Performance of an Artificial Intelligence System for Breast Cancer Detection on Screening Mammograms from BreastScreen Norway

Purpose To explore the stand-alone breast cancer detection performance, at different risk score thresholds, of a commercially available artificial intelligence (AI) system. Materials and Methods This retrospective study included information from 661 695 digital mammographic examinations performed among 242 629 female individuals screened as a part of BreastScreen Norway, 2004-2018. The study sample included 3807 screen-detected cancers and 1110 interval breast cancers. A continuous examination-level risk score by the AI system was used to measure performance as the area under the receiver operating characteristic curve (AUC) with 95% CIs and cancer detection at different AI risk score thresholds. Results The AUC of the AI system was 0.93 (95% CI: 0.92, 0.93) for screen-detected cancers and interval breast cancers combined and 0.97 (95% CI: 0.97, 0.97) for screen-detected cancers. In a setting where 10% of the examinations with the highest AI risk scores were defined as positive and 90% with the lowest scores as negative, 92.0% (3502 of 3807) of the screen-detected cancers and 44.6% (495 of 1110) of the interval breast cancers were identified with AI. In this scenario, 68.5% (10 987 of 16 040) of false-positive screening results (negative recall assessment) were considered negative by AI. When 50% was used as the cutoff, 99.3% (3781 of 3807) of the screen-detected cancers and 85.2% (946 of 1110) of the interval breast cancers were identified as positive by AI, whereas 17.0% (2725 of 16 040) of the false-positive results were considered negative. Conclusion The AI system showed high performance in detecting breast cancers within 2 years of screening mammography and a potential for use to triage low-risk mammograms to reduce radiologist workload. Keywords: Mammography, Breast, Screening, Convolutional Neural Network (CNN), Deep Learning Algorithms Supplemental material is available for this article. © RSNA, 2024 See also commentary by Bahl and Do in this issue.

AI performance by mammographic density in a retrospective cohort study of 99,489 participants in BreastScreen Norway

OBJECTIVE

To explore the ability of artificial intelligence (AI) to classify breast cancer by mammographic density in an organized screening program.

MATERIALS AND METHOD

We included information about 99,489 examinations from 74,941 women who participated in BreastScreen Norway, 2013-2019. All examinations were analyzed with an AI system that assigned a malignancy risk score (AI score) from 1 (lowest) to 10 (highest) for each examination. Mammographic density was classified into Volpara density grade (VDG), VDG1-4; VDG1 indicated fatty and VDG4 extremely dense breasts. Screen-detected and interval cancers with an AI score of 1-10 were stratified by VDG.

RESULTS

We found 10,406 (10.5% of the total) examinations to have an AI risk score of 10, of which 6.7% (704/10,406) was breast cancer. The cancers represented 89.7% (617/688) of the screen-detected and 44.6% (87/195) of the interval cancers. 20.3% (20,178/99,489) of the examinations were classified as VDG1 and 6.1% (6047/99,489) as VDG4. For screen-detected cancers, 84.0% (68/81, 95% CI, 74.1-91.2) had an AI score of 10 for VDG1, 88.9% (328/369, 95% CI, 85.2-91.9) for VDG2, 92.5% (185/200, 95% CI, 87.9-95.7) for VDG3, and 94.7% (36/38, 95% CI, 82.3-99.4) for VDG4. For interval cancers, the percentages with an AI score of 10 were 33.3% (3/9, 95% CI, 7.5-70.1) for VDG1 and 48.0% (12/25, 95% CI, 27.8-68.7) for VDG4.

CONCLUSION

The tested AI system performed well according to cancer detection across all density categories, especially for extremely dense breasts. The highest proportion of screen-detected cancers with an AI score of 10 was observed for women classified as VDG4.

CLINICAL RELEVANCE STATEMENT

Our study demonstrates that AI can correctly classify the majority of screen-detected and about half of the interval breast cancers, regardless of breast density.

KEY POINTS

• Mammographic density is important to consider in the evaluation of artificial intelligence in mammographic screening. • Given a threshold representing about 10% of those with the highest malignancy risk score by an AI system, we found an increasing percentage of cancers with increasing mammographic density. • Artificial intelligence risk score and mammographic density combined may help triage examinations to reduce workload for radiologists.

