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.

Residual Axillary Metastases in Node-Positive Breast Cancer Patients After Neoadjuvant Treatment: A Register-Based Study.

BACKGROUND: Lymph node (LN) metastasis after neoadjuvant chemotherapy (NACT) generally warrants axillary lymph node dissection, which opposes guidelines of upfront surgery in many cases. We investigated the risk of having additional metastases in the axilla when the LNs removed by targeted axillary dissection (TAD) harbored metastases after NACT. We aimed to identify subgroups suitable for de-escalated axillary treatment. METHODS: This register-based study used data from the Danish Breast Cancer Cooperative Group database. Data were analyzed with logistic regression models. The primary outcome was the metastatic burden in non-TAD LNs in patients with positive TAD LNs after NACT. RESULTS: Among 383 patients, < 66.6% positive TAD LNs (adjusted odds ratio [OR] 0.34, 95% confidence interval [CI] 0.17-0.62), only isolated tumor cells (ITCs) [OR 0.11, 95% CI < 0.01-0.82], and breast pathological complete response (pCR) [OR 0.07, 95% CI < 0.01-0.56] were associated with a low risk of having more than three positive non-TAD LNs. In 315 patients with fewer than three positive non-TAD LNs, the proportion of positive TAD LNs (OR 0.45, 95% CI 0.27-0.76 for 33.3-66.6% vs. > 66.6%), size of the TAD LN metastasis (OR 0.14, 95% CI 0.04-0.54 for ITC vs. macrometastasis), tumor size at diagnosis (OR 0.30, 95% CI 0.15-0.64 for 20-49 mm vs. ≥ 50 mm) and breast pCR (OR 0.38, 95% CI 0.15-0.96) were associated with residual LN metastases in the axilla. CONCLUSIONS: Breast pCR or ITC only in TAD LNs can, with reasonable certainty, preclude more than three positive non-TAD LNs. Additionally, patients with only ITCs in the TAD LN had a low risk of having any non-TAD LN metastases after NACT. De-escalated axillary treatment may be considered in both subgroups.

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.

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.

Standalone AI for Breast Cancer Detection at Screening Digital Mammography and Digital Breast Tomosynthesis: A Systematic Review and Meta-Analysis.

Background There is considerable interest in the potential use of artificial intelligence (AI) systems in mammographic screening. However, it is essential to critically evaluate the performance of AI before it can become a modality used for independent mammographic interpretation. Purpose To evaluate the reported standalone performances of AI for interpretation of digital mammography and digital breast tomosynthesis (DBT). Materials and Methods A systematic search was conducted in PubMed, Google Scholar, Embase (Ovid), and Web of Science databases for studies published from January 2017 to June 2022. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) values were reviewed. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and Comparative (QUADAS-2 and QUADAS-C, respectively). A random effects meta-analysis and meta-regression analysis were performed for overall studies and for different study types (reader studies vs historic cohort studies) and imaging techniques (digital mammography vs DBT). Results In total, 16 studies that include 1 108 328 examinations in 497 091 women were analyzed (six reader studies, seven historic cohort studies on digital mammography, and four studies on DBT). Pooled AUCs were significantly higher for standalone AI than radiologists in the six reader studies on digital mammography (0.87 vs 0.81, P = .002), but not for historic cohort studies (0.89 vs 0.96, P = .152). Four studies on DBT showed significantly higher AUCs in AI compared with radiologists (0.90 vs 0.79, P < .001). Higher sensitivity and lower specificity were seen for standalone AI compared with radiologists. Conclusion Standalone AI for screening digital mammography performed as well as or better than radiologists. Compared with digital mammography, there is an insufficient number of studies to assess the performance of AI systems in the interpretation of DBT screening examinations. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Scaranelo in this issue.

Targeted Axillary Dissection with 125I Seed Placement Before Neoadjuvant Chemotherapy in a Danish Multicenter Cohort.

