AI-integrated Screening to Replace Double Reading of Mammograms: A Population-wide Accuracy and Feasibility Study.

Mammography screening supported by deep learning-based artificial intelligence (AI) solutions can potentially reduce workload without compromising breast cancer detection accuracy, but the site of deployment in the workflow might be crucial. This retrospective study compared three simulated AI-integrated screening scenarios with standard double reading with arbitration in a sample of 249 402 mammograms from a representative screening population. A commercial AI system replaced the first reader (scenario 1: integrated AIfirst), the second reader (scenario 2: integrated AIsecond), or both readers for triaging of low- and high-risk cases (scenario 3: integrated AItriage). AI threshold values were chosen based partly on previous validation and setting the screen-read volume reduction at approximately 50% across scenarios. Detection accuracy measures were calculated. Compared with standard double reading, integrated AIfirst showed no evidence of a difference in accuracy metrics except for a higher arbitration rate (+0.99%, P < .001). Integrated AIsecond had lower sensitivity (-1.58%, P < .001), negative predictive value (NPV) (-0.01%, P < .001), and recall rate (-0.06%, P = .04) but a higher positive predictive value (PPV) (+0.03%, P < .001) and arbitration rate (+1.22%, P < .001). Integrated AItriage achieved higher sensitivity (+1.33%, P < .001), PPV (+0.36%, P = .03), and NPV (+0.01%, P < .001) but lower arbitration rate (-0.88%, P < .001). Replacing one or both readers with AI seems feasible; however, the site of application in the workflow can have clinically relevant effects on accuracy and workload. Keywords: Mammography, Breast, Neoplasms-Primary, Screening, Epidemiology, Diagnosis, Convolutional Neural Network (CNN) Supplemental material is available for this article. Published under a CC BY 4.0 license.

Introduction of one-view tomosynthesis in population-based mammography screening: Impact on detection rate, interval cancer rate and false-positive rate.

OBJECTIVE: To assess performance endpoints of a combination of digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) compared with FFDM only in breast cancer screening. MATERIALS AND METHODS: This was a prospective population-based screening study, including eligible (50-69 years) women attending the Capital Region Mammography Screening Program in Denmark. All attending women were offered FFDM. A subgroup was consecutively allocated to a screening room with DBT. All FFDM and DBT underwent independent double reading, and all women were followed up for 2 years after screening date or until next screening date, whichever came first. RESULTS: 6353 DBT + FFDM and 395 835 FFDM were included in the analysis and were undertaken in 196 267 women in the period from 1 November 2012 to 12 December 2018. Addition of DBT increased sensitivity: 89.9% (95% confidence interval (CI): 81.0-95.5) for DBT + FFDM and 70.1% (95% CI: 68.6-71.6) for FFDM only, p < 0.001. Specificity remained similar: 98.2% (95% CI: 97.9-98.5) for DBT + FFDM and 98.3% (95% CI: 98.2-98.3) for FFDM only, p = 0.9. Screen-detected cancer rate increased statistically significantly: 11.18/1000 for DBT + FFDM and 6.49/1000 for FFDM only, p < 0.001. False-positive rate was unchanged: 1.75% for DBT + FFDM and 1.73% for FFDM only, p = 0.9. Positive predictive value for recall was 39.0% (95% CI: 31.9-46.5) for DBT + FFDM and 27.3% (95% CI: 26.4-28.2), for FFDM only, p < 0.0005. The interval cancer rate decreased: 1.26/1000 for DBT + FFDM and 2.76/1000 for FFDM only, p = 0.02. CONCLUSION: DBT + FFDM yielded a statistically significant increase in cancer detection and program sensitivity.

An assessment of the value of deep neural networks in genetic risk prediction for surgically relevant outcomes.