Impact of a Categorical AI System for Digital Breast Tomosynthesis on Breast Cancer Interpretation by Both General Radiologists and Breast Imaging Specialists

Purpose To evaluate performance improvements of general radiologists and breast imaging specialists when interpreting a set of diverse digital breast tomosynthesis (DBT) examinations with the aid of a custom-built categorical artificial intelligence (AI) system. Materials and Methods A fully balanced multireader, multicase reader study was conducted to compare the performance of 18 radiologists (nine general radiologists and nine breast imaging specialists) reading 240 retrospectively collected screening DBT mammograms (mean patient age, 59.8 years ± 11.3 [SD]; 100% women), acquired between August 2016 and March 2019, with and without the aid of a custom-built categorical AI system. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity across general radiologists and breast imaging specialists reading with versus without AI were assessed. Reader performance was also analyzed as a function of breast cancer characteristics and patient subgroups. Results Every radiologist demonstrated improved interpretation performance when reading with versus without AI, with an average AUC of 0.93 versus 0.87, demonstrating a difference in AUC of 0.06 (95% CI: 0.04, 0.08; P < .001). Improvement in AUC was observed for both general radiologists (difference of 0.08; P < .001) and breast imaging specialists (difference of 0.04; P < .001) and across all cancer characteristics (lesion type, lesion size, and pathology) and patient subgroups (race and ethnicity, age, and breast density) examined. Conclusion A categorical AI system helped improve overall radiologist interpretation performance of DBT screening mammograms for both general radiologists and breast imaging specialists and across various patient subgroups and breast cancer characteristics. Keywords: Computer-aided Diagnosis, Screening Mammography, Digital Breast Tomosynthesis, Breast Cancer, Screening, Convolutional Neural Network (CNN), Artificial Intelligence Supplemental material is available for this article. © RSNA, 2024.

Digital breast tomosynthesis in mammographic screening: false negative cancer cases in the To-Be 1 trial

OBJECTIVES

The randomized controlled trial comparing digital breast tomosynthesis and synthetic 2D mammograms (DBT + SM) versus digital mammography (DM) (the To-Be 1 trial), 2016-2017, did not result in higher cancer detection for DBT + SM. We aimed to determine if negative cases prior to interval and consecutive screen-detected cancers from DBT + SM were due to interpretive error.

METHODS

Five external breast radiologists performed the individual blinded review of 239 screening examinations (90 true negative, 39 false positive, 19 prior to interval cancer, and 91 prior to consecutive screen-detected cancer) and the informed consensus review of examinations prior to interval and screen-detected cancers (n = 110). The reviewers marked suspicious findings with a score of 1-5 (probability of malignancy). A case was false negative if ≥ 2 radiologists assigned the cancer site with a score of ≥ 2 in the blinded review and if the case was assigned as false negative by a consensus in the informed review.

RESULTS

In the informed review, 5.3% of examinations prior to interval cancer and 18.7% prior to consecutive round screen-detected cancer were considered false negative. In the blinded review, 10.6% of examinations prior to interval cancer and 42.9% prior to consecutive round screen-detected cancer were scored ≥ 2. A score of ≥ 2 was assigned to 47.8% of negative and 89.7% of false positive examinations.

CONCLUSIONS

The false negative rates were consistent with those of prior DM reviews, indicating that the lack of higher cancer detection for DBT + SM versus DM in the To-Be 1 trial is complex and not due to interpretive error alone.

CRITICAL RELEVANCE STATEMENT

The randomized controlled trial on digital breast tomosynthesis and synthetic 2D mammograms (DBT) and digital mammography (DM), 2016-2017, showed no difference in cancer detection for the two techniques. The rates of false negative screening examinations prior to interval and consecutive screen-detected cancer for DBT were consistent with the rates in prior DM reviews, indicating that the non-superior DBT performance in the trial might not be due to interpretive error alone.

KEY POINTS

• Screening with digital breast tomosynthesis (DBT) did not result in a higher breast cancer detection rate compared to screening with digital mammography (DM) in the To-Be 1 trial. • The false negative rates for examinations prior to interval and consecutive screen-detected cancer for DBT were determined in the trial to test if the lack of differences was due to interpretive error. • The false negative rates were consistent with those of prior DM reviews, indicating that the lack of higher cancer detection for DBT versus DM was complex and not due to interpretive error alone.

Population Attributable Risk of Advanced-Stage Breast Cancer by Race and Ethnicity

Importance

Advanced-stage breast cancer rates vary by race and ethnicity, with Black women having a 2-fold higher rate than White women among regular screeners. Clinical risk factors that explain a large proportion of advanced breast cancers by race and ethnicity are unknown.

Objective

To evaluate the population attributable risk proportions (PARPs) for advanced-stage breast cancer (prognostic pathologic stage IIA or higher) associated with clinical risk factors among routinely screened premenopausal and postmenopausal women by race and ethnicity.

Design, Setting, and Participants

This cohort study used data collected prospectively from Breast Cancer Surveillance Consortium community-based breast imaging facilities from January 2005 to June 2018. Participants were women aged 40 to 74 years undergoing 3 331 740 annual (prior screening within 11-18 months) or biennial (prior screening within 19-30 months) screening mammograms associated with 1815 advanced breast cancers diagnosed within 2 years of screening examinations. Data analysis was performed from September 2022 to August 2023.

Exposures

Heterogeneously or extremely dense breasts, first-degree family history of breast cancer, overweight/obesity (body mass index >25.0), history of benign breast biopsy, and screening interval (biennial vs annual) stratified by menopausal status and race and ethnicity (Asian or Pacific Islander, Black, Hispanic/Latinx, White, other/multiracial).