BACKGROUND: Targeted axillary dissection (TAD), with marking of the metastatic lymph node before neoadjuvant chemotherapy (NACT), is increasingly used for breast cancer axillary staging. In the case of axillary pathological complete response (ax-pCR), axillary lymph node clearance can be omitted. Several marking methods exist, most using re-marking before surgery. Feasibility, learning curve, and identification rate (IR) vary. Marking with 125I seed before NACT makes re-marking at surgery redundant, possibly increasing feasibility and IR. Here, TAD with 125I seed placed before NACT is evaluated in a Danish multicenter cohort. METHODS: Patients staged with 125I TAD in Denmark between 1 January 2016 and 31 August 2021 were included. Patients were identified in radioactivity-emitting implant registries at the radiology departments and from the Danish Breast Cancer Group database. Data were extracted from patients' medical records. Information on patient/tumor characteristics, 125I seed activity, marking period, TAD success, number of sentinel nodes (SNs), the histopathological status of excised nodes, and whether the marked lymph node (MLN) was an SN were registered. RESULTS: 142 patients were included. The IR of the MLN was 99.3%, and the IR of the SLNB was 91.5%. TAD success was 91.5%. Minor challenges in marking or removal of the MLN were noted in three patients. In 72.3% of the patients, the MLN was a sentinel node. Overall, 40.8% had axillary pCR. CONCLUSION: TAD with 125I seed marking before NACT is feasible without re-marking at surgery and with only minor surgical challenges. The IR is high. Staging with TAD spares 41% of breast cancer patients an axillary dissection.

Comparing Methods for Targeted Axillary Dissection in Breast Cancer Patients: A Nationwide, Retrospective Study.

BACKGROUND: Several techniques exist for performing targeted axillary dissection (TAD) after neoadjuvant chemotherapy with the removal of the sentinel node and a marked metastatic lymph node (LN). Two-step methods include coil-marking of the metastatic LN at diagnosis and re-marking with an intraoperatively identifiable marker before surgery. Because nondetection of the marked lymph node (MLN) warrants axillary clearance and many patients achieve axillary pathological complete response (ax-pCR), the success of TAD is crucial. We compare various two-step TAD methods in a Danish national cohort. METHODS: We included patients who received two-step TAD between January 1, 2016 and August 31, 2021. Patients were identified from the Danish Breast Cancer Group database and cross-checked with locally accessible lists. Data were extracted from the patient's medical files. RESULTS: We included 543 patients. In 79.4%, preoperative, ultrasound-guided re-marking was possible. Nonidentification of the coil-marked LN was more likely in patients with ax-pCR. The second markers used were hook-wire, iodine seeds, or ink marking on the axillary skin. Of patients with successful secondary marking, the MLN identification rate (IR) was 91%, and the sentinel node (SN) IR was 95%. Marking with iodine seeds was significantly more successful than ink marking with an odds ratio of 5.34 (95% confidence interval 1.62-17.60). The success rate of the complete TAD with the removal of MLN and SN was 82.3%. CONCLUSIONS: With two-step TAD, nonidentification of the coiled LN before surgery is frequent, especially in patients with ax-pCR. Despite successful remarking, the IR of the MLN at surgery is inferior to one-step TAD.

A population-based cohort study on changes in breast, lung and colorectal cancer incidence and mortality among non-Western immigrant women.

