Background: Although breast density is an important determinant of breast cancer risk and the likelihood of masking pathological lesions on mammography, it is insufficient to fully characterize the breast imaging phenotype on its own. Age, body mass index (BMI), total body fat percentage, breast size, compressed breast thickness, tissue distribution, and reproductive history influence not only the biological composition of the breast but also the technical conditions of mammographic imaging. Aim: To synthesize the evidence on how age, BMI, body composition, breast-specific anthropometric characteristics, reproductive factors, and population-specific characteristics influence mammographic imaging. Materials and Methods: In this review, we synthesized evidence from studies indexed in PubMed/MEDLINE, Scopus, Embase, and Web of Science from 2000 through August 2026, focusing on the associations of these factors with mammographic appearance, lesion conspicuity, BI-RADS classification, image quality, radiation dose, and screening performance. Result: Breast density generally decreases with advancing age and during the menopausal transition. Increasing BMI and adipose tissue volume are also associated with lower breast tissue density. Therefore, the absolute volume of fibroglandular and connective tissue should not be inferred directly from percent breast density alone. Breast-specific parameters, particularly compressed breast thickness and breast volume, are clinically important because they influence positioning, compression, exposure parameters, and mean glandular dose. Studies in Asian cohorts have demonstrated significant associations between age, body size, and mammographic characteristics, although substantial inter-population differences have been reported. Advances in digital breast tomosynthesis (DBT) and artificial intelligence (AI) are enabling a transition from single-category breast density assessment toward multidimensional breast phenotyping. Future research should integrate DICOM technical parameters, standardized anthropometric measurements, quantitative breast density measures, and externally validated AI-derived features to improve personalized screening and radiation dose optimization. Conclusion Breast imaging phenotype should be considered a multidimensional construct integrating breast density with age, body composition, breast spatial architecture, imaging parameters, and validated AI-derived features. This approach may improve biological interpretation, radiation dose estimation, and risk stratification while avoiding the oversimplification that a single breast-density percentage or BI-RADS density category can fully characterize the breast phenotype.

Background: Although breast cancer incidence is rising in Mongolia, little is known about how mammographic findings and BI-RADS final assessment categories are recorded in routine clinical practice. Aim: To describe report-derived finding categories and BI-RADS final assessments in a single-centre mammography registry, and to examine the association of age with BI-RADS ≥3. Materials and Methods: In this retrospective analytical cross-sectional analysis of 773 mammographic examination records, the earliest examination per participant was retained, yielding 733 women aged 20–74 years. Free-text findings were assigned to mutually exclusive categories using prespecified hierarchical keyword rules, and BI-RADS categories 3 and 4 were combined as “BI-RADS ≥3”. Group differences were examined with Pearson’s χ² test and the age association with logistic regression; a body mass index (BMI)-adjusted model was fitted in 258 women with recorded height and weight. Results: Mean age was 44.2±10.8 years. The most frequent report categories were no lesion (28.4%), calcification (20.1%), density-related descriptors (19.8%) and other benign/structural findings (16.0%). BI-RADS categories 1, 2, 3 and 4 were recorded in 312 (42.6%), 342 (46.7%), 65 (8.9%) and 14 (1.9%) women, respectively, and BI-RADS ≥3 in 79 (10.8%; 95% CI 8.7–13.2). This proportion differed across age groups (χ²=12.72; P=0.026). Each additional decade of age was associated with higher odds of BI-RADS ≥3 (OR 1.44; 95% CI 1.16–1.79; P=0.001), and the association persisted after BMI adjustment (OR 1.62; 95% CI 1.10–2.36; P=0.013). BMI was not associated with BI-RADS ≥3. Conclusions 1. Among the 733 women examined at a single hospital, the most common mammographic findings were no significant abnormalities (28.4%), calcifications (20.1%), density-related findings (19.8%), and other benign or structural changes (16.0%). 2. Of the final assessments, 89.2% were classified as BI-RADS 1–2, while 10.8% were classified as BI-RADS 3–4. No cases were classified as BI-RADS 0 or BI-RADS 5. 3. For every 10-year increase in age, the odds of receiving a BI-RADS score of ≥3 increased by a factor of 1.44. This association remained independent of body mass index (BMI).

Background: Chest radiography is a fundamental imaging modality used to diagnose acute and chronic pulmonary diseases. It is relatively inexpensive, rapid, and can be performed at the bedside. Pulmonary abnormalities identified on chest radiographs are generally classified into two main categories: diffuse and focal. Depending on lesion size and image quality, abnormalities can be detected with an estimated accuracy of 70–85%. However, radiologists may overlook findings due to several factors, including heavy workloads, emergency conditions, and the presence of small focal lesions measuring less than 1 cm. Previous studies evaluating the application of artificial intelligence (AI) to chest radiographs for detecting lung cancer, COVID-19, and pneumonia have reported that the sensitivity of diagnostic interpretations improves from 88% to 95% when radiologists and AI work together. Aim: To evaluate selected thoracic abnormalities on chest radiographs using artificial intelligence and compare the results with radiologists’ interpretations. Materials and Methods: This retrospective study was conducted in the Department of Radiology at the Mongolia–Japan Hospital of the Mongolian National University of Medical Sciences. A total of 845 chest radiographs obtained between September 10 and September 30, 2022, were reviewed. After applying the exclusion criteria, 721 chest radiographs were included. The interpretations provided by four radiologists were compared with the results generated by an AI system. Results: A total of 721 posteroanterior chest radiographs were included in the study, comprising 377 images from male patients and 344 from female patients. By age group, the images included 24 from patients aged 10–19 years, 114 from those aged 20–29 years, 150 from those aged 30–39 years, 147 from those aged 40–49 years, 97 from those aged 50–59 years, 96 from those aged 60–69 years, 58 from those aged 70–79 years, and 37 from those aged 80–89 years. Radiologists identified abnormalities in 331 (46%) radiographs and reported no abnormalities in 390 (54%). In comparison, the AI system classified 392 (54%) radiographs as abnormal and 329 (46%) as normal. Using the radiologists’ interpretations as the reference standard, the AI system demonstrated a specificity of 95.8% and a sensitivity of 89% for detecting abnormalities on chest radiographs. Conclusion The AI system demonstrated high sensitivity and specificity in detecting abnormalities on chest radiographs, suggesting its potential utility in clinical practice. Its application may be particularly beneficial in supporting the interpretation of chest radiographs used for preventive screening and early detection of pulmonary abnormalities.