Main Outcomes and Measures

PARPs for advanced breast cancer.

Results

Among 904 615 women, median (IQR) age was 57 (50-64) years. Of the 3 331 740 annual or biennial screening mammograms, 10.8% were for Asian or Pacific Islander women; 9.5% were for Black women; 5.3% were for Hispanic/Latinx women; 72.0% were for White women; and 2.0% were for women of other races and ethnicities, including those who were Alaska Native, American Indian, 2 or more reported races, or other. Body mass index PARPs were larger for postmenopausal vs premenopausal women (30% vs 22%) and highest for postmenopausal Black (38.6%; 95% CI, 32.0%-44.8%) and Hispanic/Latinx women (31.8%; 95% CI, 25.3%-38.0%) and premenopausal Black women (30.3%; 95% CI, 17.7%-42.0%), with overall prevalence of having overweight/obesity highest in premenopausal Black (84.4%) and postmenopausal Black (85.1%) and Hispanic/Latinx women (72.4%). Breast density PARPs were larger for premenopausal vs postmenopausal women (37% vs 24%, respectively) and highest among premenopausal Asian or Pacific Islander (46.6%; 95% CI, 37.9%-54.4%) and White women (39.8%; 95% CI, 31.7%-47.3%) whose prevalence of dense breasts was high (62%-79%). For premenopausal and postmenopausal women, PARPs were small for family history of breast cancer (5%-8%), history of breast biopsy (7%-12%), and screening interval (2.1%-2.3%).

Conclusions and Relevance

In this cohort study among routinely screened women, the proportion of advanced breast cancers attributed to biennial vs annual screening was small. To reduce the number of advanced breast cancer diagnoses, primary prevention should focus on interventions that shift patients with overweight and obesity to normal weight.

Artificial Intelligence-Driven Mammography-Based Future Breast Cancer Risk Prediction: A Systematic Review

PURPOSE

To summarize the literature regarding the performance of mammography-image based artificial intelligence (AI) algorithms, with and without additional clinical data, for future breast cancer risk prediction.

MATERIALS AND METHODS

A systematic literature review was performed using six databases (medRixiv, bioRxiv, Embase, Engineer Village, IEEE Xplore, and PubMed) from 2012 through September 30, 2022. Studies were included if they used real-world screening mammography examinations to validate AI algorithms for future risk prediction based on images alone or in combination with clinical risk factors. The quality of studies was assessed, and predictive accuracy was recorded as the area under the receiver operating characteristic curve (AUC).

RESULTS

Sixteen studies met inclusion and exclusion criteria, of which 14 studies provided AUC values. The median AUC performance of AI image-only models was 0.72 (range 0.62-0.90) compared with 0.61 for breast density or clinical risk factor-based tools (range 0.54-0.69). Of the seven studies that compared AI image-only performance directly to combined image + clinical risk factor performance, six demonstrated no significant improvement, and one study demonstrated increased improvement.

CONCLUSIONS

Early efforts for predicting future breast cancer risk based on mammography images alone demonstrate comparable or better accuracy to traditional risk tools with little or no improvement when adding clinical risk factor data. Transitioning from clinical risk factor-based to AI image-based risk models may lead to more accurate, personalized risk-based screening approaches.

Risk of cancer versus risk of cancer diagnosis? Accounting for diagnostic bias in predictions of breast cancer risk by race and ethnicity

OBJECTIVES

Cancer risk prediction may be subject to detection bias if utilization of screening is related to cancer risk factors. We examine detection bias when predicting breast cancer risk by race/ethnicity.

METHODS

We used screening and diagnosis histories from the Breast Cancer Surveillance Consortium to estimate risk of breast cancer onset and calculated relative risk of onset and diagnosis for each racial/ethnic group compared with non-Hispanic White women.

RESULTS

Of 104,073 women aged 40-54 receiving their first screening mammogram at a Breast Cancer Surveillance Consortium facility between 2000 and 2018, 10.2% (n = 10,634) identified as Asian, 10.9% (n = 11,292) as Hispanic, and 8.4% (n = 8719) as non-Hispanic Black. Hispanic and non-Hispanic Black women had slightly lower screening frequencies but biopsy rates following a positive mammogram were similar across groups. Risk of cancer diagnosis was similar for non-Hispanic Black and White women (relative risk vs non-Hispanic White = 0.90, 95% CI 0.65 to 1.14) but was lower for Asian (relative risk = 0.70, 95% CI 0.56 to 0.97) and Hispanic women (relative risk = 0.82, 95% CI 0.62 to 1.08). Relative risks of disease onset were 0.78 (95% CI 0.68 to 0.88), 0.70 (95% CI 0.59 to 0.83), and 0.95 (95% CI 0.84 to 1.09) for Asian, Hispanic, and non-Hispanic Black women, respectively.

