{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:53:13Z","timestamp":1781880793839,"version":"3.54.5"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"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><jats:title>Background<\/jats:title><jats:p>Upper tract urothelial carcinoma (UTUC) is a rare but highly invasive urinary malignancy with a high postoperative recurrence rate.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We retrospectively collected data from 133 UTUC patients who underwent radical nephroureterectomy between 2005 and 2017. Patients were divided into a training set (n=103) and a testing set (n=30). A multi-modal deep learning model named Multi-modal Image-Clinical Combination Classifier (MICC) was developed by integrating multi-phase contrast-enhanced CT imaging and clinical data. The model\u2019s prognostic performance was compared with two unimodal models\u2014ImageNet (CT-based) and ClinicalNet (clinical data-based)\u2014and traditional clinical parameters including pathological T stage. Feature importance was evaluated using SHapley Additive exPlanations (SHAP).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The MICC model achieved superior prognostic accuracy with AUCs of 0.918 and 0.895 in the training and testing sets, respectively, outperforming unimodal models. Classification metrics were robust, with accuracy of 0.854, sensitivity of 0.889, specificity of 0.836, negative predictive value (NPV) of 0.933, and positive predictive value (PPV) of 0.744. Precision-recall analysis confirmed strong identification of high-risk patients despite dataset imbalance. SHAP analysis highlighted that CT imaging features contributed most significantly to the model\u2019s predictions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Integrating multi-phase CT imaging with clinical data, the MICC model provides accurate prognostic prediction for UTUC patients. This approach has potential to assist clinicians in personalized risk stratification and treatment planning, ultimately improving patient outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2025.1644250","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T04:12:39Z","timestamp":1754453559000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A multi-data fusion deep learning model for prognostic prediction in upper tract urothelial carcinoma"],"prefix":"10.3389","volume":"15","author":[{"given":"Hongdi","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siping","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxing","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengyan","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianguo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangwei","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fanggui","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binwei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3322\/caac.21590","article-title":"Cancer statistics, 2020","volume":"70","author":"Siegel","year":"2020","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1007\/s00345-016-1928-x","article-title":"Epidemiology, diagnosis, preoperative evaluation and prognostic assessment of upper-tract urothelial carcinoma (UTUC)","volume":"35","author":"Soria","year":"2017","journal-title":"World J Urol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejso.2014.06.007","article-title":"Radical nephroureterectomy versus endoscopic procedures for the treatment of localised upper tract urothelial carcinoma: a meta-analysis and a systematic review of current evidence from comparative studies","volume":"40","author":"Yakoubi","year":"2014","journal-title":"Eur J Surg Oncol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.2147\/CMAR.S219568","article-title":"Increased expression of SOX2 predicts A poor prognosis and promotes Malignant phenotypes in upper tract urothelial carcinoma","volume":"11","author":"Bao","year":"2019","journal-title":"Cancer Manag Res"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1093\/ckj\/sfx149","article-title":"The European renal association - European dialysis and transplant association (ERA-EDTA) registry annual report 2015: a summary","volume":"11","author":"Kramer","year":"2018","journal-title":"Clin Kidney J"},{"key":"B6","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.ejrad.2017.10.021","article-title":"Upper tract urothelial cancer","volume":"98","author":"Froemming","year":"2018","journal-title":"Eur J Radiol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1159\/000019869","article-title":"Conventional CT signs in staging transitional cell tumors of the upper urinary tract","volume":"35","author":"Mill\u00e1n-Rodr\u00edguez","year":"1999","journal-title":"Eur Urol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s13045-022-01225-3","article-title":"Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients","volume":"15","author":"Wang","year":"2022","journal-title":"J Hematol Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-02134-1","article-title":"Multistain deep learning for prediction of prognosis and therapy response in colorectal cancer","volume":"29","author":"Foersch","year":"2023","journal-title":"Nat Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.5842","article-title":"Development and validation of a deep learning model for non-small cell lung cancer survival","volume":"3","author":"She","year":"2020","journal-title":"JAMA Netw Open"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-17-0853","article-title":"Deep learning-based multi-omics integration robustly predicts survival in liver cancer","volume":"24","author":"Chaudhary","year":"2018","journal-title":"Clin Cancer Res"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.907975","article-title":"A systematic review and meta-analysis of prognostic nomograms after UTUC surgery","volume":"12","author":"Pallauf","year":"2022","journal-title":"Front Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3390\/biomedinformatics4010015","article-title":"Deep machine learning for medical diagnosis, application to lung cancer detection: A review","volume":"4","author":"Gayap","year":"2024","journal-title":"BioMedInformatics"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-022-05793-x","article-title":"Deep learning signatures reveal multiscale intratumor heterogeneity associated with biological functions and survival in recurrent nasopharyngeal carcinoma","volume":"49","author":"Zhao","year":"2022","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1097\/JS9.0000000000001483","article-title":"Radiomics-based machine learning