Search

PurposeThe aim of this study was to develop a prioritization strategy for scheduling immediate screening mammographic interpretation and possible diagnostic evaluation.MethodsA population-based cohort with screening mammograms performed from 2012 to 2020 at 126 radiology facilities from 7Breast Cancer Surveillance Consortium registries was identified. Classification trees identified combinations of clinical history (age, BI-RADS® density, time since prior mammogram, history of false-positive recall or biopsy result), screening modality (digital mammography, digital breast tomosynthesis), and facility characteristics (profit status, location, screening volume, practice type, academic affiliation) that grouped screening mammograms by recall rate, with ≥12/100 considered high and ≥16/100 very high. An efficiency ratio was estimated as the percentage of recalls divided by the percentage of mammograms.ResultsThe study cohort included 2,674,051 screening mammograms in 925,777 women, with 235,569 recalls. The most important predictor of recall was time since prior mammogram, followed by age, history of false-positive recall, breast density, history of benign biopsy, and screening modality. Recall rates were very high for baseline mammograms (21.3/100; 95% confidence interval, 19.7-23.0) and high for women with ≥5 years since prior mammogram (15.1/100; 95% confidence interval, 14.3-16.1). The 9.2% of mammograms in subgroups with very high and high recall rates accounted for 19.2% of recalls, an efficiency ratio of 2.1 compared with a random approach. Adding women

BACKGROUND: Artificial intelligence (AI) may improve cancer detection and risk prediction during mammography screening, but radiologists' preferences regarding its characteristics and implementation are unknown. PURPOSE: To quantify how different attributes of AI-based cancer detection and risk prediction tools affect radiologists' intentions to use AI during screening mammography interpretation. MATERIALS AND METHODS: Through qualitative interviews with radiologists, we identified five primary attributes for AI-based breast cancer detection and four for breast cancer risk prediction. We developed a discrete choice experiment based on these attributes and invited 150 US-based radiologists to participate. Each respondent made eight choices for each tool between three alternatives: two hypothetical AI-based tools versus screening without AI. We analyzed samplewide preferences using random parameters logit models and identified subgroups with latent class models. RESULTS: Respondents (n = 66; 44% response rate) were from six diverse practice settings across eight states. Radiologists were more interested in AI for cancer detection when sensitivity and specificity were balanced (94% sensitivity with

ImportanceWith a shortfall in fellowship-trained breast radiologists, mammography screening programs are looking toward artificial intelligence (AI) to increase efficiency and diagnostic accuracy. External validation studies provide an initial assessment of how promising AI algorithms perform in different practice settings.ObjectiveTo externally validate an ensemble deep-learning model using data from a high-volume, distributed screening program of an academic health system with a diverse patient population.Design, Setting, and ParticipantsIn this diagnostic study, an ensemble learning method, which reweights outputs of the 11 highest-performing individual AI models from the Digital Mammography Dialogue on Reverse Engineering Assessment and Methods (DREAM) Mammography Challenge, was used to predict the cancer status of an individual using a standard set of screening mammography images. This study was conducted using retrospective patient data collected between 2010 and 2020 from women aged 40 years and older who underwent a routine breast screening examination and participated in the Athena Breast Health Network at the University of California, Los Angeles (UCLA).Main Outcomes and MeasuresPerformance of the challenge ensemble method (CEM) and the CEM combined with radiologist assessment (CEM+R) were compared with diagnosed ductal carcinoma in situ and invasive cancers within a year of the screening examination using performance metrics, such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC).ResultsEvaluated on 37 317 examinations from 26 817 women (mean [SD] age, 58.4 [11.5] years), individual model AUROC estimates ranged from 0.77 (95% CI, 0.75-0.79) to 0.83 (95% CI, 0.81-0.85). The CEM model achieved an AUROC of 0.85 (95% CI, 0.84-0.87) in the UCLA cohort, lower than the performance achieved in the Kaiser Permanente Washington (AUROC, 0.90) and Karolinska Institute (AUROC, 0.92) cohorts. The CEM+R model achieved a sensitivity (0.813 [95% CI, 0.781-0.843] vs 0.826 [95% CI, 0.795-0.856]; P = .20) and specificity (0.925 [95% CI, 0.916-0.934] vs 0.930 [95% CI, 0.929-0.932]; P = .18) similar to the radiologist performance. The CEM+R model had significantly lower sensitivity (0.596 [95% CI, 0.466-0.717] vs 0.850 [95% CI, 0.766-0.923]; P P P = .004).Conclusions and RelevanceThis study found that the high performance of an ensemble deep-learning model for automated screening mammography interpretation did not generalize to a more diverse screening cohort, suggesting that the model experienced underspecification. This study suggests the need for model transparency and fine-tuning of AI models for specific target populations prior to their clinical adoption.

Background Artificial intelligence (AI) is increasingly being proposed for use in medicine, including breast cancer screening (BCS). Little is known, however, about referring primary care providers’ (PCPs’) preferences for this technology. Methods We identified the most important attributes of AI BCS for ordering PCPs using qualitative interviews: sensitivity, specificity, radiologist involvement, understandability of AI decision-making, supporting evidence, and diversity of training data. We invited US-based PCPs to participate in an internet-based experiment designed to force participants to trade off among the attributes of hypothetical AI BCS products. Responses were analyzed with random parameters logit and latent class models to assess how different attributes affect the choice to recommend AI-enhanced screening. Results Ninety-one PCPs participated. Sensitivity was most important, and most PCPs viewed radiologist participation in mammography interpretation as important. Other important attributes were specificity, understandability of AI decision-making, and diversity of data. We identified 3 classes of respondents: “Sensitivity First” (41%) found sensitivity to be more than twice as important as other attributes; “Against AI Autonomy” (24%) wanted radiologists to confirm every image; “Uncertain Trade-Offs” (35%) viewed most attributes as having similar importance. A majority (76%) accepted the use of AI in a “triage” role that would allow it to filter out likely negatives without radiologist confirmation. Conclusions and Relevance Sensitivity was the most important attribute overall, but other key attributes should be addressed to produce clinically acceptable products. We also found that most PCPs accept the use of AI to make determinations about likely negative mammograms without radiologist confirmation.

Background: Social determinants of health (SDOH) contribute to health care disparities, with social and economic barriers often leading to difficulties in obtaining necessary care. We evaluated barriers to receiving health care, focusing on caretaker responsibilities, health insurance and cost, and transportation. Materials and Methods: We included women ages ≥40 years receiving screening mammography across three Breast Cancer Surveillance Consortium registries from 2012 to 2017. Women self-reported social and financial barriers to receiving health care in the 12 months before their screening mammogram. We evaluated woman- and census-based community-level factors associated with reporting a barrier using multivariate logistic regression. We assessed interaction with urban versus nonurban residence using Wald tests. Results: Among 393,430 women, 3.6% reported a barrier with a higher proportion in urban versus nonurban settings (3.9% [n = 11,977] vs. 2.2% [n = 1,655], respectively; p

Background Established mammography screening performance metrics use the initial screening mammography assessment because they were developed for radiologist performance auditing, yet these metrics are frequently used to inform health policy and screening decision making. The authors have developed new performance metrics based on the final assessment that consider the entire screening episode, including diagnostic workup. Methods The authors used data from 2,512,577 screening episodes during 2005-2017 at 146 facilities in the United States participating in the Breast Cancer Surveillance Consortium. Screening performance metrics based on the final assessment of the screening episode were compared with conventional metrics defined with the initial assessment. Results were also stratified by breast density and breast cancer risk. Results The cancer detection rates were similar for the final assessment (4.1 per 1000; 95% confidence interval [CI], 3.8-4.3 per 1000) and the initial assessment (4.1 per 1000; 95% CI, 3.9-4.3 per 1000). The interval cancer rate was 12% higher when it was based on the final assessment (0.77 per 1000; 95% CI, 0.71-0.83 per 1000) versus the initial assessment (0.69 per 1000; 95% CI, 0.64-0.74 per 1000), and this resulted in a modest difference in sensitivity (84.1% [95% CI, 83.0%-85.1%] vs 85.7% [95% CI, 84.8%-86.6%], respectively). Absolute differences in the interval cancer rate between final and initial assessments increased with breast density and breast cancer risk (eg, a difference of 0.29 per 1000 for women with extremely dense breasts and a 5-year risk >2.49%). Conclusions Established screening performance metrics underestimate the interval cancer rate of a mammography screening episode, particularly for women with dense breasts or an elevated breast cancer risk. Women, clinicians, policymakers, and researchers should use final-assessment performance metrics to support informed screening decisions.

