PURPOSE:To develop a deep learning-based framework for automated detection and grading of breast arterial calcification (BAC) on mammograms, and to evaluate its association with major adverse cardiovascular events (MACE). MATERIAL AND METHODS:This retrospective case-control study used two datasets: SegModel (1270 mammograms with BAC annotations) and MACEPred (3190 mammographic cases of women with MACE, plus 6458 controls). A U-Net segmentation model and Cox proportional hazards models were used to assess adjusted hazard ratios (HRs) for four BAC grading strategies: binary categorization, area-based grading (none, mild, moderate, severe), intensity-based grading, and a combined approach. FINDINGS:The U-Net attained a Jaccard similarity coefficient of 0.582, accuracy of 0.996, precision of 0.801, F1 score of 0.756, and recall of 0.716 in segmenting BAC. The presence of BAC was associated with an adjusted HR of 1.16 (95% CI 1.10-1.23). For area-based grading, the HRs for mild, moderate, and severe grades were 1.13 (95% CI 1.06-1.20), 1.30 (95% CI 1.18-1.45), and 1.58 (95% CI 1.15-2.18), respectively. Intensity-based grading showed respective HRs of 1.08 (95% CI 1.00-1.17), 1.10 (95% CI 1.01-1.20), and 1.18 (95% CI 1.09-1.28). The combined approach demonstrated respective HRs of 1.102 (95% CI 1.04-1.17), 1.249 (95% CI 1.14-1.37), and 1.654 (95% CI 1.30-2.10) for mild, moderate, and severe grades. CONCLUSION:Our study presents a novel automated framework for BAC assessment that provides independent insights into cardiovascular risk in women. Combined area and intensity grading reflected increasing MACE risk across BAC severity levels, although its incremental predictive improvement was limited.

Objective Breast arterial calcification (BAC), visible on screening mammography, is increasingly recognized as a relevant vascular finding. While previous studies have explored the presence of BAC, the determinants of its severity remain underexplored. This study aimed to identify clinical, reproductive, and lifestyle factors associated with the presence and severity of BAC, using automated BAC quantification to support large-scale analysis. Methods A cohort of 9,648 women undergoing screening mammography were analyzed using a deep learning-based model to assess BAC presence and severity. BAC severity was quantified using both area- and intensity-based grading systems. Multinomial and ordinal logistic regression models were used to identify predictors of BAC presence and severity, including factors such as age, parity, body mass index (BMI), smoking, oral contraceptive use, and medication use as proxies for diabetes, hypertension, and hypercholesterolemia. Results BAC was present in 27% of the cohort, increasing with age from 10.3% in women aged 40–49 to 66.1% in those over 80. Use of glucose-lowering medications (OR: 1.37, 95% CI: 1.05–1.81) and antihypertensive medications (OR: 1.46, 95% CI: 1.24–1.71) were significantly associated with higher BAC severity. Parity (OR: 6.51, 95% CI: 4.03–10.53) was linked to severe BAC, while inverse associations were found with oral contraceptive use (OR: 0.77, 95% CI: 0.64–0.93) and smoking (OR: 0.36, 95% CI: 0.22–0.61). Conclusion Both the presence and severity of BAC were independently associated with age, parity, and the use of medications indicative of diabetes and hypertension, with stronger associations observed at higher BAC severity levels.

