Frontiers in Oncology最新文献

{"title":"Unicentric Castleman disease in the left adrenal region: a case report and literature review.","authors":"Zhen Wang, Yong Shi, Yun Chen, Zhongle Xu, Li Zheng, Yanbin Zhang, Junhua Xi","doi":"10.3389/fonc.2025.1638855","DOIUrl":"10.3389/fonc.2025.1638855","url":null,"abstract":"<p><strong>Background: </strong>Castleman disease (CD) is a rare lymphoproliferative disorder that can present either as unicentric (UCD) or multicentric (MCD), with distinct clinical and pathologic features. Involvement of the adrenal region is extremely uncommon, often mimicking more common adrenal tumors such as pheochromocytoma. This report describes a patient with a solitary retroperitoneal lesion in the left adrenal region who was ultimately diagnosed with unicentric Castleman disease (hyaline vascular type).</p><p><strong>Case presentation: </strong>A 44-year-old female was admitted for surgical management of a left retroperitoneal lesion initially suspected to be an adrenal tumor, based on imaging studies (including CT and PET-CT). Laboratory tests ruled out pheochromocytoma or endocrine hyperfunction. During robotic-assisted laparoscopic surgery, a well-defined 5-cm lesion adjacent to the left adrenal gland was resected along with regional lymph nodes. Pathological examination confirmed Castleman disease of the hyaline vascular subtype with fibrosis and calcification. Postoperative recovery was uneventful, and the patient was discharged with an excellent prognosis.</p><p><strong>Conclusions: </strong>Castleman disease manifesting in the adrenal region is exceedingly rare and may be easily mistaken for an adrenal neoplasm, especially when imaging reveals a hypervascular retroperitoneal lesion with calcification. This case underscores the importance of including Castleman disease in the differential diagnosis of indeterminate adrenal-region tumors with normal endocrine function. Complete surgical excision typically confers an excellent prognosis for unicentric disease.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1638855"},"PeriodicalIF":3.5,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12477018/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145198777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing diagnostics through flow cytometry: overcoming barriers in low resource settings.","authors":"Jeanine Alfaro, Patricia Valverde, Paola Salguero, Xiomara Arevalo, Pamela Ortega, Luisa Sanchez, Federico Antillon-Klussmann, Randall T Hayden, Alicia Rodriguez, Monika L Metzger, John K Choi, Victor M Santana, Paul E Mead, Priya Kumar","doi":"10.3389/fonc.2025.1604295","DOIUrl":"10.3389/fonc.2025.1604295","url":null,"abstract":"<p><p>Despite advancements in the treatment of acute lymphoblastic leukemia (ALL), survival rates vary greatly based on factors such as cancer subtype and geographical location. The use of diagnostic tools like immunophenotyping and measurable residual disease (MRD) detection by flow cytometry (FC) are key to optimal management. FC offers higher sensitivity and rapid turnaround compared to traditional methods like morphological evaluation and immunohistochemistry. However, in low- and middle-income countries (LMIC), the adoption of robust MRD assays via FC remains limited due to challenges such as technical complexity, the need for operator expertise, and the high costs associated with antibodies and quality control. This study discusses the design, implementation, and validation of MRD strategies using FC in resource-constrained environments, highlighting the potential for improved accessibility and patient outcomes when these barriers are addressed.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1604295"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463636/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"6-gingerol promotes apoptosis of ovarian cancer cells through miR-506/Gli3 signaling pathway activation.","authors":"Jun Xiong, Hong-Hu Wu, Hui Jiang, Huan Li, Xiao-Qing Tan, Xiao-Ju He, Xue-Xin Cheng","doi":"10.3389/fonc.2025.1547771","DOIUrl":"10.3389/fonc.2025.1547771","url":null,"abstract":"<p><strong>Purpose: </strong>Ginger rhizomes have shown potential for promoting human health, including the prevention and treatment of cancer. Here, we investigated the anticancer activities of 6-gingerol and explored its mechanisms of action in ovarian cancer cells.</p><p><strong>Methods: </strong>SKOV3 ovarian cancer cells were treated with different concentrations of 6-gingerol. Clonogenic assays, Flow cytometry, and Western blotting were used to evaluate cell survival and apoptosis. RT-qPCR and transfection experiments were performed to assess the role of miR-506, and bioinformatics tools were used to identify Gli3 as a target gene.