Translational cancer research最新文献

{"title":"The TROP2 paradox: enhancing precision in immunotherapy for advanced non-small cell lung cancer patients-a commentary.","authors":"Saqib Raza Khan, Saurav Verma, Daniel Breadner, Jacques Raphael","doi":"10.21037/tcr-24-1633","DOIUrl":"10.21037/tcr-24-1633","url":null,"abstract":"","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"660-666"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658726","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":"Expression profile, regulatory mechanism and prognostic potential of MBNL2 in esophageal squamous cell carcinoma.","authors":"Shenglai Zhang, Xiaoqin Chu, Yan Zhang, Jianwei Qiu, Liuhong Pan, Liugen Gu, Haifeng Kang, Lin Wang","doi":"10.21037/tcr-24-1933","DOIUrl":"10.21037/tcr-24-1933","url":null,"abstract":"<p><strong>Background: </strong>It remains to refresh the understanding about the pathogenic mechanism of esophageal squamous cell carcinoma (ESCC). This study aimed to profile the expression of muscleblind like protein 2 (MBNL2), as well as its associations with ESCC behaviors.</p><p><strong>Methods: </strong>Bioinformatic tools were used to mine The Cancer Genome Atlas (TCGA) database for the expression data of MBNL2 in ESCC. The expression of MBNL2 in tissue microarray of 179 ESCC patients was determined by immunohistochemistry (IHC), and the relationship of MBNL2 with patients' clinical and pathological characteristics was analyzed. The expression of MBNL2 was tested in fresh ESCC and adjacent normal tissues <i>in vitro</i>. Experiments about cellular invasion, migration and proliferation were performed to detect the impacts of silencing MBNL2 on the biological behaviors of ESCC, and the positive results were checked <i>in vivo</i>.</p><p><strong>Results: </strong>In the TCGA database, the expression of MBNL2 in ESCC was higher than that in adjacent tissues (P<0.05). The protein level of MBNL2 in the tissue microarray of 179 ESCC patients was positively correlated with tumor stage and lymph node metastasis, and negatively correlated with the prognosis of patients. The expression of MBNL2 was significantly upregulated in five fresh ESCC tissues, compared to that in adjacent tissues. In functional experiments, knocking down MBNL2 significantly inhibited the migration and invasion of ESCC cell lines KYSE150 and Eca109, but had no significant effect on their proliferation. Finally, silencing MBNL2 inhibited the epithelial-mesenchymal transition (EMT) of ESCC cells, as evidenced by the upregulation of E-cadherin, the downregulation of Snail and Slug.</p><p><strong>Conclusions: </strong>MBNL2 is highly expressed in ESCC and associated with its Tumor Node Metastasis (TNM) stage, lymph node metastasis and prognosis. MBNL2 may promote ESCC progression through facilitating EMT.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"717-730"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912065/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658731","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":"CD69 predicts prognosis through immune cell infiltration and decitabine treatment response in acute myeloid leukemia.","authors":"Jie Zhou, Hao Wu, Bing Li, Lixin Lv, Shunli Zhu, Aibin Liang, Jianfei Fu","doi":"10.21037/tcr-24-1550","DOIUrl":"10.21037/tcr-24-1550","url":null,"abstract":"<p><strong>Background: </strong>Acute myeloid leukemia (AML) is a heterogeneous myeloid neoplasm. Recent studies have focused on unraveling the complexities of the tumor microenvironment (TME) and its impact on AML, with a specific emphasis on CD69, a potential TME regulator. However, the precise relationship between CD69 and AML is yet to be fully elucidated. This study aimed to analyze the heterogeneous gene expression landscape of AML patients using public databases, and to elucidate the relationship between CD69 expression and the pathophysiology of AML.</p><p><strong>Methods: </strong>Three gene datasets from Gene Expression Omnibus (GEO), ribonucleic acid (RNA) sequence data from The Cancer Genome Atlas (TCGA) and Therapeutically Applicable Research to Generate Effective Treatments (TARGET), and tumor cell lines data from Cancer Cell Line Encyclopedia (CCLE) were used. The Cox proportional hazards regression model was employed to assess the impact of differentially expressed genes on the overall survival (OS) rate of AML. Spearman's rank correlation coefficient analysis was conducted to determine the relationship between CD69 and immune cell infiltration in AML patients. Western blot analysis was utilized to verify CD69 expression in AML cell lines.