BACKGROUND: Cancer risk varies geographically, and migrants are influenced by different risk factors before, during and after migration. Increased migration from non-Western countries to the Nordic countries calls for a better understanding of the migrants' cancer risk and the change in risk patterns over time. The aim of this study was to compare the incidence and mortality of breast, colorectal and lung cancer between non-Western immigrant and the native female population in Denmark, Finland, Iceland, and Norway. MATERIAL AND METHODS: Data from national registries were processed and pre-analysed in each country. Multivariate Poisson regression models were used to model the relative differences in incidence and mortality as rate ratios (RR). The country-specific estimates and summary statistics were pooled together using a random effects model. RESULTS: Non-Western immigrant women had significantly lower breast (RR 0.71, 0.65-0.78), colorectal (RR 0.72, 0.57-0.92) and lung (RR 0.55, 0.42-0.72) cancer incidence rates than native women, and the risk of these cancers among immigrant women increased with duration of residence. Differences were parallel in breast, colorectal and lung cancer mortality (RR 0.64, 0.55-0.74; RR 0.66, 0.48-0.92; RR 0.51, 0.34-0.79). Among immigrant women, higher education increased the risk for breast cancer and decreased it for lung cancer. CONCLUSION: The results significantly complement and add to the previous findings of cancer burden and cancer burden transition among migrants and provide evidence of a prolonged cancer risk advantage among non-Western immigrant women. However, the findings show an increasing risk of lifestyle-related cancers with increasing duration of residence in the host country. Further studies are needed to discover underlying reasons for this phenomenon.

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.

Prediction of Pathologic Complete Response in Breast Cancer Patients Comparing Magnetic Resonance Imaging with Ultrasound in Neoadjuvant Setting.

BACKGROUND: Some subgroups of breast cancer patients receiving neoadjuvant chemotherapy (NACT) show high rates of pathologic complete response (pCR) in the breast, proposing the possibility of omitting surgery. Prediction of pCR is dependent on accurate imaging methods. This study investigated whether magnetic resonance imaging (MRI) is better than ultrasound (US) in predicting pCR in breast cancer patients receiving NACT. METHODS: This institutional, retrospective study enrolled breast cancer patients receiving NACT who were examined by either MRI or combined US and mammography before surgery from 2016 to 2019. Imaging findings were compared with pathologic response evaluation of the tumor. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy for prediction of pCR were calculated and compared between MRI and US. RESULTS: Among 307 patients, 151 were examined by MRI and 156 by US. In the MRI group, 37 patients (24.5 %) had a pCR compared with 51 patients (32.7 %) in the US group. Radiologic complete response (rCR) was found in 35 patients (23.2 %) in the MRI group and 26 patients (16.7 %) in the US group. In the MRI and US groups, estimates were calculated respectively for sensitivity (87.7 % vs 91.4 %), specificity (56.8 % vs 33.3 %), PPV (86.2 % vs 73.8 %), NPV (60.0 % vs 65.4 %), and accuracy (80.1 % vs 72.4 %). CONCLUSIONS: In predicting pCR, MRI was more specific than US, but not sufficiently specific enough to be a valid predictor of pCR for omission of surgery. As an imaging method, MRI should be preferred when future studies investigating prediction of pCR in NACT patients are planned.

Breast cancer mortality and overdiagnosis after implementation of population-based screening in Denmark.

INTRODUCTION: Service breast cancer screening is difficult to evaluate because there is no unscreened control group. Due to a natural experiment, where 20% of women were offered screening in two regions up to 17 years before other women, Denmark is in a unique position. We utilized this opportunity to assess outcome of service screening. MATERIALS AND METHODS: Screening was offered in Copenhagen from 1991 and Funen from 1993 to women aged 50-69 years. We used difference-in-differences methodology with a study group offered screening; a historical control group; a regional control group; and a regional-historical control group, comparing breast cancer mortality and incidence, including ductal carcinoma in situ, between study and historical control group adjusted for changes in other regions, and calculating ratios of rate ratios (RRR) with 95% confidence intervals (CI). Data came from Central Population Register; mammography screening databases; Cause of Death Register; and Danish Cancer Register. RESULTS: For breast cancer mortality, the study group accumulated 1,551,465 person-years and 911 deaths. Long-term breast cancer mortality in Copenhagen was 20% below expected in absence of screening; RRR 0.80 (95% CI 0.71-0.90), and in Funen 22% below; RRR 0.78 (95% CI 0.68-0.89). Combined, cumulative breast cancer incidence in women followed 8+ years post-screening was 2.3% above expected in absence of screening; RRR 1.023 (95% CI 0.97-1.08). DISCUSSION: Benefit-to-harm ratio of the two Danish screening programs was 2.6 saved breast cancer deaths per overdiagnosed case. Screening can affect only breast cancers diagnosed in screening age. Due to high breast cancer incidence after age 70, only one-third of breast cancer deaths after age 50 could potentially be affected by screening. Increasing upper age limit could be considered, but might affect benefit-to-harm ratio negatively.