Objectives To analyze rates, odds ratios (OR), and characteristics of screen-detected and interval cancers after concordant and discordant initial interpretations and consensus in a population-based screening program. Methods Data were extracted from the Cancer Registry of Norway for 487,118 women who participated in BreastScreen Norway, 2006–2017, with 2 years of follow-up. All mammograms were independently interpreted by two radiologists, using a score from 1 (negative) to 5 (high suspicion of cancer). A score of 2+ by one of the two radiologists was defined as discordant and 2+ by both radiologists as concordant positive. Consensus was performed on all discordant and concordant positive, with decisions of recall for further assessment or dismiss. OR was estimated with logistic regression with 95% confidence interval (CI), and histopathological tumor characteristics were analyzed for screen-detected and interval cancer. Results Among screen-detected cancers, 23.0% (697/3024) had discordant scores, while 12.8% (117/911) of the interval cancers were dismissed at index screening. Adjusted OR was 2.4 (95% CI: 1.9–2.9) for interval cancer and 2.8 (95% CI: 2.5–3.2) for subsequent screen-detected cancer for women dismissed at consensus compared to women with concordant negative scores. We found 3.4% (4/117) of the interval cancers diagnosed after being dismissed to be DCIS, compared to 20.3% (12/59) of those with false-positive result after index screening. Conclusion Twenty-three percent of the screen-detected cancers was scored negative by one of the two radiologists. A higher odds of interval and subsequent screen-detected cancer was observed among women dismissed at consensus compared to concordant negative scores. Our findings indicate a benefit of personalized follow-up. Key Points • In this study of 487,118 women participating in a screening program using independent double reading with consensus, 23% screen-detected cancers were detected by only one of the two radiologists. • The adjusted odds ratio for interval cancer was 2.4 (95% confidence interval: 1.9, 2.9) for cases dismissed at consensus using concordant negative interpretations as the reference. • Interval cancers diagnosed after being dismissed at consensus or after concordant negative scores had clinically less favorable prognostic tumor characteristics compared to those diagnosed after false-positive results.

Breast cancer screening with digital breast tomosynthesis may decrease false-positive results compared with digital mammography.To estimate the probability of receiving at least 1 false-positive result after 10 years of screening with digital breast tomosynthesis vs digital mammography in the US.An observational comparative effectiveness study with data collected prospectively for screening examinations was performed between January 1, 2005, and December 31, 2018, at 126 radiology facilities in the Breast Cancer Surveillance Consortium. Analysis included 903 495 individuals aged 40 to 79 years. Data analysis was conducted from February 9 to September 7, 2021.Screening modality, screening interval, age, and Breast Imaging Reporting and Data System breast density.Cumulative risk of at least 1 false-positive recall for further imaging, short-interval follow-up recommendation, and biopsy recommendation after 10 years of annual or biennial screening with digital breast tomosynthesis vs digital mammography, accounting for competing risks of breast cancer diagnosis and death.In this study of 903 495 women, 2 969 055 nonbaseline screening examinations were performed with interpretation by 699 radiologists. Mean (SD) age of the women at the time of the screening examinations was 57.6 (9.9) years, and 58% of the examinations were in individuals younger than 60 years and 46% were performed in women with dense breasts. A total of 15% of examinations used tomosynthesis. For annual screening, the 10-year cumulative probability of at least 1 false-positive result was significantly lower with tomosynthesis vs digital mammography for all outcomes: 49.6% vs 56.3% (difference, -6.7; 95% CI, -7.4 to -6.1) for recall, 16.6% vs 17.8% (difference, -1.1; 95% CI, -1.7 to -0.6) for short-interval follow-up recommendation, and 11.2% vs 11.7% (difference, -0.5; 95% CI, -1.0 to -0.1) for biopsy recommendation. For biennial screening, the cumulative probability of a false-positive recall was significantly lower for tomosynthesis vs digital mammography (35.7% vs 38.1%; difference, -2.4; 95% CI, -3.4 to -1.5), but cumulative probabilities did not differ significantly by modality for short-interval follow-up recommendation (10.3% vs 10.5%; difference, -0.1; 95% CI, -0.7 to 0.5) or biopsy recommendation (6.6% vs 6.7%; difference, -0.1; 95% CI, -0.5 to 0.4). Decreases in cumulative probabilities of false-positive results with tomosynthesis vs digital mammography were largest for annual screening in women with nondense breasts (differences for recall, -6.5 to -12.8; short-interval follow-up, 0.1 to -5.2; and biopsy recommendation, -0.5 to -3.1). Regardless of modality, cumulative probabilities of false-positive results were substantially lower for biennial vs annual screening (overall recall, 35.7 to 38.1 vs 49.6 to 56.3; short-interval follow-up, 10.3 to 10.5 vs 16.6 to 17.8; and biopsy recommendation, 6.6 to 6.7 vs 11.2 to 11.7); older vs younger age groups (eg, among annual screening in women ages 70-79 vs 40-49, recall, 39.8 to 47.0 vs 60.8 to 68.0; short-interval follow-up, 13.3 to 14.2 vs 20.7 to 20.9; and biopsy recommendation, 9.1 to 9.3 vs 13.2 to 13.4); and women with entirely fatty vs extremely dense breasts (eg, among annual screening in women aged 50-59 years, recall, 29.1 to 36.3 vs 58.8 to 60.4; short-interval follow-up, 8.9 to 11.6 vs 19.5 to 19.8; and biopsy recommendation, 4.9 to 8.0 vs 15.1 to 15.3).In this comparative effectiveness study, 10-year cumulative probabilities of false-positive results were lower on digital breast tomosynthesis vs digital mammography. Biennial screening interval, older age, and nondense breasts were associated with larger reductions in false-positive probabilities than screening modality.

Purpose: The aim of this study was to describe the current state of science regarding independent external validation of artificial intelligence (AI) technologies for screening mammography. Methods: A systematic review was performed across five databases (Embase, PubMed, IEEE Explore, Engineer Village, and arXiv) through December 10, 2020. Studies that used screening examinations from real-world settings to externally validate AI algorithms for mammographic cancer detection were included. The main outcome was diagnostic accuracy, defined by area under the receiver operating characteristic curve (AUC). Performance was also compared between radiologists and either stand-alone AI or combined radiologist and AI interpretation. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 tool. Results: After data extraction, 13 studies met the inclusion criteria (148,361 total patients). Most studies (77% [n = 10]) evaluated commercially available AI algorithms. Studies included retrospective reader studies (46% [n = 6]), retrospective simulation studies (38% [n = 5]), or both (15% [n = 2]). Across 5 studies comparing stand-alone AI with radiologists, 60% (n = 3) demonstrated improved accuracy with AI (AUC improvement range, 0.02-0.13). All 5 studies comparing combined radiologist and AI interpretation with radiologists alone demonstrated improved accuracy with AI (AUC improvement range, 0.028-0.115). Most studies had risk for bias or applicability concerns for patient selection (69% [n = 9]) and the reference standard (69% [n = 9]). Only two studies obtained ground-truth cancer outcomes through regional cancer registry linkage. Conclusions: To date, external validation efforts for AI screening mammographic technologies suggest small potential diagnostic accuracy improvements but have been retrospective in nature and suffer from risk for bias and applicability concerns.

The performance of the artificial intelligence system was promising for breast cancer detection in a large population-based mammography screening program. Background Artificial intelligence (AI) has shown promising results for cancer detection with mammographic screening. However, evidence related to the use of AI in real screening settings remain sparse. Purpose To compare the performance of a commercially available AI system with routine, independent double reading with consensus as performed in a population-based screening program. Furthermore, the histopathologic characteristics of tumors with different AI scores were explored. Materials and Methods In this retrospective study, 122 969 screening examinations from 47 877 women performed at four screening units in BreastScreen Norway from October 2009 to December 2018 were included. The data set included 752 screen-detected cancers (6.1 per 1000 examinations) and 205 interval cancers (1.7 per 1000 examinations). Each examination had an AI score between 1 and 10, where 1 indicated low risk of breast cancer and 10 indicated high risk. Threshold 1, threshold 2, and threshold 3 were used to assess the performance of the AI system as a binary decision tool (selected vs not selected). Threshold 1 was set at an AI score of 10, threshold 2 was set to yield a selection rate similar to the consensus rate (8.8%), and threshold 3 was set to yield a selection rate similar to an average individual radiologist (5.8%). Descriptive statistics were used to summarize screening outcomes. Results A total of 653 of 752 screen-detected cancers (86.8%) and 92 of 205 interval cancers (44.9%) were given a score of 10 by the AI system (threshold 1). Using threshold 3, 80.1% of the screen-detected cancers (602 of 752) and 30.7% of the interval cancers (63 of 205) were selected. Screen-detected cancer with AI scores not selected using the thresholds had favorable histopathologic characteristics compared to those selected; opposite results were observed for interval cancer. Conclusion The proportion of screen-detected cancers not selected by the artificial intelligence (AI) system at the three evaluated thresholds was less than 20%. The overall performance of the AI system was promising according to cancer detection.