INTRODUCTION: Postoperative complications affect up to 15% of surgical patients constituting a major part of the overall disease burden in a modern healthcare system. While several surgical risk calculators have been developed, none have so far been shown to decrease the associated mortality and morbidity. Combining deep neural networks and genomics with the already established clinical predictors may hold promise for improvement. METHODS: The UK Biobank was utilized to build linear and deep learning models for the prediction of surgery relevant outcomes. An initial GWAS for the relevant outcomes was initially conducted to select the Single Nucleotide Polymorphisms for inclusion in the models. Model performance was assessed with Receiver Operator Characteristics of the Area Under the Curve and optimum precision and recall. Feature importance was assessed with SHapley Additive exPlanations. RESULTS: Models were generated for atrial fibrillation, venous thromboembolism and pneumonia as genetics only, clinical features only and a combined model. For venous thromboembolism, the ROC-AUCs were 60.1% [59.6%-60.4%], 63.4% [63.2%-63.4%] and 66.6% [66.2%-66.9%] for the linear models and 51.5% [49.4%-53.4%], 63.2% [61.2%-65.0%] and 62.6% [60.7%-64.5%] for the deep learning SNP, clinical and combined models, respectively. For atrial fibrillation, the ROC-AUCs were 60.3% [60.0%-60.4%], 78.7% [78.7%-78.7%] and 80.0% [79.9%-80.0%] for the linear models and 59.4% [58.2%-60.9%], 78.8% [77.8%-79.8%] and 79.8% [78.8%-80.9%] for the deep learning SNP, clinical and combined models, respectively. For pneumonia, the ROC-AUCs were 50.1% [49.6%-50.6%], 69.2% [69.1%-69.2%] and 68.4% [68.0%-68.5%] for the linear models and 51.0% [49.7%-52.4%], 69.7% [.5%-70.8%] and 69.7% [68.6%-70.8%] for the deep learning SNP, clinical and combined models, respectively. CONCLUSION: In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability was similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy.

Early Indicators of the Impact of Using AI in Mammography Screening for Breast Cancer.

Background Retrospective studies have suggested that using artificial intelligence (AI) may decrease the workload of radiologists while preserving mammography screening performance. Purpose To compare workload and screening performance for two cohorts of women who underwent screening before and after AI system implementation. Materials and Methods This retrospective study included 50-69-year-old women who underwent biennial mammography screening in the Capital Region of Denmark. Before AI system implementation (October 1, 2020, to November 17, 2021), all screenings involved double reading. For screenings conducted after AI system implementation (November 18, 2021, to October 17, 2022), likely normal screenings (AI examination score ≤5 before May 3, 2022, or ≤7 on or after May 3, 2022) were single read by one of 19 senior full-time breast radiologists. The remaining screenings were read by two radiologists with AI-assisted decision support. Biopsy and surgical outcomes were retrieved between October 1, 2020, and April 15, 2023, ensuring at least 180 days of follow-up. Screening metrics were compared using the χ2 test. Reading workload reduction was measured as saved screening reads. Results In total, 60 751 and 58 246 women were screened before and after AI system implementation, respectively (median age, 58 years [IQR, 54-64 years] for both cohorts), with a median screening interval before AI of 845 days (IQR, 820-878 days) and with AI of 993 days (IQR, 968-1013 days; P < .001). After AI system implementation, the recall rate decreased by 20.5% (3.09% before AI [1875 of 60 751] vs 2.46% with AI [1430 of 58 246]; P < .001), the cancer detection rate increased (0.70% [423 of 60 751] vs 0.82% [480 of 58 246]; P = .01), the false-positive rate decreased (2.39% [1452 of 60 751] vs 1.63% [950 of 58 246]; P < .001), the positive predictive value increased (22.6% [423 of 1875] vs 33.6% [480 of 1430]; P < .001), the rate of small cancers (≤1 cm) increased (36.6% [127 of 347] vs 44.9% [164 of 365]; P = .02), the rate of node-negative cancers was unchanged (76.7% [253 of 330] vs 77.8% [273 of 351]; P = .73), and the rate of invasive cancers decreased (84.9% [359 of 423] vs 79.6% [382 of 480]; P = .04). The reading workload was reduced by 33.5% (38 977 of 116 492 reads). Conclusion In a population-based mammography screening program, using AI reduced the overall workload of breast radiologists while improving screening performance. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Lee and Friedewald in this issue.

Breast cancer detection accuracy of AI in an entire screening population: a retrospective, multicentre study.

