Breast Cancer Research最新文献

{"title":"Deep learning and radiomics integration of photoacoustic/ultrasound imaging for non-invasive prediction of luminal and non-luminal breast cancer subtypes.","authors":"Mengyun Wang, Sijie Mo, Guoqiu Li, Jing Zheng, Huaiyu Wu, Hongtian Tian, Jing Chen, Shuzhen Tang, Zhijie Chen, Jinfeng Xu, Zhibin Huang, Fajin Dong","doi":"10.1186/s13058-025-02113-7","DOIUrl":"10.1186/s13058-025-02113-7","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to develop a Deep Learning Radiomics integrated model (DLRN), which combines photoacoustic/ultrasound(PA/US)imaging with clinical and radiomics features to distinguish between luminal and non-luminal BC in a preoperative setting.</p><p><strong>Materials and methods: </strong>A total of 388 BC patients were included, with 271 in the training group and 117 in the testing group. Radiomics and deep learning features were extracted from PA/US images using Pyradiomics and ResNet50, respectively. Feature selection was performed using independent sample t-tests, Pearson correlation analysis, and LASSO regression to build a Deep Learning Radiomics (DLR) model. Based on the results of univariate and multivariate logistic regression analyses, the DLR model was combined with valuable clinical features to construct the DLRN model. Model efficacy was assessed using AUC, accuracy, sensitivity, specificity, and NPV.</p><p><strong>Results: </strong>The DLR model comprised 3 radiomic features and 6 deep learning features, which, when combined with significant clinical predictors, formed the DLRN model. In the testing set, the AUC of the DLRN model (0.924 [0.877-0.972]) was significantly higher than that of the DLR (AUC 0.847 [0.758-0.936], p = 0.026), DL (AUC 0.822 [0.725-0.919], p = 0.06), Rad (AUC 0.717 [0.597-0.838], p < 0.001), and clinical (AUC 0.820 [0.745-0.895], p = 0.002) models. These findings indicate that the DLRN model (integrated model) exhibited the most favorable predictive performance among all models evaluated.</p><p><strong>Conclusion: </strong>The DLRN model effectively integrates PA/US imaging with clinical data, showing potential for preoperative molecular subtype prediction and guiding personalized treatment strategies for BC patients.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"161"},"PeriodicalIF":5.6,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12462168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145139189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Polygenic scores in Familial breast cancer cases with and without pathogenic variants and the risk of contralateral breast cancer.","authors":"Anders Kvist, Anders Kämpe, Therese Törngren, Bianca Tesi, Panagiotis Baliakas, Åke Borg, Daniel Eriksson","doi":"10.1186/s13058-025-02107-5","DOIUrl":"10.1186/s13058-025-02107-5","url":null,"abstract":"<p><strong>Background: </strong>Polygenic risk scores (PRS) are not yet standard in clinical risk assessments for familial breast cancer in Sweden. This study evaluated the distribution and impact of an established PRS (PRS₃₁₃) in women undergoing clinical sequencing for hereditary breast cancer.</p><p><strong>Findings: </strong>We integrated PRS₃₁₃ into a hereditary breast cancer gene panel used in clinical practice and calculated scores for 262 women. Comparisons were made between women with unilateral and contralateral breast cancer, as well as those with and without pathogenic variants in breast cancer susceptibility genes. PRS₃₁₃ was significantly higher in women with contralateral breast cancer (median + 1.3 SD, n = 33, P = 8e-9) compared to those with unilateral disease (median + 0.66 SD, n = 197, P = 5e-10). Elevated PRS₃₁₃ was also observed in women with pathogenic variants, including those in high-penetrance genes (+ 0.65 SD) and moderate-penetrance genes (+ 0.93 SD), compared to population controls. Incorporating PRS₃₁₃ into a clinical risk model (BOADICEA), shifted 20%-27% of women with moderate-penetrance variants and 23%-32% of women without pathogenic variants into different risk categories according to NCCN and NICE guidelines.</p><p><strong>Conclusions: </strong>Women with familial breast cancer showed elevated PRS₃₁₃, including those with pathogenic variants, contributing to the observed high risk in these families. Integrating PRS into risk assessment and genetic counselling has the potential to refine risk predictions, even among women with breast cancer attributed to monogenic variants.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"160"},"PeriodicalIF":5.