{"title":"Syringomatous Tumor of the Nipple Manifesting as Isolated Nipple Calcifications.","authors":"Kelsey Kimyin Lee, Chloe Siyue Yang","doi":"10.1093/jbi/wbag065","DOIUrl":"https://doi.org/10.1093/jbi/wbag065","url":null,"abstract":"","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149343894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Macy Leming, Richard Sharpe, Xiaoyan Cui, Curtis Simmons, Sarah Anderson, Laura Harper
{"title":"Dermatofibrosarcoma Protuberans of the Breast: Radiologic-Pathologic Correlation.","authors":"Macy Leming, Richard Sharpe, Xiaoyan Cui, Curtis Simmons, Sarah Anderson, Laura Harper","doi":"10.1093/jbi/wbag054","DOIUrl":"https://doi.org/10.1093/jbi/wbag054","url":null,"abstract":"<p><p>Dermatofibrosarcoma protuberans (DFSP) is a rare, locally aggressive, low-to-intermediate grade fibroblastic neoplasm arising from the skin that can uncommonly involve the breast and mimic primary breast malignancy. Dermatofibrosarcoma protuberans of the breast typically presents as a palpable, slow-growing superficial mass with an associated flesh-colored or red-brown skin lesion. On mammography, DFSP most often demonstrates an oval, circumscribed, equal or high-density mass. Ultrasound typically shows an oval hypoechoic or heterogeneous circumscribed mass, frequently with internal hypervascularity. MRI commonly demonstrates a superficial mass without circumscribed margins, with T1 hypointensity, T2 hyperintensity, and avid heterogeneous or homogeneous enhancement. Histologically, DFSP demonstrates uniform spindle cells in a storiform pattern with infiltrative extension into subcutaneous fat; immunochemistry is characteristically CD34-positive. Molecular testing can confirm the diagnosis by identifying a platelet-derived growth factor receptor Beta (PDGFB) fusion (classically collagen type I alpha 1 gene [COL1A1]: PDGFB) and may be helpful in limited sampling or atypical morphology. Treatment is complete surgical resection with negative margins, with re-excision for positive margins. Although local recurrence can occur, metastasis is uncommon, and long-term disease specific survival is excellent. Careful radiologic-pathologic correlation facilitates accurate diagnosis, concordance assessment after biopsy, and appropriate management.</p>","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149343893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Basak E Dogan, B Bersu Ozcan, Stephen J Seiler, Heather McArthur, Yan Peng, A Thomas Stavros
{"title":"Changes in Breast Cancer Optoacoustic Imaging Features During Neoadjuvant Therapy and Correlation with Pathologic Response: A Feasibility Study.","authors":"Basak E Dogan, B Bersu Ozcan, Stephen J Seiler, Heather McArthur, Yan Peng, A Thomas Stavros","doi":"10.1093/jbi/wbag049","DOIUrl":"https://doi.org/10.1093/jbi/wbag049","url":null,"abstract":"<p><strong>Objective: </strong>To assess whether changes in optoacoustic/ultrasound (OA/US) imaging features during neoadjuvant chemotherapy (NAC) correlate with treatment response, compared to US-derived tumor volumetric changes.</p><p><strong>Methods: </strong>In this IRB-approved, HIPAA-compliant prospective study, 20 patients with cT1-T4, cN1-3 breast cancer underwent serial OA/US imaging at baseline, post-cycle 1, mid-therapy, and presurgery. Optoacoustic/US features, including internal vessels (OAint), internal hemoglobin (OAHb), deoxyHb, peripheral zone (OApz), and boundary zone (OAbz) were assessed using a validated scoring system. US tumor volume and OA/US changes were compared to residual cancer burden (RCB) and pathologic complete response (pCR). Responders were defined as RCB 0-II; non-responders were defined as RCB III. Comparisons were made using Wilcoxon Rank-Sum tests and univariate logistic regression.</p><p><strong>Results: </strong>Mean age was 50.4 years (SD ± 9.5). Mean tumor size was 26.3 mm (SD ± 9.7). Pathology showed pCR in 6 (30%), partial response in 11 (55%), and no response in 3 (15%), with mean overall residual tumor cellularity of 32.7% (SD ± 33.5). Regression analysis showed no significant correlation between percent volume change and pCR at cycle1 or mid-therapy. Patients achieving pCR had significantly lower residual OAHb after cycle 1 (76.4% vs 108.8%, P = 0.01). At preoperative, all OA/US features decreased significantly more in pCR vs non-pCR cases (all P < 0.05). Higher individual and total OA/US scores at cycle 1 reflecting elevated hemoglobin and lower relative oxygen saturation predicted RCB III status. The RCB III tumors had significantly higher mean residual deoxygenated blush score at cycle 1 (117.8% vs 64.8%, P = 0.03).</p><p><strong>Conclusion: </strong>Optoacoustic/US feature changes were more highly correlated with pCR than US volumetric decrease and show promise as a potential tool to non-invasively identify pCR. Early cycle 1 OA/US scores may help identify poor responders.</p>","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149343892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kathryn W Zamora, Kristen Coffey, Stephanie Colvin, Brittany Dashevsky, Katerina Dodelzon, Santo Maimone, Jessica H Porembka, Wenhui Zhou, Sona A Chikarmane