BACKGROUND: Artificial intelligence (AI) systems are proposed as a replacement of the first reader in double reading within mammography screening. We aimed to assess cancer detection accuracy of an AI system in a Danish screening population. METHODS: We retrieved a consecutive screening cohort from the Region of Southern Denmark including all participating women between Aug 4, 2014, and August 15, 2018. Screening mammograms were processed by a commercial AI system and detection accuracy was evaluated in two scenarios, Standalone AI and AI-integrated screening replacing first reader, with first reader and double reading with arbitration (combined reading) as comparators, respectively. Two AI-score cut-off points were applied by matching at mean first reader sensitivity (AIsens) and specificity (AIspec). Reference standard was histopathology-proven breast cancer or cancer-free follow-up within 24 months. Coprimary endpoints were sensitivity and specificity, and secondary endpoints were positive predictive value (PPV), negative predictive value (NPV), recall rate, and arbitration rate. Accuracy estimates were calculated using McNemar's test or exact binomial test. RESULTS: Out of 272,008 screening mammograms from 158,732 women, 257,671 (94.7%) with adequate image data were included in the final analyses. Sensitivity and specificity were 63.7% (95% CI 61.6%-65.8%) and 97.8% (97.7-97.8%) for first reader, and 73.9% (72.0-75.8%) and 97.9% (97.9-98.0%) for combined reading, respectively. Standalone AIsens showed a lower specificity (-1.3%) and PPV (-6.1%), and a higher recall rate (+ 1.3%) compared to first reader (p < 0.0001 for all), while Standalone AIspec had a lower sensitivity (-5.1%; p < 0.0001), PPV (-1.3%; p = 0.01) and NPV (-0.04%; p = 0.0002). Compared to combined reading, Integrated AIsens achieved higher sensitivity (+ 2.3%; p = 0.0004), but lower specificity (-0.6%) and PPV (-3.9%) as well as higher recall rate (+ 0.6%) and arbitration rate (+ 2.2%; p < 0.0001 for all). Integrated AIspec showed no significant difference in any outcome measures apart from a slightly higher arbitration rate (p < 0.0001). Subgroup analyses showed higher detection of interval cancers by Standalone AI and Integrated AI at both thresholds (p < 0.0001 for all) with a varying composition of detected cancers across multiple subgroups of tumour characteristics. CONCLUSIONS: Replacing first reader in double reading with an AI could be feasible but choosing an appropriate AI threshold is crucial to maintaining cancer detection accuracy and workload.

Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms.

OBJECTIVES: To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists. MATERIALS AND METHODS: All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AIsens) and specificity (AIspec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR). RESULTS: The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AIsens had lower specificity (97.5% vs 97.7%; p < 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p < 0.0001) than first readers. AIspec was comparable to first readers in terms of all accuracy measures. Both AIsens and AIspec detected significantly fewer screen-detected cancers (1166 (AIsens), 1156 (AIspec) vs 1252; p < 0.0001) but found more interval cancers compared to first readers (126 (AIsens), 117 (AIspec) vs 39; p < 0.0001) with varying types of cancers detected across multiple subgroups. CONCLUSION: Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers. CLINICAL RELEVANCE STATEMENT: Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly. KEY POINTS: • Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics.

Robust cross-vendor mammographic texture models using augmentation-based domain adaptation for long-term breast cancer risk.

Purpose: Risk-stratified breast cancer screening might improve early detection and efficiency without comprising quality. However, modern mammography-based risk models do not ensure adaptation across vendor-domains and rely on cancer precursors, associated with short-term risk, which might limit long-term risk assessment. We report a cross-vendor mammographic texture model for long-term risk. Approach: The texture model was robustly trained using two systematically designed case-control datasets. Textural features, indicative of future breast cancer, were learned by excluding samples with diagnosed/potential malignancies from training. An augmentation-based domain adaption technique, based on flavorization of mammographic views, ensured generalization across vendor-domains. The model was validated in 66,607 consecutively screened Danish women with flavorized Siemens views and 25,706 Dutch women with Hologic-processed views. Performances were evaluated for interval cancers (IC) within 2 years from screening and long-term cancers (LTC) from 2 years after screening. The texture model was combined with established risk factors to flag 10% of women with the highest risk. Results: In Danish women, the texture model achieved an area under the receiver operating characteristic curve (AUC) of 0.71 and 0.65 for ICs and LTCs, respectively. In Dutch women with Hologic-processed views, the AUCs were not different from AUCs in Danish women with flavorized views. The AUC for texture combined with established risk factors increased to 0.68 for LTCs. The 10% of women flagged as high-risk accounted for 25.5% of ICs and 24.8% of LTCs. Conclusions: The texture model robustly estimated long-term breast cancer risk while adapting to an unseen processed vendor-domain and identified a clinically relevant high-risk subgroup.