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12418628/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145024662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Global scoring method of Ki67 immunohistochemistry in breast cancer demonstrates improved concordance using real-world multi-institutional data.","authors":"Ceren Boyaci, Wenwen Sun, Johan Hartman, Balázs Ács","doi":"10.1186/s13058-025-02114-6","DOIUrl":"10.1186/s13058-025-02114-6","url":null,"abstract":"<p><p>Ki67 is a broadly available biomarker of proliferation with various approaches to its evaluation in breast cancer. The International Ki67 in Breast Cancer Working Group (IKWG) recommends calculating Ki67 globally across the tumor area, as this method offers high interobserver concordance. These recommendations have been integrated into many international breast cancer guidelines (ASCO, ESMO), yet there is no real-world data on if it improved inter-pathologists and inter-laboratory variability. Here, we present the first real-world data on the variability and impact of Ki67 scores on clinical decision-making in breast cancer when using hotspot scoring and after implementing IKWG global scoring method in clinical practice. We extracted hotspot and global scoring results from 4313 breast cancer patients from routine diagnostics, categorizing the scores into three clinical risk groups over a one-year period across two large breast centers in Stockholm, Sweden. Variability between pathologists was not clinically significant. The global scoring method improved inter-laboratory consistency but also led to a notable increase in cases classified as intermediate at both centers This has been captured in the 2022 Swedish clinical breast cancer guidelines recommending molecular profiling test for patients with Grade II, global Ki67 intermediate score, T1c / T2 breast cancer. To conclude, our findings demonstrate acceptable consistency in Ki67 scores among individual pathologists across both scoring methods, however high inter-laboratory variability was observed with hot spot scoring. Global Ki67 scoring demonstrated low inter-laboratory variability in real world breast cancer care, thereby increasing the reliability of Ki67 assessment in clinical decision-making.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"159"},"PeriodicalIF":5.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12406372/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144975965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early thelarche, reproductive hormones, and MRI-based breast density: a prospective study in China.","authors":"Ying Li, Wenqing Liu, Yue Yu, Ya Wang, Liwei Zou, Deyun Liu, Ying Sun","doi":"10.1186/s13058-025-02116-4","DOIUrl":"10.1186/s13058-025-02116-4","url":null,"abstract":"<p><strong>Background: </strong>The age of thelarche in girls has declined globally. While earlier menarche has been linked to higher breast density - a known risk factor for breast cancer - the association between earlier thelarche and breast density remains unclear.</p><p><strong>Methods: </strong>114 Girls presenting with idiopathic central precocious puberty without medication (ICPP), early thelarche (ET), and normal age at thelarche (NT) were recruited from pediatric endocrine clinics of three hospitals during the year of 2020-2021 in Hefei, Anhui Province, China and were followed up for 3-5 years. Participants had their breast composition measured by MRI at 1-year post menarche. Fasting blood samples were collected at baseline and follow-up to measure of reproductive hormone concentrations.</p><p><strong>Results: </strong>The ET group and ICPP group exhibited significantly higher percent fibroglandular volume (%FGV: 42.1%, 52.0% ) and fibroglandular volume (FGV: 183.3 cm³, 237.0cm³) compared with the NT group (%FGV: 34.7%, FGV: 148.8cm³) . Serum estrogen levels at baseline and follow-up were elevated in the ET group relative to the NT group (52.1 vs. 40.7 pg/ml; 46.1 vs. 38.6 pg/ml), but did not differ significantly from the ICPP group (baseline: 54.6 vs. 52.1 pg/ml; follow-up: 48.9 vs. 46.1 pg/ml). Each 1-year earlier onset of thelarche was associated with a 7.8% increase in %FGV and a 35.7 cm³ increase in FGV. The combined hormonal pathway mediated the association between early puberty (age at thelarche < 9 years) and %FGV in this study, accounting for 28.7% (95% CI: 8.6% - 51.3%) of the total mediation effect. For the association between early puberty and FGV, baseline estradiol mediated 27.7% (95% CI: 11.8% - 44.8%), the pathway from baseline to follow-up estradiol mediated 13.6% (95% CI: 5.0% - 24.3%), and the combined hormonal pathway mediated 45.8% (95% CI: 18.1% - 68.0%).</p><p><strong>Conclusion: </strong>In this cohort study, earlier thelarche (even between 8.0 and 9.0 years) was associated with higher %FGV and FGV. Prolonged estrogen exposure may represent a modifiable mediator that could be targeted for breast cancer prevention strategies in girls with earlier puberty.