{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:55:02Z","timestamp":1776750902287,"version":"3.51.2"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"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. Radiol."],"abstract":"\n Objective<\/jats:title>\n To construct a multimodal machine learning model integrating computed tomography (CT) radiomics, Positron Emission Tomography (PET) metabolic parameters, and clinical data for differentiating benign from malignant pulmonary space-occupying lesions (PSOLs), and develop an interpretable nomogram for clinical application.<\/jats:p>\n <\/jats:sec>\n \n Methodology<\/jats:title>\n \n This study enrolled 384 patients with PSOLs who underwent dual-time-point\n 1<\/jats:sup>\n \u2078F-FDG PET\/CT examinations. The cohort was divided into a training set (\n n<\/jats:italic>\n \u2009=\u2009268, 145 malignant, 123 benign) and an independent temporal validation set (\n n<\/jats:italic>\n \u2009=\u2009116, 69 malignant, 47 benign) at a 7:3 ratio according to the chronological order of patient enrollment, to avoid data leakage and rigorously assess model generalizability. All malignant lesions were confirmed by pathological examination, while benign lesions were confirmed by pathology (82%) or clinical-imaging follow-up for at least 12 months (18%). CT radiomic features with Intraclass Correlation Coefficient (ICC) values &gt;0.75 were selected, and a Radiomics-score (Rad-score) was generated using the Least Absolute Shrinkage and Selection Operator (LASSO) regression algorithm. Integrated models [Logistic regression, random forest (RF), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost)] were developed by fusing the Rad-score, clinical variables, and PET metabolic parameters. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F1-score, and Brier score. Model calibration was assessed via calibration curves, and clinical utility was validated by decision curve analysis (DCA). Model interpretability was achieved using SHapley Additive exPlanations (SHAP) values for the optimal XGBoost model, and a clinically applicable, interpretable nomogram was constructed based on the core predictive features identified by SHAP analysis to facilitate clinical translation.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A Rad-score was constructed from 17 optimally selected features. In the independent temporal validation set, the single-modality models achieved AUCs of 0.808 (Radiomics Model), 0.732 (Clinical Model), and 0.874 (Metabolic Model). Among all tested models, the XGBoost integrated model achieved the highest AUC of 0.967, which was significantly higher than that of all other models (Bonferroni-adjusted\n P<\/jats:italic>\n \u2009=\u20090.002\u20130.032, all adjusted\n P<\/jats:italic>\n \u2009&lt;\u20090.05). SHAP analysis identified\n \u0394<\/jats:italic>\n SUVmax, Rad-score, and delayed phase total lesion glycolysis (TLG_d) as the top three key predictive features.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The predictive logic of the optimal XGBoost model was decoded via SHAP analysis to identify core predictive features, and a clinically applicable, interpretable nomogram was further established based on a multivariate logistic regression model using these core features, to facilitate the clinical translation of our model.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fradi.2026.1782678","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:35:12Z","timestamp":1776749712000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of a nomogram using interpretable machine learning to integrate CT radiomics and PET metabolic parameters for predicting benign-malignant differentiation of pulmonary space-occupying lesions"],"prefix":"10.3389","volume":"6","author":[{"given":"Xue","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Nuclear Medicine, Chongqing University Three Gorges Hospital","place":["Wanzhou, Chongqing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghua","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Chongqing University Three Gorges Hospital","place":["Wanzhou, Chongqing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Bin","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Chongqing University Three Gorges Hospital","place":["Wanzhou, Chongqing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Chongqing University Three Gorges Hospital","place":["Wanzhou, Chongqing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiting","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Chongqing University Three Gorges Hospital","place":["Wanzhou, Chongqing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cailiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Chongqing University Three Gorges Hospital","place":["Wanzhou, Chongqing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1136\/thorax-2023-220226","article-title":"Radiomics analysis to predict pulmonary nodule malignancy using machine learning approaches","volume":"79","author":"Warkentin","year":"2024","journal-title":"Thorax"},{"key":"B2","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1148\/radiol.2015142700","article-title":"Observer variability for classification of pulmonary nodules on low-dose CT images and its effect on nodule management","volume":"277","author":"van Riel","year":"2015","journal-title":"Radiology"},{"key":"B3","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1148\/radiol.2018181159","article-title":"Fluorine 18-FDG PET\/CT and diffusion-weighted MRI for malignant versus benign pulmonary lesions: a meta-analysis","volume":"290","author":"Basso Dias","year":"2019","journal-title":"Radiology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"208","DOI":"10.21037\/qims-23-891","article-title":"Pneumothorax after percutaneous CT-guided lung nodule biopsy: a prospective, multicenter study","volume":"14","author":"He","year":"2024","journal-title":"Quant Imaging Med Surg"},{"key":"B5","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1146\/annurev-bioeng-110220-030247","article-title":"Predictive models for health deterioration: understanding disease pathways for personalized medicine","volume":"25","author":"Eskofier","year":"2023","journal-title":"Annu Rev Biomed