Discover. Oncology最新文献

{"title":"Identification of a long non-coding RNA signature associated with cuproptosis for prognosis and immunotherapy response prediction in patients with lung adenocarcinoma.","authors":"Jie Zeng, Zhenyu Wu, Meijuan Luo, Zhibo Chen, Xie Xu, Guijing Xie, Quhai Chen, Wenjie Bai, Gang Xiao, Jianjiang Xie","doi":"10.1007/s12672-025-02092-3","DOIUrl":"10.1007/s12672-025-02092-3","url":null,"abstract":"<p><strong>Background: </strong>Lung adenocarcinoma (LUAD), the most common histotype of lung cancer, exhibits high heterogeneity due to molecular variations. Cuproptosis is a newly discovered type of cell death that is linked to copper metabolism and long non-coding RNAs (lncRNAs) may play a significant role in this process. We conducted a comprehensive analysis of lncRNA related to cuproptosis and identified a CRLscore to predict the prognosis and immune landscape for LUAD patients.</p><p><strong>Methods: </strong>The LUAD patient cohort obtained from TCGA database was divided into training and validation sets. A range of statistical methods were employed to identify lncRNAs associated with cuproptosis. Multivariate Cox regression was then utilized to develop the CRLscore, which was further used to construct and evaluate a nomogram. Additionally, we investigated the biological functions, gene mutations, and immune landscape.</p><p><strong>Results: </strong>A CRLscore, comprising six cuproptosis-related lncRNAs, was developed to stratify patients into high- and low-risk groups. The CRLscore demonstrated its ability to independently predict prognosis in both the training set and the validation set. Utilizing the CRLscore, we constructed a nomogram that exhibited favorable predictive efficiency. Furthermore, the cuproptosis-related lncRNAs exhibited associations with important signaling pathways such as p53 signaling, MYC Targets V1, and G2M Checkpoint. Notably, the CRLscore displayed substantial differences in somatic mutations and immune landscape. Finally, qRT-PCR results showed the significant differential expression of five cuproptosis-related lncRNAs between LUAD and normal cells.</p><p><strong>Conclusion: </strong>The CRLscore could serve as a potential prognostic indicator and may predict the response to immunotherapy in LUAD patients.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"432"},"PeriodicalIF":2.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143751287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prognostic implications of alternative splicing events and key splicing factors in head and neck squamous cell carcinoma.","authors":"Siyi He, Jiali Meng, Chunyan Liang, Yiru Wang, Xinling Qin, Lulu Huang, Rensheng Wang, Weimei Huang","doi":"10.1007/s12672-025-02214-x","DOIUrl":"https://doi.org/10.1007/s12672-025-02214-x","url":null,"abstract":"<p><p>The incidence of head and neck squamous cell carcinoma (HNSCC) remains high, accompanied by low 5-year survival rates. Identifying prognostic factors is essential for advancing personalized treatment approaches. Increasing evidence implicates aberrant alternative splicing (AS) plays a key role in tumor progression. Utilizing data from TCGA and TCGA SpliceSeq, prognosis-associated AS events were identified through Cox regression analysis. A prognostic risk model was developed via multivariate Cox and LASSO regression, with validation conducted using Kaplan-Meier survival analysis and ROC curve analysis. The correlation between splicing factors (SFs) and prognosis-associated AS events was analyzed using Pearson's method, followed by the construction of an SF-AS regulatory network. Key splicing factors (KSFs) were identified using Cytoscape software. Expression of KSFs in HNSCC was confirmed by quantitative PCR and Western blotting. SiRNA-mediated knockdown in HNSCC cell lines (HONE1, HN4, SAS) demonstrated effects on cell proliferation, invasion, and migration, as assessed by CCK8, colony formation, Transwell, and wound healing assays. Tumor growth was further evaluated in a subcutaneous tumor model in vivo. A total of 2347 survival-related AS events were identified, of which eleven were used to construct the prognostic model. Patients in the low-risk group exhibited significantly improved outcomes (P = 0e + 00), underscoring the model's predictive accuracy. Notably, DDX39B and PRPF39 emerged as key splicing factors, exhibiting high expression in HNSCC and correlating with poor prognosis, positioning them as potential biomarkers and therapeutic targets.