Zhonglin Zhang, Huan Liu, Xiling Gu, Yang Qiu, Jiangqing Ma, Guangyong Ai, Xiaojing He
{"title":"多模态融合放射免疫评分模型:准确识别前列腺癌进展。","authors":"Zhonglin Zhang, Huan Liu, Xiling Gu, Yang Qiu, Jiangqing Ma, Guangyong Ai, Xiaojing He","doi":"10.1186/s12880-025-01869-w","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to conceptualize, develop, and rigorously validate an innovative Radiomic-Immunologic Score (RDIS) model for accurately distinguishing prostate cancer (PCa) progression.</p><p><strong>Methods: </strong>This single-center, retrospective cohort study analyzed PCa patients diagnosed between 2019 and 2022. This study employed a comprehensive interdisciplinary approach, integrating CD3+/CD8 + T cell immunoanalysis with Multiparametric Magnetic Resonance Imaging (mpMRI) analysis, while adhering to a robust multi-phase feature selection process. This included the Akaike Information Criterion (AIC), Maximum Relevance Minimum Redundancy (mRMR), and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms, validated through 10-fold cross-validation. Logistic regression models were constructed for radiomic, immunologic, and combined RDIS models, with predictive performance rigorously evaluated using Receiver Operating Characteristic (ROC) curve analysis, calibration curve assessments, and Decision Curve Analysis (DCA).</p><p><strong>Results: </strong>The RDIS model achieved an Area Under the Curve (AUC) of 0.874 in the validation cohort, outperforming traditional single-omics models, including the radiomic model (AUC: 0.844) and the immunologic model (AUC: 0.767), supporting potential use in early intervention decision-making. The correlation heatmap reveals weak to moderate correlations among 7 pairs of radiomic and immunologic features associated with PCa progression. The RDIS model demonstrates good specificity in further predicting bone metastases and castration-resistant prostate cancer (CRPC).</p><p><strong>Conclusions: </strong>The RDIS model effectively distinguished the progression status of PCa, with its multi-omics integrative attributes likely providing comprehensive insights into the factors influencing disease progression.</p><p><strong>Advances in knowledge: </strong>The immunologic and radiologic characteristics are associated with prostate cancer progression. The RDIS multi-omics integrative scoring system shows great potential in distinguishing whether prostate cancer has progressed.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"324"},"PeriodicalIF":3.2000,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12341337/pdf/","citationCount":"0","resultStr":"{\"title\":\"Multimodal fusion radiomic-immunologic scoring model: accurate identification of prostate cancer progression.\",\"authors\":\"Zhonglin Zhang, Huan Liu, Xiling Gu, Yang Qiu, Jiangqing Ma, Guangyong Ai, Xiaojing He\",\"doi\":\"10.1186/s12880-025-01869-w\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>This study aims to conceptualize, develop, and rigorously validate an innovative Radiomic-Immunologic Score (RDIS) model for accurately distinguishing prostate cancer (PCa) progression.</p><p><strong>Methods: </strong>This single-center, retrospective cohort study analyzed PCa patients diagnosed between 2019 and 2022. This study employed a comprehensive interdisciplinary approach, integrating CD3+/CD8 + T cell immunoanalysis with Multiparametric Magnetic Resonance Imaging (mpMRI) analysis, while adhering to a robust multi-phase feature selection process. This included the Akaike Information Criterion (AIC), Maximum Relevance Minimum Redundancy (mRMR), and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms, validated through 10-fold cross-validation. Logistic regression models were constructed for radiomic, immunologic, and combined RDIS models, with predictive performance rigorously evaluated using Receiver Operating Characteristic (ROC) curve analysis, calibration curve assessments, and Decision Curve Analysis (DCA).</p><p><strong>Results: </strong>The RDIS model achieved an Area Under the Curve (AUC) of 0.874 in the validation cohort, outperforming traditional single-omics models, including the radiomic model (AUC: 0.844) and the immunologic model (AUC: 0.767), supporting potential use in early intervention decision-making. The correlation heatmap reveals weak to moderate correlations among 7 pairs of radiomic and immunologic features associated with PCa progression. The RDIS model demonstrates good specificity in further predicting bone metastases and castration-resistant prostate cancer (CRPC).</p><p><strong>Conclusions: </strong>The RDIS model effectively distinguished the progression status of PCa, with its multi-omics integrative attributes likely providing comprehensive insights into the factors influencing disease progression.</p><p><strong>Advances in knowledge: </strong>The immunologic and radiologic characteristics are associated with prostate cancer progression. The RDIS multi-omics integrative scoring system shows great potential in distinguishing whether prostate cancer has progressed.</p>\",\"PeriodicalId\":9020,\"journal\":{\"name\":\"BMC Medical Imaging\",\"volume\":\"25 1\",\"pages\":\"324\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-08-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12341337/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Medical Imaging\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12880-025-01869-w\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Medical Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12880-025-01869-w","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Multimodal fusion radiomic-immunologic scoring model: accurate identification of prostate cancer progression.
Objectives: This study aims to conceptualize, develop, and rigorously validate an innovative Radiomic-Immunologic Score (RDIS) model for accurately distinguishing prostate cancer (PCa) progression.
Methods: This single-center, retrospective cohort study analyzed PCa patients diagnosed between 2019 and 2022. This study employed a comprehensive interdisciplinary approach, integrating CD3+/CD8 + T cell immunoanalysis with Multiparametric Magnetic Resonance Imaging (mpMRI) analysis, while adhering to a robust multi-phase feature selection process. This included the Akaike Information Criterion (AIC), Maximum Relevance Minimum Redundancy (mRMR), and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms, validated through 10-fold cross-validation. Logistic regression models were constructed for radiomic, immunologic, and combined RDIS models, with predictive performance rigorously evaluated using Receiver Operating Characteristic (ROC) curve analysis, calibration curve assessments, and Decision Curve Analysis (DCA).
Results: The RDIS model achieved an Area Under the Curve (AUC) of 0.874 in the validation cohort, outperforming traditional single-omics models, including the radiomic model (AUC: 0.844) and the immunologic model (AUC: 0.767), supporting potential use in early intervention decision-making. The correlation heatmap reveals weak to moderate correlations among 7 pairs of radiomic and immunologic features associated with PCa progression. The RDIS model demonstrates good specificity in further predicting bone metastases and castration-resistant prostate cancer (CRPC).
Conclusions: The RDIS model effectively distinguished the progression status of PCa, with its multi-omics integrative attributes likely providing comprehensive insights into the factors influencing disease progression.
Advances in knowledge: The immunologic and radiologic characteristics are associated with prostate cancer progression. The RDIS multi-omics integrative scoring system shows great potential in distinguishing whether prostate cancer has progressed.
期刊介绍:
BMC Medical Imaging is an open access journal publishing original peer-reviewed research articles in the development, evaluation, and use of imaging techniques and image processing tools to diagnose and manage disease.