Effect of screening mammography on the risk of breast cancer death and of all-cause death: A systematic review with meta-analysis of cohort studies.

OBJECTIVE: Observational cohort studies are used to evaluate the effectiveness of screening mammography in women offered screening. Because screening mammography has no effect on causes of death other than breast cancer, cohort studies should show reductions in the risk of breast cancer death substantially greater than possible reductions in the risk of all cause death. We assessed the risk of breast cancer death and of all-cause (or of non-breast cancer) death associated with screening mammography attendance reported in cohort studies. STUDY DESIGN AND SETTING: Cohort studies published from 2002 to 2022 on women invited to screening mammography were searched in PubMed, Web of Sciences, Scopus and in review articles. Random effect meta-analyses were performed using relative risks of death between women who attended screening compared to women who did not attend screening. RESULTS: Eighteen cohort studies were identified, nine that reported relative risks of breast cancer death only, five that reported relative risks of all cause death only, and four that reported relative risks for both breast cancer death and all cause death. The latter four cohort studies reported 12 to 76 times more all-cause deaths than breast cancer deaths. The random-effect summary relative risk for breast cancer mortality in screening attenders vs. nonattenders was 0.55 (95% CI: 0.50-0.60) in 13 cohort studies. The summary relative risk for all-cause mortality was 0.54 (0.50-0.58) in 10 cohort studies. In the four cohort studies that evaluated both outcomes, the summary relative risks were 0.63 (0.43-0.83) for breast cancer mortality and of 0.54 (0.44-0.64) for all-cause mortality. CONCLUSION: The similar relative reductions in breast- and all-cause (or non-breast cancer) mortality indicates that screening mammography attendance is an indicator of characteristics associated with a lower risk of dying from any cause, including from breast cancer, which observational studies have falsely interpreted as a screening effect.

Combined Breast and Lung Cancer Screening Among Dual-Eligible Women: A Descriptive Study.

INTRODUCTION: Lung cancer is consistently the leading cause of cancer death among women in the United States, yet lung cancer screening (LCS) rates remain low. By contrast, screening mammography rates are reliably high, suggesting that screening mammography can be a "teachable moment" to increase LCS uptake among dual-eligible women. MATERIALS AND METHODS: This is a prospective survey study conducted at two academic institutions. Patients undergoing screening mammography were evaluated for LCS eligibility and offered enrollment in a pilot dual-cancer screening program. A series of surveys was administered to characterize participants' knowledge, perceptions, and attitudes about LCS before and after undergoing dual screening. Data were descriptively summarized. RESULTS: Between August 2022 and July 2023, 54 LCS-eligible patients were enrolled. The study cohort was 100% female and predominantly White (81%), with a median age of 57 y and median of 36 pack-y of smoking. Survey results showed that 98% felt they were at risk for lung cancer, with most (80%) motivated by early detection of potential cancer. Regarding screening barriers, 58% of patients lacked knowledge about LCS eligibility and 47% reported concerns about screening cost. Prior to undergoing LCS, 87% of patients expressed interest in combined breast and lung screening. Encouragingly, after LCS, 84% were likely or very likely to undergo dual screening again and 93% found the shared decision-making visit helpful or very helpful. CONCLUSIONS: Pairing breast and LCS is a feasible, acceptable intervention that, along with increasing patient and provider education about LCS, can increase LCS uptake and reduce lung cancer mortality.

Mammographic breast features and risk of cardiovascular diseases in korean women.

BACKGROUND: There is a growing amount of evidence on the association between cardiovascular diseases (CVDs) and breast calcification. Thus, mammographic breast features have recently gained attention as CVD predictors. OBJECTIVE: This study assessed the association of mammographic features, including benign calcification, microcalcification, and breast density, with cardiovascular diseases. METHODS: This study comprised 6,878,686 women aged ≥40 who underwent mammographic screening between 2009 and 2012 with follow-up until 2020. The mammographic features included benign calcification, microcalcification, and breast density. The cardiovascular diseases associated with the mammographic features were assessed using logistic regression. RESULTS: The prevalence of benign calcification, microcalcification, and dense breasts were 9.6 %, 0.9 % and 47.3 % at baseline, respectively. Over a median follow-up of 10 years, benign calcification and microcalcification were positively associated with an increased risk of chronic ischaemic heart disease whereas breast density was inversely associated with it; the corresponding aOR (95 % CI) was 1.14 (1.10-1.17), 1.19 (1.03-1.15), and 0.88 (0.85-0.90), respectively. A significantly increased risk of chronic ischaemic heart disease (IHD) was observed among women with benign calcifications (aHR, 1.14; 95 % CI 1.10-1.17) and microcalcifications (aOR, 1.19; 95 % CI 1.06-1.33). Women with microcalcifications had a 1.16-fold (95 % CI 1.03-1.30) increased risk of heart failure. CONCLUSIONS: Mammographic calcifications were associated with an increased risk of chronic ischaemic heart diseases, whereas dense breast was associated with a decreased risk of cardiovascular disease. Thus, the mammographic features identified on breast cancer screening may provide an opportunity for cardiovascular disease risk identification and prevention.

