Interval breast cancer rates for digital breast tomosynthesis versus digital mammography population screening: An individual participant data meta-analysis

Interval Cancers in Understanding Screening Outcomes

Interval breast cancers are not detected at routine screening and are diagnosed in the interval between screening examinations. A variety of factors contribute to interval cancers, including patient and tumor characteristics as well as the screening technique and frequency. The interval cancer rate is an important metric by which the effectiveness of screening may be assessed and may serve as a surrogate for mortality benefit.

Interval cancer in the Córdoba Breast Tomosynthesis Screening Trial (CBTST): comparison of digital breast tomosynthesis plus digital mammography to digital mammography alone

PURPOSE

This work aims to compare the interval cancer rate and interval cancer characteristics between women screened with digital breast tomosynthesis (DBT) + digital mammography (DM) and those screened with DM alone.

METHODS

The interval cancer rate and interval cancer characteristics of the study population included in the Córdoba Breast Tomosynthesis Screening Trial (CBTST) were compared to a contemporary control population screened with DM. The tumour characteristics of screen-detected and interval cancers were also compared. Contingency tables were used to compare interval cancer rates. The chi-square test and Fisher's exact test were used to compare the qualitative characteristics of the cancers whereas Student's t test and the Mann-Whitney U test were used to analyse quantitative features.

RESULTS

A total of 16,068 screening exams with DBT + DM were conducted within the CBTST (mean age 57.59 ± 5.9 [SD]) between January 2015 and December 2016 (study population). In parallel, 23,787 women (mean age 58.89 ± 5.9 standard deviation [SD]) were screened with DM (control population). The interval cancer rate was lower in the study population than in the control population (15 [0.93‰; 95% confidence interval (CI): 0.73, 1.14] vs 43 [1.8‰; 95% CI: 1.58, 2.04] respectively; p = 0.045). The difference in rate was more marked in women with dense breasts (0.95‰ in the study population vs 3.17‰ in the control population; p = 0.031). Interval cancers were smaller in the study population than in the control population (p = 0.031).

CONCLUSIONS

The interval cancer rate was lower in women screened with DBT + DM compared to those screened with DM alone. These differences were more pronounced in women with dense breasts.

CLINICAL RELEVANCE STATEMENT

Women screened using tomosynthesis and digital mammography had a lower rate of interval cancer than women screened with digital mammography, with the greatest difference in the interval cancer rate observed in women with dense breasts.

KEY POINTS

• The interval cancer rate was lower in the study population (digital breast tomosynthesis [DBT] + digital mammography [DM]) than in the control population (DM). • The difference in interval cancer rates was more pronounced in women with dense breasts. • Interval cancers were smaller in the study population (DBT + DM) than in the control population (DM).

Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (MASAI): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study

BACKGROUND

Retrospective studies have shown promising results using artificial intelligence (AI) to improve mammography screening accuracy and reduce screen-reading workload; however, to our knowledge, a randomised trial has not yet been conducted. We aimed to assess the clinical safety of an AI-supported screen-reading protocol compared with standard screen reading by radiologists following mammography.

METHODS

In this randomised, controlled, population-based trial, women aged 40-80 years eligible for mammography screening (including general screening with 1·5-2-year intervals and annual screening for those with moderate hereditary risk of breast cancer or a history of breast cancer) at four screening sites in Sweden were informed about the study as part of the screening invitation. Those who did not opt out were randomly allocated (1:1) to AI-supported screening (intervention group) or standard double reading without AI (control group). Screening examinations were automatically randomised by the Picture Archive and Communications System with a pseudo-random number generator after image acquisition. The participants and the radiographers acquiring the screening examinations, but not the radiologists reading the screening examinations, were masked to study group allocation. The AI system (Transpara version 1.7.0) provided an examination-based malignancy risk score on a 10-level scale that was used to triage screening examinations to single reading (score 1-9) or double reading (score 10), with AI risk scores (for all examinations) and computer-aided detection marks (for examinations with risk score 8-10) available to the radiologists doing the screen reading. Here we report the prespecified clinical safety analysis, to be done after 80 000 women were enrolled, to assess the secondary outcome measures of early screening performance (cancer detection rate, recall rate, false positive rate, positive predictive value [PPV] of recall, and type of cancer detected [invasive or in situ]) and screen-reading workload. Analyses were done in the modified intention-to-treat population (ie, all women randomly assigned to a group with one complete screening examination, excluding women recalled due to enlarged lymph nodes diagnosed with lymphoma). The lowest acceptable limit for safety in the intervention group was a cancer detection rate of more than 3 per 1000 participants screened. The trial is registered with ClinicalTrials.gov, NCT04838756, and is closed to accrual; follow-up is ongoing to assess the primary endpoint of the trial, interval cancer rate.

