fat fibroglandular tissue was identified as an independent risk factor for tissue marker migration, occurring in 6/16 (38%), compared to 36/262 (14%) for the other fibroglandular tissue categories (P = .03). Biopsy target size was significantly associated with clip migration, occurring in 25/114 (22%) lesions <10 mm in size vs 17/184 (9%) for larger lesions (P = .003). Clinical management was affected by clip migration in 6/42 cases (14%) with one requiring ultrasound-guided biopsy cavity marker placement and five requiring biopsy cavity wire localization. Radiologists must be vigilant in assessing for clip migration as it is not an infrequent complication. Given migration may change clinical management and require altered procedures for localization of the biopsy cavity, the possibility of clip migration should be included in informed consent.

Combined Benefit of Quantitative Three-Compartment Breast Image Analysis and Mammography Radiomics in the Classification of Breast Masses in a Clinical Data Set.

Purpose To investigate the combination of mammography radiomics and quantitative three-compartment breast (3CB) image analysis of dual-energy mammography to limit unnecessary benign breast biopsies. Materials and Methods For this prospective study, dual-energy craniocaudal and mediolateral oblique mammograms were obtained immediately before biopsy in 109 women (mean age, 51 years; range, 31-85 years) with Breast Imaging Reporting and Data System category 4 or 5 breast masses (35 invasive cancers, 74 benign) from 2013 through 2017. The three quantitative compartments of water, lipid, and protein thickness at each pixel were calculated from the attenuation at high and low energy by using a within-image phantom. Masses were automatically segmented and features were extracted from the low-energy mammograms and the quantitative compartment images. Tenfold cross-validations using a linear discriminant classifier with predefined feature signatures helped differentiate between malignant and benign masses by means of (a) water-lipid-protein composition images alone, (b) mammography radiomics alone, and (c) a combined image analysis of both. Positive predictive value of biopsy performed (PPV3) at maximum sensitivity was the primary performance metric, and results were compared with those for conventional diagnostic digital mammography. Results The PPV3 for conventional diagnostic digital mammography in our data set was 32.1% (35 of 109; 95% confidence interval [CI]: 23.9%, 41.3%), with a sensitivity of 100%. In comparison, combined mammography radiomics plus quantitative 3CB image analysis had PPV3 of 49% (34 of 70; 95% CI: 36.5%, 58.9%; P < .001), with a sensitivity of 97% (34 of 35; 95% CI: 90.3%, 100%; P < .001) and 35.8% (39 of 109) fewer total biopsies (P < .001). Conclusion Quantitative three-compartment breast image analysis of breast masses combined with mammography radiomics has the potential to reduce unnecessary breast biopsies. © RSNA, 2018 Online supplemental material is available for this article.

Performance of Screening Breast MRI After Negative Full-Field Digital Mammography Versus After Negative Digital Breast Tomosynthesis in Women at Higher Than Average Risk for Breast Cancer.

OBJECTIVE: The objective of our study was to compare the supplemental cancer yield and performance of breast MRI in women at higher-than-average risk for breast cancer after negative 2D full-field digital mammography (FFDM) or negative digital breast tomosynthesis (DBT). MATERIALS AND METHODS: Retrospective review identified 4418 screening breast MRI examinations: 2291 were performed from January 2010 through January 2012 of patients with a negative FFDM examination in the 12 months before MRI (FFDM group), and 2127 were performed from January 2013 through January 2015 of patients with a negative DBT examination in the 12 months before MRI (DBT group). Screening indications included genetic predisposition, personal history of breast cancer or high-risk lesion, prior chest irradiation, family history, or other risk factors conferring a lifetime risk of greater than 20%. Supplemental cancer detection rate (CDR), abnormal interpretation rate (AIR), and positive predictive values (PPVs) were estimated with 95% exact CIs. Logistic regression analysis, adjusting for differences in patient demographics, was used to compare metrics. RESULTS: There was no significant difference in the CDR of MRI in the FFDM group versus the DBT group (11 vs 16 cancers per 1000 examinations, respectively; odds ratio, 1.4; 95% CI, 0.4-1.2; p = 0.23). The AIR, PPV1, PPV2, and PPV3 were 7.4%, 15%, 23%, and 28% for the FFDM group and 7.3%, 22%, 33%, and 35% for the DBT group, with no statistical differences. Of the cancers detected in both groups, the majority were invasive, less than 1 cm, and node-negative. CONCLUSION: In women at higher-than-average risk of breast cancer screened with DBT, the supplemental CDR of MRI is similar to that of MRI after FFDM screening, with most cancers being invasive, subcentimeter, and node-negative.