The FDA Enhancing Quality Using the Inspection Program (EQUIP) Breast Imaging Quality Initiative. 5-Year Clinical Experience.

OBJECTIVES: To evaluate the effects of the Enhancing Quality Using the Inspection Program (EQUIP) on quality control (QC) and quality assurance (QA) at an academic medical center. METHODS: EQUIP audit logs for technologist image quality review as well as mammography unit QA and QC formed the basis for study data. One randomly selected screening mammogram was evaluated by the lead interpreting physician (LIP) using EQUIP criteria for each technologist for each imaging site worked, initially semiannually and then monthly. One randomly selected screening mammogram interpreted by each interpreting physician (IP) for each imaging site was evaluated on a semiannual basis. Quarterly, the LIP reviewed QA and QC logs for each mammography unit with deficiencies further investigated. RESULTS: Of 214 965 eligible screening mammograms performed, 5955 (2.8%) underwent EQUIP image quality review. Five were found to be technically inadequate (0.08%, 5955/214 965). The LIP identified 20 significant interpretive differences compared with the clinical interpretation resulting in 10 biopsies and 7 previously undetected malignancies, with supplemental cancer detection rate of 1.2/1000 cases reviewed. Two hundred ninety mammography unit QA/QC reviews identified 31 potential deficiencies, 29 of which were due to human documentation error (93.4%). CONCLUSION: EQUIP review of both IP and technologists' quality and mammography unit QA/QC logs as performed identified few deficiencies. EQUIP policies should be evaluated at each institution and modified to best utilize resources and provide opportunities for meaningful quality improvement. Although not an EQUIP focus, supplemental cancer detection was observed as might be expected with double reading.

Associations of State Supplemental Nutrition Assistance Program Eligibility Policies With Mammography.

PURPOSE: The Supplemental Nutrition Assistance Program (SNAP) addresses food insecurity for low-income households, which is associated with access to care. Many US states expanded SNAP access through policies eliminating the asset test (ie, restrictions based on SNAP applicant assets) and/or broadening income eligibility. The objective of this study was to determine whether state SNAP policies were associated with the use of mammography among women eligible for breast cancer screening. METHODS: Data for income-eligible women 40 to 79 years of age were obtained from the 2006 to 2019 Behavioral Risk Factor Surveillance System. Difference-in-differences analyses were conducted to compare changes in the percentage of mammography in the past year from pre- to post-SNAP policy adoption (asset test elimination or income eligibility increase) between states that and did not adopt policies expanding SNAP eligibility. RESULTS: In total, 171,684 and 294,647 income-eligible female respondents were included for the asset test elimination policy and income eligibility increase policy analyses, respectively. Mammography within 1 year was reported by 58.4%. Twenty-eight and 22 states adopted SNAP asset test elimination and income increase policies, respectively. Adoption of asset test elimination policies was associated with a 2.11 (95% confidence interval [CI], 0.07-4.15; P = .043) percentage point increase in mammography received within 1 year, particularly for nonmetropolitan residents (4.14 percentage points; 95% CI, 1.07-7.21 percentage points; P = .008), those with household incomes <$25,000 (2.82 percentage points; 95% CI, 0.68-4.97 percentage points; P = .01), and those residing in states in the South (3.08 percentage points; 95% CI, 0.17-5.99 percentage points; P = .038) or that did not expand Medicaid under the Patient Protection and Affordable Care Act (3.35 percentage points; 95% CI, 0.36-6.34; P = .028). There was no significant association between mammography and state-level policies broadening of SNAP income eligibility. CONCLUSIONS: State policies eliminating asset test requirements for SNAP eligibility were associated with increased mammography among low-income women eligible for breast cancer screening, particularly for those in the lowest income bracket or residing in nonmetropolitan areas or Medicaid nonexpansion states.