Assessing Breast Cancer Risk by Combining AI for Lesion Detection and Mammographic Texture.

Background Recent mammography-based risk models can estimate short-term or long-term breast cancer risk, but whether risk assessment may improve by combining these models has not been evaluated. Purpose To determine whether breast cancer risk assessment improves when combining a diagnostic artificial intelligence (AI) system for lesion detection and a mammographic texture model. Materials and Methods This retrospective study included Danish women consecutively screened for breast cancer at mammography from November 2012 to December 2015 who had at least 5 years of follow-up data. Examinations were evaluated for short-term risk using a commercially available diagnostic AI system for lesion detection, which produced a score to indicate the probability of cancer. A mammographic texture model, trained on a separate data set, assessed textures associated with long-term cancer risk. Area under the receiver operating characteristic curve (AUC) analysis was used to evaluate both the individual and combined performance of the AI and texture models for the prediction of future cancers in women with a negative screening mammogram, including those with interval cancers diagnosed within 2 years of screening and long-term cancers diagnosed 2 years or more after screening. AUCs were compared using the DeLong test. Results The Danish screening cohort included 119 650 women (median age, 59 years [IQR, 53-64 years]), of whom 320 developed interval cancers and 1401 developed long-term cancers. The combination model achieved a higher AUC for interval and long-term cancers grouped together than either the diagnostic AI (AUC, 0.73 vs 0.70; P < .001) or the texture risk (AUC, 0.73 vs 0.66; P < .001) models. The 10% of women with the highest combined risk identified by the combination model accounted for 44.1% (141 of 320) of interval cancers and 33.7% (472 of 1401) of long-term cancers. Conclusion Combining a diagnostic AI system and mammographic texture model resulted in improved risk assessment for interval cancers and long-term cancers and enabled identification of women at high risk. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Poynton and Slanetz in this issue.

Breast density and risk of breast cancer.

Early studies reported a 4- to 6-fold risk of breast cancer between women with extremely dense and fatty breasts. As most early studies were case-control studies, we took advantage of a population-based screening program to study density and breast cancer incidence in a cohort design. In the Capital Region, Denmark, women aged 50 to 69 are invited to screening biennially. Women screened November 2012 to December 2017 were included, and classified by BI-RADS density code, version 4, at first screen after recruitment. Women were followed up for incident breast cancer, including ductal carcinoma in situ (DCIS), to 2020 in nationwide pathology data. Rate ratios (RRs) and 95% confidence intervals (CI) were compared across density groups using Poisson-regression. We included 189 609 women; 1 067 282 person-years; and 4110 incident breast cancers/DCIS. Thirty-three percent of women had BI-RADS density code 1; 38% code 2; 24% code 3; 4.7% code 4; and missing 0.3%. Using women with BI-RADS density code 1 as baseline; women with code 2 had RR 1.69 (95% CI 1.56-1.84); women with code 3, RR 2.06 (95% CI 1.89-2.25); and women with code 4, RR 2.37 (95% CI 1.05-2.74). Results differed between observations accumulated during screening and above screening age. Our results indicated less difference in breast cancer risk across level of breast density than normally stated. Translated into absolute risk of breast cancer after age 50, we found a 6.2% risk for the one-third of women with lowest density, and 14.7% for the 5% of women with highest density.

An Artificial Intelligence-based Mammography Screening Protocol for Breast Cancer: Outcome and Radiologist Workload.