</p><p><strong>Results: </strong>(I) Gene expression: 13 differentially expressed genes were identified in AML. (II) Impact on survival: CD69 expression was inversely related to OS of AML patients, with lower CD69 levels correlating with improved survival outcomes. (III) Independent risk factors: CD69, ITGB7, SCD and age were identified as independent risk factors in AML. (IV) Immune cell infiltration: a higher expression of CD69 was associated with reduced infiltration of CD8+ T cells and macrophages in AML. (V) Effect of decitabine (DA) treatment: AML patients treated with DA exhibited decreased CD69 expression.</p><p><strong>Conclusions: </strong>The study established a correlation between the expression of ITGB7, SCD, CD69 and the OS in AML patients. SCD, ITGB7 and age were identified as key prognostic factors. The multifaceted role of CD69 in AML, encompassing its association with prognosis, immune cell infiltration, and response to chemotherapy, underscores its potential as a key player in the complex landscape of AML pathogenesis and treatment response.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"865-880"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912086/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658632","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":"A novel machine learning-driven immunogenic cell death signature for predicting ovarian cancer prognosis.","authors":"Yali Wang, Peng Zhao, Xude Sun, Felipe Batalini, Gabriel Levin, Hooman Soleymani Majd, Hao Chen, Tingting Gao","doi":"10.21037/tcr-2025-118","DOIUrl":"10.21037/tcr-2025-118","url":null,"abstract":"<p><strong>Background: </strong>Ovarian cancer (OC) is one of the most lethal malignancies in women, primarily due to the absence of reliable predictive biomarkers and effective therapies. The complex role of immunogenic cell death (ICD) in OC remains poorly understood, despite its critical implications for enhancing immune responses against tumors. We are committed to developing and validating a novel ICD-related gene signature and producing certain guiding value for the clinical treatment of OC.</p><p><strong>Methods: </strong>We employed single-sample gene set enrichment analysis (ssGSEA) and weighted gene coexpression network analysis (WGCNA) on The Cancer Genome Atlas (TCGA)-ovarian carcinoma dataset to identify ICD-associated genes. A combination of 10 different machine learning approaches was used to construct an ICD-related signature (ICDRS), which was then validated across multiple datasets. The model's predictive power was integrated into a clinical nomogram to predict patient outcomes. Ultimately, we assessed the reaction of various risk subgroups to screen pharmaceuticals designed to address specific risk factors in the context of personalized medicine.</p><p><strong>Results: </strong>We identified 72 prognostic genes related to ICD. An unanimous ICDRS was developed using a 101-combination machine learning computational structure, demonstrating outstanding predictive accuracy for prognosis and clinical use. Patients categorized as low ICDRS varied from those of high ICDRS in terms of biological processes, mutation profiles, and immune cell penetration in the tumor microenvironment. In addition, potential medications that target specific subgroups at risk were identified.</p><p><strong>Conclusions: </strong>The ICDRS presents a significant advancement for prognostication of patients with OC, facilitating refined predictions and the exploration of personalized treatment pathways. Prospective clinical trials are necessary to validate its clinical utility and expand the application of this model to other cancer types.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"1359-1374"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912067/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657936","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":"Narrative review of 3D bioprinting for the construction of <i>in vitro</i> tumor models: present and prospects.","authors":"Jia-Yu Tao, Jun Zhu, Yu-Qiong Gao, Min Jiang, Hong Yin","doi":"10.21037/tcr-2025-128","DOIUrl":"10.21037/tcr-2025-128","url":null,"abstract":"<p><strong>Background and objective: </strong>The conventional in vitro research on tumor mechanisms is typically based on two-dimensional (2D) culture of tumor cells, which has many limitations in replicating <i>in vivo</i> tumorigenesis processes. In contrast, the three-dimensional (3D) bioprinting has paved the way for the construction of more biomimetic in vitro tumor models. This article comprehensively elucidates the features of 3D bioprinting and meticulously summarizes its applications in several selected tumors, aiming to offer valuable insights for future relevant studies.</p><p><strong>Methods: </strong>A literature search was conducted in the databases of PubMed and Web of Science for articles on 3D bioprinting for <i>in vitro</i> tumor model construction.