Comparison of the effectiveness of contrast-enhanced mammography in detecting malignant lesions in patients with extremely dense breasts compared to the all-densities population.

Purpose: To assess the effectiveness of contrast-enhanced mammography (CEM) recombinant images in detecting malignant lesions in patients with extremely dense breasts compared to the all-densities population. Material and methods: 792 patients with 808 breast lesions, in whom the final decision on core-needle biopsy was made based on CEM, and who received the result of histopathological examination, were qualified for a single-centre, retrospective study. Patient electronic records and imaging examinations were reviewed to establish demographics, clinical and imaging findings, and histopathology results. The CEM images were reassessed and assigned to the appropriate American College of Radiology (ACR) density categories. Results: Extremely dense breasts were present in 86 (10.9%) patients. Histopathological examination confirmed the presence of malignant lesions in 52.6% of cases in the entire group of patients and 43% in the group of extremely dense breasts. CEM incorrectly classified the lesion as false negative in 16/425 (3.8%) cases for the whole group, and in 1/37 (2.7%) cases for extremely dense breasts. The sensitivity of CEM for the group of all patients was 96.2%, specificity - 60%, positive predictive values (PPV) - 72.8%, and negative predictive values (NPV) - 93.5%. In the group of patients with extremely dense breasts, the sensitivity of the method was 97.3%, specificity - 59.2%, PPV - 64.3%, and NPV - 96.7%. Conclusions: CEM is characterised by high sensitivity and NPV in detecting malignant lesions regardless of the type of breast density. In patients with extremely dense breasts, CEM could serve as a complementary or additional examination in the absence or low availability of MRI.

Screening for Breast Cancer: A Comparative Review of Guidelines.

Breast cancer is the most common malignancy diagnosed in the female population worldwide and the leading cause of death among perimenopausal women. Screening is essential, since earlier detection in combination with improvements in breast cancer treatment can reduce the associated mortality. The aim of this study was to review and compare the recommendations from published guidelines on breast cancer screening. A total of 14 guidelines on breast cancer screening issued between 2014 and 2022 were identified. A descriptive review of relevant guidelines by the World Health Organization (WHO), the U.S. Preventive Services Task Force (USPSTF), the American Cancer Society (ACS), the National Comprehensive Cancer Network (NCCN), the American College of Obstetricians and Gynecologists (ACOG), the American Society of Breast Surgeons (ASBrS), the American College of Radiology (ACR), the Task Force on Preventive Health Care (CTFPHC), the European Commission Initiative on Breast Cancer (ECIBC), the European Society for Medical Oncology (ESMO), the Royal Australian College of General Practitioners (RACGP) and the Japanese Journal of Clinical Oncology (JJCO) for women both at average and high-risk was carried out. There is a consensus among all the reviewed guidelines that mammography is the gold standard screening modality for average-risk women. For this risk group, most of the guidelines suggest annual or biennial mammographic screening at 40-74 years, while screening should particularly focus at 50-69 years. Most of the guidelines suggest that the age limit to stop screening should be determined based on the women's health status and life expectancy. For women at high-risk, most guidelines recommend the use of annual mammography or magnetic resonance imaging, while the starting age should be earlier than the average-risk group, depending on the risk factor. There is discrepancy among the recommendations regarding the age at onset of screening in the various high-risk categories. The development of consistent international practice protocols for the most appropriate breast cancer screening programs seems of major importance to reduce mortality rates and safely guide everyday clinical practice.

Impact of the measurement conditions and compression paddle on mammography dosimeter response.

The effect of mammography measurement conditions was investigated to evaluate their impact on measurement uncertainties in clinical practice. The most prominent physical X-ray beam quantities i.e., - air kerma, half-value layer, and X-ray tube voltage - were examined by measuring the response of two ionization chambers and six X-ray multimeters (XMMs) of different models. Measurements were performed using several anode/filter combinations and both with and without the compression paddle in the X-ray beam. Maximum differences of higher than 6 % were found for all quantities when the dosimeter displayed value was compared with the reference value or the variation within the clinical anode/filter combinations Mo/Mo and Mo/Rh were considered. The study showed that the calibration procedure with the W/Al anode/filter combination was reliable only for ionization chambers, and the response of XMMs varies in such a way that the calibration coefficient cannot be predicted between various measurement conditions used in calibration and clinical practices. XMM calibrations are typically performed without a compression paddle in the beam, and the response of the XMM changes when radiation quality is slightly altered. If XMM specific data is not available, based on this study, an additional uncertainty of 2 % (k = 1) could be used as a typical estimate, at least for air kerma measurements. XMMs should be used for clinical measurements in mammography only with correct settings. If the correct settings are not available, the XMMs should not be used or used only with extreme caution.