IntroductionArtificial intelligence (AI) algorithms for interpreting mammograms have the potential to improve the effectiveness of population breast cancer screening programmes if they can detect cancers, including interval cancers, without contributing substantially to overdiagnosis. Studies suggesting that AI has comparable or greater accuracy than radiologists commonly employ ‘enriched’ datasets in which cancer prevalence is higher than in population screening. Routine screening outcome metrics (cancer detection and recall rates) cannot be estimated from these datasets, and accuracy estimates may be subject to spectrum bias which limits generalisabilty to real-world screening. We aim to address these limitations by comparing the accuracy of AI and radiologists in a cohort of consecutive of women attending a real-world population breast cancer screening programme.Methods and analysisA retrospective, consecutive cohort of digital mammography screens from 109 000 distinct women was assembled from BreastScreen WA (BSWA), Western Australia’s biennial population screening programme, from November 2016 to December 2017. The cohort includes 761 screen-detected and 235 interval cancers. Descriptive characteristics and results of radiologist double-reading will be extracted from BSWA outcomes data collection. Mammograms will be reinterpreted by a commercial AI algorithm (DeepHealth). AI accuracy will be compared with that of radiologist single-reading based on the difference in the area under the receiver operating characteristic curve. Cancer detection and recall rates for combined AI–radiologist reading will be estimated by pairing the first radiologist read per screen with the AI algorithm, and compared with estimates for radiologist double-reading.Ethics and disseminationThis study has ethical approval from the Women and Newborn Health Service Ethics Committee (EC00350) and the Curtin University Human Research Ethics Committee (HRE2020-0316). Findings will be published in peer-reviewed journals and presented at national and international conferences. Results will also be disseminated to stakeholders in Australian breast cancer screening programmes and policy makers in population screening.

Background: We evaluated differences in diagnostic mammography performance based on women's race/ethnicity. Methods: This cohort study included 267,868 diagnostic mammograms performed to evaluate screening mammogram findings at 98 facilities in the Breast Cancer Surveillance Consortium between 2005 and 2017. Mammogram assessments were recorded prospectively and breast cancers occurring within one year were ascertained. Performance statistics were calculated with 95% confidence intervals (CI) for each racial/ethnic group. Multivariable regression was used to control for personal characteristics and imaging facility. Results: Among non-Hispanic White (70%), non-Hispanic Black (13%), Asian/Pacific Islander (10%), and Hispanic (7%) women, the invasive cancer detection rate (iCDR, per 1,000 mammograms) and positive predictive value (PPV2) were highest among non-Hispanic White women (iCDR, 35.8; 95% CI, 35.0–36.7; PPV2, 27.8; 95% CI, 27.3–28.3) and lowest among Hispanic women (iCDR, 22.3; 95% CI, 20.2–24.6; PPV2, 19.4; 95% CI, 18.0–20.9). Short interval follow-up recommendations were most common among non-Hispanic Black women [(31.0%; 95% CI, 30.6%–31.5%) vs. other groups, range, 16.6%–23.6%]. False-positive biopsy recommendations were most common among Asian/Pacific Islander women [per 1,000 mammograms: 169.2; 95% CI, 164.8–173.7) vs. other groups, range, 126.5–136.1]. Some differences were explained by adjusting for receipt of diagnostic ultrasound or MRI for iCDR and imaging facility for short-interval follow-up. Other differences changed little after adjustment. Conclusions: Diagnostic mammography performance varied across racial/ethnic groups. Addressing characteristics related to imaging facility and access, rather than personal characteristics, may help reduce some of these disparities. Impact: Diagnostic mammography performance studies should include racially and ethnically diverse populations to provide an accurate view of the population-level effects.

To compare academic and demographic metrics among recipients of three major early career radiology, interventional radiology, and radiation oncology grants to National Institutes of Health (NIH) K awardees at the time the grants were awarded and then over the course of their careers.Radiologists who received the RSNA Research Scholar Grant, General Electric Radiology Research Academic Fellowship (GERRAF), American Roentgen Ray Society (ARRS) Scholar Award, or NIH Career Development (K) Award before January 1, 2015, were included. Research metrics at the time of grant award (eg, publications) and subsequent scholarly productivity (eg, academic rank, h-index, NIH funding) were recorded until April 2020. Wilcoxon ranked-sum, χThere were 279 recipients: 48 K Award, 115 RSNA Research Scholar Grant, 36 ARRS, and 80 GERRAF. At the time of grant awarding, GERRAF recipients were less likely to have an MD-PhD degree (odds ratio [OR]: 0.36; P = .002) and were more likely to be women (OR: 1.55; P = .042) than K Award recipients. Similarly, recipients of the ARRS (OR: 2.87; P = .010) and GERRAF (OR: 3.19; P = .002) were more likely to have a master's degree. Academic rank, leadership positions, and R01 funding were significant predictors of h-index and total publications over time. Academic rank and the GERRAF were significant predictors of subsequent NIH funding duration but there were no significant predictors of NIH funding amount.Early career radiology awards, specifically the GERRAF, provide support for female and non-PhD investigators and result in comparable academic performance metrics to NIH K Award recipients.

Key Points Question What can be learned from a crowdsourced challenge for the prediction of COVID-19 diagnosis and hospitalization? Findings This diagnostic and prognostic study used a model-to-data approach to implement a continuous benchmarking challenge that has enabled 482 participants to join in the effort to use regularly updated COVID-19 patient data to build machine learning models for COVID-19 diagnosis and hospitalization prediction. Machine learning models showed high accuracy in COVID-19 outcome prediction, but analysis of subgroups and prospective data revealed limitations and bias in the models. Meaning This study suggests that crowdsourced clinical algorithms can predict COVID-19 diagnosis and hospitalization, but evaluation of the submitted models using reserved data sets is necessary to avoid self-assessment traps., Importance Machine learning could be used to predict the likelihood of diagnosis and severity of illness. Lack of COVID-19 patient data has hindered the data science community in developing models to aid in the response to the pandemic. Objectives To describe the rapid development and evaluation of clinical algorithms to predict COVID-19 diagnosis and hospitalization using patient data by citizen scientists, provide an unbiased assessment of model performance, and benchmark model performance on subgroups. Design, Setting, and Participants This diagnostic and prognostic study operated a continuous, crowdsourced challenge using a model-to-data approach to securely enable the use of regularly updated COVID-19 patient data from the University of Washington by participants from May 6 to December 23, 2020. A postchallenge analysis was conducted from December 24, 2020, to April 7, 2021, to assess the generalizability of models on the cumulative data set as well as subgroups stratified by age, sex, race, and time of COVID-19 test. By December 23, 2020, this challenge engaged 482 participants from 90 teams and 7 countries. Main Outcomes and Measures Machine learning algorithms used patient data and output a score that represented the probability of patients receiving a positive COVID-19 test result or being hospitalized within 21 days after receiving a positive COVID-19 test result. Algorithms were evaluated using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC) scores. Ensemble models aggregating models from the top challenge teams were developed and evaluated. Results In the analysis using the cumulative data set, the best performance for COVID-19 diagnosis prediction was an AUROC of 0.776 (95% CI, 0.775-0.777) and an AUPRC of 0.297, and for hospitalization prediction, an AUROC of 0.796 (95% CI, 0.794-0.798) and an AUPRC of 0.188. Analysis on top models submitting to the challenge showed consistently better model performance on the female group than the male group. Among all age groups, the best performance was obtained for the 25- to 49-year age group, and the worst performance was obtained for the group aged 17 years or younger. Conclusions and Relevance In this diagnostic and prognostic study, models submitted by citizen scientists achieved high performance for the prediction of COVID-19 testing and hospitalization outcomes. Evaluation of challenge models on demographic subgroups and prospective data revealed performance discrepancies, providing insights into the potential bias and limitations in the models., This diagnostic and prognostic study describes the development and evaluation of clinical algorithms to predict COVID-19 diagnosis and hospitalization using patient data by citizen scientists, provides an assessment of model performance, and benchmarks model performance on subgroups.

The practice leaders shared common concerns with different approaches in the immediate and longer terms. By the time this information is available to the reader, the projections for the disease burden and the recovery will have changed again. Already, some states and institutions are reporting a plateau in COVID-19 cases, and non-COVID-related admissions are on the rise. Nevertheless, the practice-level maneuvers to manage extraordinary conditions remain salient as we, collectively, will be systemically stressed again. Heeding these lessons may lessen the impact of second waves of regional COVID-19 infections and future pandemics.

As more artificial intelligence (AI)-enhanced mammography screening tools enter the clinical market, greater focus will be placed on external validation in diverse patient populations. In this viewpoint, we outline lessons learned from prior efforts in this field, the need to validate algorithms on newer screening technologies and diverse patient populations, and conclude by discussing the need for a framework for continuous monitoring and recalibration of these AI tools. Sufficient validation and continuous monitoring of emerging AI tools for breast cancer screening will require greater stakeholder engagement and the creation of shared policies and guidelines.