</p><p><strong>Results: </strong><i>In vitro</i>, ovarian cancer cells underwent apoptosis following 6-gingerol treatment. 6-Gingerol suppressed Gli3 expression without affecting Bax, Bcl-2, or Bcl-xL levels. Low miR-506 expression was observed in ovarian cancer tissues, whereas 6-gingerol significantly promoted its expression. miR-506 directly suppressed Gli3 expression and induced apoptosis in SKOV3 cells.</p><p><strong>Conclusions: </strong>Our results indicate that gingerol promoted the upregulation of miR-506, leading to the induction of apoptosis in ovarian cancer cells. This study supports the potential of 6-gingerol-based therapy for ovarian malignancies.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1547771"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463647/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging deep learning for early detection of cervical cancer and dysplasia in China using U-NET++ and RepVGG networks.","authors":"Baoqing Li, Lulu Chen, Chudi Sun, Jian Wang, Sicong Ma, Hang Xu, Luyao Wang, Taotao Rong, Qun Hu, Jie Wei, Lijuan Lu, Guannan Bai, Zhangdaihong Liu, Peng Luo, Aimin Xu, Li Liu, Guoliu Ye, Lin Zhang","doi":"10.3389/fonc.2025.1624111","DOIUrl":"10.3389/fonc.2025.1624111","url":null,"abstract":"<p><strong>Background: </strong>Cervical cancer is a significant global public health issue, primarily caused by persistent high-risk human papillomavirus (HPV) infections. The disease burden is disproportionately higher in low- and middle-income regions, such as rural China, where limited access to screening and vaccinations leads to increased incidence and mortality rates. Cervical cancer is preventable and treatable when detected early; this study utilizes deep learning to enhance early detection by improving the diagnostic accuracy of colposcopic image analysis.</p><p><strong>Objective: </strong>The aim of this study is to leverage deep learning techniques to improve the early detection of cervical cancer through the enhancement of colposcopic image diagnostic accuracy.</p><p><strong>Methods: </strong>The study sourced a comprehensive dataset of colposcopic images from The First Affiliated Hospital of Bengbu Medical University, with each image manually annotated by expert clinicians. The U-NET++ architecture was employed for precise image segmentation, converting colposcopic images into binary representations for detailed analysis. The RepVGG framework was then applied for classification, focusing on detecting cervical cancer, HPV infections, and cervical intraepithelial neoplasia (CIN). From a dataset of 848 subjects, 424 high-quality images were selected for training, with the remaining 424 used for validation.</p><p><strong>Results: </strong>The deep learning model effectively identified the disease severity in colposcopic images, achieving a predictive accuracy of 83.01%. Among the 424 validation subjects, cervical pathology was correctly identified in 352, demonstrating high diagnostic precision. The model excelled in detecting early-stage lesions, including CIN I and CIN II, which are crucial for initiating timely interventions. This capability positions the model as a valuable tool for reducing cervical cancer incidence and improving patient outcomes.</p><p><strong>Conclusion: </strong>The integration of deep learning into colposcopic image analysis marks a significant advancement in early cervical cancer detection. The study suggests that AI-driven diagnostic tools can significantly improve screening accuracy. Reducing reliance on human interpretation minimizes variability and enhances efficiency. In rural and underserved areas, the deployment of AI-based solutions could be transformative, potentially reducing cervical cancer incidence and mortality. With further refinement, these models could be adapted for broader population screening, aiding global efforts to eliminate cervical cancer as a public health threat.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1624111"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463577/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparative study of postural fixation techniques for radiotherapy in upper abdominal malignancies.","authors":"Ji-Hua Han, Dong-Cheng He, Xiao-Ye Zhang, Yan Zhang, Jun Hong, Ting-Ting Shi, Zhi-Jian Zhu","doi":"10.3389/fonc.2025.1625478","DOIUrl":"10.3389/fonc.2025.1625478","url":null,"abstract":"<p><strong>Objective: </strong>In this study, we investigated the impact of two distinct postural fixation techniques on the incidence of setup errors in patients with upper abdominal malignancies.