Breast Cancer Statistics, 2022.

This article is the American Cancer Society's update on female breast cancer statistics in the United States, including population-based data on incidence, mortality, survival, and mammography screening. Breast cancer incidence rates have risen in most of the past four decades; during the most recent data years (2010-2019), the rate increased by 0.5% annually, largely driven by localized-stage and hormone receptor-positive disease. In contrast, breast cancer mortality rates have declined steadily since their peak in 1989, albeit at a slower pace in recent years (1.3% annually from 2011 to 2020) than in the previous decade (1.9% annually from 2002 to 2011). In total, the death rate dropped by 43% during 1989-2020, translating to 460,000 fewer breast cancer deaths during that time. The death rate declined similarly for women of all racial/ethnic groups except American Indians/Alaska Natives, among whom the rates were stable. However, despite a lower incidence rate in Black versus White women (127.8 vs. 133.7 per 100,000), the racial disparity in breast cancer mortality remained unwavering, with the death rate 40% higher in Black women overall (27.6 vs. 19.7 deaths per 100,000 in 2016-2020) and two-fold higher among adult women younger than 50 years (12.1 vs. 6.5 deaths per 100,000). Black women have the lowest 5-year relative survival of any racial/ethnic group for every molecular subtype and stage of disease (except stage I), with the largest Black-White gaps in absolute terms for hormone receptor-positive/human epidermal growth factor receptor 2-negative disease (88% vs. 96%), hormone receptor-negative/human epidermal growth factor receptor 2-positive disease (78% vs. 86%), and stage III disease (64% vs. 77%). Progress against breast cancer mortality could be accelerated by mitigating racial disparities through increased access to high-quality screening and treatment via nationwide Medicaid expansion and partnerships between community stakeholders, advocacy organizations, and health systems.

Fatigue and vigilance in medical experts detecting breast cancer.

An abundance of laboratory-based experiments has described a vigilance decrement of reducing accuracy to detect targets with time on task, but there are few real-world studies, none of which have previously controlled the environment to control for bias. We describe accuracy in clinical practice for 360 experts who examined >1 million women's mammograms for signs of cancer, whilst controlling for potential biases. The vigilance decrement pattern was not observed. Instead, test accuracy improved over time, through a reduction in false alarms and an increase in speed, with no significant change in sensitivity. The multiple-decision model explains why experts miss targets in low prevalence settings through a change in decision threshold and search quit threshold and propose it should be adapted to explain these observed patterns of accuracy with time on task. What is typically thought of as standard and robust research findings in controlled laboratory settings may not directly apply to real-world environments and instead large, controlled studies in relevant environments are needed.

Cancer Screening after the Adoption of Paid-Sick-Leave Mandates.

BACKGROUND: By the end of 2022, nearly 20 million workers in the United States have gained paid-sick-leave coverage from mandates that require employers to provide benefits to qualified workers, including paid time off for the use of preventive services. Although the lack of paid-sick-leave coverage may hinder access to preventive care, current evidence is insufficient to draw meaningful conclusions about its relationship to cancer screening. METHODS: We examined the association between paid-sick-leave mandates and screening for breast and colorectal cancers by comparing changes in 12- and 24-month rates of colorectal-cancer screening and mammography between workers residing in metropolitan statistical areas (MSAs) that have been affected by paid-sick-leave mandates (exposed MSAs) and workers residing in unexposed MSAs. The comparisons were conducted with the use of administrative medical-claims data for approximately 2 million private-sector employees from 2012 through 2019. RESULTS: Paid-sick-leave mandates were present in 61 MSAs in our sample. Screening rates were similar in the exposed and unexposed MSAs before mandate adoption. In the adjusted analysis, cancer-screening rates were higher among workers residing in exposed MSAs than among those in unexposed MSAs by 1.31 percentage points (95% confidence interval [CI], 0.28 to 2.34) for 12-month colorectal cancer screening, 1.56 percentage points (95% CI, 0.33 to 2.79) for 24-month colorectal cancer screening, 1.22 percentage points (95% CI, -0.20 to 2.64) for 12-month mammography, and 2.07 percentage points (95% CI, 0.15 to 3.99) for 24-month mammography. CONCLUSIONS: In a sample of private-sector workers in the United States, cancer-screening rates were higher among those residing in MSAs exposed to paid-sick-leave mandates than among those residing in unexposed MSAs. Our results suggest that a lack of paid-sick-leave coverage presents a barrier to cancer screening. (Funded by the National Cancer Institute.).