Background Several European screening mammography programs that use independent double reading with consensus recommend an annual minimum reading volume of 5000 mammograms per radiologist. This recommendation is based only on expert opinion, and the influence of reading volume on performance in such programs is unknown. Purpose To examine the influence of annual and cumulative reading volume on radiologists' reading performance for digital mammography in a screening program that uses independent double reading with consensus. Materials and Methods This retrospective study included data from digital mammographic examinations in BreastScreen Norway obtained from 2006 to 2016. Multilevel mixed-effects models were used to determine how sensitivity, rate of screening-detected breast cancer (SDC), and false-positive rate (FPR) before and after consensus meeting related to annual and cumulative reading volume. Results The study included 2 373 433 readings performed by 121 radiologists. The median annual reading volume ranged from 153 to 19 500 mammograms, and the median cumulative reading volume was 30 566 mammograms. Sensitivity and SDC rate were relatively stable at 87% to 90% and 4.9 to 4.7 per 1000 readings (0.49% and 0.47%), respectively, between 100 and 10 000 annual readings and at 88% to 89% and 4.8 to 4.9 per 1000 readings (0.48% and 0.49%) between 500 and 100 000 cumulative readings. There was a decreasing trend with higher annual volumes (P for trend < .001 for both) to a sensitivity of 81% and SDC rate of 3.9 per 1000 readings (0.39%) at 18 000 readings. There was a decreasing trend in FPR before and after consensus with higher annual and cumulative volumes (P for trend < .001 for all). FPRs before consensus meeting were 5.3% at 100 annual readings and 4.0% at 4000 annual readings and were 6.7% at 500 cumulative readings and 3.6% at 20 000 cumulative readings. FPRs after consensus meeting were 2.5% at 100 annual readings and 2.3% at 4000 annual readings and were 2.7% at 500 cumulative readings and 2.2% at 20 000 cumulative readings. Conclusion Annual reading volumes between 4000 and 10 000 mammograms and cumulative reading volumes greater than 20 000 mammograms may be the most optimal volumes for achieving high reading performance in a screening program with independent double reading. © RSNA, 2019 See also the editorial by Rosenberg and Seidenwurm in this issue.

Objective We conducted a national survey to understand the impact of state-level density reporting laws on women’s level of density risk awareness and their engagement in conversations with providers regarding supplemental screening. Methods In all, 1,500 US women aged 40 to 74 years who obtained a mammogram within 2 years were surveyed in February 2018. The sampling design yielded 300 respondents in each of five groups categorized based on density reporting law features. Women were asked about their breast density-related knowledge, importance of being notified, and sources of information and if conversations with providers regarding density and supplemental screening occurred. Survey results were compared across groups and between women residing in states with versus without density laws. Results The majority of respondents in all groups felt that it is important for women to know their breast density type (range, 85%-90%). Women were most likely informed of breast density type by a health care provider (range, 68%-72%), followed by the mammography result letter (range, 48%-68%), and then a radiologist (range, 46%-61%). Women from states with a density law were significantly more likely to have learned of their breast tissue type from a mammogram results letter (60% versus 48%, P = .011) and discuss supplemental screening (67% versus 53%, respectively; P = .008) than women from states without a law. Conclusion State-level density reporting laws are associated with increased breast density awareness and increased likelihood of conversations between women and their providers regarding supplemental screening.

ImportanceDiagnostic delays in breast cancer detection may be associated with later-stage disease and higher anxiety, but data on multilevel factors associated with diagnostic delay are limited.ObjectiveTo evaluate individual-, neighborhood-, and health care–level factors associated with differences in time from abnormal screening to biopsy among racial and ethnic groups.Design, Setting, and ParticipantsThis prospective cohort study used data from women aged 40 to 79 years who had abnormal results in screening mammograms conducted in 109 imaging facilities across 6 US states between 2009 and 2019. Data were analyzed from February 21 to November 4, 2021.ExposuresIndividual-level factors included self-reported race and ethnicity, age, family history of breast cancer, breast density, previous breast biopsy, and time since last mammogram; neighborhood-level factors included geocoded education and income based on residential zip codes and rurality; and health care–level factors included mammogram modality, screening facility academic affiliation, and facility onsite biopsy service availability. Data were also assessed by examination year.Main Outcome and MeasuresThe main outcome was unadjusted and adjusted relative risk (RR) of no biopsy within 30, 60, and 90 days using sequential log-binomial regression models. A secondary outcome was unadjusted and adjusted median time to biopsy using accelerated failure time models.ResultsA total of 45 186 women (median [IQR] age at screening, 56 [48-65] years) with 46 185 screening mammograms with abnormal results were included. Of screening mammograms with abnormal results recommended for biopsy, 15 969 (34.6%) were not resolved within 30 days, 7493 (16.2%) were not resolved within 60 days, and 5634 (12.2%) were not resolved within 90 days. Compared with White women, there was increased risk of no biopsy within 30 and 60 days for Asian (30 days: RR, 1.66; 95% CI, 1.31-2.10; 60 days: RR, 1.58; 95% CI, 1.15-2.18), Black (30 days: RR, 1.52; 95% CI, 1.30-1.78; 60 days: 1.39; 95% CI, 1.22-1.60), and Hispanic (30 days: RR, 1.50; 95% CI, 1.24-1.81; 60 days: 1.38; 95% CI, 1.11-1.71) women; however, the unadjusted risk of no biopsy within 90 days only persisted significantly for Black women (RR, 1.28; 95% CI, 1.11-1.47). Sequential adjustment for selected individual-, neighborhood-, and health care–level factors, exclusive of screening facility, did not substantially change the risk of no biopsy within 90 days for Black women (RR, 1.27; 95% CI, 1.12-1.44). After additionally adjusting for screening facility, the increased risk for Black women persisted but showed a modest decrease (RR, 1.20; 95% CI, 1.08-1.34).Conclusions and RelevanceIn this cohort study involving a diverse cohort of US women recommended for biopsy after abnormal results on screening mammography, Black women were the most likely to experience delays to diagnostic resolution after adjusting for multilevel factors. These results suggest that adjustment for multilevel factors did not entirely account for differences in time to breast biopsy, but unmeasured factors, such as systemic racism and other health care system factors, may impact timely diagnosis.

PURPOSE Preoperative breast MRI is used to evaluate for additional cancer and extent of disease for newly diagnosed breast cancer, yet benefits and harms of preoperative MRI are not well-documented. We examined whether preoperative MRI yields additional biopsy and cancer detection by extent of breast density. METHODS We followed women in the Breast Cancer Surveillance Consortium with an incident breast cancer diagnosed from 2005 to 2017. We quantified breast biopsies and cancers detected within 6 months of diagnosis by preoperative breast MRI receipt, overall and by breast density, accounting for MRI selection bias using inverse probability weighted logistic regression. RESULTS Among 19,324 women with newly diagnosed breast cancer, 28% had preoperative MRI, 11% additional biopsy, and 5% additional cancer detected. Four times as many women with preoperative MRI underwent additional biopsy compared to women without MRI (22.6% v. 5.1%). Additional biopsy rates with preoperative MRI increased with increasing breast density (27.4% for extremely dense compared to 16.2% for almost entirely fatty breasts). Rates of additional cancer detection were almost four times higher for women with v. without MRI (9.9% v. 2.6%). Conditional on additional biopsy, age-adjusted rates of additional cancer detection were lowest among women with extremely dense breasts, regardless of imaging modality (with MRI: 35.0%; 95% CI 27.0-43.0%; without MRI: 45.1%; 95% CI 32.6-57.5%). CONCLUSION For women with dense breasts, preoperative MRI was associated with much higher biopsy rates, without concomitant higher cancer detection. Preoperative MRI may be considered for some women, but selecting women based on breast density is not supported by evidence. TRIAL REGISTRATION ClinicalTrials.gov: NCT02980848; registered 2017.