PURPOSE:Breast arterial calcification (BAC), detectable on routine mammograms, offers a promising independent risk factor for cardiovascular disease (CVD) risk stratification. However, current BAC assessment methods lack standardization and rely on subjective interpretations. This study introduces a semi-supervised deep learning (DL) model to automate BAC severity grading, enhance cross-system generalizability, and align with clinical consensus. METHODS:A U-Net-based segmentation model was trained on 2560 annotated screening mammograms from 7 vendors. A semi-supervised learning strategy employing progressive pseudo-labeling incorporated 6000 unlabeled images to enhance model robustness. BAC severity was graded by thresholding the percentage area covered by BAC and benchmarked against radiologists' assessments using Canadian Society of Breast Imaging (CSBI) guidelines. Performance was evaluated using the Jaccard Similarity Coefficient (JSC) for segmentation, along with accuracy, precision, F1-score, and recall. For detecting clinically significant (Grade 3) BAC, sensitivity, specificity, and area under the curve (AUC) were assessed. Agreement with experts was evaluated using weighted kappa statistics. RESULTS:The proposed model achieved a JSC of 0.614, an accuracy of 0.991, an F1-score of 0.756, a precision of 0.763, and a recall of 0.764. It demonstrated superior segmentation accuracy compared to the baseline U-Net model. Agreement with consensus radiologists was high, with a weighted kappa of 0.90, 95% CI = (0.70, 1.00). For clinically significant (Grade 3) BAC, the model achieved an AUC of 0.87, 95% CI = (0.72, 1.00), sensitivity of 0.80, and specificity of 0.93. CONCLUSION:The framework holds promise for clinical adoption, integrating into mammography workflows and improving women's cardiovascular risk stratification.

RATIONALE AND OBJECTIVES:Evidence for the effectiveness of radiological image interpretation (RII) e-learning approaches for medical students (MS) is unclear. Therefore, this review evaluated the effectiveness of e-learning interventions for MS RII education. Specifically, it evaluated the impact of instructional design and e-learning delivery on skill acquisition and explored the association between these outcomes and the recommended published curricula. MATERIALS AND METHODS:A systematic search of databases (EmBase [OVID, MEDLINE]), PubMed, Science Direct, Scopus, Web of Science) was conducted to February 2024. Inclusion criteria were MS participating in RII education using e-learning. Outcomes assessed were knowledge and diagnostic-skill capabilities. Quality was appraised using the Modified Medical Education Research Study Quality Instrument. Evidence synthesis was performed via thematic analysis using a deductive and iterative process. RESULTS:30 moderate quality studies were reviewed. Online learning platforms (n=15) were the most common form of e-learning delivery. 21 studies incorporated interactive learning using various instructional designs. Multiple topics covered in the published curricula were studied, with high-urgency pathologies minimally represented. The findings indicate that experiential learning is important for RII diagnostic-skill development; learning outcomes for pathologies of varying complexity are not equivalent and are impacted by the selection of delivery and instructional design; large case volumes have a strong positive association with RII outcomes. CONCLUSION:Interactivity and experiential learning support diagnostic-skill development in RII but are not necessary for radiology knowledge acquisition. There is a paucity of data on the role of case volume on higher-order tasks and educational interventions for high-urgency pathology detection.

Dust diseases, a group of non-malignant interstitial lung disorders caused by prolonged inhalation of dust particles, significantly contribute to the global burden of lung disease. This study evaluated the effectiveness of online self-assessment educational modules and feedback interventions in improving radiological assessment of dust diseases using chest X-ray and lung CT cases. Through a longitudinal design, radiologists and trainees participated in multiple intervention points, with progress measured from baseline to post-intervention datasets. Test sets curated by senior radiologists ensured comparability in difficulty and relevance to dust diseases. Performance improvements, measured in sensitivity, specificity, and weighted Cohen's Kappa, were evaluated using paired Wilcoxon signed-rank tests. The Kruskal-Wallis test further explored associations between participant characteristics and performance gains. Cohen's Kappa was used to assess agreement with expert ratings on radiological features. The findings demonstrated enhanced agreement with expert ratings for CT assessments following the educational interventions, particularly in identifying and grading diffuse well-rounded opacities and predominant parenchymal abnormalities. However, improvements in sensitivity and specificity were not statistically significant. For X-ray assessments, specificity improvement was notable, especially among participants with a specialty interest in lung disease. These results suggest that while educational interventions can enhance certain aspects of radiological assessment, particularly for CT evaluations, further research is needed to optimize their effectiveness across all performance metrics.

