To determine if lesion conspicuity on contrast-enhanced mammography (CEM) is independently associated with malignancy. This retrospective, single-institution study identified consecutive abnormal screening and diagnostic CEMs between January 2019 and December 2021. The conspicuity of enhancing lesions on CEM recombined images was graded (low, moderate, or high) by one or both breast radiologists assigned as readers for the study, blinded to two-year imaging follow-up or biopsy pathology results. The positive predictive value (PPV) for malignancy was determined for each level of conspicuity. Across 476 CEM examinations in 455 women (median age, 49 years; IQR: 44–57), there were 563 enhancing lesions (55 malignant, 508 benign). Of the 563 enhancing lesions, 52

Purpose To determine the interval cancer rate (ICR) after negative screening contrast-enhanced mammography (CEM) and compare the characteristics of interval cancers (ICs) with those of CEM screen-detected cancers. Materials and Methods This retrospective, single-institution study included consecutive screening CEM examinations performed from January 2015 through December 2021. ICs diagnosed within 1 year of a negative screening CEM and all CEM screen-detected cancers were identified. Two breast radiologists independently reviewed prior negative CEM examinations to classify ICs as missed, misinterpreted, or occult. Patient- and lesion-level characteristics were compared between ICs and screen-detected cancers using the Wilcoxon rank sum test for continuous variables and the Fisher exact or χ2 tests for categorical variables. Results The study included 6911 screening CEM examinations in 2756 female patients (median age, 53 years; IQR, 47-60 years). Among 6120 negative screening examinations, 14 ICs were diagnosed in 14 patients. The overall ICR was 2.29 cancers per 1000 examinations, and the symptomatic ICR was 0.82 per 1000 examinations (five of 6120). ICs accounted for 13% (14 of 106) of all cancers diagnosed (interval and screen detected). Invasive ICs occurred more frequently in the setting of moderate or marked background parenchymal enhancement than screen-detected cancers (six of eight, 75% vs 17 of 57, 30%; P = .02). Most ICs (10 of 14, 71%) were occult on prior screening CEM. Conclusion The ICR after CEM was 2.29 cancers per 1000 examinations, representing 13% of all cancers diagnosed. Most ICs were occult at prior CEM, and invasive ICs were more frequently associated with moderate or marked background parenchymal enhancement when compared with CEM screen-detected cancers. Keywords: Mammography, Breast, Interval Cancers Supplemental material is available for this article. © RSNA, 2026.

Background Studies have reported the value of contrast-enhanced mammography (CEM) for screening women at increased risk for breast cancer, based on prevalence ("baseline") screening. Purpose To compare the performance of CEM between prevalence and incidence screens in women at increased risk for breast cancer. Materials and Methods This retrospective study included CEM screens from January 2015 through December 2021. Screens were categorized as prevalence if there was no prior breast MRI in the past 3 years or no prior CEM; all others were incidence screens. Performance metrics, including cancer detection rate (CDR), incremental CDR (cancers found through enhancement on recombined images with negative low-energy [26-30 kVp] images), sensitivity, specificity, positive predictive value, negative predictive value, and accuracy, were compared between prevalence and incidence screens. Reference standards for malignant and benign results were biopsy or negative imaging follow-up in 1 year. P values were estimated using a generalized estimating equation model. Results Of 6911 screens in 2756 women (median age, 52 years [IQR, 46-58 years]), 1575 (22.8%) were prevalence screens and 5336 (77.2%) were incidence screens. Adjusting for the number of screens per individual, there was no evidence of a difference in CDR between prevalence and incidence screens (19 cancers per 1000 prevalence screens vs 11.6 cancers per 1000 incidence screens; P = .65) or in incremental CDR (11.4 per 1000 prevalence screens vs 6.7 per 1000 incidence screens; P = .10). Incidence CEM had higher specificity than prevalence CEM (91.5% [95% CI: 90.7, 92.2] vs 83.4% [95% CI: 81.6, 85.4]; P = .008), and higher accuracy (91.4% [95% CI: 90.6, 92.2] vs 83.5% [95% CI: 81.7, 85.4]; P = .01). Contrast enhancement alone helped detect 18 of 30 (60%) cancers during prevalence screening and 36 of 62 (58%) during incidence screening. Conclusion CEM continues to help detect cancers during incidence screening with improved specificity compared with prevalence screens. © RSNA, 2026 Supplemental material is available for this article. See also the editorial by Freitas in this issue.