INTRODUCTION: Limited evidence exists on the impact of age and comorbidity on biopsy rates and findings among older women. MATERIALS AND METHODS: We used data from 170,657 women ages 66–94 enrolled in the United States Breast Cancer Surveillance Consortium (BCSC). We estimated one-year rates of biopsy by type (any, fine-needle aspiration (FNA), core or surgical) and yield of the most invasive biopsy finding (benign, ductal carcinoma in situ (DCIS) and invasive breast cancer) by age and comorbidity. Statistical significance was assessed using Wald statistics comparing coefficients estimated from logistic regression models adjusted for age, comorbidity, BCSC registry, and interaction between age and comorbidity. RESULTS: Of 524,860 screening mammograms, 9830 biopsies were performed following 7930 exams (1.5%) within one year, specifically 5589 core biopsies (1.1%), 3422 (0.7%) surgical biopsies and 819 FNAs (0.2%). Biopsy rates per 1000 screens decreased with age (66–74:15.7, 95%CI:14.8–16.8), 75–84:14.5(13.5–15.6), 85–94:13.2(11.3,15.4), p(trend)=2:19.0 (16.9–21.5), p(trend)

Prevalent digital breast tomosynthesis (DBT) has shown higher cancer detection rates and lower recall rates compared with those of digital mammography (DM). However, data are limited on rates and histopathologic tumor characteristics of interval and subsequent round screen-detected cancers for DBT. Purpose To follow women randomized to screening with DBT or DM and to investigate rates and tumor characteristics of interval and subsequent round screen-detected cancers. Materials and Methods To-Be is a randomized controlled trial comparing the outcome of DBT and DM in organized breast cancer screening. The trial included 28 749 women, with 22 306 women returning for subsequent DBT screening 2 years later (11 201 and 11 105 originally screened with DBT and DM, respectively). Differences in rates, means, and distribution of histopathologic tumor characteristics between women prevalently screened with DBT versus DM were evaluated with Z tests, t tests, and χ2 tests. Relative risk (RR) with 95% CIs was calculated for the cancer rates. Results Interval cancer rates were 1.4 per 1000 screens (20 of 14 380; 95% CI: 0.9, 2.1) for DBT versus 2.0 per 1000 screens (29 of 14 369; 95% CI: 1.4, 2.9; P = .20) for DM. The rates of subsequent round screen-detected cancer were 8.1 per 1000 (95% CI: 6.6, 10.0) for women originally screened with DBT and 9.1 per 1000 (95% CI: 7.4, 11.0; P = .43) for women screened with DM. The distribution of tumor characteristics did not differ between groups for either interval or subsequent screen-detected cancer. The RR of interval cancer was 0.69 (95% CI: 0.39, 1.22; P = .20) for DBT versus DM, whereas RR of subsequent screen-detected cancer for women prevalently screened with DBT versus DM was 0.89 (95% CI: 0.67, 1.19; P = .43). Conclusion Rates of interval or subsequent round screen-detected cancers and their tumor characteristics did not differ between women originally screened with digital breast tomosynthesis (DBT) versus digital mammography. The analysis suggests that the benefits of prevalent DBT screening did not come at the expense of worse downstream screening performance measures in a population-based screening program.

Key Points Question How can imaging facilities optimize the number of breast cancers detected during periods of reduced capacity using clinical indication and individual characteristics? Findings In this cohort study including 898 415 individuals with 1 878 924 mammograms, 12% of mammograms with very high and high cancer detection rates accounted for 55% of detected cancers, while 44% of mammograms with very low cancer detection rate accounted for 13% of detected cancers. Meaning These findings suggest that triaging individuals most likely to have cancer detected during periods of reduced capacity could result in detecting the most cancers while performing the fewest examinations compared with a non–risk-based approach., This cohort study assesses strategies to triage patients for mammogram cancer screening during times of reduced capacity., Importance Breast cancer screening, surveillance, and diagnostic imaging services were profoundly limited during the initial phase of the coronavirus disease 2019 (COVID-19) pandemic. Objective To develop a risk-based strategy for triaging mammograms during periods of decreased capacity. Design, Setting, and Participants This population-based cohort study used data collected prospectively from mammography examinations performed in 2014 to 2019 at 92 radiology facilities in the Breast Cancer Surveillance Consortium. Participants included individuals undergoing mammography. Data were analyzed from August 10 to November 3, 2020. Exposures Clinical indication for screening, breast symptoms, personal history of breast cancer, age, time since last mammogram/screening interval, family history of breast cancer, breast density, and history of high-risk breast lesion. Main Outcomes and Measures Combinations of clinical indication, clinical history, and breast cancer risk factors that subdivided mammograms into risk groups according to their cancer detection rate were identified using classification and regression trees. Results The cohort included 898 415 individuals contributing 1 878 924 mammograms (mean [SD] age at mammogram, 58.6 [11.2] years) interpreted by 448 radiologists, with 1 722 820 mammograms in individuals without a personal history of breast cancer and 156 104 mammograms in individuals with a history of breast cancer. Most individuals were aged 50 to 69 years at imaging (1 113 174 mammograms [59.2%]), and 204 305 (11.2%) were Black, 206 087 (11.3%) were Asian or Pacific Islander, 126 677 (7.0%) were Hispanic or Latina, and 40 021 (2.2%) were another race/ethnicity or mixed race/ethnicity. Cancer detection rates varied widely based on clinical indication, breast symptoms, personal history of breast cancer, and age. The 12% of mammograms with very high (89.6 [95% CI, 82.3-97.5] to 122.3 [95% CI, 108.1-138.0] cancers detected per 1000 mammograms) or high (36.1 [95% CI, 33.1-39.3] to 47.5 [95% CI, 42.4-53.3] cancers detected per 1000 mammograms) cancer detection rates accounted for 55% of all detected cancers and included mammograms to evaluate an abnormal mammogram or breast lump in individuals of all ages regardless of breast cancer history, to evaluate breast symptoms other than lump in individuals with a breast cancer history or without a history but aged 60 years or older, and for short-interval follow-up in individuals aged 60 years or older without a breast cancer history. The 44.2% of mammograms with very low cancer detection rates accounted for 13.1% of detected cancers and included annual screening mammograms in individuals aged 50 to 69 years (3.8 [95% CI, 3.5-4.1] cancers detected per 1000 mammograms) and all screening mammograms in individuals younger than 50 years regardless of screening interval (2.8 [95% CI, 2.6-3.1] cancers detected per 1000 mammograms). Conclusions and Relevance In this population-based cohort study, clinical indication and individual risk factors were associated with cancer detection and may be useful for prioritizing mammography in times and settings of decreased capacity.

Among women, breast cancer is the most commonly diagnosed cancer and the leading cause of cancer-related death in the world. The purpose of this article is to review the evidence regarding breast cancer screening for average-risk women. The review primarily focuses on mammographic screening but also reviews clinical breast examinations, emerging screening technologies, and opportunities to build consensus. Wherever possible, the review relies on published systematic reviews, meta-analyses, and guidelines from three major societies (US Preventive Services Task Force, American College of Radiology, and the American Cancer Society) to reflect a range of evidence-based perspectives regarding mammographic screening.

Background: Digital breast tomosynthesis (DBT) is considered superior to digital mammography (DM) for women with dense breasts. Purpose: To identify differences in screening outcomes, including rates of recall, false-positive (FP) findings, biopsy, cancer detection rate, positive predictive value of recalls and biopsies, and histopathologic tumor characteristics by density using DBT combined with two-dimensional synthetic mammography (SM) (hereafter, DBT+SM) versus DM. Materials and Methods: This randomized controlled trial comparing DBT+SM and DM was performed in Bergen as part of BreastScreen Norway, 2016–2017. Automated software measured density (Volpara Density Grade [VDG], 1–4). The outcomes were compared for DBT+SM versus DM by VDG in descriptive analyses. A stratified log-binomial regression model was used to estimate relative risk of outcomes in subgroups by screening technique. Results: Data included 28 749 women, 14 380 of whom were screened with DBT+SM and 14 369 of whom were screened with DM (both groups: median age, 59 years; interquartile range [IQR], 54–64 years). The recall rate was lower for women screened with DBT+SM versus those screened with DM for VDG 1 (2.1% [81 of 3929] vs 3.3% [106 of 3212]; P = .001) and VDG 2 (3.2% [200 of 6216] vs 4.3% [267 of 6280]; P = .002). For DBT+SM, adjusted relative risk of recall (VDG 2: 1.8; P < .001; VDG 3: 2.4; P < .001; VDG 4: 1.8; P = .02) and screen-detected breast cancer (VDG 2: 2.4; P = .004; VDG 3: 2.8; P = .01; VDG 4: 2.8; P = .05) increased with VDG, whereas no differences were observed for DM (relative risk of recall for VDG 2: 1.3; P = .06; VDG 3: 1.1; P = .41; VDG 4: 1.1; P = .71; and relative risk of screen-detected breast cancer for VDG 2: 1.7; P = .13; VDG 3: 2.1; P = .06; VDG 4: 2.2; P = .15). Conclusion: Screening with digital breast tomosynthesis combined with synthetic two-dimensional mammograms (DBT+SM) versus digital mammography (DM) yielded lower recall rates for women with Volpara Density Grade (VDG) 1 and VDG 2. Adjusted relative risk of recall and screen-detected breast cancer increased with denser breasts for DBT+SM but not for DM. publishedVersion

The Oncology Grand Rounds series is designed to place original reports published in the Journal into clinical context. A case presentation is followed by a description of diagnostic and management challenges, a review of the relevant literature, and a summary of the authors’ suggested management approaches. The goal of this series is to help readers better understand how to apply the results of key studies, including those published in Journal of Clinical Oncology, to patients seen in their own clinical practice.

