Breast Cancer Screening Research Articles (Page 1)

Public health increasingly relies on digital infrastructures, yet data remains fragmented across clinical, behavioral, and social domains. Customer Data Platforms (CDPs), originally created in marketing to unify diverse information into dynamic individual profiles, could provide a new approach for person-centered public health. This article explores the strategic potential of applying CDP principles, such as data unification, identity resolution, segmentation, and timely intervention, to enhance surveillance, prevention, and chronic disease management. A conceptual framework is presented and demonstrated through a breast cancer screening scenario, illustrating how CDPs could enable personalized outreach and integration with artificial intelligence (AI). Although promising, there are significant challenges related to privacy, interoperability, fairness, and governance. Responsible deployment requires socio-technical strategies that emphasize transparency, ethical oversight, and person involvement.

India is witnessing a high and rising burden of breast and cervical cancers. More than one-third of cases in India are attributed to these two cancers. Early detection and access to affordable and timely treatment are known to reduce the burden of cancer-related deaths. Low and Middle-Income Countries (LMICs) face significant challenges in implementing organized early-detection programs due to inadequate resources, contributing to high mortality from these cancers. Recognizing this critical public health issue, this study evaluates the published literature and government reports on the implementation of breast and cervical cancer screening programs in India. Literature was systematically searched from six databases: PubMed, Embase, Scopus, CINAHL, Web of Science, and Google Scholar. In addition, reports on the National Health Mission website were reviewed to capture screening efforts that were not published in the peer-reviewed literature. 59 peer-reviewed manuscripts were identified, from 57 screening programs. The number of screening programs from Northern and Eastern states is low. Community programs focused on task shifting and engagement of local stakeholders for increasing participation. Clinical Breast Examination (CBE) and Visual inspection of the cervix (VIA) remain the mainstay of screening efforts. The main barriers to screening uptake by women were lower education, lower socioeconomic status, lack of transportation, and suboptimal services. Information on screening programs lacked uniformity in reporting and data collection. These results highlight that screening efforts in India remain disjointed and programs by different agencies need to be aligned through uniform distribution, methodology, and reporting, towards goals set by global initiatives.

False-positive indications in breast cancer screening cause pain and anxiety for patients and are a time and cost waste to healthcare systems. New quantitative ultrasound scanners aim to measure intrinsic acoustic properties of soft tissues to aid better clinical decision making. This study details the performance characterisation of a novel phase-insensitive ultrasound computed tomography (Q-UCT) scanner, developed at the UK's National Physical Laboratory, for quantitative acoustic attenuation coefficient mapping of the breast. Scans of multiple commercially sourced anthropomorphic breast phantoms were acquired, with the results being compared to X-ray computed tomography imagery and ground truth attenuation coefficients obtained from measurements of the constituent phantom materials. The novel system demonstrated the ability to detect the presence of inserts as small as 4 mm in diameter and measure the intrinsic attenuation of larger inserts and host materials with attenuation coefficients ranging from 0.7 dB cm-1 to 4.1 dB cm-1 at 3.2 MHz. For the host materials, agreement with the ground truth values of attenuation lies within the expanded measurement uncertainties of the ground-truth values.

Background Breast cancer has been a serious health problem worldwide. Early detection is undoubtedly effective in combating severe public health problems in developing countries. Meanwhile, primary care physicians play an important role in implementing screening programs. The objective of our study was to evaluate the determinants of primary care physicians’ intention to provide the breast cancer screening services (BCSs) for rural women. Methods We conducted a cross-sectional survey in 24 towns in Jiangsu Province. A total of 1,101 primary care physicians participated in and completed the study. The data collection tool was developed based on the theory of planned behavior (TPB), which includes attitude, subjective norms, and perceived behavioral control, as well as extended components including knowledge of BCSs and past providing-BCSs behavior. Results The results of our study showed that subjective norms ( β = 0.352, p < 0.001) had the strongest influence on primary care physicians’ intention to engage in breast cancer screening, followed by attitudes and perceived behavioral control. Both screening knowledge and past screening provision behavior had an indirect effect on behavioral intentions. Conclusion The present study demonstrated that extended TPB is an effective model for explaining primary care physicians’ intention to engage in breast cancer screening programs. Meanwhile, our findings provide a reference for governments, hospitals and policies aiming to increase primary care physicians’ intention to provide rural women with BCSs.