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"158"},"PeriodicalIF":5.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12403261/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The plasma proteome and breast cancer risk.","authors":"Hui-Chen Wu, Yuyan Liao, Yunjia Lai, Po-Han Lin, Regina M Santella, Gary W Miller, Mary Beth Terry","doi":"10.1186/s13058-025-02110-w","DOIUrl":"10.1186/s13058-025-02110-w","url":null,"abstract":"<p><strong>Background: </strong>Plasma proteins may serve as biomarkers for breast cancer. This study aimed to characterize the blood proteomic signatures of women with a higher risk of breast cancer due to their family history.</p><p><strong>Methods: </strong>We conducted a nested case-control study (median followup: 9.8 years) within the New York site of the Breast Cancer Family Registry (BCFR) (n = 39 cases and 48 age-matched controls). We measured the expression levels as Normalized Protein Expression (NPX) of 92 proteins using the Olink Oncology panel. We then utilized an integrative network analysis of statistically significant protein markers and metabolomic profiles to better understand the potential molecular pathways involved in breast cancer.</p><p><strong>Results: </strong>We found four proteins were positively associated with breast cancer risk; the adjusted odds ratios (ORs) (95% confidence interval (CI) per 1-standard deviation (SD) increase in NPX were 1.87 (95% CI: 1.07, 3.28) for folate receptor (FR)-alpha, 2.72 (1.36, 5.44) for C-X-C motif chemokine 13 (CXCL13), 2.63 (1.32, 5.23) for amphiregulin (AREG), and 3.59 (95% CI: 1.58, 8.19) for mesothelin (MSLN). These results were no longer statistically significant after adjusting for multiple comparisons. Results from integrative network analysis using xMWAS suggested that the candidate protein markers were associated with distinct subsets of metabolites, forming single-protein-multiple metabolite clusters (|r|>0.3, p < 0.05).</p><p><strong>Conclusions: </strong>While our results should be interpreted with caution, if replicated in larger prospective cohorts, these findings will have translational significance, attesting to the power of high-throughput profiling of circulating protein markers in identifying breast cancer biomarkers and important pathways involved in cancer development.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"157"},"PeriodicalIF":5.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12400638/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Longitudinal changes in metabolism-related metrics and breast cancer risk: a general population study.","authors":"Fan Zhang, Geertruida H de Bock, Gijs W Landman, Qingying Zhang, Bert van der Vegt, Grigory Sidorenkov","doi":"10.1186/s13058-025-02105-7","DOIUrl":"https://doi.org/10.1186/s13058-025-02105-7","url":null,"abstract":"<p><strong>Background: </strong>Metabolism-related metrics have been widely investigated for their relationship with breast cancer risk but are mostly based on single values. Weight gain during adulthood has been related to an increased risk of breast cancer, while the relationship with changes in glucose and lipids remain largely unknown.</p><p><strong>Methods: </strong>Women aged 20-80 were included from the general population-based Lifelines cohort when they had two assessments: 2007-2013 and 2014-2017. The following metrics were measured once at each of the two periods: body mass index (BMI), waist to height ratio (WHtR), hemoglobin A1c (HbA1c), HDL cholesterol (HDL-C), total cholesterol (TC), and triglyceride (TG). Women with a history of cancer, follow up less than 12 months, or who were pregnant during assessments were excluded. Mean annual changes (mean ACs) were calculated for each metric between the two periods, and further categorized into three groups - decrease, no change, and increase. Cox proportional hazards models were conducted to estimate their associations with breast cancer occurrence, reporting adjusted hazard ratios (aHR) with 95% confidence intervals (CI).</p><p><strong>Results: </strong>During a median of 92.3 months follow-up, 1,202 of 58,785 women were diagnosed with breast cancer. Among women with a baseline BMI < 25 kg/m², a negative association between BMI decrease and breast cancer risk was observed in contrast to their counterparts with no change (aHR: 0.75, 95% CI: 0.56-0.99). In addition, relative to the no change group, breast cancer risk was positively associated with reductions in HbA1c (aHR: 1.23, 95% CI: 1.07-1.40) and TG (aHR: 1.26, 95% CI: 1.06-1.49).