ACR Appropriateness Criteria® Female Breast Cancer Screening: 2023 Update.

Early detection of breast cancer from regular screening substantially reduces breast cancer mortality and morbidity. Multiple different imaging modalities may be used to screen for breast cancer. Screening recommendations differ based on an individual's risk of developing breast cancer. Numerous factors contribute to breast cancer risk, which is frequently divided into three major categories: average, intermediate, and high risk. For patients assigned female at birth with native breast tissue, mammography and digital breast tomosynthesis are the recommended method for breast cancer screening in all risk categories. In addition to the recommendation of mammography and digital breast tomosynthesis in high-risk patients, screening with breast MRI is recommended. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Imaging Findings of Primary Acinic Cell Carcinoma of the Breast: A Case Report.

Acinic cell carcinoma is a rare malignant tumor that accounts for 2%-3% of salivary gland tumors. Acinic cell carcinoma arising from the breast is extremely rare, with only approximately 70 cases reported to date. Owing to its rarity, previous studies have primarily focused on pathological findings. Herein, we present the clinical and radiological features of acinic cell carcinoma of the breast in a 33-year-old woman.

Mammography of suspicious calcifications among ductal carcinoma in situ and benign breast disease.

Background: Most ductal carcinoma in situ (DCIS) lesions manifest early as calcifications, which could be benign or malignant. The classified group of suspicious calcifications among DCIS and benign breast disease is clinically important to early evaluate patient risk factors and plan treatment options. Objectives: To compare imaging features of suspicious calcifications between DCIS and benign breast disease. Method: A retrospective study of 101 suspicious calcifications was performed at Thammasat University Hospital from June 2011 to October 2020. The calcifications were surgically excised by mammography-guided wire localisation. The mammographic features of the suspicious calcifications were reviewed according to the fifth edition of the American College of Radiology Breast Imaging-Reporting and Data System lexicon. For comparing between two groups, the student t-test, Fisher's exact test and Mann-Whitney U test were used for statistical analyses. The logistic regression analysis was calculated for DCIS prediction. Results: The pathologic results of all 101 suspicious calcifications were DCIS (30 cases) and benign breast disease (71 cases). Linear morphology and segmental distribution correlated significantly with DCIS (p = 0.003 and p = 0.024, respectively). After multivariable analysis, fine linear calcification still significantly elevated the risk of DCIS (odd ratios, 51.72 [95% confidence interval: 2.61, 1022.89], p-value of 0.01), however, the odds of predicting DCIS was not statistically significant different among any distribution. Conclusion: Ductal carcinoma in situ calcification has contrasting morphology and distribution features compared to benign breast disease. The calcification descriptor is considered an important implement for early diagnosis and distinguishes DCIS from other benign breast conditions. Contribution: Calcification descriptor is considered an important implement for early diagnosis and distinguishment of DCIS from other benign breast conditions.

Breast Cancer Knowledge and Associated Behaviors in Northern Borders, Saudi Arabia: A Cross-Sectional Study.

Background Breast cancer remains a significant public health issue globally and is notably pervasive within the female population, representing a leading cause of concern. It poses a challenge across different age groups and is influenced by diverse risk factors that include genetic predispositions and various elements of lifestyle. Saudi Arabia, mirroring the global situation, has also seen its share of this disease's impact, prompting a closer look at the factors contributing to its prevalence. Educating the public and advocating for lifestyle changes are crucial steps in cancer prevention. With early-stage diagnosis and screening, many lives can potentially be saved. Our research is focused on understanding the level of awareness and preventative practices among women in the Northern Border region of Saudi Arabia. It seeks to explore the influence of familial history on knowledge and perceptions surrounding breast cancer, which could guide future educational and screening programs. Methods This cross-sectional study engaged 643 female participants, aged 18 and above, from the Northern Border region of Saudi Arabia upon their informed consent. Data were compiled via a structured questionnaire encompassing sociodemographic information, breast cancer knowledge, and preventive practices. Results The data disclosed that a significant majority (86%) recognized breast lumps as indicative of breast cancer, with 69.1% cognizant of hereditary risks. Awareness about lactation as a preventative strategy was noted in 76.7% of the participants, followed by 70.6% acknowledging the merits of a healthy diet. The study unveiled no substantial awareness disparity between individuals with or without a family history of the disease. Alarmingly, 80.4% had never sought a breast examination, and a parallel 83.7% had not undergone mammography. Conclusion The study sheds light on the heterogeneity in breast cancer awareness among women in Saudi Arabia's Northern Border region. Although the recognition of lumps and the preventative role of lactation is relatively high, there remains a deficit in comprehending additional symptoms, signs, and risk factors. The conspicuously low rates of breast cancer examinations and mammography underscore an urgent need for enhanced educational initiatives and a strategic push toward bolstering participation in regular cancer screenings.