International evaluation of an AI system for breast cancer screening.

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.

Effect of Health Service Area on Primary Care Physician Provision of Low-Value Cancer Screening.

BACKGROUND: Using a health systems approach to investigate low-value care (LVC) may provide insights into structural drivers of this pervasive problem. OBJECTIVE: To evaluate the influence of service area practice patterns on low-value mammography and prostate-specific antigen (PSA) testing. DESIGN: Retrospective study analyzing LVC rates between 2008 and 2018, leveraging physician relocation in 3-year intervals of matched physician and patient groups. SETTING: U.S. Medicare claims data. PARTICIPANTS: 8254 physicians and 56 467 patients aged 75 years or older. MEASUREMENTS: LVC rates for physicians staying in their original service area and those relocating to new areas. RESULTS: Physicians relocating from higher-LVC areas to low-LVC areas were more likely to provide lower rates of LVC. For mammography, physicians staying in high-LVC areas (LVC rate, 10.1% [95% CI, 8.8% to 12.2%]) or medium-LVC areas (LVC rate, 10.3% [CI, 9.0% to 12.4%]) provided LVC at a higher rate than physicians relocating from those areas to low-LVC areas (LVC rates, 6.0% [CI, 4.4% to 7.5%] [difference, -4.1 percentage points {CI, -6.7 to -2.3 percentage points}] and 5.9% [CI, 4.6% to 7.8%] [difference, -4.4 percentage points {CI, -6.7 to -2.4 percentage points}], respectively). For PSA testing, physicians staying in high- or moderate-LVC service areas provided LVC at a rate of 17.5% (CI, 14.9% to 20.7%) or 10.6% (CI, 9.6% to 13.2%), respectively, compared with those relocating from those areas to low-LVC areas (LVC rates, 9.9% [CI, 7.5% to 13.2%] [difference, -7.6 percentage points {CI, -10.9 to -3.8 percentage points}] and 6.2% [CI, 3.5% to 9.8%] [difference, -4.4 percentage points {CI, -7.6 to -2.2 percentage points}], respectively). Physicians relocating from lower- to higher-LVC service areas were not more likely to provide LVC at a higher rate. LIMITATION: Use of retrospective observational data, possible unmeasured confounding, and potential for relocating physicians to practice differently from those who stay. CONCLUSION: Physicians relocating to service areas with lower rates of LVC provided less LVC than physicians who stayed in areas with higher rates of LVC. Systemic structures may contribute to LVC. Understanding which factors are contributing may present opportunities for policy and interventions to broadly improve care. PRIMARY FUNDING SOURCE: National Cancer Institute of the National Institutes of Health.

In women aged 45 to 75 y, opt-out vs. opt-in breast cancer screening outreach did not increase mammography rates.

SOURCE CITATION: Marcotte LM, Deeds S, Wheat C, et al. Automated opt-out vs opt-in patient outreach strategies for breast cancer screening: a randomized clinical trial. JAMA Intern Med. 2023;183:1187-1194. 37695621.

Recent advancements in artificial intelligence for breast cancer: Image augmentation, segmentation, diagnosis, and prognosis approaches.

Breast cancer is a significant global health burden, with increasing morbidity and mortality worldwide. Early screening and accurate diagnosis are crucial for improving prognosis. Radiographic imaging modalities such as digital mammography (DM), digital breast tomosynthesis (DBT), magnetic resonance imaging (MRI), ultrasound (US), and nuclear medicine techniques, are commonly used for breast cancer assessment. And histopathology (HP) serves as the gold standard for confirming malignancy. Artificial intelligence (AI) technologies show great potential for quantitative representation of medical images to effectively assist in segmentation, diagnosis, and prognosis of breast cancer. In this review, we overview the recent advancements of AI technologies for breast cancer, including 1) improving image quality by data augmentation, 2) fast detection and segmentation of breast lesions and diagnosis of malignancy, 3) biological characterization of the cancer such as staging and subtyping by AI-based classification technologies, 4) prediction of clinical outcomes such as metastasis, treatment response, and survival by integrating multi-omics data. Then, we then summarize large-scale databases available to help train robust, generalizable, and reproducible deep learning models. Furthermore, we conclude the challenges faced by AI in real-world applications, including data curating, model interpretability, and practice regulations. Besides, we expect that clinical implementation of AI will provide important guidance for the patient-tailored management.