Purpose Lobular neoplasia (LN) detected on breast core needle biopsy is frequently managed with surgical excision because of concern for undersampled malignancy. The authors performed a systematic review and meta-analysis to estimate the risk for upgrade to malignancy in the setting of imaging-concordant classic LN diagnosed on core biopsy. Methods PubMed and Embase were searched for original articles published from 1998 to 2020 that reported rates of upgrade to malignancy for classic LN, including atypical lobular hyperplasia (ALH) and classic lobular carcinoma in situ (LCIS). Two reviewers extracted study data and assessed the following quality criteria: exclusion of variant LCIS, exclusion of imaging-discordant lesions, and outcome reporting for ≥70% of lesions. For studies meeting all criteria, pooled risks for upgrade to any malignancy (invasive carcinoma or ductal carcinoma in situ) and invasive malignancy for all LN, ALH, and LCIS were estimated using random-effects models. Results For 65 full-text articles included in the review, the risk for upgrade to any malignancy ranged from 0% to 45%. Among the 16 studies that met all quality criteria for the meta-analysis, pooled risks for upgrade to any malignancy were 3.1% (95% confidence interval [CI], 1.8%-5.2%) for all LN, 2.5% (95% CI, 1.6%-3.9%) for ALH, and 5.8% (95% CI, 2.9%-11.3%) for LCIS. Risks for upgrade to invasive malignancy were 1.3% (95% CI, 0.7%-2.4%) for all LN, 0.4% (95% CI, 0.0%-4.2%) for ALH, and 3.5% (95% CI, 2.0%-5.9%) for LCIS. Conclusions The risk for upgrade to malignancy for LN found on breast biopsy is low. Imaging surveillance can likely be offered as an alternative to surgical management for LN, particularly for ALH.

Importance Many US radiologists have screening mammography recall rates above the expert-recommended threshold of 12%. The influence of digital breast tomosynthesis (DBT) on the distribution of radiologist recall rates is uncertain. Objective To evaluate radiologists’ recall and cancer detection rates before and after beginning interpretation of DBT examinations. Design, Setting, and Participants This cohort study included 198 radiologists from 104 radiology facilities in the Breast Cancer Surveillance Consortium who interpreted 251 384 DBT and 2 000 681 digital mammography (DM) screening examinations from 2009 to 2017, including 126 radiologists (63.6%) who interpreted DBT examinations during the study period and 72 (36.4%) who exclusively interpreted DM examinations (to adjust for secular trends). Data were analyzed from April 2018 to July 2019. Exposures Digital breast tomosynthesis and DM screening examinations. Main Outcomes and Measures Recall rate and cancer detection rate. Results A total of 198 radiologists interpreted 2 252 065 DM and DBT examinations (2 000 681 [88.8%] DM examinations; 251 384 [11.2%] DBT examinations; 710 934 patients [31.6%] aged 50-59 years; 1 448 981 [64.3%] non-Hispanic white). Among the 126 radiologists (63.6%) who interpreted DBT examinations, 83 (65.9%) had unadjusted DM recall rates of no more than 12% before using DBT, with a median (interquartile range) recall rate of 10.0% (7.5%-13.0%). On DBT examinations, 96 (76.2%) had an unadjusted recall rate of no more than 12%, with a median (interquartile range) recall rate of 8.8% (6.3%-11.3%). A secular trend in recall rate was observed, with the multivariable-adjusted risk of recall on screening examinations declining by 1.2% (95% CI, 0.9%-1.5%) per year. After adjusting for examination characteristics and secular trends, recall rates were 15% lower on DBT examinations compared with DM examinations interpreted before DBT use (relative risk, 0.85; 95% CI, 0.83-0.87). Adjusted recall rates were significantly lower on DBT examinations compared with DM examinations interpreted before DBT use for 45 radiologists (35.7%) and significantly higher for 18 (14.3%); 63 (50.0%) had no statistically significant change. The unadjusted cancer detection rate on DBT was 5.3 per 1000 examinations (95% CI, 5.0-5.7 per 1000 examinations) compared with 4.7 per 1000 examinations (95% CI, 4.6-4.8 per 1000 examinations) on DM examinations interpreted before DM use (multivariable-adjusted risk ratio, 1.21; 95% CI, 1.11-1.33). Conclusions and Relevance In this study, DBT was associated with an overall decrease in recall rate and an increase in cancer detection rate. However, our results indicated that there is wide variability among radiologists, including a subset of radiologists who experienced increased recall rates on DBT examinations. Radiology practices should audit radiologist DBT screening performance and consider additional DBT training for radiologists whose performance does not improve as expected.

Breast density (BD) is an independent risk factor for breast cancer and reduces the sensitivity of mammography. The enactment of BD legislation in a majority of states in the USA mandating notification of risks associated with BD directly to women undergoing mammography has catapulted interest in BD among women, physicians, and policymakers. We therefore report a descriptive review of the evidence on the impact of enactment of BD legislation. Based on 22 eligible studies, we identified four broad themes of research: studies of the impact on screening rates, most showing increased utilisation of supplemental screening; studies exploring the effect on women, radiologists, or primary physicians (reporting heterogeneous effects on knowledge, awareness, perceptions, attitudes and behaviour; and changes in practice); few studies assessing the population impact (effect on screening outcomes or breast cancer stage); and studies of costs highlighting the economic burden from supplemental screening. Given that many of the studies were retrospective single institution studies (comparing pre- and post-legislation) or small surveys with a paucity of population-level studies, we highlight areas meriting additional research. The information described in this review can inform research priorities where BD legislation has been introduced and can be used to guide world-wide policy or practice decisions where BD legislation may be under debate or contemplation.

Purpose: To compare the performance of digital breast tomosynthesis (DBT) and two-dimensional synthetic mammography (SM) with that of digital mammography (DM) in a population-based mammographic screening program. Materials and Methods: In this prospective cohort study, data from 37 185 women screened with DBT and SM and from 61 742 women screened with DM as part of a population-based screening program in 2014 and 2015 were included. Early performance measures, including recall rate due to abnormal mammographic findings, rate of screen-detected breast cancer, positive predictive value of recall, positive predictive value of needle biopsy, histopathologic type, tumor size, tumor grade, lymph node involvement, hormonal status, Ki-67 level, and human epidermal growth factor receptor 2 status were compared in women who underwent DBT and SM screening and in those who underwent DM screening by using x2 tests, two-sample unpaired t tests, and tests of proportions. Results: Recall rates were 3.4% for DBT and SM screening and 3.3% for DM screening (P = .563). DBT and SM screening showed a significantly higher rate of screen-detected cancer compared with DM screening (9.4 vs 6.1 cancers per 1000 patients screened, respectively; P , .001). The rate of detection of tumors 10 mm or smaller was 3.2 per 1000 patients screened with DBT and SM and 1.8 per 1000 patients screened with DM (P , .001), and the rate of grade 1 tumors was 3.3 per 1000 patients screened with DBT and SM versus 1.4 per 1000 patients screened with DM (P , .001). On the basis of immunohistochemical analyses, rates of lymph node involvement and tumor subtypes did not differ between women who underwent DBT and SM screening and those who underwent DM screening. Conclusion: DBT and SM screening increased the detection rate of histologically favorable tumors compared with that attained with DM screening.

In 2009, the U.S. Preventive Services Task Force (USPSTF) recommended biennial mammography for women aged 50-74 years and shared decision-making for women aged 40-49 years for breast cancer screening. We evaluated changes in mammography screening interval after the 2009 recommendations.We conducted a prospective cohort study of women aged 40-74 years who received 821,052 screening mammograms between 2006 and 2012 using data from the Breast Cancer Surveillance Consortium. We compared changes in screening intervals and stratified intervals based on whether the mammogram at the end of the interval occurred before or after the 2009 recommendation. Differences in mean interval length by woman-level characteristics were compared using linear regression.The mean interval (in months) minimally decreased after the 2009 USPSTF recommendations. Among women aged 40-49 years, the mean interval decreased from 17.2 months to 17.1 months (difference -0.16%, 95% confidence interval [CI] -0.30 to -0.01). Similar small reductions were seen for most age groups. The largest change in interval length in the post-USPSTF period was declines among women with a first-degree family history of breast cancer (difference -0.68%, 95% CI -0.82 to -0.54) or a 5-year breast cancer risk ≥2.5% (difference -0.58%, 95% CI -0.73 to -0.44).The 2009 USPSTF recommendation did not lengthen the average mammography interval among women routinely participating in mammography screening. Future studies should evaluate whether breast cancer screening intervals lengthen toward biennial intervals following new national 2016 breast cancer screening recommendations, particularly among women less than 50 years of age.