The accuracy of titanium contrast-enhanced mammography: a retrospective multicentric study.

BACKGROUND: Recently, a new mammography system to perform contrast-enhanced mammography has become available in the market. For the high-energy acquisition, it uses a titanium filter instead of a copper one, reducing the tube load while maintaining image quality. PURPOSE: To retrospectively evaluate the accuracy of contrast-enhanced mammography with a titanium filter (TiCEM) in three readers with different grades of experience. MATERIAL AND METHODS: IRB-approved retrospective multicentric lesion by lesion study with 200 lesions, all of them initially classified as BI-RADS categories 0/3/4/5 on mammography and/or ultrasound and with pathological confirmation, in 135 patients. Three readers with different levels of experience (expert, resident, intermediate) blinded to the final diagnosis, retrospectively evaluated the low-energy (LE) images and the combination of LE and recombined (subtracted) images and classified the lesions according to the BI-RADS categories. Reader 1 also categorized the breast density. ROC curves were performed for each reader. RESULTS: Out of the 200 lesions, 82 were benign and 118 malignant (20 DCIS, 10 ILC, 88 IDC). The AUCs of LE versus TiCEM for were: Reader 1: 0.7 vs. 0.88, P < 0.001; Reader 2: 0.63 vs. 0.83, P < 0.001; and Reader 3: 0.63 vs. 0.84, P < 0.001. For the three readers, the AUCs of LE versus TiCEM were significantly superior in both dense and non-dense breasts (P < 0.001). Comparing the AUC of LE for Reader 1 (expert) versus the AUC of TiCEM for Reader 2 (resident) there were significant differences (0.7 vs. 0.83, P < 0.001). CONCLUSION: The accuracy of TiCEM was significantly better for all the readers, in both dense and non-dense breasts. The accuracy of a resident reading a TiCEM study was better than the accuracy of an expert radiologist reading LE images.

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.

The efficacy of using computer-aided detection (CAD) for detection of breast cancer in mammography screening: a systematic review.

BACKGROUND: Early detection of breast cancer (BC) is crucial in lowering the mortality. PURPOSE: To present an overview of studies concerning computer-aided detection (CAD) in screening mammography for early detection of BC and compare diagnostic accuracy and recall rates (RR) of single reading (SR) with SR + CAD and double reading (DR) with SR + CAD. MATERIAL AND METHODS: PRISMA guidelines were used as a review protocol. Articles on clinical trials concerning CAD for detection of BC in a screening population were included. The literature search resulted in 1522 records. A total of 1491 records were excluded by abstract and 18 were excluded by full text reading. A total of 13 articles were included. RESULTS: All but two studies from the SR vs. SR + CAD group showed an increased sensitivity and/or cancer detection rate (CDR) when adding CAD. The DR vs. SR + CAD group showed no significant differences in sensitivity and CDR. Adding CAD to SR increased the RR and decreased the specificity in all but one study. For the DR vs. SR + CAD group only one study reported a significant difference in RR. CONCLUSION: All but two studies showed an increase in RR, sensitivity and CDR when adding CAD to SR. Compared to DR no statistically significant differences in sensitivity or CDR were reported. Additional studies based on organized population-based screening programs, with longer follow-up time, high-volume readers, and digital mammography are needed to evaluate the efficacy of CAD.

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.

Regular physical activity and mammographic density: a cohort study.