Breast cancer patients enrolled in the Swiss mammography screening program "donna" demonstrate prolonged survival.

STUDY GOAL: We compared the survival rates of women with breast cancer (BC) detected within versus outside the mammography screening program (MSP) "donna". METHODS: We merged data from the MSP with the data from corresponding cancer registries to categorize BC cases as within MSP (screen-detected and interval carcinomas) and outside the MSP. We analyzed the tumor stage distribution, tumor characteristics and the survival of the women. We further estimated hazard ratios using Cox-regressions to account for different characteristics between groups and corrected the survival rates for lead-time bias. RESULTS: We identified 1057 invasive (ICD-10: C50) and in-situ (D05) BC cases within the MSP and 1501 outside the MSP between 2010 and 2019 in the Swiss cantons of St. Gallen and Grisons. BC within the MSP had a higher share of stage I carcinoma (46.5% vs. 33.0%; p < 0.01), a smaller (mean) tumor size (19.1 mm vs. 24.9 mm, p < 0.01), and fewer recurrences and metastases in the follow-up period (6.7% vs. 15.6%, p < 0.01). The 10-year survival rates were 91.4% for women within and 72.1% for women outside the MSP (p < 0.05). Survival difference persisted but decreased when women within the same tumor stage were compared. Lead-time corrected hazard ratios for the MSP accounted for age, tumor size and Ki-67 proliferation index were 0.550 (95% CI 0.389, 0.778; p < 0.01) for overall survival and 0.469 (95% CI 0.294, 0.749; p < 0.01) for BC related survival. CONCLUSION: Women participating in the "donna" MSP had a significantly higher overall and BC related survival rate than women outside the program. Detection of BC at an earlier tumor stage only partially explains the observed differences.

Deep learning of mammogram images to reduce unnecessary breast biopsies: a preliminary study.

BACKGROUND: Patients with a Breast Imaging Reporting and Data System (BI-RADS) 4 mammogram are currently recommended for biopsy. However, 70-80% of the biopsies are negative/benign. In this study, we developed a deep learning classification algorithm on mammogram images to classify BI-RADS 4 suspicious lesions aiming to reduce unnecessary breast biopsies. MATERIALS AND METHODS: This retrospective study included 847 patients with a BI-RADS 4 breast lesion that underwent biopsy at a single institution and included 200 invasive breast cancers, 200 ductal carcinoma in-situ (DCIS), 198 pure atypias, 194 benign, and 55 atypias upstaged to malignancy after excisional biopsy. We employed convolutional neural networks to perform 4 binary classification tasks: (I) benign vs. all atypia + invasive + DCIS, aiming to identify the benign cases for whom biopsy may be avoided; (II) benign + pure atypia vs. atypia-upstaged + invasive + DCIS, aiming to reduce excision of atypia that is not upgraded to cancer at surgery; (III) benign vs. each of the other 3 classes individually (atypia, DCIS, invasive), aiming for a precise diagnosis; and (IV) pure atypia vs. atypia-upstaged, aiming to reduce unnecessary excisional biopsies on atypia patients. RESULTS: A 95% sensitivity for the "higher stage disease" class was ensured for all tasks. The specificity value was 33% in Task I, and 25% in Task II, respectively. In Task III, the respective specificity value was 30% (vs. atypia), 30% (vs. DCIS), and 46% (vs. invasive tumor). In Task IV, the specificity was 35%. The AUC values for the 4 tasks were 0.72, 0.67, 0.70/0.73/0.72, and 0.67, respectively. CONCLUSION: Deep learning of digital mammograms containing BI-RADS 4 findings can identify lesions that may not need breast biopsy, leading to potential reduction of unnecessary procedures and the attendant costs and stress.

Optimising the diagnostic accuracy of First post-contrAst SubtracTed breast MRI (FAST MRI) through interpretation-training: a multicentre e-learning study, mapping the learning curve of NHS Breast Screening Programme (NHSBSP) mammogram readers using an enriched dataset.