Breast amyloidosis is a rare disease that can be secondary to systemic disease or localized to the breast. The imaging findings are variable with features suspicious for breast malignancy such as calcifications, focal asymmetry, and mass that prompt the recommendation for biopsy. US correlates are also variable, though when present, most are irregular hypoechoic masses. The imaging features overlap with those of primary breast malignancy. Therefore, biopsy and histopathologic correlation are needed to confirm a concordant diagnosis and for amyloid typing. Because approximately half of cases are associated with B-cell disorders, referral to hematology-oncology for evaluation is important. An additional 16% of patients have systemic autoimmune inflammatory disease such as Sjogren's syndrome, rheumatoid arthritis, systemic lupus erythematosus, and polymyalgia rheumatica. Very rare cases are associated with iatrogenic amyloid formation because of injection of synthetic insulin. The remaining approximate one-third of cases are localized to the breast and other limited sites. These cases most commonly occur in postmenopausal women and are often detected on screening mammography. After evaluation to exclude systemic disease, these patients do not require surgical excision or medical treatment.

Background: Breast cancer remains the most diagnosed cancer in European countries, with diverse screening modalities requiring economic evaluation for optimal resource allocation. This systematic review evaluated the cost-effectiveness of breast cancer screening strategies across European healthcare contexts. Methods: We conducted a comprehensive search across PubMed, ScienceDirect, Cochrane Library, Scopus, and Google Scholar following PRISMA guidelines (1990–2024). Studies were evaluated using the Consolidated Health Economic Evaluation Reporting Standards (CHEERS) checklist. Economic standardization employed healthcare-specific inflation indices and purchasing power parity adjustments, with costs converted to 2020 EUR. Results: From 1449 studies, 23 met inclusion criteria, with significant geographic imbalance (74% from North-Western/Central Europe, 4% from South-Eastern Europe). Mammography screening for women aged 50–69 years demonstrated consistent cost-effectiveness (EUR 3000–8000 per quality-adjusted life year (QALY)) with high confidence. For women under 50, screening showed substantially higher costs (EUR 105,000 per year of life saved). Magnetic resonance imaging (MRI) screening showed cost-effectiveness for high-risk populations (EUR 18,201–33,534 per QALY) with moderate confidence. Conclusions: Biennial mammography screening for women aged 50–69 demonstrates consistent cost-effectiveness across European contexts. Findings have highest applicability to North-Western and Central European healthcare systems, with limited generalizability to Southern and Eastern Europe due to evidence gaps.

Breast cancer (BC) is now the most common malignancy in women. Early detection and precise diagnosis are essential for improving survival. To develop an integrated computer-aided diagnosis (CAD) system that automatically detects, segments and classifies lesions in mammographic images, thereby aiding BC diagnosis. We adopted YOLOv5 as the object-detection backbone and used the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). Data augmentation (random rotations, crops and flips) increased the dataset to 5,801 images, which were randomly split into training, validation and test sets (7 : 2 : 1). Lesion-classification performance was evaluated with the area under the receiver operating characteristic (ROC) curve (AUC), precision, recall, and mean average precision at a 0.5 confidence threshold (mAP@0.5). The CAD system yielded an mAP@0.5 of 0.417 and an F1-score of 0.46 for lesion detection, achieved an AUC of 0.90 for distinguishing benign from malignant lesions, and processed images at 65 fps. The integrated CAD system combines rapid detection and classification with high accuracy, underscoring its strong clinical value.