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"430"},"PeriodicalIF":2.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143751302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Emerging strategies and translational advancements of DDR1 in oncology.","authors":"Yuxi Luo, Tianxin Liu, Jinli Pei, Shengnan Xu, Jie Liu, Jinming Yu","doi":"10.1007/s12672-025-02107-z","DOIUrl":"https://doi.org/10.1007/s12672-025-02107-z","url":null,"abstract":"<p><p>Discoidin domain receptor 1 (DDR1) has emerged as a promising therapeutic target in oncology due to its unique role in tumor-stroma interactions and its involvement in key signaling pathways that drive cancer progression. DDR1 is homologous to the transmembrane receptor tyrosine kinase (RTK) family and uniquely requires binding to collagen for its activation. It regulates several cellular processes related to tumor cell proliferation, metabolism, migration, stromal remodeling, and epithelial-mesenchymal transition (EMT), ultimately influencing patient survival. Dysregulation of DDR1 may contribute to cancer progression, neurodegenerative diseases, fibrotic conditions, and atherosclerosis. Moreover, DDR1 has been shown to affect a wide variety of cancers, including lung, breast, stomach, colon, ovarian, and pancreatic cancers, underscoring its potential as a therapeutic target. Various small-molecule tyrosine kinase inhibitors aimed at DDR1 have been developed and have demonstrated significant effectiveness in reducing tumor growth. This review focuses on the structure, function, and mechanism of DDR1, as well as its involvement in cancer progression. Additionally, it examines the development and therapeutic potential of DDR1 inhibitors, offering a comprehensive overview of their application in cancer treatment. By synthesizing current knowledge, this article provides valuable insights to guide future research and innovation in targeting DDR1 for clinical therapeutic advancement.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"428"},"PeriodicalIF":2.8,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143751189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intratumor heterogeneity related signature for clinical outcome and immunotherapy advantages in lung adenocarcinoma.","authors":"Yanhua Zuo, Li Lin, Libo Sun","doi":"10.1007/s12672-025-02173-3","DOIUrl":"https://doi.org/10.1007/s12672-025-02173-3","url":null,"abstract":"<p><strong>Background: </strong>Immunotherapy benefits shows discrepancy in different lung adenocarcinoma (LUAD) patients because of the intratumor heterogeneity (ITH). ITH favors tumor evolution and correlated with drug resistance. The genes mediating ITH in LUAD and their role in predicting prognosis and therapy benefits is unclear.</p><p><strong>Methods: </strong>An ITH-related signature (IRS) was built by ten methods-based integrative machine learning programs using TCGA, GSE68571, GSE42127, GSE30129, GSE50081, GSE72094, GSE37745, GSE68467, and GSE31210 dataset. To assess the relationship between IRS and the tumor immune microenvironment, numerous prediction scores were employed.</p><p><strong>Results: </strong>The optimal predictive signature for LUAD cases was the IRS developed using Lasso + stepCox(both) method, which had the highest average C-index of 0.80. It performed consistently and effectively in predicting the clinical outcomes of LUAD patients. Additionally, compared to the clinical stage and numerous other existing prediction models, a higher C-index was demonstrated in IRS. LUAD patients with low IRS score had a higher level of immuno-activated cells, higher TMB score, lower ITH score, higher PD1&CTLA4 immunophenoscore, and tumor escape score in LUAD. The gene set score for angiogenesis, coagulation, hypoxia, and NOTCH signaling were increased in LUAD with high IRS score.