BACKGROUND: Abbreviated breast MRI (FAST MRI) is being introduced into clinical practice to screen women with mammographically dense breasts or with a personal history of breast cancer. This study aimed to optimise diagnostic accuracy through the adaptation of interpretation-training. METHODS: A FAST MRI interpretation-training programme (short presentations and guided hands-on workstation teaching) was adapted to provide additional training during the assessment task (interpretation of an enriched dataset of 125 FAST MRI scans) by giving readers feedback about the true outcome of each scan immediately after each scan was interpreted (formative assessment). Reader interaction with the FAST MRI scans used developed software (RiViewer) that recorded reader opinions and reading times for each scan. The training programme was additionally adapted for remote e-learning delivery. STUDY DESIGN: Prospective, blinded interpretation of an enriched dataset by multiple readers. RESULTS: 43 mammogram readers completed the training, 22 who interpreted breast MRI in their clinical role (Group 1) and 21 who did not (Group 2). Overall sensitivity was 83% (95%CI 81-84%; 1994/2408), specificity 94% (95%CI 93-94%; 7806/8338), readers' agreement with the true outcome kappa = 0.75 (95%CI 0.74-0.77) and diagnostic odds ratio = 70.67 (95%CI 61.59-81.09). Group 1 readers showed similar sensitivity (84%) to Group 2 (82% p = 0.14), but slightly higher specificity (94% v. 93%, p = 0.001). Concordance with the ground truth increased significantly with the number of FAST MRI scans read through the formative assessment task (p = 0.002) but by differing amounts depending on whether or not a reader had previously attended FAST MRI training (interaction p = 0.02). Concordance with the ground truth was significantly associated with reading batch size (p = 0.02), tending to worsen when more than 50 scans were read per batch. Group 1 took a median of 56 seconds (range 8-47,466) to interpret each FAST MRI scan compared with 78 (14-22,830, p < 0.0001) for Group 2. CONCLUSIONS: Provision of immediate feedback to mammogram readers during the assessment test set reading task increased specificity for FAST MRI interpretation and achieved high diagnostic accuracy. Optimal reading-batch size for FAST MRI was 50 reads per batch. Trial registration (25/09/2019): ISRCTN16624917.

Improving lesion detection in mammograms by leveraging a Cycle-GAN-based lesion remover.

BACKGROUND: The wide heterogeneity in the appearance of breast lesions and normal breast structures can confuse computerized detection algorithms. Our purpose was therefore to develop a Lesion Highlighter (LH) that can improve the performance of computer-aided detection algorithms for detecting breast cancer on screening mammograms. METHODS: We hypothesized that a Cycle-GAN based Lesion Remover (LR) could act as an LH, which can improve the performance of lesion detection algorithms. We used 10,310 screening mammograms from 4,832 women that included 4,942 recalled lesions (BI-RADS 0) and 5,368 normal results (BI-RADS 1). We divided the dataset into Train:Validate:Test folds with the ratios of 0.64:0.16:0.2. We segmented image patches (400 × 400 pixels) from either lesions marked by MQSA radiologists or normal tissue in mammograms. We trained a Cycle-GAN to develop two GANs, where each GAN transferred the style of one image to another. We refer to the GAN transferring the style of a lesion to normal breast tissue as the LR. We then highlighted the lesion by color-fusing the mammogram after applying the LR to its original. Using ResNet18, DenseNet201, EfficientNetV2, and Vision Transformer as backbone architectures, we trained three deep networks for each architecture, one trained on lesion highlighted mammograms (Highlighted), another trained on the original mammograms (Baseline), and Highlighted and Baseline combined (Combined). We conducted ROC analysis for the three versions of each deep network on the test set. RESULTS: The Combined version of all networks achieved AUCs ranging from 0.963 to 0.974 for identifying the image with a recalled lesion from a normal breast tissue image, which was statistically improved (p-value < 0.001) over their Baseline versions with AUCs that ranged from 0.914 to 0.967. CONCLUSIONS: Our results showed that a Cycle-GAN based LR is effective for enhancing lesion conspicuity and this can improve the performance of a detection algorithm.

Low-dose acetylsalicylic acid reduces local inflammation and tissue perfusion in dense breast tissue in postmenopausal women.