{"title":"Clinical Implications of Background Parenchymal Enhancement on Breast MRI.","authors":"Kathryn W Zamora, Kristen Coffey, Stephanie Colvin, Brittany Dashevsky, Katerina Dodelzon, Santo Maimone, Jessica H Porembka, Wenhui Zhou, Sona A Chikarmane","doi":"10.1093/jbi/wbag059","DOIUrl":"https://doi.org/10.1093/jbi/wbag059","url":null,"abstract":"<p><p>Breast MRI is an essential tool for breast cancer detection, evaluation, and characterization, offering greater sensitivity than mammography and ultrasound. Normal breast tissue demonstrates variable enhancement on MRI, known as background parenchymal enhancement (BPE), which reflects the physiologic enhancement of fibroglandular tissue after gadolinium administration. Initially considered an incidental finding, BPE is now recognized as a dynamic imaging feature influenced by several factors, including age, menopausal status, exogenous hormone use, and prior breast cancer treatments. Increasing evidence supports its clinical relevance since variations in BPE have been associated with differences in breast cancer risk, lesion detection, and imaging interpretation. Background parenchymal enhancement (BPE) is emerging as an important imaging biomarker with potential applications in risk stratification, evaluation of disease extent, and monitoring response to neoadjuvant therapy. Differences in BPE patterns may also correlate with tumor biology and molecular subtypes, further supporting its role in personalized breast imaging assessment. This article provides a comprehensive review of BPE, highlighting its biologic basis, imaging characteristics, and clinical implications in breast cancer care. It also examines the evolving role of artificial intelligence tools in the assessment and quantification of BPE, which may improve standardization and integration into clinical decision-making and research.</p>","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149335536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Incidental Male Breast Ductal Carcinoma in Situ (DCIS) in a Papilloma.","authors":"Jessica Ghobrial, Lori Gallardo","doi":"10.1093/jbi/wbag063","DOIUrl":"https://doi.org/10.1093/jbi/wbag063","url":null,"abstract":"","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149335537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Innovative Learning Tools in Breast Imaging.","authors":"Benjamin Vega, Yiming Gao","doi":"10.1093/jbi/wbag060","DOIUrl":"https://doi.org/10.1093/jbi/wbag060","url":null,"abstract":"<p><p>Radiology and breast imaging curricula have relied almost entirely on passive learning tools such as lectures, books, journal articles, and videos for more than two decades. Despite their wide availability, trainee engagement with these tools to accumulate and synthesize the vast amount of information required to succeed in radiology remains challenging. Knowledge gaps exist among trainees because of natural differences in learning styles, study habits, and case exposure at the reading station. Further, current pressures in academic radiology limit the availability of workstation teaching, which is the most effective teaching and learning strategy in the field. Leading educators aim to bridge these gaps both by leveraging artificial intelligence (AI) large language models (LLM) to develop precision learning curricula personalized to the trainee and by creating gamified learning tools to boost the engagement of trainees. Gamification can also be used to simulate learning experiences for trainees. These tools show promise based on user feedback, both by educators and learners. Further, the synergy of AI and gamification strategies may help address knowledge gaps precisely and efficiently. We explore some of these emerging tools, their application, potential benefits, and limitations within radiology with a focus on breast imaging training.</p>","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149240069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kazim Ayberk Sinci, Mehmet Aksit, Merve Gursoy Bulut