CONCLUSIONS

Racial/ethnic differences in mammography and biopsy utilization did not induce substantial detection bias; relative risks of disease onset were similar to or modestly different than relative risks of diagnosis. Asian and Hispanic women have lower risks of developing breast cancer than non-Hispanic Black and White women, who have similar risks.

Digital mammography and digital breast tomosynthesis for detecting invasive lobular and ductal carcinoma

PURPOSE

Invasive lobular carcinoma (ILC) is a distinct histological subtype of breast cancer that can make early detection with mammography challenging. We compared imaging performance of digital breast tomosynthesis (DBT) to digital mammography (DM) for diagnoses of ILC, invasive ductal carcinoma (IDC), and invasive mixed carcinoma (IMC) in a screening population.

METHODS

We included screening exams (DM; n = 1,715,249 or DBT; n = 414,793) from 2011 to 2018 among 839,801 women in the Breast Cancer Surveillance Consortium. Examinations were followed for one year to ascertain incident ILC, IDC, or IMC. We measured cancer detection rate (CDR) and interval invasive cancer rate/1000 screening examinations for each histological subtype and stratified by breast density and modality. We calculated relative risk (RR) for DM vs. DBT using log-binomial models to adjust for the propensity of receiving DBT vs. DM.

RESULTS

Unadjusted CDR per 1000 mammograms of ILC overall was 0.33 (95%CI: 0.30-0.36) for DM; 0.45 (95%CI: 0.39-0.52) for DBT, and for women with dense breasts- 0.33 (95%CI: 0.29-0.37) for DM and 0.54 (95%CI: 0.43-0.66) for DBT. Similar results were noted for IDC and IMC. Adjusted models showed a significantly increased RR for cancer detection with DBT compared to DM among women with dense breasts for all three histologies (RR; 95%CI: ILC 1.53; 1.09-2.14, IDC 1.21; 1.02-1.44, IMC 1.76; 1.30-2.38), but no significant increase among women with non-dense breasts.

CONCLUSION

DBT was associated with higher CDR for ILC, IDC, and IMC for women with dense breasts. Early detection of ILC with DBT may improve outcomes for this distinct clinical entity.

Racial and Ethnic Variation in Diagnostic Mammography Performance among Women Reporting a Breast Lump

BACKGROUND

We evaluated diagnostic mammography among women with a breast lump to determine whether performance varied across racial and ethnic groups.

METHODS

This study included 51,014 diagnostic mammograms performed between 2005 and 2018 in the Breast Cancer Surveillance Consortium among Asian/Pacific Islander (12%), Black (7%), Hispanic/Latina (6%), and White (75%) women reporting a lump. Breast cancers occurring within 1 year were ascertained from cancer registry linkages. Multivariable regression was used to adjust performance statistic comparisons for breast cancer risk factors, mammogram modality, demographics, additional imaging, and imaging facility.

RESULTS

Cancer detection rates were highest among Asian/Pacific Islander [per 1,000 exams, 84.2 (95% confidence interval (CI): 72.0-98.2)] and Black women [81.4 (95% CI: 69.4-95.2)] and lowest among Hispanic/Latina women [42.9 (95% CI: 34.2-53.6)]. Positive predictive values (PPV) were higher among Black [37.0% (95% CI: 31.2-43.3)] and White [37.0% (95% CI: 30.0-44.6)] women and lowest among Hispanic/Latina women [22.0% (95% CI: 17.2-27.7)]. False-positive results were most common among Asian/Pacific Islander women [per 1,000 exams, 183.9 (95% CI: 126.7-259.2)] and lowest among White women [112.4 (95% CI: 86.1-145.5)]. After adjustment, false-positive and cancer detection rates remained higher for Asian/Pacific Islander and Black women (vs. Hispanic/Latina and White). Adjusted PPV was highest among Asian/Pacific Islander women.

CONCLUSIONS

Among women with a lump, Asian/Pacific Islander and Black women were more likely to have cancer detected and more likely to receive a false-positive result compared with White and Hispanic/Latina women.

IMPACT

Strategies for optimizing diagnostic mammography among women with a lump may vary by racial/ethnic group, but additional factors that influence performance differences need to be identified. See related In the Spotlight, p. 1479.

Early screening outcomes before, during, and after a randomized controlled trial with digital breast tomosynthesis

PURPOSE

To describe and compare early screening outcomes before, during and after a randomized controlled trial with digital breast tomosynthesis (DBT) including synthetic 2D mammography versus standard digital mammography (DM) (To-Be 1) and a follow-up cohort study using DBT (To-Be 2).

METHODS

Retrospective results of 125,020 screening examinations from four consecutive screening rounds performed in 2014-2021 were described and compared for pre-To-Be 1 (DM), To-Be 1 (DM or DBT), To-Be 2 (DBT), and post-To-Be 2 (DM) cohorts. Descriptive analyses of rates of recall, biopsy, screen-detected and interval cancer, distribution of histopathologic tumor characteristics and time spent on image interpretation and consensus were presented for the four rounds including five cohorts, one cohort in each screening round except for the To-Be 1 trail, which included a DBT and a DM cohort. Odds ratios (OR) with 95% CIs was calculated for recall and cancer detection rates.