Background Developments in artificial intelligence (AI) systems to assist radiologists in reading mammograms could improve breast cancer screening efficiency. Purpose To investigate whether an AI system could detect normal, moderate-risk, and suspicious mammograms in a screening sample to safely reduce radiologist workload and evaluate across Breast Imaging Reporting and Data System (BI-RADS) densities. Materials and Methods This retrospective simulation study analyzed mammographic examination data consecutively collected from January 2014 to December 2015 in the Danish Capital Region breast cancer screening program. All mammograms were scored from 0 to 10, representing the risk of malignancy, using an AI tool. During simulation, normal mammograms (score < 5) would be excluded from radiologist reading and suspicious mammograms (score > recall threshold [RT]) would be recalled. Two radiologists read the remaining mammograms. The RT was fitted using another independent cohort (same institution) by matching to the radiologist sensitivity. This protocol was further applied to each BI-RADS density. Screening outcomes were measured using the sensitivity, specificity, workload, and false-positive rate. The AI-based screening was tested for noninferiority sensitivity compared with radiologist screening using the Farrington-Manning test. Specificities were compared using the McNemar test. Results The study sample comprised 114 421 screenings for breast cancer in 114 421 women, resulting in 791 screen-detected, 327 interval, and 1473 long-term cancers and 2107 false-positive screenings. The mean age of the women was 59 years ± 6 (SD). The AI-based screening sensitivity was 69.7% (779 of 1118; 95% CI: 66.9, 72.4) and was noninferior (P = .02) to the radiologist screening sensitivity of 70.8% (791 of 1118; 95% CI: 68.0, 73.5). The AI-based screening specificity was 98.6% (111 725 of 113 303; 95% CI: 98.5, 98.7), which was higher (P < .001) than the radiologist specificity of 98.1% (111 196 of 113 303; 95% CI: 98.1, 98.2). The radiologist workload was reduced by 62.6% (71 585 of 114 421), and 25.1% (529 of 2107) of false-positive screenings were avoided. Screening results were consistent across BI-RADS densities, although not significantly so for sensitivity. Conclusion Artificial intelligence (AI)-based screening could detect normal, moderate-risk, and suspicious mammograms in a breast cancer screening program, which may reduce the radiologist workload. AI-based screening performed consistently across breast densities. © RSNA, 2022 Online supplemental material is available for this article.

[Artificial intelligence for cancer detection in breast cancer screening].

Artificial intelligence (AI) has the potential to increase quality and efficiency of breast cancer screening. Recent studies have provided comparative data on AI versus human performance in cancer detection with encouraging results, and commercially available AI systems are used worldwide as a clinical tool for mammography screening. There are, however, a number of methodological concerns in relation to the evaluation of AI systems. This review discusses these aspects as well as the opportunities and challenges of clinical validation and implementation in breast cancer screening practice.

Impact of adding breast density to breast cancer risk models: A systematic review.

PURPOSE: Assessment of a woman's risk of breast cancer is essential when moving towards personalized screening. Breast density is a well-known risk factor and has the potential to improve accuracy of risk prediction models. In this study we reviewed the impact on model performance of adding breast density to clinical breast cancer risk prediction models. METHODS: We conducted a systematic review using a pre-specified search strategy for PubMed, EMBASE, Web of Science, and Cochrane Library from January 2007 until November 2019. Studies were screened using the Covidence software. Eligible studies developed or modified existing breast cancer risk prediction models applicable to the general population of women by adding breast density to the model. Improvement in discriminatory accuracy was measured as an increase in the Area Under the Curve or concordance statistics. RESULTS: Eleven eligible studies were identified by the search and one by reference check. Four studies modified the Gail model, four modified the Tyrer-Cuzick model, and five studies developed new models. Several methods were used to measure breast density, including visual, semi- and fully automated methods. Eleven studies reported discriminatory accuracy and one study reported calibration. Seven studies found a statistically significantly increased discriminatory accuracy when including density in the model. The increase in AUC ranged 0.03 to 0.14. Four studies did not report on statistical significance, but reported an increased AUC ranging from 0.01 to 0.06. CONCLUSION: Including mammographic breast density has the potential to improve breast cancer risk prediction models. However, all models demonstrated limited discrimination accuracy.

Chronic Obstructive Pulmonary Disease Quantification Using CT Texture Analysis and Densitometry: Results From the Danish Lung Cancer Screening Trial.