Breast cancer is the most commonly diagnosed cancer among women worldwide, and concerns regarding radiation exposure from mammography screening remain a potential barrier to participation. This scoping review explores existing models estimating long-term radiation risks associated with repeated mammography screening. A structured search across five databases (Medline, Embase, Scopus, Web of Science and CINAHL) along with manual searching identified 24 studies published between 2014 and 2024. These were categorised into three themes: (1) models estimating dose-risk profiles, (2) factors affecting radiation dose and (3) the use of artificial intelligence (AI) in dose estimation and mammographic breast density (MBD) estimation. Studies showed that breast density, compressed breast thickness (CBT) and technical imaging parameters significantly influence mean glandular dose (MGD). Modelling studies highlighted the low risk of radiation-induced cancer, inconsistencies in protocols and vendor-specific limitations. AI applications are emerging as promising tools for improving individualised dose-risk assessments but require further development for compatibility across different imaging platforms.

Silicosis is a type of occupational lung disease or pneumoconiosis that results from the inhalation of crystalline silica dust that can lead to fatal respiratory conditions. This study aims to develop an online platform and benchmark radiologists' performance in diagnosing silicosis. Fifty readers (33 radiologists and 17 radiology trainees) interpreted a test-set of 15 HRCT cases. The median AUROC for all readers combined was 0.92 (0.93 for radiologists and 0.91 for trainees). No statistical differences were observed among the radiologists and trainees for their performance. Moderate agreement was recorded among readers for the correct diagnosis of silicosis (kappa=0.57), however, there was considerable variability (kappa<0.2) in the accurate detection of irregular opacities and ground glass opacities. Our online platform shows promise in providing tailored education to clinicians and facilitating future works of long-term observer studies and development of educational solutions to enhance the diagnostic accuracy of silicosis detection.

Breast arterial calcifications (BAC) are increasingly recognized as indicative markers for cardiovascular disease (CVD). In this study, we manually annotated BAC areas on 3,330 mammograms, forming the foundational dataset for developing a deep learning model to automate assessment of BAC. Using this annotated data, we propose a semi-supervised deep learning approach to analyze unannotated mammography images, leveraging both labeled and unlabeled data to improve BAC segmentation accuracy. Our approach combines the U-net architecture, a well-established deep learning method for medical image segmentation, with a semi-supervised learning technique. We retrieved mammographic examinations of 6,000 women (3,000 with confirmed CVD and 3,000 without) from the screening archive to allow for a focused study. Utilizing our trained deep learning model, we accurately detected and measured the severity of BAC in these mammograms. Additionally, we examined the time between mammogram screenings and the occurrence of CVD events. Our study indicates that both the presence and severity (grade) of BAC, identified and measured using deep learning for automated segmentation, are crucial for primary CVD prevention. These findings underscore the value of technology in understanding the link between BAC in mammograms and cardiovascular disease, shaping future screening and prevention strategies for women's health.

The communicating safely policy, publicised by the catchphrase See Something, Say Something was released by the Medical Radiation Practice Board of Australia in 2019. It was developed to support medical radiation practitioners (MRPs) upholding the obligation to communicate urgent or unexpected findings in a timely manner, when identified on medical images. Prior to this policy being part of the professional capabilities, several untimely deaths occurred-the majority of whose causal factors could have been mitigated if imaging findings were urgently communicated by MRPs. This commentary summarises three coronial inquests that involved MRPs, discusses how these coronial findings are reflected in the communicating safely policy and provides some recommendations for the profession to ensure this policy is enacted in clinical practice.

Objective The Radiation Risk In Mammography Screening (RRIMS) model was introduced as a novel tool to help females accurately calculate their lifetime mean glandular dose (MGD) and estimate their population-level risk of radiation-induced breast cancer incidence and mortality.Methods The model's accuracy was evaluated by comparing the received MGD of 317 women who had undergone a total of 733 visits across one to four rounds of screening. This was achieved by comparing the RRIMS predicted dose values with the same examination dose calculated manually by hand. Qualitative and quantitative statistical analyses were performed to assess the percentage difference (% diff) or agreement between the two values.Results Qualitative statistical analysis using the Bland-Altman plots demonstrated a statistically significant bias for the % diff between the manually calculated and RRIMS predicted dose values, where the mean (bias) was -2.02% with an upper and lower limit of agreement of 40.24% and -44.27%, respectively. Quantitative statistical analysis revealed an intraclass correlation coefficient (ICC, 3,1) of 0.64 (p-value < 0.001) and a Kendall's W of 0.83 (p-value < 0.001).Conclusion The results indicate a statistically significant and reasonably good level of agreement between the manually calculated vs RRIMS predicted dose values. This work was focused on one of the major mammography equipment manufacturers that is Hologic, however there is potential for a multivendor applicability study of this model with future iterations. This will further improve upon this innovative dose and risk prediction tool that can empower healthcare professionals when making informed decisions and enhance patient care.Advances in knowledge This paper assesses the precision of the dose and risk model that our team has previously established. The results bring us one step closer to providing females and clinicians with a useful tool that can help explain and contextualise the benefits and risks associated with screening mammography.