</p><p><strong>Conclusion: </strong>Overall, the study developed a unique IRS for LUAD that may serve as a predictor of the clinical outcome and immunotherapy advantages for individuals with LAUD.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"425"},"PeriodicalIF":2.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ANAPC10 expression predicts poor prognosis in oral squamous cell carcinoma and promotes tumor growth via the PI3K/AKT/mTOR pathway.","authors":"Jing Fang, Yanhao Duan, Yongle Qiu, Shanshan Liu, Xue Bai, Hong Cai, Meijie Zhang, Wei Liu","doi":"10.1007/s12672-025-02125-x","DOIUrl":"https://doi.org/10.1007/s12672-025-02125-x","url":null,"abstract":"<p><p>Oral squamous cell carcinoma (OSCC) is associated with high morbidity and mortality, emphasizing the need for early detection through advanced biomarkers and non-invasive methods. This study analyzed Anaphase Promoting Complex Subunit 10 (ANAPC10) mRNA expression across various cancers using multi-platform tools to assess its diagnostic potential and clinical relevance. We developed a prognostic model linking ANAPC10 expression to survival outcomes using TCGA and GTEx data, and constructed a protein-protein interaction network via GeneMANIA. Functional studies, including cell culture and various assays, demonstrated that ANAPC10 is highly expressed in OSCC and correlates with poor prognosis. ANAPC10 was found to be involved in key pathways, including NF-κB signaling and cell cycle regulation. Knockdown experiments revealed that reducing ANAPC10 expression led to decreased cell proliferation, migration, and invasion, as well as inhibition of the PI3K/AKT/mTOR signaling pathway. These findings suggest that ANAPC10 is a promising biomarker for OSCC and a potential therapeutic targetClinical Trial Number: Not applicable.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"423"},"PeriodicalIF":2.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11953518/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pan-cancer analysis reveal that m⁶A writer WTAP involve in tumor cell cycle regulation and tumor immunity.","authors":"Jingwei Shi, Gongyi Xie, Sijing Ye, Xiaoqiong Weng, Qingmei Zhou","doi":"10.1007/s12672-025-02196-w","DOIUrl":"https://doi.org/10.1007/s12672-025-02196-w","url":null,"abstract":"<p><strong>Background: </strong>Wilm's tumor 1-associated protein (WTAP) is a critical component of the methyltransferase complex responsible for N6-methyladenosine (m6A) modification in RNA. This modification is involved in various cancer-related biological processes. However, the precise role of WTAP in tumor cell cycle regulation and immune responses remains poorly understood.</p><p><strong>Methods: </strong>A comprehensive analysis was conducted using multi-database resources to investigate the role of WTAP in tumorigenesis. Data from 33 tumor types were collected from the Genotype-Tissue Expression (GTEx), The Cancer Genome Atlas (TCGA), and Cancer Cell Line Encyclopedia (CCLE) databases. Correlations between WTAP expression and prognosis, immune microenvironment, immune neoantigens, immune checkpoint molecules, tumor mutation burden (TMB), and microsatellite instability (MSI) were analyzed. Additionally, Gene Set Enrichment Analysis (GSEA) was performed to explore the signaling pathways associated with WTAP expression.</p><p><strong>Results: </strong>Pan-cancer analysis revealed differential expression of WTAP across multiple tumor types compared to normal tissues. High WTAP expression was significantly associated with poor prognosis in adrenocortical carcinoma (ACC), brain lower-grade glioma (LGG), liver hepatocellular carcinoma (LIHC), and ovarian serous cystadenocarcinoma (OV). In contrast, low WTAP expression correlated with improved survival in skin cutaneous melanoma (SKCM) and thymoma (THYM). WTAP expression demonstrated a positive correlation with immune cell infiltration, including B cells, CD4 + T cells, CD8 + T cells, dendritic cells, macrophages, and neutrophils. Additionally, WTAP expression was positively associated with stromal, immune, and overall immune estimate scores. No significant association was identified between WTAP expression and immune neoantigen counts. However, WTAP expression correlated with the expression of most common immune checkpoint genes, DNA mismatch repair genes, and DNA methyltransferases. Furthermore, WTAP expression significantly influenced TMB and MSI levels. GSEA indicated that WTAP predominantly contributes to cell cycle regulation, thereby promoting tumorigenesis.