Breast Cancer Screening and Diagnosis, Version 3.2018, NCCN Clinical Practice Guidelines in Oncology.

The NCCN Guidelines for Breast Cancer Screening and Diagnosis have been developed to facilitate clinical decision making. This manuscript discusses the diagnostic evaluation of individuals with suspected breast cancer due to either abnormal imaging and/or physical findings. For breast cancer screening recommendations, please see the full guidelines on NCCN.org.

Utility of Breast MRI for Further Evaluation of Equivocal Findings on Digital Breast Tomosynthesis.

OBJECTIVE: The purpose of this study is to evaluate the utility of MRI as a problem-solving tool for equivocal findings on diagnostic digital mammography (DM) and digital breast tomosynthesis (DBT). MATERIALS AND METHODS: Breast MRI examinations performed from March 2011 to November 2014 were retrospectively reviewed to identify those examinations that were performed to further assess equivocal findings on combined DM and DBT (DM/DBT) examinations. All patients underwent diagnostic ultrasound in conjunction with their DM/DBT examination. Imaging reports were retrospectively reviewed for BI-RADS findings and assessments of diagnostic DM/DBT and diagnostic MRI examinations. A review of the electronic medical records provided information on demographic data, cancer diagnoses, and pathologic findings. Differences in the positive predictive values and negative predictive values of DM/DBT and MRI were compared using a generalized estimating equation for correlated binary data. RESULTS: Of 5330 MRI examinations performed during the study, 67 (1%) were performed for evaluation of an equivocal finding, including 27 asymmetries (40%), 16 focal asymmetries (24%), five masses (7%), and 19 architectural distortion (28%). MRI correlates were identified in 22 of 67 examinations (33%). Biopsies yielded a cancer diagnosis for five of 67 patients (7%). For MRI, the positive predictive value and negative predictive value were 19% and 98%, respectively, whereas for DM/DBT they were 6% and 90%, respectively (p = 0.009 and p = 0.059, respectively). The frequency of recommendations for breast MRI to evaluate equivocal findings decreased exponentially in the 3 years after DBT implementation. CONCLUSION: As clinical implementation of DBT becomes increasingly widespread, breast radiologists need an algorithm for addressing the small number of inconclusive findings that remain equivocal despite thorough DM/DBT and ultrasound examinations. Breast MRI is a useful adjunctive tool for these selected cases.

Screening for Breast Cancer in Women Age 75 Years and Older.

OBJECTIVE: Older women undergoing regular mammography experience significant reductions in breast cancer mortality, except in women with severe comorbidities or limited life expectancy. Optimizing screening strategies requires informed discussions of benefits and risks given each woman's health status. CONCLUSION: This article will review the benefits and risks of screening mammography in women older than 75 years within the context of life expectancy and comorbidities and summarize the current recommendations from professional organizations for screening mammography in older women.

Screening Mammography: Patient Perceptions and Preferences Regarding Communication of Estimated Breast Cancer Risk.

OBJECTIVE: Many models exist to estimate a woman's risk of development of breast cancer. At screening mammography, many imaging centers collect data required for these models to identify women who may benefit from supplemental screening and referral for cancer risk assessment. The purpose of this study was to discern perceptions and preferences of screening mammography patients regarding communication of estimated breast cancer risk. SUBJECTS AND METHODS: An anonymous survey was distributed to screening and surveillance mammography patients between April and June 2015. Survey questions were designed to assess patient preferences regarding the receipt and complexity of risk estimate communication, including hypothetical scenarios with and without > 20% estimated risk of breast cancer. The McNemar test and the Wilcoxon signed rank test were used with p ≤ 0.05 considered statistically significant. RESULTS: The survey was distributed to 1061 screening and surveillance mammography patients, and 503 patients responded (response rate, 47%). Although 86% (431/503) of patients expressed interest in learning their estimated risk, only 8% (38/503) had undergone formal risk assessment. The preferred method (241 respondents [26%]) of communication of risk < 20% was a mailed letter accompanying annual mammogram results. For risk > 20%, patients preferred oral communication and were 10-fold as likely to choose only oral communication (p < 0.000001). For risk < 20% and > 20%, patients preferred to learn their estimated risk in great detail (69% and 85%), although women were significantly more likely to choose greater detail for risk > 20% (p < 0.00001). CONCLUSION: Screening mammography patients expressed interest in learning their estimated risk of breast cancer regardless of their level of hypothetical risk.