{"title":"Benchmark Evaluation of Vision-Enabled Large Language Models in Mammography: A Case-Control Study.","authors":"Kazim Ayberk Sinci, Mehmet Aksit, Merve Gursoy Bulut","doi":"10.1093/jbi/wbag038","DOIUrl":"https://doi.org/10.1093/jbi/wbag038","url":null,"abstract":"<p><strong>Objective: </strong>To compare the diagnostic performance of five contemporary vision-enabled large language models (LLMs) in mammography interpretation using a case-control benchmark design.</p><p><strong>Methods: </strong>A total of 200 cases were analyzed using a quota-balanced case-control design (100 malignant, BI-RADS 4-5; 100 controls, BI-RADS 1-2). All models (ChatGPT-5T, ChatGPT-5I, ChatGPT-4o, Gemini 2.5 Pro, and Gemini 2.5 Flash) received standard mammography images. Models were evaluated for lesion detection, laterality, quadrant localization, lesion type, and malignant-benign discrimination. Performance was assessed using accuracy, sensitivity, specificity, balanced accuracy, Cohen's κ, and area under the receiver operating characteristic curve (AUC). Breast density was recorded for all cases, while histopathological subtype and lesion size were documented for malignant cases.</p><p><strong>Results: </strong>Lesion detection accuracy ranged from 79% to 91%, with high malignant sensitivity (92%-100%) but lower specificity in normal cases (24%-82%). ChatGPT-5T performed best in laterality (83%; κ = 0.70) and quadrant localization (73%; κ = 0.62). Lesion type classification was modest (74%-85%). In malignant-benign discrimination, ChatGPT-5T achieved the highest balanced accuracy (87%), while ChatGPT-4o showed poor specificity (28%). The study cohort was predominantly composed of lower-density breasts, larger lesions, and invasive ductal carcinoma as the most common subtype.</p><p><strong>Conclusion: </strong>Vision-enabled LLMs demonstrated high sensitivity for breast lesion detection and classification tasks. More deliberative models, particularly ChatGPT-5T, consistently outperformed faster counterparts, especially in spatial reasoning tasks. However, reduced specificity in normal cases underscores that current LLM outputs should remain under radiologist supervision as supportive second-reader tools rather than standalone diagnostic systems. Given the quota-balanced design and cohort composition, results should be interpreted as comparative benchmarking rather than real-world diagnostic performance.</p>","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149240077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mei Wei, Lisa Pappas, Margaret Van Meter, Phoebe Freer, Saundra S Buys, Karen Curtin
{"title":"Clinical Characteristics of Interval Breast Cancer Diagnosed Within 12 Months of a Normal Screening Mammogram Compared with Those Diagnosed Between 13-24 Months in Utah.","authors":"Mei Wei, Lisa Pappas, Margaret Van Meter, Phoebe Freer, Saundra S Buys, Karen Curtin","doi":"10.1093/jbi/wbag036","DOIUrl":"https://doi.org/10.1093/jbi/wbag036","url":null,"abstract":"<p><strong>Objective: </strong>Interval breast cancer (IBC) is detected after a negative/benign screening mammogram, but before the next expected screening mammogram. This study examined clinical characteristics and risk factors for 1-12 month (12 m IBC) and 13-24 month (24 m IBC).</p><p><strong>Methods: </strong>Utah medical records linked to cancer data were used to define a cohort of 149 769 women age 38-79 years with no history of breast cancer prior to a first-observed screening mammogram between 2005-2019, with at least one normal or benign (including probably benign) result. Index screening mammogram was defined as the last normal/benign mammogram before a diagnostic mammogram or clinical encounter leading to a breast cancer diagnosis, but before the next expected screening. Cancers identified by the diagnostic mammogram or clinical encounter after the index mammogram defined an IBC. Clinical characteristics of 12 m IBC were compared to 24 m IBC using multivariable logistic regression.</p><p><strong>Results: </strong>The study population included 2122 women with IBC: 486 (22.9%) 12 m IBC and 1636 (77.1%) 24 m IBC. Compared to those ≥70 years, younger women were more likely to develop 12 m vs 24 m IBC (eg, age 38-49 years, OR = 2.34, 95%CI: 1.61-3.40, P < 0.01). Compared to 24 m IBC, 12 m IBC was associated with higher odds of axillary lymph node metastases (OR = 1.68, 95%CI: 1.29-2.19, P < 0.01); HER2+ cancer (OR = 2.10, 95%CI: 1.36-3.22, P < 0.01); triple negative cancer (OR = 2.08, 95%CI: 1.26-3.39, P < 0.01); and extremely dense breast tissue (OR = 2.05, 95%CI: 1.13-3.80, P < 0.01).</p><p><strong>Conclusion: </strong>12 m IBC may be more aggressive than 24 m IBC. Women under 70 years old may benefit from annual instead of biennial screening mammogram.</p>","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149240084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Vision-Enabled Large Language Models in Mammography: From Benchmarking to Clinical Accountability.","authors":"Yuki Arita, Noam Nissan","doi":"10.1093/jbi/wbag058","DOIUrl":"https://doi.org/10.1093/jbi/wbag058","url":null,"abstract":"","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149240103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Commentary on \"Dual-Layer Spectral CT-Based Models for the Differential Diagnosis of Breast Lesions\".","authors":"Eren Yeh","doi":"10.1093/jbi/wbag026","DOIUrl":"10.1093/jbi/wbag026","url":null,"abstract":"","PeriodicalId":43134,"journal":{"name":"Journal of Breast Imaging","volume":" ","pages":"509-511"},"PeriodicalIF":1.7,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}