RESULTS

Rate of screen-detected cancer was 0.90% for women screened with DBT in To-Be 2 and 0.64% for DM in pre-To-Be 1. The rates did not differ for the To-Be 1 DM (0.61%), To-Be 1 DBT (0.66%) and post-To-Be 2 DM (0.67%) cohorts. The interval cancer rates ranged between 0.13% and 0.20%. The distribution of histopathologic tumor characteristics did not differ between the cohorts.

CONCLUSIONS

Screening all women with DBT following a randomized controlled trial in an organized, population-based screening program showed a temporary increase in the rate of screen-detected cancer.

Strategies for Mitigating Consequences of Federal Breast Density Notifications

This Viewpoint describes new federal updates to screening mammography rules and recommends strategies for mitigating potential consequences of the rules.

Comparative Performance of Contrast-enhanced Mammography, Abbreviated Breast MRI, and Standard Breast MRI for Breast Cancer Screening

Background Contrast-enhanced mammography (CEM) and abbreviated breast MRI (ABMRI) are emerging alternatives to standard MRI for supplemental breast cancer screening. Purpose To compare the diagnostic performance of CEM, ABMRI, and standard MRI. Materials and Methods This single-institution, prospective, blinded reader study included female participants referred for breast MRI from January 2018 to June 2021. CEM was performed within 14 days of standard MRI; ABMRI was produced from standard MRI images. Two readers independently interpreted each CEM and ABMRI after a washout period. Examination-level performance metrics calculated were recall rate, cancer detection, and false-positive biopsy recommendation rates per 1000 examinations and sensitivity, specificity, and positive predictive value of biopsy recommendation. Bootstrap and permutation tests were used to calculate 95% CIs and compare modalities. Results Evaluated were 492 paired CEM and ABMRI interpretations from 246 participants (median age, 51 years; IQR, 43-61 years). On 49 MRI scans with lesions recommended for biopsy, nine lesions showed malignant pathology. No differences in ABMRI and standard MRI performance were identified. Compared with standard MRI, CEM demonstrated significantly lower recall rate (14.0% vs 22.8%; difference, -8.7%; 95% CI: -14.0, -3.5), lower false-positive biopsy recommendation rate per 1000 examinations (65.0 vs 162.6; difference, -97.6; 95% CI: -146.3, -50.8), and higher specificity (87.8% vs 80.2%; difference, 7.6%; 95% CI: 2.3, 13.1). Compared with standard MRI, CEM had significantly lower cancer detection rate (22.4 vs 36.6; difference, -14.2; 95% CI: -28.5, -2.0) and sensitivity (61.1% vs 100%; difference, -38.9%; 95% CI: -66.7, -12.5). The performance differences between CEM and ABMRI were similar to those observed between CEM and standard MRI. Conclusion ABMRI had comparable performance to standard MRI and may support more efficient MRI screening. CEM had lower recall and higher specificity compared with standard MRI or ABMRI, offset by lower cancer detection rate and sensitivity compared with standard MRI. These trade-offs warrant further consideration of patient population characteristics before widespread screening with CEM. Clinical trial registration no. NCT03517813 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Chang in this issue.

Variability Among Breast Cancer Risk Classification Models When Applied at the Level of the Individual Woman

BACKGROUND

Breast cancer risk models guide screening and chemoprevention decisions, but the extent and effect of variability among models, particularly at the individual level, is uncertain.

OBJECTIVE

To quantify the accuracy and disagreement between commonly used risk models in categorizing individual women as average vs. high risk for developing invasive breast cancer.

DESIGN

Comparison of three risk prediction models: Breast Cancer Risk Assessment Tool (BCRAT), Breast Cancer Surveillance Consortium (BCSC) model, and International Breast Intervention Study (IBIS) model.

SUBJECTS

Women 40 to 74 years of age presenting for screening mammography at a multisite health system between 2011 and 2015, with 5-year follow-up for cancer outcome.

MAIN MEASURES

Comparison of model discrimination and calibration at the population level and inter-model agreement for 5-year breast cancer risk at the individual level using two cutoffs (≥ 1.67% and ≥ 3.0%).

KEY RESULTS

A total of 31,115 women were included. When using the ≥ 1.67% threshold, more than 21% of women were classified as high risk for developing breast cancer in the next 5 years by one model, but average risk by another model. When using the ≥ 3.0% threshold, more than 5% of women had disagreements in risk severity between models. Almost half of the women (46.6%) were classified as high risk by at least one of the three models (e.g., if all three models were applied) for the threshold of ≥ 1.67%, and 11.1% were classified as high risk for ≥ 3.0%. All three models had similar accuracy at the population level.

CONCLUSIONS

Breast cancer risk estimates for individual women vary substantially, depending on which risk assessment model is used. The choice of cutoff used to define high risk can lead to adverse effects for screening, preventive care, and quality of life for misidentified individuals. Clinicians need to be aware of the high false-positive and false-negative rates and variation between models when talking with patients.

