Breast density effect on the sensitivity of digital screening mammography in a UK cohort.

OBJECTIVES: To assess the performance of breast cancer screening by category of breast density and age in a UK screening cohort. METHODS: Raw full-field digital mammography data from a single site in the UK, forming a consecutive 3-year cohort of women aged 50 to 70 years from 2016 to 2018, were obtained retrospectively. Breast density was assessed using Volpara software. Examinations were grouped by density category and age group (50-60 and 61-70 years) to analyse screening performance. Statistical analysis was performed to determine the association between density categories and age groups. Volumetric breast density was assessed as a binary classifier of interval cancers (ICs) to find an optimal density threshold. RESULTS: Forty-nine thousand nine-hundred forty-eight screening examinations (409 screen-detected cancers (SDCs) and 205 ICs) were included in the analysis. Mammographic sensitivity, SDC/(SDC + IC), decreased with increasing breast density from 75.0% for density a (p = 0.839, comparisons made to category b), to 73.5%, 59.8% (p = 0.001), and 51.3% (p < 0.001) in categories b, c, and d, respectively. IC rates were highest in the densest categories with rates of 1.8 (p = 0.039), 3.2, 5.7 (p < 0.001), and 7.9 (p < 0.001) per thousand for categories a, b, c, and d, respectively. The recall rate increased with breast density, leading to more false positive recalls, especially in the younger age group. There was no significant difference between the optimal density threshold found, 6.85, and that Volpara defined as the b/c boundary, 7.5. CONCLUSIONS: The performance of screening is significantly reduced with increasing density with IC rates in the densest category four times higher than in women with fatty breasts. False positives are a particular issue for the younger subgroup without prior examinations. CLINICAL RELEVANCE STATEMENT: In women attending screening there is significant underdiagnosis of breast cancer in those with dense breasts, most marked in the highest density category but still three times higher than in women with fatty breasts in the second highest category. KEY POINTS: Breast density can mask cancers leading to underdiagnosis on mammography. Interval cancer rate increased with breast density categories 'a' to 'd'; 1.8 to 7.9 per thousand. Recall rates increased with increasing breast density, leading to more false positive recalls.

Mammography Breast Cancer Screening Triage Using Deep Learning: A UK Retrospective Study.

Background Breast screening enables early detection of cancers; however, most women have normal mammograms, resulting in repetitive and resource-intensive reading tasks. Purpose To investigate if deep learning (DL) algorithms can be used to triage mammograms by identifying normal results to reduce workload or flag cancers that may be overlooked. Materials and Methods In this retrospective study, three commercial DL algorithms were investigated using consecutive mammograms from two UK Breast Screening Program sites from January 2015 to December 2017 and January 2017 to December 2018 on devices from two mammography vendors. Normal mammograms with a 3-year follow-up and histopathologically proven cancer detected at screening, the subsequent round, or in the 3-year interval were included. Two algorithm thresholds were set: in scenario A, 99.0% sensitivity for rule-out triage to a lone reader, and in scenario B, approximately 1.0% additional recall providing a rule-in triage for further assessment. Both thresholds were then applied to the screening workflow in scenario C. The sensitivity and specificity were used to assess the overall predictive performance of each DL algorithm. Results The data set comprised 78 849 patients (median age, 59 years [IQR, 53-63 years]) and 887 screening-detected, 439 interval, and 688 subsequent screening round-detected cancers. In scenario A (rule-out triage), models DL-1, DL-2, and DL-3 triaged 35.0% (27 565 of 78 849), 53.2% (41 937 of 78 849), and 55.6% (43 869 of 78 849) of mammograms, respectively, with 0.0% (0 of 887) to 0.1% (one of 887) of screening-detected cancers undetected. In scenario B, DL algorithms triaged in 4.6% (20 of 439) to 8.2% (36 of 439) of interval and 5.2% (36 of 688) to 6.1% (42 of 688) of subsequent-round cancers when applied after the routine double-reading workflow. Combining both approaches in scenario C resulted in an overall noninferior specificity (difference, -0.9%; P < .001) and superior sensitivity (difference, 2.7%; P < .001) for the adaptive workflow compared with routine double reading for all three algorithms. Conclusion Rule-out and rule-in DL-adapted triage workflows can improve the efficiency and efficacy of mammography breast cancer screening. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Nishikawa and Lu in this issue.

Machine Learning for Workflow Applications in Screening Mammography: Systematic Review and Meta-Analysis.

Background Advances in computer processing and improvements in data availability have led to the development of machine learning (ML) techniques for mammographic imaging. Purpose To evaluate the reported performance of stand-alone ML applications for screening mammography workflow. Materials and Methods Ovid Embase, Ovid Medline, Cochrane Central Register of Controlled Trials, Scopus, and Web of Science literature databases were searched for relevant studies published from January 2012 to September 2020. The study was registered with the PROSPERO International Prospective Register of Systematic Reviews (protocol no. CRD42019156016). Stand-alone technology was defined as a ML algorithm that can be used independently of a human reader. Studies were quality assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and the Prediction Model Risk of Bias Assessment Tool, and reporting was evaluated using the Checklist for Artificial Intelligence in Medical Imaging. A primary meta-analysis included the top-performing algorithm and corresponding reader performance from which pooled summary estimates for the area under the receiver operating characteristic curve (AUC) were calculated using a bivariate model. Results Fourteen articles were included, which detailed 15 studies for stand-alone detection (n = 8) and triage (n = 7). Triage studies reported that 17%-91% of normal mammograms identified could be read by adapted screening, while "missing" an estimated 0%-7% of cancers. In total, an estimated 185 252 cases from three countries with more than 39 readers were included in the primary meta-analysis. The pooled sensitivity, specificity, and AUC was 75.4% (95% CI: 65.6, 83.2; P = .11), 90.6% (95% CI: 82.9, 95.0; P = .40), and 0.89 (95% CI: 0.84, 0.98), respectively, for algorithms, and 73.0% (95% CI: 60.7, 82.6), 88.6% (95% CI: 72.4, 95.8), and 0.85 (95% CI: 0.78, 0.97), respectively, for readers. Conclusion Machine learning (ML) algorithms that demonstrate a stand-alone application in mammographic screening workflows achieve or even exceed human reader detection performance and improve efficiency. However, this evidence is from a small number of retrospective studies. Therefore, further rigorous independent external prospective testing of ML algorithms to assess performance at preassigned thresholds is required to support these claims. ©RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Whitman and Moseley in this issue.

Adoption of artificial intelligence in breast imaging: evaluation, ethical constraints and limitations.

Retrospective studies have shown artificial intelligence (AI) algorithms can match as well as enhance radiologist's performance in breast screening. These tools can facilitate tasks not feasible by humans such as the automatic triage of patients and prediction of treatment outcomes. Breast imaging faces growing pressure with the exponential growth in imaging requests and a predicted reduced workforce to provide reports. Solutions to alleviate these pressures are being sought with an increasing interest in the adoption of AI to improve workflow efficiency as well as patient outcomes. Vast quantities of data are needed to test and monitor AI algorithms before and after their incorporation into healthcare systems. Availability of data is currently limited, although strategies are being devised to harness the data that already exists within healthcare institutions. Challenges that underpin the realisation of AI into everyday breast imaging cannot be underestimated and the provision of guidance from national agencies to tackle these challenges, taking into account views from a societal, industrial and healthcare prospective is essential. This review provides background on the evaluation and use of AI in breast imaging in addition to exploring key ethical, technical, legal and regulatory challenges that have been identified so far.