OBJECTIVE. The purpose of this study is to establish whether texture analysis and densitometry are complementary quantitative measures of chronic obstructive pulmonary disease (COPD) in a lung cancer screening setting. MATERIALS AND METHODS. This was a retrospective study of data collected prospectively (in 2004-2010) in the Danish Lung Cancer Screening Trial. The texture score, relative area of emphysema, and percentile density were computed for 1915 baseline low-dose lung CT scans and were evaluated, both individually and in combination, for associations with lung function (i.e., forced expiratory volume in 1 second as a percentage of predicted normal [FEV1% predicted]), diagnosis of mild to severe COPD, and prediction of a rapid decline in lung function. Multivariate linear regression models with lung function as the outcome were compared using the likelihood ratio test or the Vuong test, and AUC values for diagnostic and prognostic capabilities were compared using the DeLong test. RESULTS. Texture showed a significantly stronger association with lung function (p < 0.001 vs densitometric measures), a significantly higher diagnostic AUC value (for COPD, 0.696; for Global Initiative for Chronic Obstructive Lung Disease (GOLD) grade 1, 0.648; for GOLD grade 2, 0.768; and for GOLD grade 3, 0.944; p < 0.001 vs densitometric measures), and a higher but not significantly different association with lung function decline. In addition, only texture could predict a rapid decline in lung function (AUC value, 0.538; p < 0.05 vs random guessing). The combination of texture and both densitometric measures strengthened the association with lung function and decline in lung function (p < 0.001 and p < 0.05, respectively, vs texture) but did not improve diagnostic or prognostic performance. CONCLUSION. The present study highlights texture as a promising quantitative CT measure of COPD to use alongside, or even instead of, densitometric measures. Moreover, texture may allow early detection of COPD in subjects who undergo lung cancer screening.

Sensitivity of screening mammography by density and texture: a cohort study from a population-based screening program in Denmark.

BACKGROUND: Screening mammography works better in fatty than in dense breast tissue. Computerized assessment of parenchymal texture is a non-subjective method to obtain a refined description of breast tissue, potentially valuable in addition to breast density scoring for the identification of women in need of supplementary imaging. We studied the sensitivity of screening mammography by a combination of radiologist-assessed Breast Imaging Reporting and Data System (BI-RADS) density score and computer-assessed parenchymal texture marker, mammography texture resemblance (MTR), in a population-based screening program. METHODS: Breast density was coded according to the fourth edition of the BI-RADS density code, and MTR marker was divided into quartiles from 1 to 4. Screening data were followed up for the identification of screen-detected and interval cancers. We calculated sensitivity and specificity with 95% confidence intervals (CI) by BI-RADS density score, MTR marker, and combination hereof. RESULTS: Density and texture were strongly correlated, but the combination led to the identification of subgroups with different sensitivity. Sensitivity was high, about 80%, in women with BI-RADS density score 1 and MTR markers 1 or 2. Sensitivity was low, 67%, in women with BI-RADS density score 2 and MTR marker 4. For women with BI-RADS density scores 3 and 4, the already low sensitivity was further decreased for women with MTR marker 4. Specificity was 97-99% in all subgroups. CONCLUSION: Our study showed that women with low density constituted a heterogenous group. Classifying women for extra imaging based on density only might be a too crude approach. Screening sensitivity was systematically high in women with fatty and homogenous breast tissue.

Change in mammographic density across birth cohorts of Dutch breast cancer screening participants.

High mammographic density is a well-known risk factor for breast cancer. This study aimed to search for a possible birth cohort effect on mammographic density, which might contribute to explain the increasing breast cancer incidence. We separately analyzed left and right breast density of Dutch women from a 13-year period (2003-2016) in the breast cancer screening programme. First, we analyzed age-specific changes in average percent dense volume (PDV) across birth cohorts. A linear regression analysis (PDV vs. year of birth) indicated a small but statistically significant increase in women of: 1) age 50 and born from 1952 to 1966 (left, slope = 0.04, p = 0.003; right, slope = 0.09, p < 0.0001); 2) age 55 and born from 1948 to 1961 (right, slope = 0.04, p = 0.01); and 3) age 70 and born from 1933 to 1946 (right, slope = 0.05, p = 0.002). A decrease of total breast volume seemed to explain the increase in PDV. Second, we compared proportion of women with dense breast in women born in 1946-1953 and 1959-1966, and observed a statistical significant increase of proportion of highly dense breast in later born women, in the 51 to 55 age-groups for the left breast (around a 20% increase in each age-group), and in the 50 to 56 age-groups for the right breast (increase ranging from 27% to 48%). The study indicated a slight increase in mammography density across birth cohorts, most pronounced for women in their early 50s, and more marked for the right than for the left breast.