Cardiovascular diseases (CVD), including coronary artery disease (CAD), continue to be the leading cause of global mortality among women. While traditional CVD/CAD prevention tools play a significant role in reducing morbidity and mortality among both men and women, current tools for preventing CVD/CAD rely on traditional risk factor-based algorithms that often underestimate CVD/CAD risk in women compared with men. In recent years, some studies have suggested that breast arterial calcifications (BAC), which are benign calcifications seen in mammograms, may be linked to CVD/CAD. Considering that millions of women older than 40 years undergo annual screening mammography for breast cancer as a regular activity, innovative risk prediction factors for CVD/CAD involving mammographic data could offer a gender-specific and convenient solution. Such factors that may be independent of, or complementary to, current risk models without extra cost or radiation exposure are worthy of detailed investigation. This review aims to discuss relevant studies examining the association between BAC and CVD/CAD and highlights some of the issues related to previous studies' design such as sample size, population types, method of assessing BAC and CVD/CAD, definition of cardiovascular events, and other confounding factors. The work may also offer insights for future CVD risk prediction research directions using routine mammograms and radiomic features other than BAC such as breast density and macrocalcifications.

Introduction/Background: In medical imaging a benefit to risk analysis is required when justifying or implementing diagnostic procedures. Screening mammography is no exception and in particular concerns around the use of radiation to help diagnose cancer must be addressed. Methods: The Medline database and various established reports on breast screening and radiological protection were utilised to explore this review. Results/Discussion: The benefit of screening is well argued; the ability to detect and treat breast cancer has led to a 91% 5-year survival rate and 497 deaths prevented from breast cancer amongst 100,000 screened women. Subsequently, screening guidelines by various countries recommend annual, biennial or triennial screening from ages somewhere between 40-74 years. Whilst the literature presents different perspectives on screening younger and older women, the current evidence of benefit for screening women < 40 and >= 75 years is currently not strong. The radiation dose and associated risk delivered to each woman for a single examination is dependent upon age, breast density and breast thickness, however the average mean glandular dose is around 2.5-3 mGy, and this would result in 65 induced cancers and 8 deaths per 100,000 women over a screening lifetime from 40-74 years. This results in a ratio of lives saved to deaths from induced cancer of 62:1. Conclusion: Therefore, compared to the potential mortality reduction achievable with screening mammography, the risk is small.

Objectives: Radiation Risk In Mammography Screening (RRIMS) builds on the prototype, formerly known as Breast-iRRISC, to develop a model that aims to establish a dose and risk profile for females by calculating their lifetime mean glandular dose (MGD) for each age of screening between 40 and 75 years, using only the information from her first screening visit. This is then used to allocate her to a dose category and estimate the lifetime risk of radiation-induced breast cancer incidence and mortality for a population of females in that category. Methods: This model training was developed using a large dataset of Hologic images containing a total of 20,232 images from 5,076 visits from 4,154 females. The female’s breast characteristics and exposure parameters were extracted from the images to calculate the female’s MGD throughout a lifetime of screening from just her first screening visit, using modelling of various parameters and their change through time. Results: This development has ultimately provided a model that uses the female’s first screening visit to calculate the received MGD for all ages of potential screening. This has enabled the allocation of females to either a low-, medium-, or high-dose category, ultimately followed by the lifetime effective risk (LER) estimation for any screening attendance pattern. A female in the low-dose category undergoing biennial screening from 50 to 74 years would expect a risk of radiation-induced breast cancer incidence and mortality of 8.64 and 2.61 cases per 100,000 females, respectively. Similarly, a female in the medium- or high-dose category undergoing the same regimen would expect an incidence and mortality risk of 11.76 and 3.55, and 15.08 and 4.55 cases per 100,000 females, respectively. Conclusions: This novel approach of establishing a female’s dose profile and lifetime risk from a single visit will further assist females in their informed consent on breast screening attendance and help inform policy-makers when exploring the benefits and drawbacks of various screening patterns and frequencies. Advances in knowledge: RRIMS is a novel tool that enables the assessment of a female’s lifetime dose and risk profile using only the information from her first screening visit.