</p><p><strong>Conclusion: </strong>WTAP is a potential immune-related prognostic biomarker in malignancies. Its role in regulating the cell cycle and immune microenvironment highlights its influence on tumor development and progression.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"426"},"PeriodicalIF":2.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cytokine biomarkers for independent prediction of hepatocellular carcinoma prognosis.","authors":"Long-Bin Jeng, Fu-Ying Shih, Wen-Ling Chan, Chiao-Fang Teng","doi":"10.1007/s12672-025-02188-w","DOIUrl":"https://doi.org/10.1007/s12672-025-02188-w","url":null,"abstract":"<p><p>Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality worldwide. Although various therapeutic modalities have been established for HCC, the overall outcomes of patients after treatment remain unsatisfactory, highlighting the need for valuable independent prognostic biomarkers. Cytokines are a large group of multifunctional secretory proteins and play critical roles in regulating development and progression of many cancer types, including HCC. Moreover, the expression levels of many cytokines in tumor/peritumor tissues and serum/plasma samples have been validated as important biomarkers for independently predicting the prognosis of HCC patients. This review provides a comprehensive summary of literature evidence for the independent prognostic significance of cytokine biomarkers in HCC patients receiving different therapies.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"421"},"PeriodicalIF":2.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11953510/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nanotechnology-based drug delivery system for the diagnosis and treatment of ovarian cancer.","authors":"Rajeswari Saripilli, Dinesh Kumar Sharma","doi":"10.1007/s12672-025-02062-9","DOIUrl":"https://doi.org/10.1007/s12672-025-02062-9","url":null,"abstract":"<p><p>Current research in nanotechnology is improving or developing novel applications that could improve disease diagnosis or treatment. This study highlights several nanoscale drug delivery technologies, such as nano micelles, nanocapsules, nanoparticles, liposomes, branching dendrimers, and nanostructured lipid formulations for the targeted therapy of ovarian cancer (OC), to overcome the limitations of traditional delivery. Because traditional drug delivery to malignant cells has intrinsic flaws, new nanotechnological-based treatments have been developed to address these conditions. Ovarian cancer is the most common gynecological cancer and has a higher death rate because of its late diagnosis and recurrence. This review emphasizes the discipline of medical nanotechnology, which has made great strides in recent years to solve current issues and enhance the detection and treatment of many diseases, including cancer. This system has the potential to provide real-time monitoring and diagnostics for ovarian cancer treatment, as well as simultaneous delivery of therapeutic agents.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"422"},"PeriodicalIF":2.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11953507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantifying CD73 expression after chemotherapy or chemoradiotherapy in esophageal squamous cell carcinoma.","authors":"Zachary A Cooper, Ying Wang, Philip L Martin, Kosho Murayama, Rakesh Kumar, Ken Kato, Shun Yamamoto, Shigeki Sekine","doi":"10.1007/s12672-025-02179-x","DOIUrl":"https://doi.org/10.1007/s12672-025-02179-x","url":null,"abstract":"<p><strong>Background: </strong>CD73 and CD39, key components of the adenosine axis, are expressed in multiple malignancies; the impact of standard-of-care treatment on their expression and antitumor immunity in esophageal squamous cell carcinoma (ESCC) remains unclear. We evaluated the adenosine axis in the context of neoadjuvant therapy received and its relationship to immune markers in ESCC tumor samples.