PURPOSE: Physical activity is a modifiable lifestyle risk factor in prevention of breast cancer. Mammographic density (MD) is a strong risk factor for breast cancer. We investigate the association of regular physical activity with MD. METHODS: For 5,703 women who participated in the Danish Diet, Cancer and Health cohort (1993-1997) and attended mammographic screening in Copenhagen (1993-2001), MD was assessed at the first screening after cohort entry. MD was defined as a binary measure equivalent to Breast Imaging Report and Data System (BI-RADS) to either mixed/dense or fatty. Participation and duration in physical activities (hours/week) and confounders were assessed by questionnaire at cohort baseline. Logistic regression was used to estimate associations [odds ratios (OR), 95% confidence intervals (CI)] between physical activities and MD. RESULTS: 56.3% of women had mixed/dense MD and 47.6% participated in sports. We found a significant positive association between participation in sports (OR 1.15; 95% CI 1.03-1.28) and do-it-yourself work (1.17; 1.05-1.31) and odds of having mixed/dense MD, which attenuated (1.08; 0.96-1.22 and 1.11; 0.98-1.25, respectively) in a fully adjusted model. No associations were found for time spent on physical activities or total metabolic equivalent of task scores with MD, in fully adjusted models. There was no effect modification of association between any physical activities and MD by obesity (BMI ≥ 30 kg/m2) and menopause status. CONCLUSIONS: Physical activity is not a determinant of MD.

Residential traffic noise and mammographic breast density in the Diet, Cancer, and Health cohort.

OBJECTIVES: Traffic is the most important source of community noise, and it has been proposed to be associated with a range of disease outcomes, including breast cancer. As mammographic breast density (MD) is one of the strongest risk factors for developing breast cancer, the present study investigated whether there is an association between residential exposure to traffic noise and MD in a Danish cohort. METHODS: We included women with reproductive and lifestyle information available from the Diet, Cancer, and Health cohort, who also participated in the Copenhagen Mammography Screening Programme (n = 5,260). Present and historical addresses from 1987 to 2011 were found in national registries, and traffic noise was modeled 5 years before mammogram. Analyses between residential traffic noise and MD were performed using logistic regression. RESULTS: We found no association between residential road and railway noise exposure 5 years before mammogram, and having a mixed/dense versus a fatty mammogram, and no interaction with menopausal status, BMI, HRT use, and railway noise exposure, for analyses on road traffic noise. CONCLUSION: The present study does not suggest an association between residential traffic noise exposure and subsequent MD in a cohort of middle-aged Danish women.

Hormone replacement therapy, mammographic density, and breast cancer risk: a cohort study.

PURPOSE: Hormone replacement therapy (HRT) use increases breast cancer risk and mammographic density (MD). We examine whether MD mediates or modifies the association of HRT with the breast cancer. METHODS: For the 4,501 participants in the Danish diet, cancer and health cohort (1993-1997) who attended mammographic screening in Copenhagen (1993-2001), MD (mixed/dense or fatty) was assessed at the first screening after cohort entry. HRT use was assessed by questionnaire and breast cancer diagnoses until 2012 obtained from the Danish cancer registry. The associations of HRT with MD and with breast cancer were analyzed separately using Cox's regression. Mediation analyses were used to estimate proportion [with 95% confidence intervals (CI)] of an association between HRT and breast cancer mediated by MD. RESULTS: 2,444 (54.3%) women had mixed/dense breasts, 229 (5.4%) developed breast cancer, and 35.9% were current HRT users at enrollment. Compared to never users, current HRT use was statistically significantly associated with having mixed/dense breasts (relative risk and 95% CI 1.24; 1.14-1.35), and higher risk of breast cancer (hazard ratio 1.87; 1.40-2.48). Association between current HRT use and breast cancer risk was partially mediated by MD (percent mediated = 10%; 95% CI 4-22%). The current HRT use-related breast cancer risk was higher in women with mixed/dense (1.94; 1.37-3.87) than fatty (1.37; 0.80-2.35) breasts (p value for interaction = 0.15). CONCLUSIONS: MD partially mediates some of the association between HRT and breast cancer risk. The association between HRT and breast cancer seems to be stronger in women with dense breasts.