Objectives: Asymmetries on screening contrast-enhanced mammography (CEM) often lead to patient recall. However, in diagnostic settings, negative CEM has effectively classified these as normal or benign, questioning the need for further workup of non-enhancing asymmetries (NEAs). Material and methods: A computational search of all screening CEM examinations performed between December2012 and June-2021 was conducted to identify cases reporting NEAs. Their diagnostic workup was reviewed, and the positive predictive value for cancer was statistically compared to that of enhancing asymmetries on screening CEMs. Results: During the study period, 97 cases of 106 NEAs were identified among 3,482 screening CEM exams (2.8 %). NEAs were classified as asymmetry (n = 83), focal asymmetry (n = 22), and global asymmetry (n = 1), with no cases of developing asymmetry. The mean size of NEAs was 1.0 +/- 0.7 cm (range: 0.3-4.9 cm). Diagnostic workup for NEAs included additional mammographic views (AMV) (n = 63), AMV plus ultrasound (n = 30), AMV plus MRI (n = 1), and all three modalities (n = 3), leading to four biopsies. None of the NEAs were malignant on follow-up, as opposed to enhancing asymmetries (P < 0.05). Conclusion: NEAs detected on CEM were relatively uncommon and were usually investigated with additional mammographic views and US, yielding no cancer. Ruling out malignancy based on lack of enhancement without further workup may reduce patient recall rates and improve CEMs specificity.

Abstract Bladder cancer is the 10th most common and 13th most deadly cancer worldwide, with urothelial carcinomas being the most common type. Distinguishing between non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC) is essential due to significant differences in management and prognosis. MRI may play an important diagnostic role in this setting. The Vesical Imaging Reporting and Data System (VI-RADS), a multiparametric MRI (mpMRI)-based consensus reporting platform, allows for standardized preoperative muscle invasion assessment in BCa with proven diagnostic accuracy. However, post-treatment assessment using VI-RADS is challenging because of anatomical changes, especially in the interpretation of the muscle layer. MRI techniques that provide tumor tissue physiological information, including diffusion-weighted (DW)- and dynamic contrast-enhanced (DCE)-MRI, combined with derived quantitative imaging biomarkers (QIBs), may potentially overcome the limitations of BCa evaluation when predominantly focusing on anatomic changes at MRI, particularly in the therapy response setting. Delta-radiomics, which encompasses the assessment of changes (Δ) in image features extracted from mpMRI data, has the potential to monitor treatment response. In comparison to the current Response Evaluation Criteria in Solid Tumors (RECIST), QIBs and mpMRI-based radiomics, in combination with artificial intelligence (AI)-based image analysis, may potentially allow for earlier identification of therapy-induced tumor changes. This review provides an update on the potential of QIBs and mpMRI-based radiomics and discusses the future applications of AI in BCa management, particularly in assessing treatment response. Critical relevance statement Incorporating mpMRI-based quantitative imaging biomarkers, radiomics, and artificial intelligence into bladder cancer management has the potential to enhance treatment response assessment and prognosis prediction. Key Points Quantitative imaging biomarkers (QIBs) from mpMRI and radiomics can outperform RECIST for bladder cancer treatments. AI improves mpMRI segmentation and enhances radiomics feature extraction effectively. Predictive models integrate imaging biomarkers and clinical data using AI tools. Multicenter studies with strict criteria validate radiomics and QIBs clinically. Consistent mpMRI and AI applications need reliable validation in clinical practice. Graphical Abstract