Eng"},{"key":"B6","doi-asserted-by":"publisher","first-page":"5064","DOI":"10.3390\/jcm10215064","article-title":"Role of (18)F-FDG PET\/CT radiomics features in the differential diagnosis of solitary pulmonary nodules: diagnostic accuracy and comparison between two different PET\/CT scanners","volume":"10","author":"Albano","year":"2021","journal-title":"J Clin Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s40658-024-00685-5","article-title":"PET Radiomics in lung cancer: advances and translational challenges","volume":"11","author":"Zhang","year":"2024","journal-title":"EJNMMI Phys"},{"key":"B8","doi-asserted-by":"publisher","first-page":"568857","DOI":"10.3389\/fonc.2020.568857","article-title":"Performance of (18)F-FDG PET\/CT radiomics for predicting EGFR mutation status in patients with non-small cell lung cancer","volume":"10","author":"Zhang","year":"2020","journal-title":"Front Oncol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2770","DOI":"10.1007\/s00259-019-04418-0","article-title":"Integrating manual diagnosis into radiomics for reducing the false positive rate of (18)F-FDG PET\/CT diagnosis in patients with suspected lung cancer","volume":"46","author":"Kang","year":"2019","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1802","DOI":"10.1111\/1759-7714.14924","article-title":"Deep learning PET\/CT-based radiomics integrates clinical data: a feasibility study to distinguish between tuberculosis nodules and lung cancer","volume":"14","author":"Zhang","year":"2023","journal-title":"Thorac Cancer"},{"key":"B11","doi-asserted-by":"publisher","first-page":"205017","DOI":"10.1088\/1361-6560\/ac287d","article-title":"Multi-level multi-modality (PET and CT) fusion radiomics: prognostic modeling for non-small cell lung carcinoma","volume":"66","author":"Amini","year":"2021","journal-title":"Phys Med Biol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"13087","DOI":"10.1038\/srep13087","article-title":"Machine learning methods for quantitative radiomic biomarkers","volume":"5","author":"Parmar","year":"2015","journal-title":"Sci Rep"},{"key":"B13","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: the bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat Rev Clin Oncol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"707288","DOI":"10.3389\/fonc.2021.707288","article-title":"CT radiomics and machine-learning models for predicting tumor-stroma ratio in patients with pancreatic ductal adenocarcinoma","volume":"11","author":"Meng","year":"2021","journal-title":"Front Oncol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.3390\/cancers15041000","article-title":"Qualitative and semiquantitative parameters of (18)F-FDG-PET\/CT as predictors of malignancy in patients with solitary pulmonary nodule","volume":"15","author":"Corica","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"035016","DOI":"10.1088\/2057-1976\/ad34db","article-title":"From pixels to prognosis: unveiling radiomics models with SHAP and LIME for enhanced interpretability","volume":"10","author":"Raptis","year":"2024","journal-title":"Biomed Phys Eng Express"},{"key":"B17","doi-asserted-by":"publisher","first-page":"eadf0837","DOI":"10.1126\/sciadv.adf0837","article-title":"Radiogenomic-based multiomic analysis reveals imaging intratumor heterogeneity phenotypes and therapeutic targets","volume":"9","author":"Su","year":"2023","journal-title":"Sci Adv"},{"key":"B18","doi-asserted-by":"publisher","first-page":"5063","DOI":"10.3390\/cancers15205063","article-title":"AI deployment on GBM diagnosis: a novel approach to analyze histopathological images using image feature-based analysis","volume":"15","author":"Cheung","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B19","doi-asserted-by":"publisher","first-page":"6412","DOI":"10.21037\/tcr-20-1934","article-title":"Correlation analysis between metabolic tumor burden measured by positron emission tomography\/computed tomography and the 2015 World Health Organization classification of lung adenocarcinoma, with a risk prediction model of tumor spread through air spaces","volume":"9","author":"Wang","year":"2020","journal-title":"Transl Cancer Res"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3202","DOI":"10.3390\/diagnostics13203202","article-title":"Diagnostic superiority of dual-time point [(18)F]FDG PET\/CT to differentiate malignant from benign soft tissue tumors","volume":"13","author":"d'Abadie","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1007\/s11739-022-02996-w","article-title":"Machine learning and LACE index for predicting 30-day readmissions after heart failure hospitalization in elderly patients","volume":"17","author":"Polo Friz","year":"2022","journal-title":"Intern Emerg Med"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1280047","DOI":"10.3389\/fneur.2023.1280047","article-title":"A nomogram for the prediction of short-term mortality in patients with aneurysmal subarachnoid hemorrhage requiring mechanical ventilation: a post-hoc analysis","volume":"14","author":"Mei","year":"2023","journal-title":"Front Neurol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"101975","DOI":"10.1016\/j.eclinm.2023.101975","article-title":"An independently validated nomogram for individualised estimation of short-term mortality risk among patients with severe traumatic brain injury: a modelling analysis of the CENTER-TBI China Registry Study","volume":"59","author":"Lang","year":"2023","journal-title":"EClinicalMedicine"},{"key":"B24","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1186\/s12911-023-02171-x","article-title":"Construction of the XGBoost model for early lung cancer prediction based on metabolic indices","volume":"23","author":"Guan","year":"2023","journal-title":"BMC Med Inform Decis Mak"}],"container-title":["Frontiers in Radiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fradi.2026.1782678\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:35:14Z","timestamp":1776749714000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fradi.2026.1782678\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":24,"alternative-id":["10.3389\/fradi.2026.1782678"],"URL":"https:\/\/doi.org\/10.3389\/fradi.2026.1782678","relation":{},"ISSN":["2673-8740"],"issn-type":[{"value":"2673-8740","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"article-number":"1782678"}}