Measurement challenge: protocol for international case-control comparison of mammographic measures that predict breast cancer risk.

INTRODUCTION: For women of the same age and body mass index, increased mammographic density is one of the strongest predictors of breast cancer risk. There are multiple methods of measuring mammographic density and other features in a mammogram that could potentially be used in a screening setting to identify and target women at high risk of developing breast cancer. However, it is unclear which measurement method provides the strongest predictor of breast cancer risk. METHODS AND ANALYSIS: The measurement challenge has been established as an international resource to offer a common set of anonymised mammogram images for measurement and analysis. To date, full field digital mammogram images and core data from 1650 cases and 1929 controls from five countries have been collated. The measurement challenge is an ongoing collaboration and we are continuing to expand the resource to include additional image sets across different populations (from contributors) and to compare additional measurement methods (by challengers). The intended use of the measurement challenge resource is for refinement and validation of new and existing mammographic measurement methods. The measurement challenge resource provides a standardised dataset of mammographic images and core data that enables investigators to directly compare methods of measuring mammographic density or other mammographic features in case/control sets of both raw and processed images, for the purposes of the comparing their predictions of breast cancer risk. ETHICS AND DISSEMINATION: Challengers and contributors are required to enter a Research Collaboration Agreement with the University of Melbourne prior to participation in the measurement challenge. The Challenge database of collated data and images are stored in a secure data repository at the University of Melbourne. Ethics approval for the measurement challenge is held at University of Melbourne (HREC ID 0931343.3).

Screening mammography: benefit of double reading by breast density.

PURPOSE: The currently recommended double reading of all screening mammography examinations is an economic burden for screening programs. The sensitivity of screening is higher for women with low breast density than for women with high density. One may therefore ask whether single reading could replace double reading at least for women with low density. We addressed this question using data from a screening program where the radiologists coded their readings independently. METHODS: Data include all screening mammography examinations in the Capital Region of Denmark from 1 November 2012 to 31 December 2013. Outcome of screening was assessed by linkage to the Danish Pathology Register. We calculated sensitivity, specificity, number of interval cancers, and false positive-tests per 1000 screened women by both single reader and consensus BI-RADS density code. RESULTS: In total 54,808 women were included. The overall sensitivity of double reading was 72%, specificity was 97.6%, 3 women per 1000 screened experienced an interval cancer, and 24 a false-positive test. Across all BI-RADS density codes, single reading consistently decreased sensitivity as compared with consensus reading. The same was true for specificity, apart from results across BI-RADS density codes set by reader 2. CONCLUSIONS: Single reading decreased sensitivity as compared with double reading across all BI-RADS density codes. This included results based on consensus BI-RADS density codes. This means that replacement of double with single reading would have negative consequences for the screened women, even if density could be assessed automatically calibrated to the usual consensus level.

The combined effect of mammographic texture and density on breast cancer risk: a cohort study.

BACKGROUND: Texture patterns have been shown to improve breast cancer risk segregation in addition to area-based mammographic density. The additional value of texture pattern scores on top of volumetric mammographic density measures in a large screening cohort has never been studied. METHODS: Volumetric mammographic density and texture pattern scores were assessed automatically for the first available digital mammography (DM) screening examination of 51,400 women (50-75 years of age) participating in the Dutch biennial breast cancer screening program between 2003 and 2011. The texture assessment method was developed in a previous study and validated in the current study. Breast cancer information was obtained from the screening registration system and through linkage with the Netherlands Cancer Registry. All screen-detected breast cancers diagnosed at the first available digital screening examination were excluded. During a median follow-up period of 4.2 (interquartile range (IQR) 2.0-6.2) years, 301 women were diagnosed with breast cancer. The associations between texture pattern scores, volumetric breast density measures and breast cancer risk were determined using Cox proportional hazard analyses. Discriminatory performance was assessed using c-indices. RESULTS: The median age of the women at the time of the first available digital mammography examination was 56 years (IQR 51-63). Texture pattern scores were positively associated with breast cancer risk (hazard ratio (HR) 3.16 (95% CI 2.16-4.62) (p value for trend <0.001), for quartile (Q) 4 compared to Q1). The c-index of texture was 0.61 (95% CI 0.57-0.64). Dense volume and percentage dense volume showed positive associations with breast cancer risk (HR 1.85 (95% CI 1.32-2.59) (p value for trend <0.001) and HR 2.17 (95% CI 1.51-3.12) (p value for trend <0.001), respectively, for Q4 compared to Q1). When adding texture measures to models with dense volume or percentage dense volume, c-indices increased from 0.56 (95% CI 0.53-0.59) to 0.62 (95% CI 0.58-0.65) (p < 0.001) and from 0.58 (95% CI 0.54-0.61) to 0.60 (95% CI 0.57-0.63) (p = 0.054), respectively. CONCLUSIONS: Deep-learning-based texture pattern scores, measured automatically on digital mammograms, are associated with breast cancer risk, independently of volumetric mammographic density, and augment the capacity to discriminate between future breast cancer and non-breast cancer cases.