Introduction:The surveillance scheme for early detection of breast cancer (BC) in BRCA1/BRCA2 (=BRCA) PSV carriers in Israel includes semiannual imaging: MRI alternating with ultrasound (US) from age 25 to 29 years, with mammography (MG) replacing US from age 30 onward. The purpose of the study was to assess the added value and yield of MG/US to annual screening MRI in the surveillance scheme of young BRCA PSV carriers when BC was diagnosed ≤35 years of age. Methods:This retrospective study encompassed female BRCA PSV carriers attending the Meirav high-risk clinic at Sheba Medical Center, who were diagnosed with BC ≤35 years after joining the clinic between 2010 and 2023. Relevant clinical, radiological, pathological, genetic data, and imaging modalities used were retrieved from the computerized-archiving system, using an IRB-approved protocol. Results:Overall, 28/1,375 BRCA PSV carriers undergoing surveillance at the clinic during the study period met the inclusion criteria: 24/28 (86%) were BRCA1, and 4/28 (14%) were BRCA2 PSV carriers. In 17/28 (61%), BC was diagnosed by screening MRI and in 11/28 (39%) by MG/US (p > 0.05), of whom 7 underwent MG/US because they were either pregnant or breastfeeding. In the group diagnosed by MG/US, 5/11 had a palpable mass (interval cancers) and none in the MRI group. In 17/24 non-pregnant patients, BC was diagnosed by MRI (p = 0.03). Mean MRI-diagnosed tumor size was 12.5 ± 6.2 mm (range 5-30 mm) and 24.6 ± 13.8 mm for MG/US-based diagnosed tumors (range 6-50 mm) (p = 0.003). Conclusion:In the current study, young (≤35 years) BRCA PSV carriers diagnosed with BC were effectively diagnosed by MRI screening, and MRI-diagnosed BCs were smaller than MG/US-diagnosed BC. Thus, it seems that MRI screening is sufficient for early-stage BC detection in young, non-pregnant or breastfeeding BRCA PSV carriers with no palpable breast mass. For pregnant BRCA PSV carriers, US surveillance seems important to minimize risk for interval cancers.

Objective Quantitative changes in mammographic properties during pregnancy and lactation remain underexplored. Therefore, the purpose of this study was to quantify mammographic changes in the breast from prepregnancy through lactation to postweaning at the individual level. Methods Mammograms of 39 women at elevated risk (mean age 38.7 years) who underwent 3 sequential examinations spanning the lactation period were retrospectively analyzed. Volpara-derived mammographic properties, including breast volume, fibroglandular tissue volume, volumetric breast density, compression force, and radiation dose, were automatically extracted and were statistically compared between the periods. Results Significant longitudinal changes in breast tissue were observed. During lactation, breast volume increased by 45%, fibroglandular tissue volume increased by 138.5%, and volumetric breast density increased by 53.2% compared with prepregnancy levels (P <.001 for all). After weaning, these values decreased by 23.3%, 52.8%, and 27.3%, respectively, compared with lactation (P <.001 for all). Breast compression was decreased by 22.3% on average during lactation compared with prepregnancy (P <.001), while it was not different between lactation and postweaning (P = .11). The radiation dose during lactation increased by 20% compared with both prepregnancy (P = .004) and postweaning (P = .005). Conclusion The temporal changes in mammographic properties from prepregnancy to lactation include significant increases in breast volume, fibroglandular tissue volume, breast density, and radiation dose, along with a decrease in compression force. While these changes reverse from lactation to postweaning, they generally do not return to prepregnancy levels.

OBJECTIVES:Background parenchymal enhancement (BPE) and mammographic density (MD) are imaging biomarkers derived from contrast-enhanced mammography (CEM). However, unlike MD, the consistency of BPE across consecutive examinations in pre- and postmenopausal women has remained unexplored. MATERIALS AND METHODS:A computational search was conducted for all screening CEM exams performed at our facility between December-2012 and January-2024 to identify patients with at least five consecutive negative annual screenings. BPE grades and MD categories were extracted from the official radiology reports, and their variability parameters were statistically compared both between these factors and across age groups. RESULTS:Forty-five eligible patients at premenopausal age-group were identified (mean age at first scan 38.2 ± 3.4 years, range: 27-42) and a matched postmenopausal age-group was assembled (mean age at first scan 63.7 ± 3.8 years, range: 60-74), resulting in 450 CEMs analyzed. BPE demonstrated greater variability than MD, including fluctuations of at least one category on the scale (71.1-91.1 %), two-category changes (17.8-22.2 %), and transitions between low and high binary categories (17.8-27.7 %) (P < 0.01 for all). Similar rates of two-category BPE transitions (P = 0.65) and shifts between low and high binary categories (P = 0.32) were observed in pre- and postmenopausal women; however, the latter group had a significantly smaller proportion of cases with five consistent grades (P = 0.02). CONCLUSION:BPE on CEM demonstrates greater longitudinal variability than MD across all age groups and is not more pronounced in premenopausal compared to postmenopausal women. This highlights its dynamic nature and underscores the need for caution when considering BPE in clinical decision-making or as a biomarker, while also suggesting that strict menstrual cycle phase targeting may be less critical.

Breast cancer detection improved with contrast-enhanced mammography compared with low-energy imaging alone or low-energy imaging with whole-breast US.