ObjectiveWe sought to identify and characterize examinations in women with a personal history of breast cancer likely performed for asymptomatic surveillance.MethodsWe included surveillance mammograms (1997-2017) in asymptomatic women with a personal history of breast cancer diagnosed at age ≥18 years (1996-2016) from 103 Breast Cancer Surveillance Consortium facilities. We examined facility-level variability in examination indication. We modeled the relative risk (RR) and 95% confidence intervals (CIs) at the examination level of a (1) nonscreening indication and (2) surveillance interval ≤9 months using Poisson regression with fixed effects for facility, stage, diagnosis age, surgery, examination year, and time since diagnosis.ResultsAmong 244,855 surveillance mammograms, 69.5% were coded with a screening indication, 12.7% short-interval follow-up, and 15.3% as evaluation of a breast problem. Within a facility, the proportion of examinations with a screening indication ranged from 6% to 100% (median 86%, interquartile range 79%-92%). Facilities varied the most for examinations in the first 5 years after diagnosis, with 39.4% of surveillance mammograms having a nonscreening indication. Within a facility, breast conserving surgery compared with mastectomy (RR= 1.64; 95% CI= 1.60-1.68) and less time since diagnosis (1 year versus 5 years; RR= 1.69; 95% CI= 1.66-1.72; 3 years versus 5 years= 1.20; 95% CI= 1.18-1.23) were strongly associated with a nonscreening indication with similar results for ≤9-month surveillance interval. Screening indication and >9-month surveillance intervals were more common in more recent years.ConclusionVariability in surveillance indications across facilities in the United States supports including indications beyond screening in studies evaluating surveillance mammography effectiveness and demonstrates the need for standardization.

BACKGROUND: Artificial intelligence (AI) systems performing at radiologist-like levels in the evaluation of digital mammography (DM) would improve breast cancer screening accuracy and efficiency. We aimed to compare the stand-alone performance of an AI system to that of radiologists in detecting breast cancer in DM. METHODS: Nine multi-reader, multi-case study datasets previously used for different research purposes in seven countries were collected. Each dataset consisted of DM exams acquired with systems from four different vendors, multiple radiologists’ assessments per exam, and ground truth verified by histopathological analysis or follow-up, yielding a total of 2652 exams (653 malignant) and interpretations by 101 radiologists (28 296 independent interpretations). An AI system analyzed these exams yielding a level of suspicion of cancer present between 1 and 10. The detection performance between the radiologists and the AI system was compared using a noninferiority null hypothesis at a margin of 0.05. RESULTS: The performance of the AI system was statistically noninferior to that of the average of the 101 radiologists. The AI system had a 0.840 (95% confidence interval [CI] = 0.820 to 0.860) area under the ROC curve and the average of the radiologists was 0.814 (95% CI = 0.787 to 0.841) (difference 95% CI = −0.003 to 0.055). The AI system had an AUC higher than 61.4% of the radiologists. CONCLUSIONS: The evaluated AI system achieved a cancer detection accuracy comparable to an average breast radiologist in this retrospective setting. Although promising, the performance and impact of such a system in a screening setting needs further investigation.

Background: The purpose of this study was to assess advanced imaging (bone scan, CT, or PET/CT) and serum tumor biomarker use in asymptomatic breast cancer survivors during the surveillance period. Patients and Methods: Cancer registry records for 2,923 women diagnosed with primary breast cancer in Washington State between January 1, 2007, and December 31, 2014, were linked with claims data from 2 regional commercial insurance plans. Clinical data including demographic and tumor characteristics were collected. Evaluation and management codes from claims data were used to determine advanced imaging and serum tumor biomarker testing during the peridiagnostic and surveillance phases of care. Multivariable logistic regression models were used to identify clinical factors and patterns of peridiagnostic imaging and biomarker testing associated with surveillance advanced imaging. Results: Of 2,923 eligible women, 16.5% (n=480) underwent surveillance advanced imaging and 31.8% (n=930) received surveillance serum tumor biomarker testing. Compared with women diagnosed before the launch of the Choosing Wisely campaign in 2012, later diagnosis was associated with lower use of surveillance advanced imaging (odds ratio [OR], 0.68; 95% CI, 0.52–0.89). Factors significantly associated with use of surveillance advanced imaging included increasing disease stage (stage III: OR, 3.65; 95% CI, 2.48–5.38), peridiagnostic advanced imaging use (OR, 1.76; 95% CI, 1.33–2.31), and peridiagnostic serum tumor biomarker testing (OR, 1.35; 95% CI, 1.01–1.80). Conclusions: Although use of surveillance advanced imaging in asymptomatic breast cancer survivors has declined since the launch of the Choosing Wisely campaign, frequent use of surveillance serum tumor biomarker testing remains prevalent, representing a potential target for further efforts to reduce low-value practices.

Changes to mammography practice, including revised Breast Imaging Reporting and Data System (BI-RADS) density classification guidelines and implementation of digital breast tomosynthesis (DBT), may impact clinical breast density assessment. We investigated temporal trends in clinical breast density assessment among 2 990 291 digital mammography (DM) screens and 221 063 DBT screens interpreted by 722 radiologists from 144 facilities in the Breast Cancer Surveillance Consortium. After age-standardization, 46.3% (95% CI = 44.1% to 48.6%) of DM screens were assessed as dense (heterogeneously/extremely dense) during the BI-RADS 4th edition era (2005-2013), compared to 46.5% (95% CI = 43.8% to 49.1%) during the 5th edition era (2014-2016) (P = .93 from two-sided generalized score test). Among DBT screens in the BI-RADS 5th edition era, 45.8% (95% CI = 42.0% to 49.7%) were assessed as dense (P = .77 from two-sided generalized score test) compared to 46.5% (95% CI = 43.8% to 49.1%) dense on DM in BI-RADS 5th edition era. Results were similar when examining all four density categories and age subgroups. Clinicians, researchers, and policymakers may reasonably expect stable density distributions across screened populations despite changes to the BI-RADS guidelines and implementation of DBT.

The American College of Physicians Clinical Guidelines Committee presented an assessment of the quality and content of 7 English-language breast cancer screening guidelines and gave 4 guidance stat...

Purpose To describe factors associated with screening ultrasound ordering and determine whether adoption of state-level breast density reporting laws was associated with changes in ordering rates. Materials and Methods We performed a cohort study using National Ambulatory Medical Care Survey data for 2007 to 2015. We included preventive office visits for women aged 40 to 74 years without breast symptoms and signs or additional reasons requiring ultrasound ordering. Multivariate logistic regression was used to identify changes in ultrasound ordering rates pre- versus post-state-level density reporting laws, accounting for patient-, physician-, and practice-level characteristics. Analyses were weighted to account for the multistage probability sampling design of National Ambulatory Medical Care Survey. Results Our sample included 12,787 visits over the 9-year study period. Overall, 28.9% (3,370 of 12,787) of women underwent a breast examination and 22.1% (2,442 of 12,787) had a screening mammogram ordered. Only 3.3% (379 of 12,787) had screening ultrasound ordered. Screening ultrasounds were ordered more frequently for younger women (rate ratio [RR] 0.8 per 10-year increase in age, 95% confidence interval [CI]: 0.6-0.9, P = .003) and at urban practices (RR 2.3, 95% CI: 1.1-5.0, P = .028), and less frequently in practices with computer reminders for ordering screening tests (RR 0.6, 95% CI: 0.3-0.9, P = .024). In multivariate analyses, the rate of ultrasound ordering did not change after adoption of density notification laws (RR 0.7, 95% CI: 0.3-2.0, P = .57). Conclusion The rate of screening ultrasound ordering remains low over time. There was no observed association between adoption of state-level density reporting laws and overall changes in ultrasound ordering.

BACKGROUND: There is growing evidence that digital breast tomosynthesis (DBT) results in lower recall rates and higher cancer detection rates when compared with digital mammography. However, whether DBT interpretative performance changes with experience (learning curve effect) is unknown. PURPOSE: To evaluate screening DBT performance by cumulative DBT volume within 2 years after adoption relative to digital mammography (DM) performance 1 year before DBT adoption. MATERIALS AND METHODS: This prospective study included 106 126 DBT and 221 248 DM examinations in 271 362 women (mean age, 57.5 years) from 2010 to 2017 that were interpreted by 104 radiologists from 53 facilities in the Breast Cancer Surveillance Consortium. Conditional logistic regression was used to estimate within-radiologist effects of increasing cumulative DBT volume on recall and cancer detection rates relative to DM and was adjusted for examination-level characteristics. Changes were also evaluated by subspecialty and breast density. RESULTS: Before DBT adoption, DM recall rate was 10.4% (95% confidence interval [CI]: 9.5%, 11.4%) and cancer detection rate was 4.0 per 1000 screenings (95% CI: 3.6 per 1000 screenings, 4.5 per 1000 screenings); after DBT adoption, DBT recall rate was lower (9.4%; 95% CI: 8.2%, 10.6%; P = .02) and cancer detection rate was similar (4.6 per 1000 screenings; 95% CI: 4.0 per 1000 screenings, 5.2 per 1000 screenings; P = .12). Relative to DM, DBT recall rate decreased for a cumulative DBT volume of fewer than 400 studies (odds ratio [OR] = 0.83; 95% CI: 0.78, 0.89) and remained lower as volume increased (400–799 studies, OR = 0.8 [95% CI: 0.75, 0.85]; 800–1199 studies, OR = 0.81 [95% CI: 0.76, 0.87]; 1200–1599 studies, OR = 0.78 [95% CI: 0.73, 0.84]; 1600–2000 studies, OR = 0.81 [95% CI: 0.75, 0.88]; P < .001). Improvements were sustained for breast imaging subspecialists (OR range, 0.67–0.85; P < .02) and readers who were not breast imaging specialists (OR range, 0.80–0.85; P < .001). Recall rates decreased more in women with nondense breasts (OR range, 0.68–0.76; P < .001) than in those with dense breasts (OR range, 0.86–0.90; P ≤ .05; P interaction < .001). Cancer detection rates for DM and DBT were similar, regardless of DBT volume (P ≥ .10). CONCLUSION: Early performance improvements after digital breast tomosynthesis (DBT) adoption were sustained regardless of DBT volume, radiologist subspecialty, or breast density. © RSNA, 2019 See also the editorial by Hooley in this issue.