Preoperative Tomosynthesis-guided Needle Localization of Mammographically and Sonographically Occult Breast Lesions.

PURPOSE: To assess the feasibility and accuracy of digital breast tomosynthesis (DBT)-guided needle localization for DBT-detected suspicious abnormalities not visualized with other modalities and to analyze the imaging and pathologic characteristics of abnormalities detected only with DBT to determine the positive predictive value for malignancy. MATERIALS AND METHODS: This HIPAA-compliant study was approved by the institutional review board, and the requirement to obtain informed consent was waived. A retrospective query of the imaging database identified 34 consecutive women (average age, 55 years; age range, 28-84 years) with 36 lesions who underwent DBT-guided needle localization between April 2011 and January 2013 with use of commercially available equipment. Imaging findings and medical records were reviewed. Findings that were attributable to previous surgical changes were classified as benign or probably benign and excluded from analysis because the lesions did not proceed to localization. RESULTS: Architectural distortion was the imaging finding identified in all 36 abnormalities (100%). Findings from pathologic examination after the first attempt at localization were concordant with those from imaging in 35 of the 36 lesions (97%), which is suggestive of appropriate sampling. Histologic findings were malignant in 17 of the 36 lesions (47%; 95% confidence interval: 30.4%, 64.5%). Thirteen of the 17 lesions (76%; 95% confidence interval: 50.1%, 93.1%) were invasive malignancies. Twenty-two of the 36 abnormalities (61%) were either malignant or high-risk lesions (atypical ductal hyperplasia, lobular carcinoma in situ, atypical lobular hyperplasia). CONCLUSION: DBT-guided needle localization is an accurate and feasible method with which to biopsy DBT-detected suspicious architectural distortions not visualized at mammography or sonography. The high risk of malignancy in abnormalities detected only with DBT (47%) confirms that routine biopsy is required for histologic analysis.

Extramammary Findings on Breast MR Examinations: Frequency, Clinical Relevance, and Patient Outcomes.

PURPOSE: To evaluate the frequency of extramammary findings on breast magnetic resonance (MR) images, recommendations for further imaging evaluation of each finding, and the subsequent effect on patient outcomes and health care expenditures. MATERIALS AND METHODS: Institutional review board approval was acquired for this HIPAA-compliant study. Informed consent was waived. Review of the institutional database identified 2324 breast MR examinations performed in women from January 1, 2010, to December 31, 2010. Breast MR imaging reports were reviewed for extramammary findings. Extramammary findings were categorized by using the computed tomography (CT) colonography reporting and data system (C-RADS). The electronic medical record was reviewed for each patient with a C-RADS category E3 and E4 finding to assess clinical relevance and pathologic outcome. If an E3 or E4 finding was previously described and evaluated, the finding was downgraded and assigned a final C-RADS E2 category. The cost of additional imaging was estimated by using the Medicare physician fee schedule. Statistical significance was assessed by using χ(2) statistics. A P value less than .05 indicated statistical significance, and 95% exact confidence intervals (CIs) were constructed. RESULTS: Extramammary findings were identified in 391 of 2324 breast MR examinations (16.8%), which included 105 patients (4.5%) with E3 or E4 findings. Of the 2324 patients, 86 patients (3.7% [95% CI: 3.0%, 4.5%]) were recommended to undergo further imaging. After undergoing evaluation for additional imaging, a clinically important finding was found in nine patients (0.4% [95% CI: 0.2%, 0.7%]). Most frequently, hepatic lesions were the indication for additional imaging. Abdominal MR examinations accounted for 55% of costs related to additional imaging. Averaged across the entire cohort, further imaging evaluation and follow-up of incidental findings contributed an additional $16 to each breast MR imaging performed. CONCLUSION: Additional imaging evaluation for E3 and E4 extramammary findings at breast MR imaging can identify clinically important disease without substantially increasing cost. .

Prospective analysis of an interprofessional team training program using high-fidelity simulation of contrast reactions.