</p><p><strong>Methods: </strong>Seventy-seven patients with upper abdominal malignancies were divided into two groups: an observation group comprising 31 patients managed with a combination of thermoplastic body film and an air bag, and a control group consisting of 46 patients managed solely with thermoplastic body film. Prior to radiotherapy, a cone-beam computed tomography (CBCT) scan was performed, followed by registration of CBCT scans and positioning computed tomography (CT) images. Setup errors along the X (left/right), Y (superior/inferior), and Z (anterior/posterior) axes of the two groups were recorded and analyzed. A Wilcoxon rank-sum test was used for data analysis. Random errors (Σ), systematic errors (σ), and planning target volume (PTV) margins (MPTV) were evaluated.</p><p><strong>Results: </strong>The three-directional setup errors of the observation group [X: 1.9 (0.90, 2.73), Y: 2.5 (1.48, 3.7), Z: 1.4 (0.78, 2.3)] and the resultant displacement vector [T: 3.97 (3.08, 5.32)] exhibited lower magnitudes compared to those observed in the control group [X: 2.3 (1.1, 3.6), Y: 3.5 (2.1, 5.4), Z: 1.8 (0.9, 3.1); T: 5.51 (4.18, 7.25)]. These differences were statistically significant (p < 0.05). Notably, the Σ, σ, and MPTV in the observation group were consistently smaller than those observed in the control group.</p><p><strong>Conclusion: </strong>The combined use of thermoplastic body film and an air bag in postural fixation significantly reduces setup errors during radiotherapy for patients with upper abdominal tumors. This combined approach enhances the precision of postural alignment, thereby improving positional repeatability and reducing both random and systematic errors. Furthermore, this method is associated with decreased planning target volume margins, providing better protection to adjacent normal tissue structures.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1625478"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463582/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the prognostic value of EBV DNA in advanced nasopharyngeal carcinoma treated with chemoradiotherapy using AI-based modeling.","authors":"Yang Yang, Ningchuan Shang, Shun Lu, Lintao Li, Peng Xu, Xianliang Wang, Fan Li, Yue Su, Yuan Qin, Jinyi Lang, Jie Zhou","doi":"10.3389/fonc.2025.1650377","DOIUrl":"10.3389/fonc.2025.1650377","url":null,"abstract":"<p><strong>Background: </strong>Epstein-Barr virus (EBV) DNA is a well-established biomarker in nasopharyngeal carcinoma (NPC), but its integration into artificial intelligence (AI)-based prognostic tools remains limited. This study aimed to develop and validate AI models incorporating EBV DNA load levels to predict progression-free survival (PFS) in patients with advanced NPC treated with concurrent chemoradiotherapy (CRT).</p><p><strong>Methods: </strong>A retrospective multicenter cohort of 503 patients was divided into training (n = 301) and validation (n = 202) sets. Four machine learning algorithms-Cox regression, LASSO, RSF, and GBM-were applied to predict 1- and 1.5-year PFS in patients with advanced NPC. Model performance was evaluated using the concordance index (C-index), time-dependent receiver operating characteristic (ROC), decision curve analysis (DCA), and interpretability tools such as SHAP values and partial dependence plots (PDP).</p><p><strong>Results: </strong>The 1-, 3-, and 5-year PFS rates were 100.0%, 91.5%, and 88.6% in the EBV = 0 group; 99.4%, 91.2%, and 88.5% in the > 0 and < 1500 group; and 92.3%, 81.0%, and 75.7% in the ≥ 1500 group, respectively, with statistically significant differences among the three groups (<i>P</i> = 0.0024). The RSF model outperformed other models with the highest C-index (0.778) and area under the ROC curve of 0.810 and 0.634 at 1 and 1.5 years, respectively. EBV DNA emerged as the most influential predictor across all interpretability analyses. Patients with EBV DNA ≥1500 copies/ml had the poorest predicted survival, showing a distinct threshold effect in the PDP.</p><p><strong>Conclusions: </strong>High EBV DNA levels were associated with poorer PFS in advanced NPC. Among the models evaluated, the RSF model demonstrated the best predictive performance and interpretability. EBV-informed AI modeling represents a promising approach for enhancing individualized risk prediction and clinical decision-making in NPC.