The COVID-19 pandemic disrupted breast cancer screening and diagnostic imaging in the United States. We sought to evaluate how medical facilities prioritized breast imaging services during periods of reduced capacity or upon re-opening after closures. In fall 2020, we surveyed 77 breast imaging facilities within the Breast Cancer Surveillance Consortium in the United States. The survey ascertained the pandemic's impact on clinical practices during March-September 2020. Nearly all facilities (97%) reported closing or operating at reduced capacity at some point during this period. All facilities were open by August 2020, though 14% were still operating at reduced capacity in September 2020. During periods of re-opening or reduced capacity, 93% of facilities reported prioritizing diagnostic breast imaging over breast cancer screening. For diagnostic imaging, facilities prioritized based on rescheduling canceled appointments (89%), specific indication for diagnostic imaging (89%), patient demand (84%), individual characteristics and risk factors (77%), and time since last imaging examination (72%). For screening mammography, facilities prioritized based on rescheduled cancelations (96%), patient demand (83%), individual characteristics and risk factors (73%), and time since last mammogram (71%). For biopsy services, more than 90% of facilities reported prioritization based on rescheduling of canceled exams, patient demand, patient characteristics and risk factors and level of suspicion on imaging. The observed patterns from this large and geographically diverse sample of facilities in the United States indicate that multiple factors were commonly used to prioritize breast imaging services during periods of reduced capacity.

Purpose This study aims to determine whether radiologists who perform well in screening also perform well in interpreting diagnostic mammography. Materials and methods We evaluated the accuracy of 468 radiologists interpreting 2,234,947 screening and 196,164 diagnostic mammograms. Adjusting for site, radiologist, and patient characteristics, we identified radiologists with performance in the highest tertile and compared to those with lower performance. Results A moderate correlation was noted for radiologists' accuracy when interpreting screening versus their accuracy on diagnostic examinations: sensitivity (r spearman =0.51, 95% CI: 0.22, 0.80; P =.0006) and specificity (r spearman =0.40, 95% CI: 0.30, 0.49; P Conclusion Different educational approaches to screening and diagnostic imaging should be considered.

Emerging imaging technologies, including digital breast tomosynthesis, have the potential to transform breast cancer screening. However, the rapid adoption of these new technologies outpaces the evidence of their clinical and cost-effectiveness. The authors describe the forces driving the rapid diffusion of tomosynthesis into clinical practice, comparing it with the rapid diffusion of digital mammography shortly after its introduction. They outline the potential positive and negative effects that adoption can have on imaging workflow and describe the practice management challenges when incorporating tomosynthesis. The authors also provide recommendations for collecting evidence supporting the development of policies and best practices.

In the U.S., guidelines recommend that women continue mammography screening until at least age 74, but recent evidence suggests declining screening rates in older women. We estimated adherence to screening mammography and multilevel factors associated with adherence in a longitudinal cohort of older women. Women aged 66–75 years receiving screening mammography within the Breast Cancer Surveillance Consortium were linked to Medicare claims (2005–2010). Claims data identified baseline adherence, defined as receiving subsequent mammography within approximately 2 years, and length of time adherent to guidelines. Characteristics associated with adherence were investigated using logistic and Cox proportional hazards regression models. Analyses were stratified by age to investigate variation in relationships between patient factors and adherence. Among 49,775 women, 89% were adherent at baseline. Among women 66–70 years, those with less than a high school education were more likely to be non-adherent at baseline (odds ratio [OR] 1.96; 95% confidence interval [CI] 1.65–2.33) and remain adherent for less time (hazard ratio [HR] 1.41; 95% CI 1.11–1.80) compared to women with a college degree. Women with ≥ 1 versus no Charlson co-morbidities were more likely to be non-adherent at baseline (OR 1.46; 95% CI 1.31–1.62) and remain adherent for less time (HR 1.44; 95% CI 1.24–1.66). Women aged 71–75 had lower adherence overall, but factors associated with non-adherence were similar. In summary, adherence to guidelines is high among Medicare-enrolled women in the U.S. receiving screening mammography. Efforts are needed to ensure that vulnerable populations attain these same high levels of adherence.

Key Points Question Does screening performance of digital breast tomosynthesis vs digital mammography differ by breast density, age, or screening round in community practice? Findings In this comparative effectiveness study assessing 1 584 079 screening examinations across 46 US facilities, the largest improvements in recall and cancer detection rates with digital breast tomosynthesis were observed on baseline screens. On subsequent screens, both recall and cancer detection rates improved using digital breast tomosynthesis vs digital mammography for women aged 40 to 79 years with heterogeneously dense breasts and for women aged 50 to 79 years with scattered fibroglandular density; by contrast, performance was similar in women with extremely dense breasts. Meaning Women undergoing baseline screening may benefit most from digital breast tomosynthesis, whereas on subsequent screens, the benefits of digital breast tomosynthesis may vary by age and density category., Importance Digital mammography (DM) and digital breast tomosynthesis (DBT) are used for routine breast cancer screening. There is minimal evidence on performance outcomes by age, screening round, and breast density in community practice. Objective To compare DM vs DBT performance by age, baseline vs subsequent screening round, and breast density category. Design, Setting, and Participants This comparative effectiveness study assessed 1 584 079 screening examinations of women aged 40 to 79 years without prior history of breast cancer, mastectomy, or breast augmentation undergoing screening mammography at 46 participating Breast Cancer Surveillance Consortium facilities from January 2010 to April 2018. Exposures Age, Breast Imaging Reporting and Data System breast density category, screening round, and modality. Main Outcomes and Measures Absolute rates and relative risks (RRs) of screening recall and cancer detection. Results Of 1 273 492 DM and 310 587 DBT examinations analyzed, 1 028 891 examinations (65.0%) were of white non-Hispanic women; 399 952 women (25.2%) were younger than 50 years; and 671 136 women (42.4%) had heterogeneously dense or extremely dense breasts. Adjusted differences in DM vs DBT performance were largest on baseline examinations: for example, per 1000 baseline examinations in women ages 50 to 59, recall rates decreased from 241 examinations for DM to 204 examinations for DBT (RR, 0.84; 95% CI, 0.73-0.98), and cancer detection rates increased from 5.9 with DM to 8.8 with DBT (RR, 1.50; 95% CI, 1.10-2.08). On subsequent examinations, women aged 40 to 79 years with heterogeneously dense breasts had improved recall rates and improved cancer detection with DBT. For example, per 1000 examinations in women aged 50 to 59 years, the number of recall examinations decreased from 102 with DM to 93 with DBT (RR, 0.91; 95% CI, 0.84-0.98), and cancer detection increased from 3.7 with DM to 5.3 with DBT (RR, 1.42; 95% CI, 1.23-1.64). Women aged 50 to 79 years with scattered fibroglandular density also had improved recall and cancer detection rates with DBT. Women aged 40 to 49 years with scattered fibroglandular density and women aged 50 to 79 years with almost entirely fatty breasts benefited from improved recall rates without change in cancer detection rates. No improvements in recall or cancer detection rates were observed in women with extremely dense breasts on subsequent examinations for any age group. Conclusions and Relevance This study found that improvements in recall and cancer detection rates with DBT were greatest on baseline mammograms. On subsequent screening mammograms, the benefits of DBT varied by age and breast density. Women with extremely dense breasts did not benefit from improved recall or cancer detection with DBT on subsequent screening rounds., This comparative effectiveness study evaluates the screening recall and cancer detection rates of digital mammography vs digital breast tomosynthesis stratified by age, baseline screening, subsequent screening round, and breast density category in a large US cohort of women aged 40 to 79 years.