OBJECTIVE:To evaluate the T2 signal intensity (SI) of axillary lymph nodes as a potential functional imaging marker for metastasis in patients with mucinous breast cancer. METHODS:A retrospective review of breast MRIs performed from April 2008 to March 2024 was conducted to identify patients with mucinous breast cancer and adenopathy. Two independent, masked readers qualitatively assessed the T2 SI of tumors and lymph nodes. The T2 SI ratio for adenopathy and contralateral normal lymph nodes was quantitatively measured using the ipsilateral pectoralis muscle as a reference. Comparisons between malignant and nonmalignant lymph nodes were made using the chi-square test for qualitative assessments and the Mann-Whitney U test for quantitative assessments. RESULTS:Of 17 patients (all female; mean age, 48.4 ± 10.7 years; range: 29-80 years), 12 had malignant nodes, while 5 had benign nodes. Qualitative assessment revealed that the primary mucinous breast cancer was T2 hyperintense in most cases (88.2%-94.1%). No significant difference in qualitative T2 hyperintensity was observed between malignant and nonmalignant nodes (P = .51-.84). Quantitative T2 SI ratio parameters, including the ratio of mean and minimal node T2 SI to mean ipsilateral pectoralis muscle T2 SI, were higher in malignant nodes vs benign and contralateral normal nodes (P <.05). CONCLUSION:Metastatic axillary lymph nodes exhibit high T2 SI, which could serve as a functional biomarker beyond traditional morphological assessment. Future studies should prioritize investigating more precise measurements, such as T2 mapping, and confirm these results in larger groups and across mucinous neoplasms in other organs.

Contrast-enhanced mammography (CEM) has increasingly been established as a valuable tool in breast imaging that enhances lesion detection and characterization by combining functional and anatomical information. This review highlights the recent key advances in CEM technology, explores its expanding clinical applications, and discusses the common interpretation pitfalls and current limitations. Instead of offering a comprehensive overview, this review focuses on providing a case-based perspective on emerging applications and how CEM can be efficiently incorporated into clinical practice. Through illustrative case examples, we offer practical insights into optimizing breast imaging strategies and demonstrate how CEM can effectively complement other imaging modalities in both routine practice and complex diagnostic scenarios.

Objective This review provides a comprehensive overview of the current research landscape on artificial intelligence (AI) in prostate cancer (PCa) management, highlighting its potential to enhance diagnosis, improve medical image quality, facilitate risk stratification, and aid prognosis. The review also identifies opportunities and challenges associated with integrating AI into clinical practice. Methods This review synthesizes findings from recent studies on AI applications in PCa management. It examines the use of machine learning and deep learning techniques in diagnostic imaging, surgical skill assessment, and outcome prediction. The analysis emphasizes empirical evidence demonstrating the efficacy and limitations of AI models in clinical settings. Results AI, particularly machine learning and deep learning algorithms, is improving diagnostic accuracy by analyzing medical images with greater efficiency and precision compared to traditional methods. AI-based tools are also being developed for surgical skill assessment, offering objective evaluations and feedback to surgeons. Additionally, AI applications in predicting patient outcomes are facilitating the creation of personalized treatment plans. Empirical evidence shows that AI models exhibit higher sensitivity and specificity in detecting clinically significant PCa, outperforming conventional diagnostic techniques. Conclusion AI holds significant promise for transforming PCa management by improving diagnostic accuracy, personalizing treatment plans, and enhancing patient outcomes. While the evidence underscores its potential, challenges such as the need for larger, more diverse datasets and addressing implementation barriers remain critical. Despite these hurdles, the benefits of AI in PCa management represent a compelling area for future research and clinical integration.

Background parenchymal enhancement observed at contrast-enhanced mammography decreased with menopause and use of tamoxifen and increased with lactation, hormone replacement therapy use, and tamoxifen cessation, suggesting these effects should be considered at imaging interpretation.