OBJECTIVE: Successful management of a contrast reaction requires prompt recognition and treatment and effective team dynamics among radiologists, technologists, and nurses. A radiology department implemented a simulation program in which teams of nurses, technologists, and physicians managed simulated contrast reactions. The purpose of this study was to evaluate whether simulation improved the participants' abilities to manage a contrast reaction and work in a team during an emergency. SUBJECTS AND METHODS: Physicians, nurses, and technologists worked in inter-professional teams to manage two high-fidelity simulated adverse contrast reactions. Participants completed surveys before and after the simulation that included knowledge-based questions about the appropriate management of contrast reactions. Surveys also included questions for assessing participants' perceptions of their ability to manage adverse contrast reactions, measured with a 6-point Likert scale. Before and after comparisons were made with the McNemar test with a Bonferroni correction requiring p ≤ 0.003 for significance. For the other analyses, p ≤ 0.05 was considered significant. RESULTS: After completion of the simulation exercises, participants had significant improvement in knowledge (p < 0.001). After the simulation, participants reported significant improvement in their ability to manage an anaphylactoid reaction and their ability to work in a team (p < 0.00001). Participants requested repeat simulation exercises every 6-12 months. CONCLUSION: Simulation exercises improved the self-reported ability of radiology personnel to manage contrast reactions and work in a team during an emergency. Simulation should be incorporated into future educational initiatives to improve patient safety in radiology practices.

Patient outcomes in canceled MRI-guided breast biopsies.

OBJECTIVE: The reported frequency of aborted MRI-guided breast biopsies ranges from 8% to 17%, usually secondary to nonvisualization at attempted biopsy. Our study examines the frequency of MRI-guided breast biopsies aborted because of lesion nonvisualization and the subsequent risk of malignancy. MATERIALS AND METHODS: We identified 350 patients and 445 lesions scheduled for MRI-guided biopsy between January 1, 2007, and December 31, 2009. Medical records and imaging studies were reviewed to ascertain patient demographics, lesion and imaging characteristics, and subsequent pathology results. Chi-square statistics were calculated for patient level analyses. RESULTS: MRI-guided biopsies were aborted in 13% (56/445) of lesions and 15% (53/350; 95% CI, 11.6-19.3%) of patients because of nonvisualization of the biopsy target at the time of attempted biopsy. Of these 53 patients, 50 patients had follow-up data available. Malignancy was subsequently diagnosed in five of those 50 patients (10%; 95% CI, 3.3-21.8%), three with invasive ductal carcinomas and two with ductal carcinoma in situ. The mean time to malignant diagnosis from the date of aborted biopsy was 2.6 months (range, 1.1-6.9 months). CONCLUSION: Informed consent for MRI-guided breast biopsies should include discussion of biopsy cancellation because of nonvisualization of the target lesion. The low yet significant risk of malignancy in patients subsequent to an aborted MRI-guided breast biopsy warrants short-term follow-up MRI after a canceled biopsy.

Tumor Doubling Time and Screening Interval.

The goal of screening is to detect breast cancers when still curable to decrease breast cancer-specific mortality. Breast cancer screening in the United States is routinely performed with digital mammography and digital breast tomosynthesis. This article reviews breast cancer doubling time by tumor subtype and examines the impact of doubling time on breast cancer screening intervals. By the article's end, the reader will be better equipped to have informed discussions with patients and medical professionals regarding the benefits and disadvantages of the currently recommended screening mammography intervals.

Presurgical Upgrade Prediction of DCIS to Invasive Ductal Carcinoma Using Time-dependent Deep Learning Models with DCE MRI.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To determine whether time-dependent deep learning models can outperform single timepoint models in predicting preoperative upgrade of ductal carcinoma in situ (DCIS) to invasive malignancy on dynamic contrastenhanced (DCE) breast MRI without lesion segmentation prerequisite. Materials and Methods In this exploratory study, 154 cases of biopsy-proven DCIS (25 upgraded at surgery and 129 not upgraded) were selected consecutively from a retrospective cohort of preoperative DCE MRI in women with an average age of 58.6 years at time of diagnosis from 2012 to 2022. Binary classification was implemented with convolutional neural network-long short-term memory (CNN-LSTM) architectures benchmarked against traditional CNNs without manual segmentation of the lesions. Combinatorial performance analysis of ResNet50 versus VGG16-based models was performed with each contrast phase. Binary classification area under the receiver operating characteristic curve (AUC) was reported. Results VGG16-based models consistently provided better hold-out test AUCs than ResNet50 in CNN and CNNLSTM studies (multiphase test AUC: 0.67 versus 0.59, respectively, for CNN models; P = .04 and 0.73 versus 0.62 for CNN-LSTM models; P = .008). The time-dependent model (CNN-LSTM) provided a better multiphase test AUC over single-timepoint (CNN) models (0.73 versus 0.67, P = .04). Conclusion Compared with single-timepoint architectures, sequential deep learning algorithms using preoperative DCE MRI improved prediction of DCIS lesions upgraded to invasive malignancy without the need for lesion segmentation. ©RSNA, 2024.