PURPOSE: One major risk factor for breast cancer is high mammographic density. It has been estimated that dense breast tissue contributes to ~ 30% of all breast cancer. Prevention targeting dense breast tissue has the potential to improve breast cancer mortality and morbidity. Anti-estrogens, which may be associated with severe side-effects, can be used for prevention of breast cancer in women with high risk of the disease per se. However, no preventive therapy targeting dense breasts is currently available. Inflammation is a hallmark of cancer. Although the biological mechanisms involved in the increased risk of cancer in dense breasts is not yet fully understood, high mammographic density has been associated with increased inflammation. We investigated whether low-dose acetylsalicylic acid (ASA) affects local breast tissue inflammation and/or structural and dynamic changes in dense breasts. METHODS: Postmenopausal women with mammographic dense breasts on their regular mammography screen were identified. A total of 53 women were randomized to receive ASA 160 mg/day or no treatment for 6 months. Magnetic resonance imaging (MRI) was performed before and after 6 months for a sophisticated and continuous measure breast density by calculating lean tissue fraction (LTF). Additionally, dynamic quantifications including tissue perfusion were performed. Microdialysis for sampling of proteins in vivo from breasts and abdominal subcutaneous fat, as a measure of systemic effects, before and after 6 months were performed. A panel of 92 inflammatory proteins were quantified in the microdialysates using proximity extension assay. RESULTS: After correction for false discovery rate, 20 of the 92 inflammatory proteins were significantly decreased in breast tissue after ASA treatment, whereas no systemic effects were detected. In the no-treatment group, protein levels were unaffected. Breast density, measured by LTF on MRI, were unaffected in both groups. ASA significantly decreased the perfusion rate. The perfusion rate correlated positively with local breast tissue concentration of VEGF. CONCLUSIONS: ASA may shape the local breast tissue microenvironment into an anti-tumorigenic state. Trials investigating the effects of low-dose ASA and risk of primary breast cancer among postmenopausal women with maintained high mammographic density are warranted. Trial registration EudraCT: 2017-000317-22.

Are better AI algorithms for breast cancer detection also better at predicting risk? A paired case-control study.

BACKGROUND: There is increasing evidence that artificial intelligence (AI) breast cancer risk evaluation tools using digital mammograms are highly informative for 1-6 years following a negative screening examination. We hypothesized that algorithms that have previously been shown to work well for cancer detection will also work well for risk assessment and that performance of algorithms for detection and risk assessment is correlated. METHODS: To evaluate our hypothesis, we designed a case-control study using paired mammograms at diagnosis and at the previous screening visit. The study included n = 3386 women from the OPTIMAM registry, that includes mammograms from women diagnosed with breast cancer in the English breast screening program 2010-2019. Cases were diagnosed with invasive breast cancer or ductal carcinoma in situ at screening and were selected if they had a mammogram available at the screening examination that led to detection, and a paired mammogram at their previous screening visit 3y prior to detection when no cancer was detected. Controls without cancer were matched 1:1 to cases based on age (year), screening site, and mammography machine type. Risk assessment was conducted using a deep-learning model designed for breast cancer risk assessment (Mirai), and three open-source deep-learning algorithms designed for breast cancer detection. Discrimination was assessed using a matched area under the curve (AUC) statistic. RESULTS: Overall performance using the paired mammograms followed the same order by algorithm for risk assessment (AUC range 0.59-0.67) and detection (AUC 0.81-0.89), with Mirai performing best for both. There was also a correlation in performance for risk and detection within algorithms by cancer size, with much greater accuracy for large cancers (30 mm+, detection AUC: 0.88-0.92; risk AUC: 0.64-0.74) than smaller cancers (0 to < 10 mm, detection AUC: 0.73-0.86, risk AUC: 0.54-0.64). Mirai was relatively strong for risk assessment of smaller cancers (0 to < 10 mm, risk, Mirai AUC: 0.64 (95% CI 0.57 to 0.70); other algorithms AUC 0.54-0.56). CONCLUSIONS: Improvements in risk assessment could stem from enhancing cancer detection capabilities of smaller cancers. Other state-of-the-art AI detection algorithms with high performance for smaller cancers might achieve relatively high performance for risk assessment.

Association of area- and volumetric-mammographic density and breast cancer risk in women of Asian descent: a case control study.