FINDINGS

Between April 12, 2021, and July 28, 2022, 80 033 women were randomly assigned to AI-supported screening (n=40 003) or double reading without AI (n=40 030). 13 women were excluded from the analysis. The median age was 54·0 years (IQR 46·7-63·9). Race and ethnicity data were not collected. AI-supported screening among 39 996 participants resulted in 244 screen-detected cancers, 861 recalls, and a total of 46 345 screen readings. Standard screening among 40 024 participants resulted in 203 screen-detected cancers, 817 recalls, and a total of 83 231 screen readings. Cancer detection rates were 6·1 (95% CI 5·4-6·9) per 1000 screened participants in the intervention group, above the lowest acceptable limit for safety, and 5·1 (4·4-5·8) per 1000 in the control group-a ratio of 1·2 (95% CI 1·0-1·5; p=0·052). Recall rates were 2·2% (95% CI 2·0-2·3) in the intervention group and 2·0% (1·9-2·2) in the control group. The false positive rate was 1·5% (95% CI 1·4-1·7) in both groups. The PPV of recall was 28·3% (95% CI 25·3-31·5) in the intervention group and 24·8% (21·9-28·0) in the control group. In the intervention group, 184 (75%) of 244 cancers detected were invasive and 60 (25%) were in situ; in the control group, 165 (81%) of 203 cancers were invasive and 38 (19%) were in situ. The screen-reading workload was reduced by 44·3% using AI.

INTERPRETATION

AI-supported mammography screening resulted in a similar cancer detection rate compared with standard double reading, with a substantially lower screen-reading workload, indicating that the use of AI in mammography screening is safe. The trial was thus not halted and the primary endpoint of interval cancer rate will be assessed in 100 000 enrolled participants after 2-years of follow up.

FUNDING

Swedish Cancer Society, Confederation of Regional Cancer Centres, and the Swedish governmental funding for clinical research (ALF).

Digital Breast Tomosynthesis: A Decade of Practice in Review

Digital breast tomosynthesis (DBT), introduced in 2011, was thought to be a further evolution of full-field digital mammography (DM). Assessing DBT presents unique challenges. The widely variable settings in which DBT has been applied affect outcomes. In initial studies comparing DM-DBT with DM, outcomes for cancer detection rates (CDRs) and recall rates have been mixed. CDR improves most in biennial screening settings, with little or no improvement in annual screening. Recall rates improve most where rates are highest; no improvement is seen in European prospective trials. Adoption of synthesized mammography (SM), derived from the tomosynthesis acquisition and intended to avoid the DM exposure, has been slow because of inferior image quality. Despite this, SM-DBT has shown equivalent outcomes measures to DM-DBT. An important exception is the To-Be randomized controlled trial, which showed that SM-DBT was equivalent to DM in CDR, not better. To date, interval cancer rate, a surrogate for mortality reduction, has not been shown to be improved by DBT. We may have reached the limit of morphological assessment in x-ray technique. Its use may evolve with advancements in technology as use of contrast agents expands, algorithms for SM progress, and tomosynthesis-guided biopsy proliferates. Our expectations of the contributions of DBT will evolve as well.

Artificial intelligence for digital breast tomosynthesis: Impact on diagnostic performance, reading times, and workload in the era of personalized screening

The ultimate goals of the application of artificial intelligence (AI) to digital breast tomosynthesis (DBT) are the reduction of reading times, the increase of diagnostic performance, and the reduction of interval cancer rates. In this review, after outlining the journey from computer-aided detection/diagnosis systems to AI applied to digital mammography (DM), we summarize the results of studies where AI was applied to DBT, noting that long-term advantages of DBT screening and its crucial ability to decrease the interval cancer rate are still under scrutiny. AI has shown the capability to overcome some shortcomings of DBT in the screening setting by improving diagnostic performance and by reducing recall rates (from -2 % to -27 %) and reading times (up to -53 %, with an average 20 % reduction), but the ability of AI to reduce interval cancer rates has not yet been clearly investigated. Prospective validation is needed to assess the cost-effectiveness and real-world impact of AI models assisting DBT interpretation, especially in large-scale studies with low breast cancer prevalence. Finally, we focus on the incoming era of personalized and risk-stratified screening that will first see the application of contrast-enhanced breast imaging to screen women with extremely dense breasts. As the diagnostic advantage of DBT over DM was concentrated in this category, we try to understand if the application of AI to DM in the remaining cohorts of women with heterogeneously dense or non-dense breast could close the gap in diagnostic performance between DM and DBT, thus neutralizing the usefulness of AI application to DBT.