Successful health promotion involves messages that are quickly captured and held long enough to permit eligibility, credibility, and calls to action to be coded. This research develops an exploratory eye-tracking atlas of breast cancer screening ads viewed by midlife women and a replicable pipeline that distinguishes early capture from long-term processing. Areas of Interest are divided into design-influential categories and graphed with two complementary measures: first hit and time to first fixation for entry and a tie-aware pairwise dominance model for dwell that produces rankings and an “early-vs.-sticky” quadrant visualization. Across creatives, pictorial and symbolic features were more likely to capture the first glance when they were perceptually dominant, while layouts containing centralized headlines or institutional cues deflected entry to the message and source. Prolonged attention was consistently focused on blocks of text, locations, and badges of authoring over ornamental pictures, demarcating the functional difference between capture and processing. Subgroup differences indicated audience-sensitive shifts: Older and household families shifted earlier toward source cues, more educated audiences shifted toward copy and locations, and younger or single viewers shifted toward symbols and images. Internal diagnostics verified that pairwise matrices were consistent with standard dwell summaries, verifying the comparative approach. The atlas converts the patterns into design-ready heuristics: defend sticky and early pieces, encourage sticky but late pieces by pushing them toward probable entry channels, de-clutter early but not sticky pieces to convert to processing, and re-think pieces that are neither. In practice, the diagnostics can be incorporated into procurement, pretesting, and briefs by agencies, educators, and campaign managers in order to enhance actionability without sacrificing segmentation of audiences. As an exploratory investigation, this study invites replication with larger and more diverse samples, generalizations to dynamic media, and associations with downstream measures such as recall and uptake of services.

Background: Takayasu arteritis is a rare, granulomatous large-vessel vasculitis primarily affecting the aorta and its branches. Its non-specific presentation often delays diagnosis and can increase the risk of cardiovascular complications. Case Summary: A healthy 42-year-old woman with a BRCA mutation presented for breast cancer screening via a magnetic resonance imaging (MRI). This revealed cardiomegaly, for which she was referred to our hospital for workup. Her exam revealed a widened pulse pressure (70 mmHg) and a diastolic murmur at the right upper sternal border. Subsequently, a computed tomography (CT) and transthoracic echocardiogram showed perivascular fat-stranding concerning for aortitis (Figure 1A) and aortic regurgitation (AR) with left ventricular (LV) dilation and dysfunction, respectively. These findings were confirmed with a cardiac MRI (Figure 2) and transesophageal echo. Subsequent coronary CT angiogram ruled out aortic dissection but revealed 70% ostial left main (LM) coronary artery stenosis (Figure 1B), which was confirmed on coronary angiogram (Figure 3A). Given these findings, she was started on empiric steroids for presumed Takayasu arteritis after multidisciplinary discussions. Due to her severe AR associated with LV dysfunction and severe left main disease, she met Class I indications for surgical aortic valve replacement (SAVR) and coronary artery bypass grafting (CABG). A multidisciplinary discussion was held between cardiology, cardiothoracic surgery, and rheumatology regarding surgical timing given concerns for ongoing inflammation and associated surgical risks. However, her course was complicated by refractory chest pain requiring nitroglycerin infusion. After extensive discussions, via shared decision-making we proceeded with a temporizing, high-risk coronary stenting as a bridge to surgery following successful tapering of immunosuppressive therapy. She underwent a successful PCI (Figure 3B) and was initiated on dual-antiplatelet therapy. Ultimately, she was discharged on a prednisone taper and methotrexate, with plans for interval SAVR and CABG once on the lowest dose steroid. Discussion: Timely diagnosis and treatment is crucial to improving outcomes in Takayasu arteritis. Complications such as coronary artery stenosis and AR often require surgery but can be complicated by inflammation leading to friable tissue and an increased operative risk. Multidisciplinary management is key for optimal management and timing of such.

Early and accurate breast cancer detection is critical for patient outcomes. The Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) has been instrumental for computer-aided diagnosis (CAD) systems. However, the lack of a standardized preprocessing pipeline and consistent metadata has limited its utility for reproducible quantitative imaging or radiomics. This paper introduces CBIS-DDSM-R, an open-source, radiomics-ready extension of the original dataset. It provides an automated pipeline for preprocessing mammograms and extracts a standardized set of 93 radiomics features per lesion, adhering to Image Biomarker Standardisation Initiative (IBSI) guidelines using PyRadiomics. The resulting dataset combines clinical and radiomics data into a unified format, offering a robust benchmark for developing and validating reproducible radiomics models for breast cancer characterization.