Digital Breast Tomosynthesis versus Digital Mammography Screening Performance on Successive Screening Rounds from the Breast Cancer Surveillance Consortium

Background Prior cross-sectional studies have observed that breast cancer screening with digital breast tomosynthesis (DBT) has a lower recall rate and higher cancer detection rate compared with digital mammography (DM). Purpose To evaluate breast cancer screening outcomes with DBT versus DM on successive screening rounds. Materials and Methods In this retrospective cohort study, data from 58 breast imaging facilities in the Breast Cancer Surveillance Consortium were collected. Analysis included women aged 40-79 years undergoing DBT or DM screening from 2011 to 2020. Absolute differences in screening outcomes by modality and screening round were estimated during the study period by using generalized estimating equations with marginal standardization to adjust for differences in women's risk characteristics across modality and round. Results A total of 523 485 DBT examinations (mean age of women, 58.7 years ± 9.7 [SD]) and 1 008 123 DM examinations (mean age, 58.4 years ± 9.8) among 504 863 women were evaluated. DBT and DM recall rates decreased with successive screening round, but absolute recall rates in each round were significantly lower with DBT versus DM (round 1 difference, -3.3% [95% CI: -4.6, -2.1] [P < .001]; round 2 difference, -1.8% [95% CI: -2.9, -0.7] [P = .003]; round 3 or above difference, -1.2% [95% CI: -2.4, -0.1] [P = .03]). DBT had significantly higher cancer detection (difference, 0.6 per 1000 examinations [95% CI: 0.2, 1.1]; P = .009) compared with DM only for round 3 and above. There were no significant differences in interval cancer rate (round 1 difference, 0.00 per 1000 examinations [95% CI: -0.24, 0.30] [P = .96]; round 2 or above difference, 0.04 [95% CI: -0.19, 0.31] [P = .76]) or total advanced cancer rate (round 1 difference, 0.00 per 1000 examinations [95% CI: -0.15, 0.19] [P = .94]; round 2 or above difference, -0.06 [95% CI: -0.18, 0.11] [P = .43]). Conclusion DBT had lower recall rates and could help detect more cancers than DM across three screening rounds, with no difference in interval or advanced cancer rates. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Skaane in this issue.

Mammographic density and interval cancers in mammographic screening: Moving towards more personalized screening

PURPOSE

The European Society on Breast Imaging has recommended supplemental magnetic resonance imaging (MRI) every two to four years for women with mammographically dense breasts. This may not be feasible in many screening programs. Also, the European Commission Initiative on Breast Cancer suggests not implementing screening with MRI. By analyzing interval cancers and time from screening to diagnosis by density, we present alternative screening strategies for women with dense breasts.

METHODS

Our BreastScreen Norway cohort included 508 536 screening examinations, including 3125 screen-detected and 945 interval breast cancers. Time from screening to interval cancer was stratified by density measured by an automated software and classified into Volpara Density Grades (VDGs) 1-4. Examinations with volumetric density ≤3.4% were categorized as VDG1, 3.5%-7.4% as VDG2, 7.5%-15.4% as VDG3, and ≥15.5% as VDG4. Interval cancer rates were also determined by continuous density measures.

RESULTS

Median time from screening to interval cancer was 496 (IQR: 391-587) days for VDG1, 500 (IQR: 350-616) for VDG2, 482 (IQR: 309-595) for VDG3 and 427 (IQR: 266-577) for VDG4. A total of 35.9% of the interval cancers among VDG4 were detected within the first year of the biennial screening interval. For VDG2, 26.3% were detected within the first year. The highest annual interval cancer rate (2.7 per 1000 examinations) was observed for VDG4 in the second year of the biennial interval.

CONCLUSIONS

Annual screening of women with extremely dense breasts may reduce the interval cancer rate and increase program-wide sensitivity, especially in settings where supplemental MRI screening is not feasible.

Community-based Participatory Research: A Practical Guide for Radiologists

Community-based participatory research (CBPR) is defined by the Kellogg Community Health Scholars Program as a collaborative process that equitably involves all partners in the research process and recognizes the unique strengths that each community member brings. The CBPR process begins with a research topic of importance to the community, with the goal of combining knowledge and action with social change to improve community health and eliminate health disparities. CBPR engages and empowers affected communities to collaborate in defining the research question; sharing the study design process; collecting, analyzing, and disseminating the data; and implementing solutions. A CBPR approach in radiology has several potential applications, including removing limitations to high-quality imaging, improving secondary prevention, identifying barriers to technology access, and increasing diversity in the research participation for clinical trials. The authors provide an overview with the definitions of CBPR, explain how to conduct CBPR, and illustrate its applications in radiology. Finally, the challenges of CBPR and useful resources are discussed in detail. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

National Performance Benchmarks for Screening Digital Breast Tomosynthesis: Update from the Breast Cancer Surveillance Consortium