A randomised controlled trial of digital breast tomosynthesis vs digital mammography as primary screening tests: Screening results over subsequent episodes of the Proteus Donna study

Proteus Donna is a randomised controlled trial aimed at prospectively evaluating screening with digital breast tomosynthesis (DBT), including interval cancer detection (ICD) and cancer detection (CD) in the analysis as a cumulative measure over subsequent screening episodes. Consenting women aged 46 to 68 attending the regional Breast Screening Service were randomly assigned to conventional digital mammography (DM, control arm) or DBT in addition to DM (DBT, study arm). At the subsequent round all participants underwent DM. Thirty-six months follow-up allowed for the identification of cancers detected in the subsequent screening and interscreening interval. Relative risk (RR) and 95% confidence interval (95% CI) were computed. Cumulative CD and Nelson-Aalen incidence were analysed over the follow-up period. Between 31 December 2014 and 31 December 2017, 43 022 women were randomised to DM and 30 844 to DBT. At baseline, CD was significantly higher (RR: 1.44, 95% CI: 1.21-1.71) in the study arm. ICD did not differ significantly between the two arms (RR: 0.92, 95% CI: 0.62-1.35). At subsequent screening with DM, the CD was lower (nearly significant) in the study arm (RR: 0.83, 95% CI: 0.65-1.06). Over the follow-up period, the cumulative CD (comprehensive of ICD) was slightly higher in the study arm (RR: 1.15, 95% CI: 1.01-1.31). The Nelson-Aalen cumulative incidence over time remained significantly higher in the study arm for approximately 24 months. Benign lesions detection was higher in the study arm at baseline and lower at subsequent tests. Outcomes are consistent with a lead time gain of DBT compared to DM, with an increase in false positives and moderate overdiagnosis.

Contrast-enhanced Mammography: A Systematic Review and Meta-Analysis of Diagnostic Performance

Background Contrast-enhanced mammography (CEM) is a promising technique for breast cancer detection, but conflicting results have been reported in previous meta-analyses. Purpose To perform a systematic review and meta-analysis of CEM diagnostic performance considering different interpretation methods and clinical settings. Materials and Methods The MEDLINE, EMBASE, Web of Science, and Cochrane Library databases were systematically searched up to July 15, 2021. Prospective and retrospective studies evaluating CEM diagnostic performance with histopathology and/or follow-up as the reference standard were included. Study quality was assessed with the Quality Assessment of Diagnostic Accuracy Studies 2 tool. Summary diagnostic odds ratio and area under the receiver operating characteristic curve were estimated with the hierarchical summary receiver operating characteristic (HSROC) model. Summary estimates of sensitivity and specificity were obtained with the hierarchical bivariate model, pooling studies with the same image interpretation approach or focused on the same findings. Heterogeneity was investigated through meta-regression and subgroup analysis. Results Sixty studies (67 study parts, 11 049 CEM examinations in 10 605 patients) were included. The overall area under the HSROC curve was 0.94 (95% CI: 0.91, 0.96). Pooled diagnostic odds ratio was 55.7 (95% CI: 42.7, 72.7) with high heterogeneity (τ² = 0.3). At meta-regression, CEM interpretation with both low-energy and recombined images had higher sensitivity (95% vs 94%, P < .001) and specificity (81% vs 71%, P = .03) compared with recombined images alone. At subgroup analysis, CEM showed a 95% pooled sensitivity (95% CI: 92, 97) and a 78% pooled specificity (95% CI: 66, 87) from nine studies in patients with dense breasts, while in 10 studies on mammography-detected suspicious findings, CEM had a 92% pooled sensitivity (95% CI: 89, 94) and an 84% pooled specificity (95% CI: 73, 91). Conclusion Contrast-enhanced mammography demonstrated high performance in breast cancer detection, especially with joint interpretation of low-energy and recombined images. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Bahl in this issue.