</p><p><strong>Methods: </strong>Samples from patients who underwent surgical resection at the National Cancer Center Hospital, Tokyo, Japan, between January 2002 and July 2019 following no neoadjuvant therapy (n = 55; treatment-naïve), chemotherapy (n = 200), or chemoradiotherapy (CRT; n = 20) were immunohistochemically stained for CD73, CD39, PD-L1, FoxP3, and CD8; markers were quantified across tumor microenvironment (TME) compartments.</p><p><strong>Results: </strong>Median CD73 TME expression was lower in the treatment-naïve (2.8%) versus chemotherapy (7.2%; p < 0.0001) and CRT (6.4%; p < 0.01) cohorts, most profoundly in the stroma (median 4.1% vs 9.4% [p < 0.0001] and 8.1% [p < 0.01]). Median intraepithelial CD8-positive cell density was higher in the treatment-naïve (200.7 cells/mm²) versus chemotherapy (93.9 cells/mm²; p < 0.0001) and CRT (30.5 cells/mm²; p < 0.001) cohorts. Three-year recurrence-free survival (RFS) was 73.0%, 58.0%, and 30.0%, and 3-year overall survival (OS) was 78.2%, 71.4%, and 33.5%, in the treatment-naïve, chemotherapy, and CRT cohorts, respectively. High versus low CD73 TME expression was prognostic for longer RFS (treatment-naïve cohort: hazard ratio [HR] 0.16, 95% confidence interval [CI] 0.05-0.58, p = 0.0014; chemotherapy cohort: HR 0.52, 95% CI 0.34-0.78, p = 0.0012) and OS.</p><p><strong>Conclusions: </strong>These translational data demonstrating higher CD73 expression in tumors after neoadjuvant chemotherapy or CRT support potential combination strategies with CD73-targeted treatment in ESCC.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"427"},"PeriodicalIF":2.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The value of predicting breast cancer with a DBT 2.5D deep learning model.","authors":"Huandong Niu, Li Li, Ximing Wang, Han Xu","doi":"10.1007/s12672-025-02170-6","DOIUrl":"https://doi.org/10.1007/s12672-025-02170-6","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the accuracy and efficacy of a 2.5-dimensional deep learning (DL) model based on digital breast tomosynthesis (DBT) in predicting breast cancer.</p><p><strong>Methods: </strong>Through a retrospective analysis of data from 361 patients with breast tumor lesions treated at Shandong Provincial Hospital Affiliated to Shandong First Medical University between 2018 and 2020, this study utilized deep convolutional neural networks (DCNN) to automatically extract key features from DBT images. By applying dimensionality reduction and feature fusion selection, a variety of machine learning predictive models based on a 2.5-dimensional feature set were constructed. Additionally, a comprehensive predictive model was developed by combining univariate and multivariate logistic regression analyses with clinical data. The model's performance was assessed using receiver operating characteristic (ROC) curves, area under the curve (AUC) values, and accuracy rates.</p><p><strong>Results: </strong>In the test set, DBT 2.5D deep learning-based logistic regression, LightGBM, multilayer perceptron, and comprehensive models achieved accuracies of 72.2%, 75.0%, 79.2%, and 80.6%; AUCs of 0.826, 0.756, 0.859, and 0.871; sensitivities of 63.8%, 70.2%, 80.9%, and 87.2%; specificities of 88.0%, 84.0%, 76.0%, and 68.0%; PPVs of 90.9%, 89.2%, 86.4%, and 83.7%; NPVs of 56.4%, 60.0%, 67.9%, and 73.9%; and F1 scores of 75.0%, 78.6%, 83.5%, and 85.4%, respectively. These results underscore the high efficiency and potential of DBT 2.5D deep learning models in breast cancer diagnosis, particularly the comprehensive model's superior performance across key metrics.</p><p><strong>Conclusion: </strong>The 2.5D deep learning model based on DBT shows good performance in preoperative breast cancer prediction, with its integration with clinical data further enhancing its effectiveness. The combination of deep learning and radiomics offers a viable approach for early breast cancer diagnosis, supporting the development of more accurate personalized diagnostic and treatment strategies.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"420"},"PeriodicalIF":2.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11953484/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}