USPSTF Recommendations and Overdiagnosis.

Overdiagnosis is the concept that some cancers detected at screening would never have become clinically apparent during a woman's lifetime in the absence of screening. This could occur if a woman dies of a cause other than breast cancer in the interval between mammographic detection and clinical detection (obligate overdiagnosis) or if a mammographically detected breast cancer fails to progress to clinical presentation. Overdiagnosis cannot be measured directly. Indirect methods of estimating overdiagnosis include use of data from randomized controlled trials (RCTs) designed to evaluate breast cancer mortality, population-based screening studies, or modeling. In each case, estimates of overdiagnosis must consider lead time, breast cancer incidence trends in the absence of screening, and accurate and predictable rates of tumor progression. Failure to do so has led to widely varying estimates of overdiagnosis. The U.S. Preventive Services Task Force (USPSTF) considers overdiagnosis a major harm of mammography screening. Their 2024 report estimated overdiagnosis using summary evaluations of 3 RCTs that did not provide screening to their control groups at the end of the screening period, along with Cancer Intervention and Surveillance Network modeling. However, there are major flaws in their evidence sources and modeling estimates, limiting the USPSTF assessment. The most plausible estimates remain those based on observational studies that suggest overdiagnosis in breast cancer screening is 10% or less and can be attributed primarily to obligate overdiagnosis and nonprogressive ductal carcinoma in situ.

A Systematic Review to Evaluate the Barriers to Breast Cancer Screening in Women with Disability.

Background: Breast cancer (BC) is one of the leading causes of mortality worldwide. There are observed disparities in patients with disability as compared to those without disability, which leads to poor BC screening attendance, thereby worsening disease management. Aim: The aim of this systematic review is to investigate if there are disparities in screening rates in women with disability as compared to those without disability, as well as the different factors that pose barriers to patients with disability for enrolment in BC screening programs. Method: Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed published articles between 2008 and 2023, which assessed different factors that contributed to poor attendance in BC screening programs held across different countries. Detailed study characteristics were obtained, and methodological quality assessment was performed on the individual studies included in this review. Result: A total of fifty-three articles were identified as eligible studies based on the pre-defined inclusion and exclusion criteria. These included 7,252,913 patients diagnosed with BC (913,902 patients with disability/6,339,011 patients without disability). The results revealed there are demographic, clinical, financial, and service-related barriers that contributed to lower screening rates in disabled patients as compared to non-disabled. Patient age is the most common factor, with the highest effect observed for 80 years (vs. 30-44 years) [odds ratio (OR) = 13.93 (95% confidence interval (CI) = 8.27-23.47), p < 0.0001], followed by race/ethnicity for Hispanic (vs. non-Hispanic white) [OR = 9.5 (95%CI = 1.0-91.9), p < 0.05]. Additionally, patients with multiple disabilities had the highest rate of dropouts [OR = 27.4 (95%CI = 21.5-33.3)]. Other factors like education, income, marital status, and insurance coverage were essential barriers in screening programs. Conclusions: This study presents a holistic view of all barriers to poor BC screening attendance in disabled patients, thereby exacerbating health inequalities. A standardized approach to overcome the identified barriers and the need for a tailored guideline, especially for disability groups, is inevitable.

Digital Mammography (DM) vs. Dynamic Contrast Enhancement-Magnetic Resonance Imaging (DCE-MRI) in Microcalcifications Assessment: A Radiological-Pathological Comparison.