Background It is important to establish screening mammography performance benchmarks for quality improvement efforts. Purpose To establish performance benchmarks for digital breast tomosynthesis (DBT) screening and evaluate performance trends over time in U.S. community practice. Materials and Methods In this retrospective study, DBT screening examinations were collected from five Breast Cancer Surveillance Consortium (BCSC) registries between 2011 and 2018. Performance measures included abnormal interpretation rate (AIR), cancer detection rate (CDR), sensitivity, specificity, and false-negative rate (FNR) and were calculated based on the American College of Radiology Breast Imaging Reporting and Data System, fifth edition, and compared with concurrent BCSC DM screening examinations, previously published BCSC and National Mammography Database benchmarks, and expert opinion acceptable performance ranges. Benchmarks were derived from the distribution of performance measures across radiologists (n = 84 or n = 73 depending on metric) and were presented as percentiles. Results A total of 896 101 women undergoing 2 301 766 screening examinations (458 175 DBT examinations [median age, 58 years; age range, 18-111 years] and 1 843 591 DM examinations [median age, 58 years; age range, 18-109 years]) were included in this study. DBT screening performance measures were as follows: AIR, 8.3% (95% CI: 7.5, 9.3); CDR per 1000 screens, 5.8 (95% CI: 5.4, 6.1); sensitivity, 87.4% (95% CI: 85.2, 89.4); specificity, 92.2% (95% CI: 91.3, 93.0); and FNR per 1000 screens, 0.8 (95% CI: 0.7, 1.0). When compared with BCSC DM screening examinations from the same time period and previously published BCSC and National Mammography Database performance benchmarks, all performance measures were higher for DBT except sensitivity and FNR, which were similar to concurrent and prior DM performance measures. The following proportions of radiologists achieved acceptable performance ranges with DBT: 97.6% for CDR, 91.8% for sensitivity, 75.0% for AIR, and 74.0% for specificity. Conclusion In U.S. community practice, large proportions of radiologists met acceptable performance ranges for screening performance metrics with DBT. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Lee and Moy in this issue.

Breast Imaging Research: Tips for Obtaining Funding and Sustaining a Successful Career

Many factors are involved in the successful development of early career breast imaging radiologists into independent investigators conducting impactful research. Key basic prerequisites for success include a motivated and resilient radiologist, institutional and departmental commitment to supporting early career physician-scientists, strong mentorship, and a flexible strategy for extramural funding that accounts for individualized professional goals. In this review, we describe these factors in greater detail, providing a practical overview for residents, fellows, and junior faculty who are interested in an academic career as a breast imaging radiologist engaged in original scientific research. We also describe the essential pieces of grant applications and summarize the professional milestones for early career physician-scientists as they look toward promotion to associate professor and sustained extramural funding.

Prioritizing Screening Mammograms for Immediate Interpretation and Diagnostic Evaluation on the Basis of Risk for Recall

PURPOSE

The aim of this study was to develop a prioritization strategy for scheduling immediate screening mammographic interpretation and possible diagnostic evaluation.

METHODS

A population-based cohort with screening mammograms performed from 2012 to 2020 at 126 radiology facilities from 7 Breast 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.

RESULTS

The 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 <50 years of age with dense breasts accounted for 20.3% of mammograms and 33.9% of recalls (efficiency ratio = 1.7). Results including facility-level characteristics were similar.

CONCLUSIONS

Prioritizing women with baseline mammograms or ≥5 years since prior mammogram for immediate interpretation and possible diagnostic evaluation could considerably reduce the number of women needing to return for diagnostic imaging at another visit.

External Validation of an Ensemble Model for Automated Mammography Interpretation by Artificial Intelligence

Importance

With 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.

Objective

To 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 Participants

In 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 Measures

Performance 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).

Results

Evaluated 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 < .001) and specificity (0.803 [95% CI, 0.734-0.861] vs 0.945 [95% CI, 0.936-0.954]; P < .001) than the radiologist in women with a prior history of breast cancer and Hispanic women (0.894 [95% CI, 0.873-0.910] vs 0.926 [95% CI, 0.919-0.933]; P = .004).

Conclusions and Relevance

This 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.

Radiologist Preferences for Artificial Intelligence-Based Decision Support During Screening Mammography Interpretation

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 <25% of examinations marked) and AI markup appeared at the end of the hanging protocol after radiologists complete their independent review. For AI-based risk prediction, radiologists preferred AI models using both mammography images and clinical data. Overall, 46% to 60% intended to adopt any of the AI tools presented in the study; 26% to 33% approached AI enthusiastically but were deterred if the features did not align with their preferences.

CONCLUSION

Although most radiologists want to use AI-based decision support, short-term uptake may be maximized by implementing tools that meet the preferences of dissuadable users.

Multilevel Factors Associated With Time to Biopsy After Abnormal Screening Mammography Results by Race and Ethnicity

Importance

Diagnostic 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.

Objective

To 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 Participants

This 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.