BACKGROUND: Mammographic density (MD) has been shown to be a strong and independent risk factor for breast cancer in women of European and Asian descent. However, the majority of Asian studies to date have used BI-RADS as the scoring method and none have evaluated area and volumetric densities in the same cohort of women. This study aims to compare the association of MD measured by two automated methods with the risk of breast cancer in Asian women, and to investigate if the association is different for premenopausal and postmenopausal women. METHODS: In this case-control study of 531 cases and 2297 controls, we evaluated the association of area-based MD measures and volumetric-based MD measures with breast cancer risk in Asian women using conditional logistic regression analysis, adjusting for relevant confounders. The corresponding association by menopausal status were assessed using unconditional logistic regression. RESULTS: We found that both area and volume-based MD measures were associated with breast cancer risk. Strongest associations were observed for percent densities (OR (95% CI) was 2.06 (1.42-2.99) for percent dense area and 2.21 (1.44-3.39) for percent dense volume, comparing women in highest density quartile with those in the lowest quartile). The corresponding associations were significant in postmenopausal but not premenopausal women (premenopausal versus postmenopausal were 1.59 (0.95-2.67) and 1.89 (1.22-2.96) for percent dense area and 1.24 (0.70-2.22) and 1.96 (1.19-3.27) for percent dense volume). However, the odds ratios were not statistically different by menopausal status [p difference = 0.782 for percent dense area and 0.486 for percent dense volume]. CONCLUSIONS: This study confirms the associations of mammographic density measured by both area and volumetric methods and breast cancer risk in Asian women. Stronger associations were observed for percent dense area and percent dense volume, and strongest effects were seen in postmenopausal individuals.

Breast density knowledge and willingness to delay treatment for pre-operative breast cancer imaging among women with a personal history of breast cancer.

BACKGROUND: Following a breast cancer diagnosis, it is uncertain whether women's breast density knowledge influences their willingness to undergo pre-operative imaging to detect additional cancer in their breasts. We evaluated women's breast density knowledge and their willingness to delay treatment for pre-operative testing. METHODS: We surveyed women identified in the Breast Cancer Surveillance Consortium aged ≥ 18 years, with first breast cancer diagnosed within the prior 6-18 months, who had at least one breast density measurement within the 5 years prior to their diagnosis. We assessed women's breast density knowledge and correlates of willingness to delay treatment for 6 or more weeks for pre-operative imaging via logistic regression. RESULTS: Survey participation was 28.3% (969/3,430). Seventy-two percent (469/647) of women with dense and 11% (34/322) with non-dense breasts correctly knew their density (p < 0.001); 69% (665/969) of all women knew dense breasts make it harder to detect cancers on a mammogram; and 29% (285/969) were willing to delay treatment ≥ 6 weeks to undergo pre-operative imaging. Willingness to delay treatment did not differ by self-reported density (OR:0.99 for non-dense vs. dense; 95%CI: 0.50-1.96). Treatment with chemotherapy was associated with less willingness to delay treatment (OR:0.67; 95%CI: 0.46-0.96). Having previously delayed breast cancer treatment more than 3 months was associated with an increased willingness to delay treatment for pre-operative imaging (OR:2.18; 95%CI: 1.26-3.77). CONCLUSIONS: Understanding of personal breast density was not associated with willingness to delay treatment 6 or more weeks for pre-operative imaging, but aspects of a woman's treatment experience were. CLINICALTRIALS: GOV : NCT02980848 registered December 2, 2016.

Screening mammography performance according to breast density: a comparison between radiologists versus standalone intelligence detection.

BACKGROUND: Artificial intelligence (AI) algorithms for the independent assessment of screening mammograms have not been well established in a large screening cohort of Asian women. We compared the performance of screening digital mammography considering breast density, between radiologists and AI standalone detection among Korean women. METHODS: We retrospectively included 89,855 Korean women who underwent their initial screening digital mammography from 2009 to 2020. Breast cancer within 12 months of the screening mammography was the reference standard, according to the National Cancer Registry. Lunit software was used to determine the probability of malignancy scores, with a cutoff of 10% for breast cancer detection. The AI's performance was compared with that of the final Breast Imaging Reporting and Data System category, as recorded by breast radiologists. Breast density was classified into four categories (A-D) based on the radiologist and AI-based assessments. The performance metrics (cancer detection rate [CDR], sensitivity, specificity, positive predictive value [PPV], recall rate, and area under the receiver operating characteristic curve [AUC]) were compared across breast density categories. RESULTS: Mean participant age was 43.5 ± 8.7 years; 143 breast cancer cases were identified within 12 months. The CDRs (1.1/1000 examination) and sensitivity values showed no significant differences between radiologist and AI-based results (69.9% [95% confidence interval [CI], 61.7-77.3] vs. 67.1% [95% CI, 58.8-74.8]). However, the AI algorithm showed better specificity (93.0% [95% CI, 92.9-93.2] vs. 77.6% [95% CI, 61.7-77.9]), PPV (1.5% [95% CI, 1.2-1.9] vs. 0.5% [95% CI, 0.4-0.6]), recall rate (7.1% [95% CI, 6.9-7.2] vs. 22.5% [95% CI, 22.2-22.7]), and AUC values (0.8 [95% CI, 0.76-0.84] vs. 0.74 [95% CI, 0.7-0.78]) (all P < 0.05). Radiologist and AI-based results showed the best performance in the non-dense category; the CDR and sensitivity were higher for radiologists in the heterogeneously dense category (P = 0.059). However, the specificity, PPV, and recall rate consistently favored AI-based results across all categories, including the extremely dense category. CONCLUSIONS: AI-based software showed slightly lower sensitivity, although the difference was not statistically significant. However, it outperformed radiologists in recall rate, specificity, PPV, and AUC, with disparities most prominent in extremely dense breast tissue.