</p><p><strong>Conclusions: </strong>Changes over time in this real-world dataset from the general population highlight the benefits of weight loss and the harms of decreased glucose and TG in relation to breast cancer risk. These longitudinal patterns are affected by age, BMI, and initial values, emphasizing the importance of personalized metabolic health management.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"155"},"PeriodicalIF":5.6,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382006/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144975952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pre-diagnostic serum metabolome and breast cancer risk: a nested case-control study.","authors":"Ly Trinh, Jaclyn Parks, Treena McDonald, Andrew Roth, Grace Shen-Tu, Jennifer Vena, Rachel A Murphy, Parveen Bhatti","doi":"10.1186/s13058-025-02102-w","DOIUrl":"https://doi.org/10.1186/s13058-025-02102-w","url":null,"abstract":"<p><strong>Background: </strong>Metabolomics offers a promising approach to identify biomarkers for timely intervention and enhanced screening of individuals at increased risk of developing breast cancer.</p><p><strong>Methods: </strong>We conducted a study of 593 female breast cancer cases and 593 matched controls nested in two prospective cohort studies. Mass spectrometry, without liquid chromatography, was used to conduct untargeted metabolomics profiling of serum samples collected, on average, 5.3 years before cancer diagnosis. Logistic regression was used to estimate odds ratios (OR) for a one standard deviation increase of metabolite intensities. Partial least squares discriminant analyses were applied to those metabolites significantly associated with breast cancer to develop risk prediction models.</p><p><strong>Results: </strong>Associations were evaluated with a total of 837 metabolites. Twenty-four metabolites were significantly associated with overall breast cancer risk, including 13 associated with decreased risk and 11 associated with increased risk. Putative identities of the metabolites included various amino acids (n = 3), dietary factors (n = 10), fatty acids (n = 2), phosplipids (n = 4), sex hormone derivatives (n = 2), and xenobiotics (n = 3). For example, a metabolite identified as acetyl tributyl citrate, a plasticizer in food wrappings, was associated with an increased risk of breast cancer (OR = 1.21; 95% CI: 1.07-1.37). Risk prediction models for overall breast cancer and the various subtypes were found to have modest levels of prediction accuracy (area under the curve ranged from 0.60 to 0.63).</p><p><strong>Conclusions: </strong>Additional studies are needed to confirm the identities of the metabolites and validate their associations with breast cancer risk. Metabolomics should be evaluated in conjunction with other 'omics' technologies for creation of clinically useful risk prediction models.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"156"},"PeriodicalIF":5.6,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382045/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144975993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterization of the tumor immune microenvironment in pregnancy-associated breast cancer through multiplex immunohistochemistry and transcriptome analyses.","authors":"Ching-Hsuan Chen, I-Chun Chen, Chia-Lang Hsu, Tzu-Pin Lu, Ming-Yang Wang, Li-Wei Tsai, Chiun-Sheng Huang, Yen-Shen Lu, Ching-Hung Lin","doi":"10.1186/s13058-025-02097-4","DOIUrl":"https://doi.org/10.1186/s13058-025-02097-4","url":null,"abstract":"<p><strong>Background: </strong>Pregnancy-associated breast cancer (PABC) is breast cancer diagnosed during pregnancy or within 2 years postpartum. Although relatively rare, it is associated with a poor prognosis, and the underlying mechanisms contributing to this unfavorable condition remain incompletely understood. In this study, we investigated tumor microenvironmental features linked to pregnancy and lactation in an effort to elucidate these mechanisms.</p><p><strong>Methods: </strong>This retrospective study included 26 patients with PABC, 51 patients with breast cancer diagnosed 2-5 years postpartum (post-weaning breast cancer [PWBC]), and 28 patients with no prior history of pregnancy at the time of breast cancer diagnosis (nulliparous breast cancer [NPBC]). The tumor immune microenvironment in PABC, PWBC, and NPBC cases was profiled using Opal Polaris 7 color immunohistochemistry (IHC) and the NanoString Breast Cancer 360 Gene Expression Panel.