</p><p><strong>Key content and findings: </strong>This article introduces various 3D bioprinting technologies for <i>in vitro</i> tumor model construction, focusing on their pros and cons, principles, and protocols. Several <i>in vitro</i> tumor models are presented, detailing their utility in tumorigenesis research and their constraints. To date, 3D bioprinting has been widely applied in oncology, addressing the limitation of traditional 2D tumor cell culture in replicating tumor microenvironment (TME).</p><p><strong>Conclusions: </strong>Advanced 3D bioprinting technology accurately replicates the complex TME and the heterogeneity of intratumor structures, enabling further <i>in vitro</i> tumor studies. It significantly fuels our understanding of tumor pathophysiology and offers new hope for cancer patients.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"1479-1491"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912033/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658192","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":"Construction and validation of a prognostic model of lncRNAs associated with RNA methylation in lung adenocarcinoma.","authors":"Liren Zhang, Lei Yang, Xiaobo Chen, Qiubo Huang, Zhiqiang Ouyang, Ran Wang, Bingquan Xiang, Hong Lu, Wenjun Ren, Ping Wang","doi":"10.21037/tcr-24-1085","DOIUrl":"10.21037/tcr-24-1085","url":null,"abstract":"<p><strong>Background: </strong>Lung adenocarcinoma (LUAD) is a common type of lung cancer and one of the leading causes of cancer death worldwide. Long non-coding RNAs (lncRNAs) play a crucial role in tumors. The purpose of this study was to explore the expression of lncRNAs associated with RNA methylation modification and their prognostic value in LUAD.</p><p><strong>Methods: </strong>The RNA sequencing and clinical data were downloaded from The Cancer Genome Atlas dataset, and the messenger RNA and lncRNAs were annotated by Ensemble. The lncRNAs related to RNA methylation regulators (RMlncRNAs) were filtered by Pearson correlation analysis between differentially expressed lncRNAs and RNA methylation regulators. Univariate Cox regression analysis, multivariate Cox regression analysis, and least absolute shrinkage and selection operator regression analysis were used to construct a prognostic model. The receiver operating characteristic curve (ROC) was plotted to validate the predictive value of the prognostic model. Then, tumor mutational burden (TMB) and microsatellite instability were used to compare the immunotherapy response. Finally, to perform a drug sensitivity analysis, the half-maximal inhibitory concentration (IC₅₀) of targeted drugs was calculated using pRRophetic package.</p><p><strong>Results: </strong>In total, 18 RMlncRNAs associated with the prognosis of LUAD patients were identified. Then, six feature lncRNAs (<i>NFYC-AS1</i>, <i>OGFRP1</i>, <i>MIR4435-2HG</i>, <i>TDRKH-AS1</i>, <i>DANCR</i>, and <i>TMPO-AS1</i>) were used to construct a prognostic model. The ROC curves for training, testing, and validation sets showed that the prognosis model was effective. The subindex based on the prognostic model had a high correlation with TMB. The high-risk group might be subject to greater immune resistance according to the comparison of Tumor Immune Dysfunction and Exclusion scores. Finally, the IC₅₀ of 11 drugs had differences between high- and low-risk group, and only three of the drug's target genes (<i>ERBB4</i>, <i>CASP8</i>, and <i>CD86</i>) were differentially expressed.</p><p><strong>Conclusions: </strong>In conclusion, a prognostic model based on six feature lncRNAs (<i>NFYC-AS1</i>, <i>OGFRP1</i>, <i>MIR4435-2HG</i>, <i>TDRKH-AS1</i>, <i>DANCR</i>, and <i>TMPO-AS1</i>) was constructed by bioinformatics analysis, which might provide a new insight into the evaluation and treatment of LUAD.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"761-777"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912078/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658692","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":"Construction and validation of machine learning models for predicting lymph node metastasis in cutaneous malignant melanoma: a large population-based study.","authors":"Ling-Feng Lan, Yi-Long Kai, Xiao-Ling Xu, Jun-Kun Zhang, Guang-Bo Xu, Yan-Bi Dai, Yan Shen, Hua-Ya Lu, Ben Wang","doi":"10.21037/tcr-24-1672","DOIUrl":"10.21037/tcr-24-1672","url":null,"abstract":"<p><strong>Background: </strong>Lymph node status is essential for determining the prognosis of cutaneous malignant melanoma (CMM). This study aimed to develop a machine learning (ML) model for predicting lymph node metastases (LNM) in CMM.