Effect of testosterone therapy on breast tissue composition and mammographic breast density in trans masculine individuals.

BACKGROUND: The effect of gender-affirming testosterone therapy (TT) on breast cancer risk is unclear. This study investigated the association between TT and breast tissue composition and breast tissue density in trans masculine individuals (TMIs). METHODS: Of the 444 TMIs who underwent chest-contouring surgeries between 2013 and 2019, breast tissue composition was assessed in 425 TMIs by the pathologists (categories of lobular atrophy and stromal composition) and using our automated deep-learning algorithm (% epithelium, % fibrous stroma, and % fat). Forty-two out of 444 TMIs had mammography prior to surgery and their breast tissue density was read by a radiologist. Mammography digital files, available for 25/42 TMIs, were analyzed using the LIBRA software to obtain percent density, absolute dense area, and absolute non-dense area. Linear regression was used to describe the associations between duration of TT use and breast tissue composition or breast tissue density measures, while adjusting for potential confounders. Analyses stratified by body mass index were also conducted. RESULTS: Longer duration of TT use was associated with increasing degrees of lobular atrophy (p < 0.001) but not fibrous content (p = 0.82). Every 6 months of TT was associated with decreasing amounts of epithelium (exp(ß) = 0.97, 95% CI 0.95,0.98, adj p = 0.005) and fibrous stroma (exp(ß) = 0.99, 95% CI 0.98,1.00, adj p = 0.05), but not fat (exp(ß) = 1.01, 95%CI 0.98,1.05, adj p = 0.39). The effect of TT on breast epithelium was attenuated in overweight/obese TMIs (exp(ß) = 0.98, 95% CI 0.95,1.01, adj p = 0.14). When comparing TT users versus non-users, TT users had 28% less epithelium (exp(ß) = 0.72, 95% CI 0.58,0.90, adj p = 0.003). There was no association between TT and radiologist's breast density assessment (p = 0.58) or LIBRA measurements (p > 0.05). CONCLUSIONS: TT decreases breast epithelium, but this effect is attenuated in overweight/obese TMIs. TT has the potential to affect the breast cancer risk of TMIs. Further studies are warranted to elucidate the effect of TT on breast density and breast cancer risk.

Associations between quantitative measures of mammographic density and terminal ductal lobular unit involution in Chinese breast cancer patients.

