{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:53:29Z","timestamp":1782917609828,"version":"3.54.5"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003454","name":"Guangxi Zhuang Autonomous Region Health Department","doi-asserted-by":"publisher","award":["Z-A20250454"],"award-info":[{"award-number":["Z-A20250454"]}],"id":[{"id":"10.13039\/501100003454","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011827","name":"Guangxi Medical University","doi-asserted-by":"publisher","award":["2025LCJG05, 2025LCJG02, 2025XJGY18"],"award-info":[{"award-number":["2025LCJG05, 2025LCJG02, 2025XJGY18"]}],"id":[{"id":"10.13039\/501100011827","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop and internally validate a multimodal fusion model integrating clinical features, lymphocyte-to-monocyte ratio (LMR), and venous-phase CT radiomic data for preoperative benign-versus-malignant risk stratification of parotid masses (PMs), and to exploratorily evaluate its potential adjunctive role relative to standard diagnostic modalities including fine-needle aspiration biopsy (FNAB).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective analysis of 490 patients with histopathologically confirmed PMs (2013\u20132022) was performed, with random assignment to training (70%) and internal validation (30%) cohorts. Radiomic features from venous-phase CT were selected via t-tests, mRMR, and LASSO regression, with all feature selection performed strictly within training folds. Eleven machine learning models were trained and optimized by 10-fold cross-validation, and the model with the highest cross-validated AUC was selected as the optimal radiomic signature. The previously established LMR-based clinical\u2013laboratory signature was re-validated, and logistic regression was used to fuse the two signatures into a multimodal model. Model performance was assessed using receiver operating characteristic analysis, Hosmer\u2013Lemeshow test, calibration curves, and decision curve analysis (DCA). As an exploratory secondary analysis, in 135 patients with preoperative FNAB, the model\u2019s risk estimates were compared against retrospectively assigned MSRSGC categories using DeLong\u2019s test, net reclassification improvement (NRI), and integrated discrimination improvement (IDI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The multimodal model achieved an AUC of 0.931 (95% CI: 0.888\u20130.973) in the internal validation set, outperforming the clinical\u2013laboratory signature (AUC = 0.761; p &amp;lt; 0.001) and radiomic signature (AUC = 0.919; p = 0.038), with sensitivity of 0.957, specificity of 0.782, PPV of 0.449, and NPV of 0.990. In an exploratory secondary analysis of the FNAB subset, the model achieved an AUC of 0.952 (95% CI: 0.918\u20130.987), with higher statistical discrimination than retrospectively assigned MSRSGC categories (AUC = 0.712; p &amp;lt; 0.001; categorical NRI = 0.399, IDI = 0.386, both p &amp;lt; 0.001).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The multimodal fusion model demonstrated improved statistical risk discrimination over single-modal approaches in this retrospective cohort. The model is an investigational adjunctive risk-stratification instrument that is not intended to replace FNAB, MRI, or histopathologic diagnosis. These preliminary findings require prospective multicenter validation before clinical consideration.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2026.1842957","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:10:12Z","timestamp":1782915012000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Could a multimodal fusion model integrating CT radiomics and systemic inflammatory markers improve preoperative risk stratification of parotid masses? A retrospective exploratory study"],"prefix":"10.3389","volume":"17","author":[{"given":"Feng","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Otolaryngology, Head and Neck Surgery, The First Affiliated Hospital of Guangxi Medical University","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Head and Neck Surgery, The First Affiliated Hospital of Guangxi Medical University","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwen","family":"Ling","sequence":"additional","affiliation":[{"name":"The School of Information and Management, Guangxi Medical University","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pathology, The First Affiliated Hospital of Guangxi Medical University","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Pathology, The First Affiliated Hospital of Guangxi Medical University","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Pathology, The First Affiliated Hospital of Guangxi Medical University","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiping","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Head and Neck Surgery, The First Affiliated Hospital of Guangxi Medical University","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.21037\/tcr-22-695","article-title":"Multimodal magnetic resonance imaging for the diagnosis of parotid gland Malignancies: systematic review and meta-analysis","volume":"11","author":"Li","year":"2022","journal-title":"Transl Cancer Res"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-017-0813-z","article-title":"Assessment of salivary gland tumors using MRI and CT: impact of experience on diagnostic accuracy","volume":"123","author":"Vogl","year":"2018","journal-title":"Radiol Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1177\/0194599815607841","article-title":"Sensitivity, specificity, and posttest probability of parotid fine-needle aspiration: a systematic review and meta-analysis","volume":"154","author":"Liu","year":"2016","journal-title":"Otolaryngol Head Neck Surg"},{"key":"B4","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1097\/PAP.0000000000000224","article-title":"Salivary gland fine needle aspiration and introduction of the Milan reporting system","volume":"26","author":"Pusztaszeri","year":"2019","journal-title":"Adv Anat Pathol"},{"key":"B5","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":"B6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1576\/1\/012040","article-title":"Research on the practical classification and privacy protection of CT images of parotid tumors based on ResNet50 model","volume":"1576","author":"Yuan","year":"2020","journal-title":"J Physics: Conf Ser"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1\u2013","DOI":"10.1109\/ACCESS.2021.3064752","article-title":"Research on the classification of benign and Malignant parotid tumors based on transfer learning and a convolutional neural network","author":"Zhang","year":"2021","journal-title":"IEEE Access"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-08830-3","article-title":"CT-based radiomics analysis of different machine learning models for differentiating benign and Malignant parotid tumors","volume":"32","author":"Zheng","year":"2022","journal-title":"Eur Radiol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1111\/odi.14474","article-title":"Deep learning-assisted diagnosis of parotid gland tumors by using contrast-enhanced CT imaging","volume":"29","author":"Shen","year":"2023","journal-title":"Oral Dis"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1002\/hed.27396","article-title":"Neural network combining with clinical ultrasonography: a new approach for classification of salivary gland tumors","volume":"45","author":"Tu","year":"2023","journal-title":"Head Neck"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-09568-2","article-title":"Deep learning-assisted diagnosis of benign and Malignant parotid tumors based on contrast-enhanced CT: a multicenter study","volume":"33","author":"Yu","year":"2023","journal-title":"Eur Radiol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1650943","article-title":"Clinical value of intratumoral and peritumoral CT radiomics models for discriminating benign and Malignant parotid gland tumors","volume":"15","author":"Zhang","year":"2025","journal-title":"Front Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1566555","article-title":"The value of multi-phase CT based intratumor and peritumoral radiomics models for evaluating capsular characteristics of parotid pleomorphic adenoma","volume":"12","author":"Shen","year":"2025","journal-title":"Front Med (Lausanne)"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.62347\/AXQW1100","article-title":"Preoperative CT-based intra- and peri-tumoral radiomic models for differentiating benign and Malignant tumors of the parotid gland: a two-center study","volume":"14","author":"Shen","year":"2024","journal-title":"Am J Cancer Res"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15204918","article-title":"Radiomics analysis in characterization of salivary gland tumors on MRI: a systematic review","volume":"15","author":"Mao","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14051762","article-title":"The role of blood inflammatory markers in salivary gland carcinoma: a scoping review","volume":"14","author":"Migliorelli","year":"2025","journal-title":"J Clin Med"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/ijms262010199","article-title":"Epithelial-immune cell crosstalk in salivary gland tumors: implications for tumor progression and diagnostic assessment","volume":"26","author":"Sausa","year":"2025","journal-title":"Int J Mol Sci"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15061876","article-title":"Support tools in the differential diagnosis of salivary gland tumors through inflammatory biomarkers and radiomics metrics: a preliminary study","volume":"15","author":"Committeri","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nat Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1007\/s12105-022-01420-1","article-title":"Update from the 5th edition of the World Health Organization classification of head and neck tumors: salivary glands","volume":"16","author":"Sk\u00e1lov\u00e1","year":"2022","journal-title":"Head Neck Pathol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.2962","article-title":"Texture-based and diffusion-weighted discrimination of parotid gland lesions on MR images at 3.0 Tesla","volume":"26","author":"Fruehwald-Pallamar","year":"2013","journal-title":"NMR BioMed"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s00432-023-05032-2","article-title":"A nomogram for distinguishing benign and Malignant parotid gland tumors using clinical data and preoperative blood markers: development and validation","volume":"149","author":"Zhao","year":"2023","journal-title":"J Cancer Res Clin Oncol"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.5152\/dir.2019.19321","article-title":"Radiomics with artificial intelligence: a practical guide for beginners","volume":"25","author":"Ko\u00e7ak","year":"2019","journal-title":"Diagn Interv Radiol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2021210037","article-title":"Radiomics in oncology: a practical guide","volume":"41","author":"Shur","year":"2021","journal-title":"Radiographics"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-06957-9","article-title":"Reliability and prognostic value of radiomic features are highly dependent on choice of feature extraction platform","volume":"30","author":"Fornacon-Wood","year":"2020","journal-title":"Eur Radiol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-10217-x","article-title":"Reproducibility of radiomics quality score: an intra- and inter-rater reliability study","volume":"34","author":"Akinci D'Antonoli","year":"2023","journal-title":"Eur Radiol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-020-04756-4","article-title":"Effect of machine learning re-sampling techniques for imbalanced datasets in (18)F-FDG PET-based radiomics model on prognostication performance in cohorts of head and neck cancer patients","volume":"47","author":"Xie","year":"2020","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06176-x","article-title":"CT radiomics may predict the grade of pancreatic neuroendocrine tumors: a multicenter study","volume":"29","author":"Gu","year":"2019","journal-title":"Eur Radiol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000855","article-title":"Benchmarking feature selection methods in radiomics","volume":"57","author":"Demircio\u011flu","year":"2022","journal-title":"Invest Radiol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.2196\/27060","article-title":"Prediction and feature importance analysis for severity of COVID-19 in South Korea using artificial intelligence: model development and validation","volume":"23","author":"Chung","year":"2021","journal-title":"J Med Internet Res"},{"key":"B31","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s41746-022-00712-8","article-title":"Multimodal