Risk stratification of women with false-positive test results in mammography screening based on mammographic morphology and density: A case control study.

BACKGROUND: The long-term risk of breast cancer is increased in women with false-positive (FP) mammography screening results. We investigated whether mammographic morphology and/or density can be used to stratify these women according to their risk of future breast cancer METHODS: We undertook a case-control study nested in the population-based screening programme in Copenhagen, Denmark. We included 288 cases and 288 controls based on a cohort of 4743 women with at least one FP-test result in 1991-2005 who were followed up until 17 April 2008. Film-based mammograms were assessed using the Breast Imaging-Reporting and Data System (BI-RADS) density classification, the Tabár classification, and two automated techniques quantifying percentage mammographic density (PMD) and mammographic texture (MTR), respectively. The association with breast cancer was estimated using binary logistic regression calculating Odds Ratios (ORs) and the area under the receiver operating characteristic (ROC) curves (AUCs) adjusted for birth year and age and invitation round at the FP-screen RESULTS: Significantly increased ORs were seen for BI-RADS D(density)2-D4 (OR 1.94; 1.30-2.91, 2.36; 1.51-3.70 and 4.01; 1.67-9.62, respectively), Tabár's P(pattern)IV (OR 1.83; 1.16-2.89), PMD Q(quartile)2-Q4 (OR 1.71; 1.02-2.88, 1.97; 1.16-3.35 and 2.43; 1.41-4.19, respectively) and MTR Q4 (1.97; 1.12-3.46) using the lowest/fattiest category as reference CONCLUSION: All four methods, capturing either mammographic morphology or density, could segregate women with FP-screening results according to their risk of future breast cancer - using already available screening mammograms. Our findings need validation on digital mammograms, but may inform potential future risk stratification and tailored screening strategies.

A Split-GFP Gateway Cloning System for Topology Analyses of Membrane Proteins in Plants.

To understand the function of membrane proteins, it is imperative to know their topology. For such studies, a split green fluorescent protein (GFP) method is useful. GFP is barrel-shaped, consisting of 11 ß-sheets. When the first ten ß-sheets (GFP1-10) and the 11th ß-sheet (GFP11) are expressed from separate genes they will self-assembly and reconstitute a fluorescent GFP protein. However, this will only occur when the two domains co-localize in the same cellular compartment. We have developed an easy-to-use Gateway vector set for determining on which side of the membrane the N- and C-termini are located. Two vectors were designed for making N- and C-terminal fusions between the membrane proteins-of-interest and GFP11, while another three plasmids were designed to express GFP1-10 in either the cytosol, the endoplasmic reticulum (ER) lumen or the apoplast. We tested functionality of the system by applying the vector set for the transmembrane domain, CNXTM, of the ER membrane protein, calnexin, after transient expression in Nicotiana benthamiana leaves. We observed GFP signal from the ER when we reciprocally co-expressed GFP11-CNXTM with GFP1-10-HDEL and CNXTM-GFP with cytosolic GFP1-10. The opposite combinations did not result in GFP signal emission. This test using the calnexin ER-membrane domain demonstrated its C-terminus to be in the cytosol and its N-terminus in the ER lumen. This result confirmed the known topology of calnexin, and we therefore consider this split-GFP system highly useful for ER membrane topology studies. Furthermore, the vector set provided is useful for detecting the topology of proteins on other membranes in the cell, which we confirmed for a plasma membrane syntaxin. The set of five Ti-plasmids are easily and efficiently used for Gateway cloning and transient transformation of N. benthamiana leaves.