BACKGROUND: Higher mammographic density (MD), a radiological measure of the proportion of fibroglandular tissue in the breast, and lower terminal duct lobular unit (TDLU) involution, a histological measure of the amount of epithelial tissue in the breast, are independent breast cancer risk factors. Previous studies among predominantly white women have associated reduced TDLU involution with higher MD. METHODS: In this cohort of 611 invasive breast cancer patients (ages 23-91 years [58.4% ≥ 50 years]) from China, where breast cancer incidence rates are lower and the prevalence of dense breasts is higher compared with Western countries, we examined the associations between TDLU involution assessed in tumor-adjacent normal breast tissue and quantitative MD assessed in the contralateral breast obtained from the VolparaDensity software. Associations were estimated using generalized linear models with MD measures as the outcome variables (log-transformed), TDLU measures as explanatory variables (categorized into quartiles or tertiles), and adjusted for age, body mass index, parity, age at menarche and breast cancer subtype. RESULTS: We found that, among all women, percent dense volume (PDV) was positively associated with TDLU count (highest tertile vs. zero: Expbeta = 1.28, 95% confidence interval [CI] 1.08-1.51, ptrend = < .0001), TDLU span (highest vs. lowest tertile: Expbeta = 1.23, 95% CI 1.11-1.37, ptrend = < .0001) and acini count/TDLU (highest vs. lowest tertile: Expbeta = 1.22, 95% CI 1.09-1.37, ptrend = 0.0005), while non-dense volume (NDV) was inversely associated with these measures. Similar trend was observed for absolute dense volume (ADV) after the adjustment of total breast volume, although the associations for ADV were in general weaker than those for PDV. The MD-TDLU associations were generally more pronounced among breast cancer patients ≥ 50 years and those with luminal A tumors compared with patients < 50 years and with luminal B tumors. CONCLUSIONS: Our findings based on quantitative MD and TDLU involution measures among Chinese breast cancer patients are largely consistent with those reported in Western populations and may provide additional insights into the complexity of the relationship, which varies by age, and possibly breast cancer subtype.

A comparative analysis of risk factor associations with interval and screen-detected breast cancers: A large UK prospective study.

The associations of certain factors, such as age and menopausal hormone therapy, with breast cancer risk are known to differ for interval and screen-detected cancers. However, the extent to which associations of other established breast cancer risk factors differ by mode of detection is unclear. We investigated associations of a wide range of risk factors using data from a large UK cohort with linkage to the National Health Service Breast Screening Programme, cancer registration, and other health records. We used Cox regression to estimate adjusted relative risks (RRs) and 95% confidence intervals (CIs) for associations between risk factors and breast cancer risk. A total of 9421 screen-detected and 5166 interval cancers were diagnosed in 517,555 women who were followed for an average of 9.72 years. We observed the following differences in risk factor associations by mode of detection: greater body mass index (BMI) was associated with a smaller increased risk of interval (RR per 5 unit increase 1.07, 95% CI 1.03-1.11) than screen-detected cancer (RR 1.27, 1.23-1.30); having a first-degree family history was associated with a greater increased risk of interval (RR 1.81, 1.68-1.95) than screen-detected cancer (RR 1.52, 1.43-1.61); and having had previous breast surgery was associated with a greater increased risk of interval (RR 1.85, 1.72-1.99) than screen-detected cancer (RR 1.34, 1.26-1.42). As these differences in associations were relatively unchanged after adjustment for tumour grade, and are in line with the effects of these factors on mammographic density, they are likely to reflect the effects of these risk factors on screening sensitivity.

Baseline breast tissue characteristics determine the effect of tamoxifen on mammographic density change.

Tamoxifen prevents recurrence of breast cancer and is also approved for preventive, risk-reducing, therapy. Tamoxifen alters the breast tissue composition and decreases the mammographic density. We aimed to test if baseline breast tissue composition influences tamoxifen-associated density change. This biopsy-based study included 83 participants randomised to 6 months daily intake of placebo, 20, 10, 5, 2.5, or 1 mg tamoxifen. The study is nested within the double-blinded tamoxifen dose-determination trial Karolinska Mammography Project for Risk Prediction of Breast Cancer Intervention (KARISMA) Study. Ultrasound-guided core-needle breast biopsies were collected at baseline before starting treatment. Biopsies were quantified for epithelial, stromal, and adipose distributions, and epithelial and stromal expression of proliferation marker Ki67, oestrogen receptor (ER) and progesterone receptor (PR). Mammographic density was measured using STRATUS. We found that greater mammographic density at baseline was positively associated with stromal area and inversely associated with adipose area and stromal expression of ER. Premenopausal women had greater mammographic density and epithelial tissue, and expressed more epithelial Ki67, PR, and stromal PR, compared to postmenopausal women. In women treated with tamoxifen (1-20 mg), greater density decrease was associated with higher baseline density, epithelial Ki67, and stromal PR. Women who responded to tamoxifen with a density decrease had on average 17% higher baseline density and a 2.2-fold higher PR expression compared to non-responders. Our results indicate that features in the normal breast tissue before tamoxifen exposure influences the tamoxifen-associated density decrease, and that the age-associated difference in density change may be related to age-dependant differences in expression of Ki67 and PR.