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1650377"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463603/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"¹²⁵I seed brachytherapy with cement augmentation versus cement alone for acetabular metastases: a comparative study.","authors":"Zhi-Qian Sun, Shuai Li, Bao-Quan Zhu, Qi-Yu Sun, Min Li","doi":"10.3389/fonc.2025.1673676","DOIUrl":"10.3389/fonc.2025.1673676","url":null,"abstract":"<p><strong>Objective: </strong>As the survival of cancer patients improves, the incidence of bone metastases increases. Acetabular metastases often cause severe pain, limit hip mobility, and impair quality of life. Percutaneous cement augmentation (PCA) provides short-term pain relief and improves mechanical stability, but its anti-tumor effect is limited. ¹²⁵I seed brachytherapy offers precise local tumor control but cannot enhance bone strength. We proposed a novel strategy combining ¹²⁵I seeds with cement augmentation to achieve better tumor killing and bone stabilization.</p><p><strong>Methods: </strong>We retrospectively analyzed 64 patients (determined by power analysis assuming α=0.05, β=0.2, and expected difference in VAS scores of 1.5) with acetabular metastases who underwent either PCA alone (group A, n=34) or ¹²⁵I seed brachytherapy plus PCA (group B, n=30) between December 2008 and December 2022. Pain intensity (VAS), functional status (ECOG), and complications were evaluated as primary endpoints before and up to 6 months after treatment. Survival analysis was performed using Kaplan-Meier method with log-rank test.</p><p><strong>Results: </strong>The two groups had similar baseline characteristics. Group B showed significantly lower mean VAS scores (mean difference: 2.1; 95% CI: 1.6-2.6; <i>p</i> < 0.001) and ECOG scores (mean difference: 1.51; 95% CI: 1.1-1.9; <i>p</i> < 0.001) at 6 months post-treatment compared to group A. Complication rates were comparable between groups (5.9% vs 3.0%, <i>p</i> = 0.62), with no significant difference in median survival (16.8 vs 16.7 months, <i>p</i> = 0.85).</p><p><strong>Conclusion: </strong>Combined ¹²⁵I seed brachytherapy and PCA (¹²⁵I-PCA) provides superior long-term pain control and functional outcomes compared to PCA alone for acetabular metastases. This is attributed to the synergistic effect of PMMA-mediated mechanical stabilization and continuous low-dose radiation-induced tumor suppression, effectively addressing the transient cytoreduction limitation of standalone PCA. Integration of TPS(Treatment Planning System)-guided brachytherapy dosing with precise CT-guided cementoplasty represents an effective and safe palliative strategy for these complex lesions.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1673676"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463584/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnosis and management of a rare bilateral ovarian mixed germ cell tumor: a case report.","authors":"Xuanling Li, Min You, Xiaoyun Zhang, Jingjing Wei, Guangyao Lin, Qianjue Tang, Lianwei Xu","doi":"10.3389/fonc.2025.1504231","DOIUrl":"10.3389/fonc.2025.1504231","url":null,"abstract":"<p><strong>Background: </strong>Mixed ovarian malignant germ cell tumors (MOGCTs) are rare neoplasms composed of two or more malignant germ cell components, representing less than 1% of all ovarian germ cell tumors. They primarily affect adolescents and young women, presenting a clinical challenge due to their histologic heterogeneity, potential for recurrence, and the need to balance oncologic safety with fertility preservation.</p><p><strong>Case presentation: </strong>We reported a 22-year-old woman diagnosed with a four-component MOGCT in the right ovary-comprising yolk sac tumor, immature teratoma, embryonal carcinoma, and dysgerminoma-along with a dysgerminoma component in the left ovary. Considering her age and fertility desire, fertility-sparing surgery was performed, followed by adjuvant BEP chemotherapy. At 12-month follow-up, the patient remained disease-free with regular menstruation and no signs of recurrence.</p><p><strong>Conclusion: </strong>This case highlights the feasibility of fertility-sparing treatment in patients with complex bilateral MOGCTs. Given the rarity and histological diversity of such tumors, individualized treatment planning, strict staging, and long-term surveillance are essential to optimize clinical outcomes and preserve reproductive potential.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1504231"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463601/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FGFR2 expression relates to subtype-specific tumour microenvironment (TIME) during luminal breast cancer evolution.","authors":"Julia Sołek, Aleksandra Zielińska, Radzisław Kordek, Hanna Romańska, Marcin Braun","doi":"10.3389/fonc.2025.1655438","DOIUrl":"10.3389/fonc.2025.1655438","url":null,"abstract":"<p><strong>Background: </strong>Fibroblast growth factor receptor 2 (FGFR2) is an oncogenic driver in luminal breast cancer (BCa), with emerging evidence linking it to tumour immune microenvironment (TIME) modulation. While FGFR2's role in endocrine resistance is established, its potential involvement in shaping immune infiltration-particularly in the transition from ductal carcinoma <i>in situ</i> (DCIS) to invasive ductal carcinoma (IDC)-remains underexplored.