</p><p><strong>Methods: </strong>We gathered data on 6,196 patients from the Surveillance, Epidemiology, and End Results (SEER) database, including known clinicopathologic variables, using six ML algorithms, including logistic regression (LR), support vector machine (SVM), Complement Naive Bayes (CNB), Extreme Gradient Boosting (XGBoost), RandomForest (RF), and k-nearest neighbor algorithm (kNN), to predict the presence of LNM in CMM. Subsequently, we established prediction models. The utilization of the adaptive synthetic (ADASYN) method served to address the challenge posed by imbalanced data. We assessed prediction model performance in terms of average precision (AP), sensitivity, specificity, accuracy, F1 score, precision-recall curves, calibration plots, and decision curve analysis (DCA). Furthermore, employing SHapley Additive exPlanation (SHAP) analysis resulted in the creation of visualized explanations tailored to individual patients.</p><p><strong>Results: </strong>Among the 6,196 CMM cases, 19.9% (n=1,234) presented with LNM. The XGBoost model showed the best predictive performance when compared with the other algorithms (AP of 0.805). XGBoost showed that age and Breslow thickness were the two most important factors related to LNM.</p><p><strong>Conclusions: </strong>The XGBoost model predicted LNM of CMM with a high level of precision. We hope that this model could assist surgeons in accurately evaluating surgical approaches and determining the extent of surgery, while also guiding the subsequent adjuvant therapies, thereby improving the prognosis of patients.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"706-716"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912072/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658696","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":"Construction of a prognostic signature for breast cancer based on genes involved in unsaturated fatty acid biosynthesis.","authors":"Hua Meng, Shuangyi Zhang, Min Ling, Yuanyuan Hu, Xiaohong Xie","doi":"10.21037/tcr-24-1668","DOIUrl":"10.21037/tcr-24-1668","url":null,"abstract":"<p><strong>Background: </strong>The biosynthesis of unsaturated fatty acids (UFAs) has been implicated in the onset and advancement of breast cancer (BC). This study aimed to develop molecular subtypes and prognostic signatures for BC based on UFA-related genes (UFAGs).</p><p><strong>Methods: </strong>This study integrates multi-omics and survival data from public databases to elucidate molecular classifications and risk profiles based on UFAGs. Consensus clustering and Lasso Cox regression methodologies are employed for subtype identification and risk signature development, respectively. Immune microenvironment assessment is conducted using CIBERSORT and ESTIMATE algorithms, while drug sensitivity and response to immunotherapy are evaluated via pRRophetic and TIDE methods. Gene set enrichment analysis augments signature characterization, followed by nomogram construction and validation.</p><p><strong>Results: </strong>We successfully identified two distinct BC molecular subtypes with significantly different prognoses utilizing UFAGs correlated with outcomes. A prognostic signature comprising three UFAGs [acetyl-CoA acyltransferase 1 (<i>ACAA1</i>), acyl-CoA thioesterase 2 (<i>ACOT2</i>), and ELOVL fatty acid elongase 2 (<i>ELOVL2</i>)] is developed, stratifying patients into high- and low-risk groups exhibiting divergent outcomes, clinicopathological traits, gene expression patterns, immune infiltration profiles, therapeutic susceptibility, and immunotherapy responses. The signature demonstrates robust prognostic performance in both training and validation cohorts, emerging as an independent predictor alongside age, which is integrated into a nomogram. Decision curve analysis highlights the nomogram's superiority over other factors in prognosis prediction. Calibration plots and receiver operating characteristic curves affirm its excellent performance in BC prognosis assessment.</p><p><strong>Conclusions: </strong>Expression profiles of UFAGs are associated with BC prognosis, enabling the creation of a risk signature with implications for understanding the molecular mechanisms underlying BC progression.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"1190-1204"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912055/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658703","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":"Identification of Fanconi anemia pathway genes as novel prognostic biomarkers and therapeutic targets for breast cancer.","authors":"Yunyong Wang, Xiaohang Lu, Hongsheng Lin, Yangling Zeng, Jiaqian He, Jinna Tan, Mingfen Li","doi":"10.21037/tcr-24-772","DOIUrl":"10.21037/tcr-24-772","url":null,"abstract":"<p><strong>Background: </strong>Globally, breast cancer is one of the most common cancers with poor prognosis. The Fanconi anemia (FA) pathway genes maintain genome stability and play important roles in human diseases, including cancer. However, the prognostic values and biological roles of FA pathway genes in breast cancer have not been clarified. This study aims to investigate the potential of FA pathway genes as prognostic biomarkers and therapeutic targets in breast cancer.