Exposures

Individual-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 Measures

The 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.

Results

A 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 Relevance

In 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.

Diagnostic Mammography Performance across Racial and Ethnic Groups in a National Network of Community-Based Breast Imaging Facilities

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.

Association of Screening With Digital Breast Tomosynthesis vs Digital Mammography With Risk of Interval Invasive and Advanced Breast Cancer

Importance

Digital breast tomosynthesis (DBT) was developed with the expectation of improving cancer detection in women with dense breasts. Studies are needed to evaluate interval invasive and advanced breast cancer rates, intermediary outcomes related to breast cancer mortality, by breast density and breast cancer risk.

Objective

To evaluate whether DBT screening is associated with a lower likelihood of interval invasive cancer and advanced breast cancer compared with digital mammography by extent of breast density and breast cancer risk.

Design, Setting, and Participants

Cohort study of 504 427 women aged 40 to 79 years who underwent 1 003 900 screening digital mammography and 375 189 screening DBT examinations from 2011 through 2018 at 44 US Breast Cancer Surveillance Consortium (BCSC) facilities with follow-up for cancer diagnoses through 2019 by linkage to state or regional cancer registries.

Exposures

Breast Imaging Reporting and Data System (BI-RADS) breast density; BCSC 5-year breast cancer risk.

Main Outcomes and Measures

Rates per 1000 examinations of interval invasive cancer within 12 months of screening mammography and advanced breast cancer (prognostic pathologic stage II or higher) within 12 months of screening mammography, both estimated with inverse probability weighting.

Results

Among 504 427 women in the study population, the median age at time of mammography was 58 years (IQR, 50-65 years). Interval invasive cancer rates per 1000 examinations were not significantly different for DBT vs digital mammography (overall, 0.57 vs 0.61, respectively; difference, -0.04; 95% CI, -0.14 to 0.06; P = .43) or among all the 836 250 examinations with BCSC 5-year risk less than 1.67% (low to average-risk) or all the 413 061 examinations with BCSC 5-year risk of 1.67% or higher (high risk) across breast density categories. Advanced cancer rates were not significantly different for DBT vs digital mammography among women at low to average risk or at high risk with almost entirely fatty, scattered fibroglandular densities, or heterogeneously dense breasts. Advanced cancer rates per 1000 examinations were significantly lower for DBT vs digital mammography for the 3.6% of women with extremely dense breasts and at high risk of breast cancer (13 291 examinations in the DBT group and 31 300 in the digital mammography group; 0.27 vs 0.80 per 1000 examinations; difference, -0.53; 95% CI, -0.97 to -0.10) but not for women at low to average risk (10 611 examinations in the DBT group and 37 796 in the digital mammography group; 0.54 vs 0.42 per 1000 examinations; difference, 0.12; 95% CI, -0.09 to 0.32).

Conclusions and Relevance

Screening with DBT vs digital mammography was not associated with a significant difference in risk of interval invasive cancer and was associated with a significantly lower risk of advanced breast cancer among the 3.6% of women with extremely dense breasts and at high risk of breast cancer. No significant difference was observed in the 96.4% of women with nondense breasts, heterogeneously dense breasts, or with extremely dense breasts not at high risk.

Artificial Intelligence Evaluation of 122 969 Mammography Examinations from a Population-based 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. © RSNA, 2022.

Artificial Intelligence Evaluation of 122 969 Mammography Examinations from a Population-based 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. © RSNA, 2022.

Cumulative Probability of False-Positive Results After 10 Years of Screening With Digital Breast Tomosynthesis vs Digital Mammography

Importance

Breast cancer screening with digital breast tomosynthesis may decrease false-positive results compared with digital mammography.

Objective

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.

Design, Setting, and Participants

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.

Exposures

Screening modality, screening interval, age, and Breast Imaging Reporting and Data System breast density.

Main Outcomes and Measures

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.

Results

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).

Conclusions and Relevance

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.

Breast biopsy patterns and findings among older women undergoing screening mammography: The role of age and comorbidity

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 < 0.001) and increased with Charlson Comorbidity Score (CCS = 0:14.4 (13.5-15.3), CCS = 1:16.6 (15.2-18.1), CCS ≥2:19.0 (16.9-21.5), p_trend < 0.001).Biopsy rates increased with CCS at ages 66-74 and 75-84 but not 85-94. Core and surgical biopsy rates increased with CCS at ages 66-74 only. For each biopsy type, the yield of invasive breast cancer increased with age irrespective of comorbidity.

DISCUSSION

Women aged 66-84 with significant comorbidity in a breast cancer screening population had higher breast biopsy rates and similar rates of invasive breast cancer diagnosis than their counterparts with lower comorbidity. A considerable proportion of these diagnoses may represent overdiagnoses, given the high competing risk of death from non-breast-cancer causes among older women.

Independent External Validation of Artificial Intelligence Algorithms for Automated Interpretation of Screening Mammography: A Systematic Review

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.