Background:In Canada, patients who move may choose to stay on their original family physician’s roster, creating long distances to seek primary care. We sought to explore how distance to primary care affected health care use and quality of care.Methods:We conducted a population-based study in Ontario, Canada, including urban and suburban patients enrolled with a family physician as of Mar. 31, 2023. The primary exposure was patients’ travel distance to their physician. Outcomes included emergency department visits, primary care visits, continuity of care, and cancer screening rates.Results:We included 9 967 955 patients. Of these, 1 261 112 (12.7%) patients lived farther than 30 km from their family physician. These patients had greater odds of having nonurgent emergency department visits in the past year (odds ratio [OR] 1.43, 95% confidence interval [CI] 1.42 to 1.44); having no visits with any family physician in the previous 2 years (OR 1.28, 95% CI 1.27 to 1.28); and not having had screening for colon cancer (OR 1.17, 95% CI 1.16 to 1.18), breast cancer (OR 1.24, 95% CI 1.23 to 1.25), and cervical cancer (OR 1.17, 95% CI 1.16 to 1.18).Interpretation:Among Ontario patients living in urban or suburban areas and rostered to a family physician within a patient enrolment model, more than 10% of patients resided farther than 30 km from their family physician. Proximity to primary care was associated with higher use of primary care, reduced emergency department use, and increased uptake of recommended cancer screening, underscoring the importance of reforms that enhance access to care close to home.

Introduction Breast cancer remains the most frequently diagnosed cancer and a leading cause of cancer-related death among women globally, emphasising the urgent need for early, accurate, and interpretable diagnostic tools. While digital mammography serves as the cornerstone of breast cancer screening, its diagnostic performance is often hindered by image quality variability, dense breast tissue, and limited visual interpretability. Furthermore, conventional Computer-Aided Diagnostic (CAD) systems and deep learning models have struggled with clinical adoption due to high false-positive rates, difficult decision-making, and excessive computational demands. Methods To address these critical challenges, we introduce ASG-MammoNet, an Attention-Guided and Streamlined deep learning framework for robust, real-time, and explainable mammographic breast cancer classification. The framework is composed of three integrated stages: (1) Data Preparation and Balanced Feature Representation, which applies advanced preprocessing, augmentation, and weighted sampling to mitigate data imbalance and variations across the dataset; (2) Attention-Guided Streamlined Classification, where an EfficientNet-B0 backbone is enhanced by a dual-stage Convolutional Block Attention Module (CBAM) to selectively emphasise diagnostically relevant features; and (3) Explainable Inference, in which Gradient-weighted Class Activation Mapping (Grad-CAM) is employed to provide class-specific visualisations of lesion regions, supporting interpretability and clinical decision-making. Results ASG-MammoNet is thoroughly validated on three benchmark mammography datasets, CBIS-DDSM, INbreast, and MIAS, achieving accuracy above 99.1%, AUC scores exceeding 99.6%, and DIP (Distance from Ideal Position) scores above 0.99, with an average inference time under 14 milliseconds per image. The framework exhibits strong generalisability, consistent performance across data folds, and clinically relevant attention maps, highlighting its readiness for real-world deployment. Discussion The model consistently outperforms or matches recent state-of-the-art approaches while offering superior balance across sensitivity and specificity. Its robust generalisability, consistent fold-wise performance, and clinically meaningful attention visualisations support its practical utility. By addressing critical limitations such as high computational cost, limited interpretability, and precision, ASG-MammoNet represents a practical and reliable solution for AI-assisted breast cancer diagnosis in modern screening settings.