</p><p><strong>Methods: </strong>This retrospective study analysed 99 BCa specimens collected between 2004-2019. Immunohistochemistry was used to assess FGFR2 expression and immune markers (CD8, CD68, CD163, FOXP3). Clinical and pathological variables were evaluated, and immune cell densities were compared across disease stages and BCa subtypes (luminal vs. non-luminal). Correlations between FGFR2 expression and immune markers were assessed using non-parametric statistical tests.</p><p><strong>Results: </strong>Progression from DCIS to IDC was associated with increased infiltration by CD8+ T cells and CD68+ macrophages. FGFR2 expression showed differences between DCIS and IDC with an extensive DCIS component and was positively correlated with CD8+, CD163+, and FOXP3+ cell densities. The latter associations were exclusive to luminal A tumours, with no such correlations observed in non-luminal subtypes.</p><p><strong>Conclusions: </strong>FGFR2 expression in luminal A BCa correlates with markers of immunosuppressive TIME, particularly CD163+ macrophages and FOXP3+ T cells. These subtype-specific interactions suggest a synergistic role of FGFR2 and estrogen receptor signalling in immune evasion and tumour progression, warranting further mechanistic and therapeutic investigation. However, the small number of cases in certain subgroups, particularly DCIS and non-luminal tumours, limits the generalizability of these findings and warrants cautious interpretation.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1655438"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463615/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence integrates multi-omics data for precision stratification and drug resistance prediction in breast cancer.","authors":"Deshui Ran, Jing Li, Mengmeng Zhao, Li Du, Yang Zhang, Jida Zhu","doi":"10.3389/fonc.2025.1612474","DOIUrl":"10.3389/fonc.2025.1612474","url":null,"abstract":"<p><p>Breast cancer (BC), the most prevalent malignancy in the female population, often presents significant difficulties in early diagnosis and identification of molecular subtypes. In addition, due to the lack of obvious clinical symptoms in the early stage and the lack of effective early detection means or specific biomarkers, about 30% of the cases are already in the advanced stage at the time of diagnosis, which directly leads to the patients missing the best treatment period. Unfortunately, BC is also highly heterogeneous, and its different molecular typing directly affects the outcome of treatment regimens such as chemotherapy, immunotherapy, etc., and significantly correlates with patients' 5-year survival rates. Artificial intelligence (AI) has rapidly advanced from proof of concept to prospective and real-world deployments, delivering radiologist level accuracy, improved specificity, and substantial workload reduction (≈44%-68%) without compromising cancer detection. Some studies even report more cancers detected when AI supports readers. These gains translate into earlier diagnosis, fewer unnecessary recalls, and more efficient screening workflows. Concurrently, multi-modal AI (integrating mammography, ultrasound/DBT, MRI, digital pathology, and multi omics) enables robust subtype identification, immune tumor microenvironment quantification, and prediction of immunotherapy response and drug resistance, thereby supporting individualized treatment design and drug discovery. The aim of this review is to systematically illustrate the efficient application of AI technology in BC diagnosis, such as constructing early diagnostic models based on multi-omics data, identifying molecular subtypes of BC, quantifying the tumor immune microenvironment and predicting the immunotherapeutic response, as well as investigating drug resistance of BC and developing new therapeutic agents. In the future, AI technology will be able to provide more accurate individualized diagnosis and treatment for BC patients.</p>","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1612474"},"PeriodicalIF":3.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463597/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145185322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}