Diagnostic efficacy in medical imaging is ultimately a reflection of radiologist performance. This can be influenced by numerous factors, some of which are patient related, such as the physical size and density of the breast, and machine related, where some lesions are difficult to visualise on traditional imaging techniques. Other factors are human reader errors that occur during the diagnostic process, which relate to reader experience and their perceptual and cognitive oversights. Given the large-scale nature of breast cancer screening, even small increases in diagnostic performance equate to large numbers of women saved. It is important to identify the causes of diagnostic errors and how detection efficacy can be improved. This narrative review will therefore explore the various factors that influence mammographic performance and the potential solutions used in an attempt to ameliorate the errors made.

Objectives: To examine whether radiologists' mammogram reading performance varies according to how long they have been awake ("hours awake") and the number of hours they slept ("hours slept") the night before a reading session. Methods: Retrospective data were retrieved from the BreastScreen Reader Assessment Strategy database. Malignancy-enriched mammographic readings were performed by 133 radiologists. Information on their hours awake and hours slept was collected. Analysis of covariance was performed to determine whether these two variables influenced radiologists' sensitivity, specificity, lesion sensitivity, receiver operating characteristic (ROC) curve, and jackknife alternative free-response ROC. Radiologists were divided into a more experienced and a less experienced groups (based on reading >= 2,000 and <2,000 mammogram readings per year, respectively). Results: The hours awake significantly influenced less experienced radiologists' lesion sensitivity (F-6,F-63 = 2.51; P = .03). Those awake for <2 hours had significantly lower lesion sensitivity than those awake for 8 to 10 hours (P = .01), and those awake for 4 to 6 hours had significantly lower lesion sensitivity than those awake for 8 to 10 hours (P = .002) and 10 to 12 hours (P = .02). The hours slept also influenced the ROC values of less experienced radiologists (F-1,F-68 = 4.96; P = .02). Radiologists with up to 6 hours of sleep had a significantly lower value (0.72) than those who had slept more than 6 hours (0.77). No statistically significant findings were noted for more experienced radiologists. Conclusion: Inexperienced radiologists' performance may be influenced by the hours awake and hours slept before reading sessions.

OBJECTIVES:This work establishes the prototype of a new innovative risk model that aims to evaluate the total risk involved with screening mammography for each individual female. This has been specifically designed to accommodate any combination of lifetime screening regimes, using only the information gathered from a single mammographic examination.METHODS:This model prototype was developed with the aid of a large dataset of images from the Cancer Institute New South Wales (CINSW) with over 30,000 images from over 7000 examinations. Each examination is derived from a separate female.RESULTS:This prototype which we have called Breast Individualised Risk of Radiation-Induced Screening Cancer (Breast-iRRISC) is a novel tool for the assessment of the lifetime risk involved with screening mammography. The results demonstrate the applicability of this approach to the various screening regimes utilised around the globe, in addition to the personalised screening frequency patterns females have undergone and are likely to receive in the future.CONCLUSIONS:This unique tailored approach to risk assessment will further empower females and clinicians towards a more informed clinical decision process regarding future imaging pathways. It will also inform health policy decisions regarding alternate screening durations and intervals.ADVANCES IN KNOWLEDGE:Breast-iRRISC is a novel tool that provides females, clinicians and health policymakers around the globe with the ability to quantify the lifetime risk of radiation-induced breast cancer from screening mammography on an individual level from a single exposure.