</p><p><strong>Methods: </strong>In this study, the Oncomine Cancer Microarray (ONCOMINE), University of ALabama at Birmingham Cancer (UALCAN), Kaplan-Meier plotter, cBio Cancer Genomics Portal (cBioPortal), Gene Expression Profiling Interactive Analysis (GEPIA), Gene Multi-Association Network Integration Algorithm (GeneMANIA), the Database for Annotation, Visualization and Integrated Discovery (DAVID) and Tumor Immune Estimation Resource (TIMER) databases were used to investigate the transcriptional and survival data of FA pathway genes in patients with breast cancer.</p><p><strong>Results: </strong>Most of the FA pathway genes were found to be significantly upregulated in breast cancer tissues when compared to normal tissues. Additionally, the elevated expression levels of FA pathway genes were significantly associated with poor survival outcomes in breast cancer patients. Through functional enrichment analysis, the FA pathway genes were positively associated with cell cycle and nucleoplasm and negatively correlated with signal recognition particle-dependent co-translational protein targeting to membrane and ribosome. Furthermore, the expression levels of FA pathway genes exhibited a significant positive association with immune infiltration.</p><p><strong>Conclusions: </strong>The FA pathway genes are potential prognostic biomarkers for breast cancer and may offer effective as well as new strategies for cancer management.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"843-864"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912030/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657909","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":"Radiomics models using machine learning algorithms to differentiate the primary focus of brain metastasis.","authors":"Yuping Xie, Xuanzi Li, Shuai Yang, Fujie Jia, Yuanyuan Han, Mingsheng Huang, Lei Chen, Wei Zou, Chuntao Deng, Zibin Liang","doi":"10.21037/tcr-24-1355","DOIUrl":"10.21037/tcr-24-1355","url":null,"abstract":"<p><strong>Background: </strong>Brain metastases are common brain tumors in adults. Brain metastases from different primary tumors have special magnetic resonance imaging (MRI) features. As a new technology that can extract and quantify medical image data, and with the rapid development of artificial intelligence, the machine learning model based on radiology has been successfully applied to the diagnosis and differentiation of tumors. This study aimed to develop radiomics models from post-contrast T1-weighted images using machine learning algorithms to differentiate lung cancer from breast cancer brain metastases.</p><p><strong>Methods: </strong>A retrospective analysis was conducted on 118 lung cancer brain metastases patients and 62 breast cancer brain metastases patients confirmed by surgery pathology or combined clinical and imaging diagnosis at The Fifth Affiliated Hospital of Sun Yat-sen University from August 2015 to September 2023. Patients were randomly divided into a training set (126 cases) and a validation set (54 cases) at a 7:3 ratio. Enhanced T1-weighted images of all patients were imported into ITK-SNAP software to manually delineate the region of interest (ROI). Radiomic features were extracted based on the ROI and feature selection was performed using the least absolute shrinkage and selection operator. Significant features were used to develop models using logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), multilayer perceptron (MLP), and light gradient boosting machine (LightGBM). The diagnostic performance of the models was assessed using the receiver operating characteristic (ROC) curve.</p><p><strong>Results: </strong>The LightGBM radiomics model exhibited the best diagnostic performance, with an area under the curve (AUC) of 0.875 [95% confidence interval (CI): 0.819-0.931] in the training set and 0.866 (95% CI: 0.740-0.993) in the validation set.</p><p><strong>Conclusions: </strong>The enhanced MRI radiomics model, especially the LightGBM model, can accurately predict the primary lesion types of brain metastases from lung cancer and breast cancer origins.</p>","PeriodicalId":23216,"journal":{"name":"Translational cancer research","volume":"14 2","pages":"731-742"},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912090/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658336","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}