Benign breast disease (BBD), particularly with proliferative changes, is a risk factor for breast cancer (BC) development in average risk women. There is a paucity of data on high-risk, BRCA1 and BRCA2 pathogenic variants (PVs) carriers. Female BRCA1 and BRCA2 PV carriers treated at the Meirav Clinic, Sheba Medical Center between May 2011 and December 2024 were eligible. Data on in-hospital breast biopsies were retrieved following an ethically approved protocol. Statistical analyses included χ2 test (categorical variables) Mann–Whitney U test (continuous variables) and logistic regression for multivariate analysis. Overall, 1466 women (849 BRCA1 PV carriers) were monitored over 10,113 women/years. A total of 1453 biopsies were carried out in 454 participants (range 1–8 biopsies), with the majority (76.3

PURPOSE:To evaluate the role of mammography in the diagnostic workup of pregnancy-associated breast cancer (PABC). MATERIALS AND METHODS:This retrospective single-institution study included patients diagnosed with PABC from February 2009 to January 2024 and imaged by mammography. The additional diagnostic value of mammography as statistically compared with ultrasound (US) was evaluated, focusing on rate of initial detection, identification of additional cancer, changes in lesion size ≥1 cm, and changes in T-staging. RESULTS:A total of 167 patients with newly diagnosed PABC were included (mean age, 37.0 years ±4.4), including 30/167 (18 %) who were pregnant (mean pregnancy duration, 6.3 months ±2.7) and 137/167 (82 %) who were lactating. Almost all patient had dense breasts (163/167, 97.6 %), including 77 % with extremely dense breasts. Most PABCs (137/167, 82.0 %) were visible on mammography, including cases in which mammography was the sole detection modality (n = 21), had additional positive stereotactic biopsy (n = 17, 10.2 %), showed changes in lesion size by ≥1 cm (n = 35, 21.0 %) (P < 0.001), or changed the T-staging (n = 35, 21.0 %). Excluding cases with duplicate contributions, mammography added value in 64/167 (38.3 %) patients. CONCLUSION:Despite the high proportions of increased mammographic density, mammography successfully demonstrated most pregnancy-associated breast cancers and frequently provided valuable additional information for their evaluation. Regardless of how PABC presents clinically, mammography and US must serve as complementary tools in the diagnostic evaluation of PABC.

Background Mammogram interpretation is challenging in female patients with extremely dense breasts (Breast Imaging Reporting and Data System [BI-RADS] category D), who have a higher breast cancer risk. Contrast-enhanced mammography (CEM) has recently emerged as a potential alternative; however, data regarding CEM utility in this subpopulation are limited. Purpose To evaluate the diagnostic performance of CEM for breast cancer screening in female patients with extremely dense breasts. Materials and Methods This retrospective single-institution study included consecutive CEM examinations in asymptomatic female patients with extremely dense breasts performed from December 2012 to March 2022. From CEM examinations, low-energy (LE) images were the equivalent of a two-dimensional full-field digital mammogram. Recombined images highlighting areas of contrast enhancement were constructed using a postprocessing algorithm. The sensitivity and specificity of LE images and CEM images (ie, including both LE and recombined images) were calculated and compared using the McNemar test. Results This study included 1299 screening CEM examinations (609 female patients; mean age, 50 years ± 9 [SD]). Sixteen screen-detected cancers were diagnosed, and two interval cancers occured. Five cancers were depicted at LE imaging and an additional 11 cancers were depicted at CEM (incremental cancer detection rate, 8.7 cancers per 1000 examinations). CEM sensitivity was 88.9% (16 of 18; 95% CI: 65.3, 98.6), which was higher than the LE examination sensitivity of 27.8% (five of 18; 95% CI: 9.7, 53.5) (P = .003). However, there was decreased CEM specificity (88.9%; 1108 of 1246; 95% CI: 87.0, 90.6) compared with LE imaging (specificity, 96.2%; 1199 of 1246; 95% CI: 95.0, 97.2) (P < .001). Compared with specificity at baseline, CEM specificity at follow-up improved to 90.7% (705 of 777; 95% CI: 88.5, 92.7; P = .01). Conclusion Compared with LE imaging, CEM showed higher sensitivity but lower specificity in female patients with extremely dense breasts, although specificity improved at follow-up. © RSNA, 2024 See also the editorial by Lobbes in this issue.

To summarize our institutional experience with contrast-enhanced mammography (CEM) exams reporting asymmetric background parenchymal enhancement (BPE). Consecutive CEMs performed between December 2012 and July 2023 were retrospectively reviewed to identify exams reporting asymmetric BPE. Associated factors, the level of reporting certainty, BI-RADS score, diagnostic workup, and clinical outcome were summarized. BPE grades and BI-RADS were compared between initial CEM vs. immediate MRI and 6-month follow-up CEM, when indicated, using the Sign test. Overall, 175/12,856 (1.4