{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:14:19Z","timestamp":1783314859808,"version":"3.54.6"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To evaluate the performance of a multimodal fusion framework integrating a Vision Transformer (ViT), radiomics, and clinical features for predicting bone metastasis (BM) status in patients with prostate cancer (PCa).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients with pathologically confirmed PCa were retrospectively included. Based on clinical features and apparent diffusion coefficient (ADC) images, three single-modal models were constructed: the clinical model (Model_Clin), the radiomics model (Model_Rad), and the ViT model (Model_ViT). Subsequently, a multimodal fusion model (Model_Fusion) was constructed by integrating ViT, radiomics, and clinical features. Model performance was evaluated using the receiver operating characteristic (ROC) curve and the DeLong test. The clinical utility and interpretability of the Model_Fusion were assessed using decision curve analysis (DCA) and Shapley additive explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Model_ViT demonstrated the best performance among the single-modal models, achieving AUCs of 0.909 and 0.872 in the training and validation sets, respectively, outperforming both Model_Rad (AUC\u00a0=\u00a00.885 and 0.842) and Model_Clin (AUC\u00a0=\u00a00.861 and 0.781). By integrating multimodal information, Model_Fusion achieved superior performance (AUC\u00a0=\u00a00.944 and 0.894). DeLong test results showed that, in the training set, Model_Fusion had a significantly higher AUC than Model_Clin, Model_Rad, and Model_ViT (all\n                      <jats:italic>P<\/jats:italic>\n                      \u00a0&amp;lt;\u00a00.05), whereas in the validation set, a significant difference was observed only when compared with Model_Clin. DCA further demonstrated that Model_Fusion provided a higher net benefit. SHAP analysis indicated that the predicted probability of ViT contributed the most to Model_Fusion.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A fusion model integrating ViT, radiomics, and clinical features provides a non-invasive framework for predicting BM in PCa, which may help guide personalized clinical decision-making and prognostic evaluation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1841761","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T04:20:42Z","timestamp":1783311642000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A multimodal fusion model integrating Vision Transformer, radiomics, and clinical features for predicting bone metastasis in prostate cancer"],"prefix":"10.3389","volume":"16","author":[{"given":"Guobo","family":"Li","sequence":"first","affiliation":[{"name":"Department of Radiology, Taizhou Central Hospital (Taizhou University Hospital)","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqiu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taizhou Central Hospital (Taizhou University Hospital)","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuliang","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taizhou Central Hospital (Taizhou University Hospital)","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenmei","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taizhou Central Hospital (Taizhou University Hospital)","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Clinical Medical College, Jiamusi University","place":["Jiamusi, Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zishan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taizhou Central Hospital (Taizhou University Hospital)","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taizhou Central Hospital (Taizhou University Hospital)","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dabin","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taizhou Central Hospital (Taizhou University Hospital)","place":["Taizhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3322\/caac.21871","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.6004\/jnccn.2023.0050","article-title":"Prostate cancer, version 4.2023, NCCN clinical practice guidelines in oncology","volume":"21","author":"Schaeffer","year":"2023","journal-title":"J Natl Compr Canc Netw"},{"key":"B4","doi-asserted-by":"publisher","first-page":"9104","DOI":"10.1038\/s41598-020-64073-6","article-title":"Prognosis of prostate cancer and bone metastasis pattern of patients: a SEER-based study and a local hospital based study from China","volume":"10","author":"Liu","year":"2020","journal-title":"Sci Rep"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-018-0935-y","article-title":"Identification of the most significant magnetic resonance imaging (MRI) radiomic features in oncological patients with vertebral bone marrow metastatic disease: a feasibility study","volume":"124","author":"Filograna","year":"2019","journal-title":"Radiol Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.eururo.2017.06.002","article-title":"Management of patients with advanced prostate cancer: the report of the advanced prostate cancer consensus conference APCCC 2017","volume":"73","author":"Gillessen","year":"2018","journal-title":"Eur Urol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.119.228320","article-title":"Multimodality imaging of prostate cancer","volume":"60","author":"Ghafoor","year":"2019","journal-title":"J Nucl Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.juro.2010.03.034","article-title":"Skeletal related events, bone metastasis and survival of prostate cancer: a population based cohort study in Denmark (1999 to 2007)","volume":"184","author":"N\u00f8rgaard","year":"2010","journal-title":"J Urol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: extracting more information from medical images using advanced feature analysis","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur J Cancer"},{"key":"B10","doi-asserted-by":"publisher","first-page":"4006","DOI":"10.1038\/ncomms5006","article-title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts","year":"2014","journal-title":"Nat Commun"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2025.11.033","article-title":"Noninvasive prediction of perineural invasion and lymphovascular