approach for the prediction of grade and stage in upper urinary tract urothelial carcinoma: a step towards virtual biopsy","volume":"110","author":"Alqahtani","year":"2024","journal-title":"Int J Surg"},{"key":"B16","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1186\/s13244-025-01988-6","article-title":"Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images","volume":"16","author":"Xiao","year":"2025","journal-title":"Insights into Imaging"},{"key":"B17","doi-asserted-by":"publisher","first-page":"102220","DOI":"10.1016\/j.clgc.2024.102220","article-title":"Survival outcomes by race following surgical treatment for upper tract urothelial carcinoma","volume":"22","author":"Zappia","year":"2024","journal-title":"Clin Genitourinary Cancer"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.6901","article-title":"A computed tomography urography-based machine learning model for predicting preoperative pathological grade of upper urinary tract urothelial carcinoma","volume":"13","author":"Zheng","year":"2024","journal-title":"Cancer Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1186\/s13045-021-01167-2","article-title":"Deep learning for differential diagnosis of Malignant hepatic tumors based on multi-phase contrast-enhanced CT and clinical data","volume":"14","author":"Gao","year":"2021","journal-title":"J Hematol Oncol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.11946","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"Int Conf Mach learning"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B22","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"B23","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s43856-023-00276-y","article-title":"Multimodal deep learning to predict prognosis in adult and pediatric brain tumors","volume":"3","author":"Steyaert","year":"2023","journal-title":"Commun Med (Lond)"},{"key":"B24","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.annonc.2021.09.007","article-title":"Improved breast cancer histological grading using deep learning","volume":"33","author":"Wang","year":"2022","journal-title":"Ann Oncol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"101146","DOI":"10.1016\/j.xcrm.2023.101146","article-title":"Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics","volume":"4","author":"Jiang","year":"2023","journal-title":"Cell Rep Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"104115","DOI":"10.1016\/j.compbiomed.2020.104115","article-title":"A scoping review of transfer learning research on medical image analysis using ImageNet","volume":"128","author":"Morid","year":"2021","journal-title":"Comput Biol Med"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1038\/nrurol.2016.252","article-title":"Diagnostic dilemmas in patients with upper tract urothelial carcinoma","volume":"14","author":"Baard","year":"2017","journal-title":"Nat Rev Urol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1111\/j.1464-410X.2011.10288.x","article-title":"Combining imaging and ureteroscopy variables in a preoperative multivariable model for prediction of muscle-invasive and non-organ confined disease in patients with upper tract urothelial carcinoma","volume":"109","author":"Favaretto","year":"2012","journal-title":"BJU Int"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1559325819882872","DOI":"10.1177\/1559325819882872","article-title":"A model for the prediction of survival in patients with upper tract urothelial carcinoma after surgery","volume":"17","author":"Zhang","year":"2019","journal-title":"Dose Response"},{"key":"B30","doi-asserted-by":"publisher","first-page":"296","DOI":"10.3322\/canjclin.39.5.296","article-title":"Anemia and cancer","volume":"39","author":"Steinberg","year":"1989","journal-title":"CA Cancer J Clin"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1177\/1756287218811050","article-title":"Risk stratification by means of biological age-related factors better predicts cancer-specific survival than chronological age in patients with upper tract urothelial carcinoma: a multi-institutional database study","volume":"10","author":"Inamoto","year":"2018","journal-title":"Ther Adv Urol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.2147\/CMAR.S267969","article-title":"The significance of preoperative serum sodium and hemoglobin in outcomes of upper tract urothelial carcinoma: multi-center analysis between China and the United States","volume":"12","author":"Fang","year":"2020","journal-title":"Cancer Manag Res"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1002\/ajh.23628","article-title":"Diagnosis and treatment of cancer-related anemia","volume":"89","author":"Gilreath","year":"2014","journal-title":"Am J Hematol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.urolonc.2016.03.018","article-title":"Is preoperative anemia a risk factor for upper tract urothelial carcinoma following radical nephroureterectomy","volume":"34","author":"Yeh","year":"2016","journal-title":"Urol Oncol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1179\/1607845414Y.0000000161","article-title":"Anemia in Malignancies: pathogenetic and diagnostic considerations","volume":"20","author":"Gaspar","year":"2015","journal-title":"Hematology"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1002\/imt2.70033","article-title":"Efficacy and biomarker analysis of neoadjuvant disitamab vedotin (RC48-ADC) combined immunotherapy in patients with muscle-invasive bladder cancer: A multi-center real-world study","volume":"4","author":"Hu","year":"2025","journal-title":"iMeta"},{"key":"B37","doi-asserted-by":"publisher","first-page":"100785","DOI":"10.1016\/j.xcrm.2022.100785","article-title":"Neoadjuvant immunotherapy, chemotherapy, and combination therapy in muscle invasive bladder cancer: A multi-center real-world retrospective study","volume":"3","author":"Hu","year":"2022","journal-title":"Cell Rep Med"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14004","article-title":"A deep learning method for producing ventilation images from 4DCT: First comparison with technegas SPECT ventilation","volume":"47","author":"Liu","year":"2020","journal-title":"Med Phys"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1644250\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T04:12:40Z","timestamp":1754453560000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1644250\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":38,"alternative-id":["10.3389\/fonc.2025.1644250"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1644250","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,6]]},"article-number":"1644250"}}