Abstract Background Breast asymmetry is a frequent finding on mammography, which could be the result of summing artifacts or normal variation in the breast parenchymal pattern, or it could be a sign of underlying actual pathology. When mammography and breast sonography are unclear or produce inconsistent results, magnetic resonance imaging (MRI) may be utilized to accurately diagnose breast diseases. Objectives To figure out the diagnostic value of both unenhanced and dynamic contrast-enhanced MRI (UEMRI and DCEMRI) in the assessment of cases with mammographically detected breast asymmetries. Methods Fifty-one women with breast asymmetries identified through diagnostic or screening mammography participated in this prospective trial. All patients had UEMRI and DCEMRI, and the reported results were compared either by using the histopathology from suspicious lesions with a score of BIRADS 4 or 5 or by ultrasonography follow-up in benign instances with a score of BIRADS 3. Results The results of UEMRI in correlation to pathology/follow-up data revealed a sensitivity of 100.00%, a specificity of 90.62%, a positive predictive value of 87.5%, a negative predictive value of 100.00%, and an accuracy of 94.3%. DCEMRI showed a sensitivity of 100.00%, a specificity of 81.2%, a positive predictive value of 77.78%, a negative predictive value of 100.00%, and an accuracy of 88.68%. Conclusions The diagnostic performance of the DCEMRI and UEMRI in breast asymmetries showed no significant difference, and hence for assessing breast asymmetry, UEMRI may be regarded as a valid substitute for DCEMRI and a trustworthy diagnostic method, especially in cases where contrast administration can’t be done.

Background Breast cancer screening is essential for early detection and reducing mortality; however, hesitancy towards screening persists globally, particularly in low- and middle-income countries (LMICs). To further understand the psychological, cultural, and structural barriers we need to utilize the validated tools to measure screening hesitancy as the first step in improving participation rates in the future. Method This systematic scoping review uses the Arksey and O’Malley framework together with the PRISMA extension, to filter studies based on relevancy regarding breast cancer screening and analytical quality. Studies are pulled from academic databases such as PubMed, Scopus, Web of Science, and Google Scholar that include frameworks such as the Health Belief Model (HBM) and Knowledge Attitude Practice (KAP) that focus on psychological and behavioral factors. The studies are pulled from the past decade. Results This review identified numerous frameworks used around the globe for determining screening hesitancy. However, among the most developed countries, HBM and KAP were the most widely used frameworks. These tools have good measurements of psychometric factors, but their lack of cultural adaptation limits their application in more diverse environments, especially in LMICs. Conclusion The findings highlight there need to have a more culturally adaptive, and a high psychometric standard tool for measuring breast cancer screening hesitancy. In the future, research should focus on developing more adaptive tools and using digital platforms to increase accessibility. By addressing these gaps, public health strategies can better reduce screening hesitancy, enhance early detection, and improve health conditions worldwide. BJMS, Vol. 24 No. 04 October’25 Page : 1304-1328

After the COVID-19 pandemic, racial and ethnic minority groups experienced disproportionate delays in returning to breast cancer. The GW Cancer Center's Community Outreach and Engagement team developed a novel Neighborhood Health Ambassador (NHA) network to increase knowledge and access to breast cancer screening in the Washington, DC metropolitan region. First, we recruited NHAs to complete a paid 100-h Community Health Worker (CHW) training and 44-h practicum. We coached NHAs to conduct community outreach and breast cancer screening education in their neighborhoods. Second, we partnered with two community-based organizations to arrange direct screenings for Hispanic/Latina and African immigrant women. Twenty-six NHAs completed the CHW Curriculum. Nineteen NHAs completed the practicum. NHAs reached 2,189 direct beneficiaries at 108 events over a year. GW Cancer Center staff navigated 21 women to mammograms. Out-of-pocket costs were paid to allow an additional 102 uninsured women to obtain mammograms. This project piloted a community-based network to strengthen breast cancer screening in the GW Cancer Center catchment area. Creating a grassroots network of community health workers is feasible and impactful, but time-intensive. Directly partnering with longstanding community partners yielded faster screening uptake among priority groups for breast cancer screening.

Breast cancer early detection and molecular subtype prediction by combination of Raman spectroscopy with deep learning.

ACR Appropriateness Criteria® Male Breast Cancer Screening.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. The MammosighTR dataset, derived from Türkiye's national breast cancer screening mammography program, provides BI-RADS-labeled mammograms with detailed annotations on breast composition and lesion quadrant location, which may be useful for developing and testing AI models in breast cancer detection. ©RSNA, 2025.

The perceived ethical appropriateness of messaging on breast cancer screening cessation among older women.

Breast cancer detection in mammography images using Neighborhood Attention transformer and Shearlet Transform.