invasion in prostate cancer using bpmri radiomic signatures","volume":"33","author":"Zhang","year":"2026","journal-title":"Acad Radiol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2023.10.020","article-title":"Delta radiomics model for the prediction of overall survival and local recurrence in small cell lung cancer patients after chemotherapy","volume":"31","author":"Ding","year":"2024","journal-title":"Acad Radiol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2026.100741","article-title":"Convolutional neural networks for prostate cancer detection, classification, and segmentation: a systematic review and bibliometric analysis","volume":"16","author":"G\u00fclmez","year":"2026","journal-title":"Eur J Radiol Open"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.mex.2025.103769","article-title":"BRAIN-META: a reproducible CNN-vision transformer meta-ensemble pipeline for explainable brain tumor classification","volume":"16","author":"Kumar Napa","year":"2025","journal-title":"Methodsx"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2026.109260","article-title":"Enhancing accuracy and explainability in colorectal lesion classification with attention-supervised vision transformers","volume":"277","author":"Carlini","year":"2026","journal-title":"Comput Methods Programs BioMed"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/651580","article-title":"Cellular plasticity in prostate cancer bone metastasis","volume":"2015","author":"Jadaan","year":"2015","journal-title":"Prostate Cancer"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000788","article-title":"De novo radiomics approach using image augmentation and features from T1 mapping to predict Gleason scores in prostate cancer","volume":"56","author":"Makowski","year":"2021","journal-title":"Invest Radiol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.5100","article-title":"Development and external validation of a novel nomogram to predict prostate cancer in biopsy-na\u00efve patients with PSA <10 ng\/ml and PI-RADS v2.1 = 3 lesions","volume":"12","author":"Hu","year":"2023","journal-title":"Cancer Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-022-03639-6","article-title":"Preoperative prediction of invasive behavior of pancreatic solid pseudopapillary neoplasm by MRI-based multiparametric radiomics models","volume":"47","author":"Liang","year":"2022","journal-title":"Abdom Radiol (NY)"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2020.109020","article-title":"A radiomics nomogram for predicting bone metastasis in newly diagnosed prostate cancer patients","volume":"128","author":"Zhang","year":"2020","journal-title":"Eur J Radiol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11080250","article-title":"The role of radiomic analysis and different machine learning models in prostate cancer diagnosis","volume":"11","author":"Bekou","year":"2025","journal-title":"J Imaging"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1555315","article-title":"Prediction of bone metastasis of prostate cancer based on intratumoral and peritumoral radiomics of MRI T2WI combined with ADC images","volume":"15","author":"Lin","year":"2025","journal-title":"Front Oncol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1148\/radiol.13122697","article-title":"Quantitative imaging in cancer evolution and ecology","volume":"269","author":"Gatenby","year":"2013","journal-title":"Radiology"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.222223","article-title":"An MRI deep learning model predicts outcome in rectal cancer","volume":"307","author":"Jiang","year":"2023","journal-title":"Radiology"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.21037\/qims-23-542","article-title":"Transformers in medical image segmentation: a narrative review","volume":"13","author":"Khan","year":"2023","journal-title":"Quant Imaging Med Surg"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202503925","article-title":"A dynamic contrast-enhanced MRI-based vision transformer model for distinguishing HER2-zero, -low, and -positive expression in breast cancer and exploring model interpretability","volume":"12","author":"Zhang","year":"2025","journal-title":"Adv Sci (Weinh)"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12112654","article-title":"BUViTNet: breast ultrasound detection via vision transformers","volume":"12","author":"Ayana","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"B29","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s13244-026-02205-8","article-title":"Integrating deep learning with multimodal MRI habitat radiomics: toward personalized prediction of risk stratification and androgen deprivation therapy outcomes in prostate cancer","volume":"17","author":"Zhang","year":"2026","journal-title":"Insights Imaging"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"B31","doi-asserted-by":"publisher","first-page":"44413","DOI":"10.1038\/s41598-025-31623-9","article-title":"Enhanced classification prostate cancer based on generative adversarial networks and integrated deep learning with vision transformer models","volume":"15","author":"Salama","year":"2025","journal-title":"Sci Rep"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3390\/clinpract15010004","article-title":"Magnetic resonance imaging techniques for post-treatment evaluation after external beam radiation therapy of prostate cancer: narrative review","volume":"15","author":"Bekou","year":"2024","journal-title":"Clin Pract"},{"key":"B33","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1186\/s13244-025-02167-3","article-title":"MRI-based habitat radiomics and deep learning for predicting vessels encapsulating tumor clusters and survival in hepatocellular carcinoma","volume":"16","author":"Wang","year":"2025","journal-title":"Insights Imaging"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1841761\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T04:20:43Z","timestamp":1783311643000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1841761\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":33,"alternative-id":["10.3389\/fonc.2026.1841761"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1841761","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"article-number":"1841761"}}