</p><p><strong>Results: </strong>No significant differences in tumor stage or molecular subtype were observed among the PABC, PWBC, and NPBC groups. The age of diagnosis was comparable between NPBC and PABC patients (38.0 vs. 35.4 years), but significantly higher in the PWBC group (42.2 years). Both multiplex IHC and transcriptomic analyses consistently demonstrated that the PABC and PWBC groups exhibited a higher abundance of tumor-infiltrating immune cells than the NPBC group. Specifically, multiplex IHC analysis revealed that PABC and PWBC were associated with increased densities of CD4⁺, CD8⁺, CD20⁺, and CD68⁺CD163⁺ cells. Consistently, transcriptomic analysis indicated that the PABC and PWBC groups exhibited elevated gene expression signatures associated with macrophages, cytotoxic cells, CD8⁺ T cells, and B cells compared with the NPBC group. The primary differences observed between the PABC and NPBC groups were validated using three publicly available datasets from the Gene Expression Omnibus.</p><p><strong>Conclusions: </strong>Using multiplex IHC and transcriptome analyses, this study demonstrated that PABC was associated with a higher abundance of immune cells, including increased infiltration of T cells, B cells, and macrophages, in the breast tumor microenvironment. Future research is required to focus on the role of immune cells in pregnancy-associated breast cancer patients.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"154"},"PeriodicalIF":5.6,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382146/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Analysis of ductal carcinoma in situ by self-reported race reveals molecular differences related to outcome.","authors":"Siri H Strand, Kathleen E Houlahan, Vernal Branch, Lorraine M King, Thomas Lynch, Belén Rivero-Guitiérrez, Bryan Harmon, Fergus Couch, Kristalyn Gallagher, Mark Kilgore, Shi Wei, Angela DeMichele, Tari King, Priscilla McAuliffe, Christina Curtis, Kouros Owzar, Jeffrey R Marks, Graham A Colditz, E Shelley Hwang, Robert B West","doi":"10.1186/s13058-025-02106-6","DOIUrl":"https://doi.org/10.1186/s13058-025-02106-6","url":null,"abstract":"","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"153"},"PeriodicalIF":5.6,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12379414/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144975997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"External validation of precisebreast, a digital prognostic test for predicting breast cancer recurrence, in an early-stage cohort from the Netherlands.","authors":"Pieter J Westenend, Claudia Meurs, Gerardo Fernandez, Marcel Prastawa, Abishek Sainath Madduri, Aaron Feliz, Juan Carlos Mejias, Alexander Shtabsky, Xiaozhu Zhang, Brandon Veremis, Rebecca DeAngel, Michael J Donovan","doi":"10.1186/s13058-025-02104-8","DOIUrl":"https://doi.org/10.1186/s13058-025-02104-8","url":null,"abstract":"<p><strong>Background: </strong>Current clinical guidelines recommend gene expression profiling to guide treatment in early-stage breast cancer. PreciseBreast (PDxBR) is a digital prognostic tool that integrates artificial intelligence (AI)-derived features from hematoxylin and eosin (H&E) slides with clinicopathologic data to predict recurrence risk. This study externally validated PDxBR in an independent cohort and compared its performance to other risk models.</p><p><strong>Methods: </strong>We retrospectively analyzed PDxBR in a cohort of 739 patients with early-stage hormone receptor-positive, HER2-negative breast cancer (median follow-up of 8.8 years). For each case, one H&E-stained slide was digitized and analyzed to generate recurrence risk scores using the full PDxBR model, as well as image-only and clinical-only variants. A subset of patients who underwent MammaPrint testing was also evaluated. Model performance was assessed by AUC/C-index, hazard ratios, sensitivity, specificity, and negative and positive predictive values (NPV and PPV, respectively).</p><p><strong>Results: </strong>PDxBR showed prognostic accuracy in this external cohort (AUC/C-index 0.71, 95% CI: 0.66-0.75). Applying the PDxBR threshold (≥ 58 versus < 58) yielded a hazard ratio of 3.05 (95% CI: 2.1-4.4, p < 0.001), sensitivity 0.70, specificity 0.59, NPV 0.90, and PPV 0.27. PDxBR outperformed the modified Adjuvant! Online clinical model (MINDACT model, p < 0.00001) and effectively reclassified grade 2 tumors into distinct risk groups.</p><p><strong>Conclusions: </strong>PDxBR demonstrated robust prognostic performance in an independent cohort, supporting its potential as a scalable, reproducible alternative to genomic assays for individualized risk stratification in early-stage breast cancer.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"152"},"PeriodicalIF":5.6,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12369158/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144975957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}