machine learning in precision health: a scoping review","volume":"5","author":"Kline","year":"2022","journal-title":"NPJ Digit Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jasc.2018.02.002","article-title":"The Milan system for reporting salivary gland cytopathology (MSRSGC): an ASC-IAC-sponsored system for reporting salivary gland fine-needle aspiration","volume":"7","author":"Rossi","year":"2018","journal-title":"J Am Soc Cytopathol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2","DOI":"10.5334\/jbsr.1596","article-title":"Contrast-enhanced multi-detector CT examination of parotid gland tumors: determination of the most helpful scanning delay for predicting histologic subtypes","volume":"103","author":"Kim","year":"2019","journal-title":"J Belg Soc Radiol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.913898","article-title":"Multiphasic CT-based radiomics analysis for the differentiation of benign and Malignant parotid tumors","volume":"12","author":"Yu","year":"2022","journal-title":"Front Oncol"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.canlet.2021.12.015","article-title":"A nomogram based on clinical information, conventional ultrasound and radiomics improves prediction of Malignant parotid gland lesions","volume":"527","author":"Li","year":"2022","journal-title":"Cancer Lett"},{"key":"B36","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13550-023-00956-9","article-title":"Predicting PD-L1 expression status in patients with non-small cell lung cancer using [18F]FDG PET\/CT radiomics","volume":"13","author":"Zhao","year":"2023","journal-title":"EJNMMI Res"},{"key":"B37","doi-asserted-by":"publisher","first-page":"7433","DOI":"10.1038\/s41598-025-90128-7","article-title":"MRI radiomics based on machine learning in high-grade gliomas as a promising tool for prediction of CD44 expression and overall survival","volume":"15","author":"Yu","year":"2025","journal-title":"Sci Rep"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.2217\/fon-2021-1173","article-title":"Radiomics features based on T2-weighted fluid-attenuated inversion recovery MRI predict the expression levels of CD44 and CD133 in lower grade gliomas","volume":"18","author":"Wang","year":"2022","journal-title":"Future Oncol"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0228972","article-title":"A simple model for glioma grading based on texture analysis applied to conventional brain MRI","volume":"15","author":"Su\u00e1rez-Garc\u00eda","year":"2020","journal-title":"PloS One"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1121485","article-title":"Development and validation of a CECT-based radiomics model for predicting IL1B expression and prognosis of head and neck squamous cell carcinoma","volume":"13","author":"Xie","year":"2023","journal-title":"Front Oncol"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.5603\/GP.2016.0096","article-title":"Clinical, ultrasound parameters and tumor marker-based mathematical models and scoring systems in pre-surgical diagnosis of adnexal tumors","volume":"87","author":"Abdalla","year":"2016","journal-title":"Ginekol Pol"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-021-05371-7","article-title":"Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer","volume":"48","author":"Kirienko","year":"2021","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B43","doi-asserted-by":"publisher","first-page":"3254","DOI":"10.1038\/s41598-020-74399-w","article-title":"Multimodal deep learning models for early detection of Alzheimer's disease stage","volume":"11","author":"Venugopalan","year":"2021","journal-title":"Sci Rep"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1038\/s43018-022-00388-9","article-title":"Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer","volume":"3","author":"Boehm","year":"2022","journal-title":"Nat Cancer"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1038\/s43018-022-00416-8","article-title":"Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer","volume":"3","author":"Vanguri","year":"2022","journal-title":"Nat Cancer"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac448","article-title":"ICSDA: a multi-modal deep learning model to predict breast cancer recurrence and metastasis risk by integrating pathological, clinical and gene expression data","volume":"23","author":"Yao","year":"2022","journal-title":"Brief Bioinform"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4408","article-title":"Classification of parotid gland tumors by using multimodal MRI and deep learning","volume":"34","author":"Chang","year":"2021","journal-title":"NMR BioMed"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2020.08.002","article-title":"Multiparametric magnetic resonance imaging of parotid tumors: a systematic review","volume":"102","author":"Coudert","year":"2021","journal-title":"Diagn Interv Imaging"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1002\/lary.30154","article-title":"A deep learning model for classification of parotid neoplasms based on multimodal magnetic resonance image sequences","volume":"133","author":"Liu","year":"2023","journal-title":"Laryngoscope"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2023382","article-title":"A review on multimodal machine learning in medical diagnostics","volume":"20","author":"Yan","year":"2023","journal-title":"Math Biosci Eng"},{"key":"B51","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1038\/s41746-019-0122-0","article-title":"Deep learning and alternative learning strategies for retrospective real-world clinical data","volume":"2","author":"Chen","year":"2019","journal-title":"NPJ Digit Med"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1002\/dc.24187","article-title":"The Milan system for reporting salivary gland cytopathology: A study of inter-observer reproducibility","volume":"47","author":"Layfield","year":"2019","journal-title":"Diagn Cytopathol"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1842957\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:10:14Z","timestamp":1782915014000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1842957\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":52,"alternative-id":["10.3389\/fimmu.2026.1842957"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2026.1842957","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"article-number":"1842957"}}