The aim of this study was to compare the characteristics of breast microcalcification on digital mammography (DM) with the histological and molecular subtypes of breast cancer and to identify the predictive value of DM and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in assessing microcalcifications for radiologic-pathologic correlation. We relied on our prospectively maintained database of suspicious microcalcifications on DM, from which data were retrospectively collected between January 2020 and April 2023. We enrolled 158 patients, all of whom were subjected to biopsy. Additionally, 63 patients underwent breast DCE-MRI. Microcalcifications with a linear branched morphology were correlated with malignancies (p < 0.001), among which an association was highlighted between triple negatives (TNs) and segmental distribution (p < 0.001). Amorphous calcifications were correlated with atypical ductal hyperplasia (ADH) (p = 0.013), coarse heterogeneous (p < 0.001), and fine-pleomorphic (p = 0.008) with atypical lobular hyperplasia (ALH) and fine pleomorphic (p = 0.009) with flat epithelial atypia (FEA). Regarding DCE-MRI, no statistical significance was observed between non-mass lesions and ductal carcinoma in situ (DCIS). Concerning mass lesions, three were identified as DCIS and five as invasive ductal carcinoma (IDC). In conclusion, microcalcifications assessed in DM exhibit promising predictive characteristics concerning breast lesion subtypes, leading to a reduction in diagnostic times and further examination costs, thereby enhancing the clinical management of patients.

Enhancing Accuracy in Breast Density Assessment Using Deep Learning: A Multicentric, Multi-Reader Study.

The evaluation of mammographic breast density, a critical indicator of breast cancer risk, is traditionally performed by radiologists via visual inspection of mammography images, utilizing the Breast Imaging-Reporting and Data System (BI-RADS) breast density categories. However, this method is subject to substantial interobserver variability, leading to inconsistencies and potential inaccuracies in density assessment and subsequent risk estimations. To address this, we present a deep learning-based automatic detection algorithm (DLAD) designed for the automated evaluation of breast density. Our multicentric, multi-reader study leverages a diverse dataset of 122 full-field digital mammography studies (488 images in CC and MLO projections) sourced from three institutions. We invited two experienced radiologists to conduct a retrospective analysis, establishing a ground truth for 72 mammography studies (BI-RADS class A: 18, BI-RADS class B: 43, BI-RADS class C: 7, BI-RADS class D: 4). The efficacy of the DLAD was then compared to the performance of five independent radiologists with varying levels of experience. The DLAD showed robust performance, achieving an accuracy of 0.819 (95% CI: 0.736-0.903), along with an F1 score of 0.798 (0.594-0.905), precision of 0.806 (0.596-0.896), recall of 0.830 (0.650-0.946), and a Cohen's Kappa (κ) of 0.708 (0.562-0.841). The algorithm achieved robust performance that matches and in four cases exceeds that of individual radiologists. The statistical analysis did not reveal a significant difference in accuracy between DLAD and the radiologists, underscoring the model's competitive diagnostic alignment with professional radiologist assessments. These results demonstrate that the deep learning-based automatic detection algorithm can enhance the accuracy and consistency of breast density assessments, offering a reliable tool for improving breast cancer screening outcomes.

Sociodemographic Factors Associated with Breast Cancer Screening among Women in Serbia, National Health Survey.

Background: Approximately 2.3 million female breast cancer cases were identified globally in 2020, resulting in 685,000 fatalities among women. Serbia too experiences a high breast cancer burden. Effective reduction of breast cancer incidence and mortality necessitates strategic measures encompassing the implementation of cost-effective screening technology. However, various impediments to screening implementation persist. We aimed to estimate the impact of socioeconomic factors on breast cancer screening in Serbia. Methods: Data from the 2019 National Health Survey of the population of Serbia was. The research was a descriptive, cross-sectional analytical study by design, on a representative sample of the population of Serbia. Data from women aged 15+ yr were used to examine the demographic and socioeconomic factors associated with breast cancer screening inequalities. Results: In Serbia the age group of women who predominantly participated in organized breast cancer screening (39.5%) were the ones aged 65+ yr. Women with a secondary education were 2.1x more likely to undergo a screening exam voluntarily (57.5%), compared to women with a higher education background (26.6%). When considering marital and financial circumstances, married/unmarried women from an affluent financial category exhibited a notably higher frequency of self-initiating a mammography (73% and 48.5%) in comparison to those financially struggling (27.6%). Conclusion: Strong support is imperative for countries to establish prevention and early detection programs for cancer.

Reproducibility and Explainability of Deep Learning in Mammography: A Systematic Review of Literature.

Background Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. Purpose To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. Methods The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. Results A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. Conclusion While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.