{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T06:03:32Z","timestamp":1784527412922,"version":"3.55.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"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>Objective<\/jats:title>\n                    <jats:p>To develop and validate a foundation model\u2013driven multimodal fusion framework for non-invasive prediction of treatment response to first-line chemo-immunotherapy in patients with advanced lung squamous cell carcinoma (LUSC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective study, baseline contrast-enhanced computer tomography (CT) images and clinical data from patients with advanced LUSC receiving first-line chemo-immunotherapy were collected. Handcrafted radiomics features were extracted from tumor regions of interest, and 2.5D deep learning features were extracted using a DINO-pretrained vision Transformer foundation model. Clinical variables were incorporated to construct a multi-source features fusion model based on machine learning classifiers. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. DeLong testing, decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were performed for comparative assessment. Shapley additive explanations (SHAP) analysis was applied to enhance model interpretability and decision transparency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the constructed models, the multi-source features fusion model (FusionModel) achieved the best predictive performance, with an AUC of 0.903 and an accuracy of 0.885 in the training cohort, and an AUC of 0.863 and an accuracy of 0.836 in the validation cohort. FusionModel outperformed models based on single-modality features and demonstrated superior net clinical benefit on DCA. NRI and IDI analyses further supported improved reclassification ability. SHAP analysis revealed that deep learning features contributed dominantly, while radiomics and clinical variables provided complementary prognostic information, supporting the biological plausibility of the model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The foundation model-driven multi-source features fusion model enabled accurate and interpretable prediction of chemo-immunotherapy response in advanced LUSC. This strategy demonstrated strong discriminative performance and clinical applicability, highlighting its potential as a non-invasive tool for individualized treatment stratification.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1863080","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T05:34:21Z","timestamp":1784525661000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Foundation model-enhanced multimodal radiomics for predicting response to chemo-immunotherapy in advanced lung squamous cell carcinoma"],"prefix":"10.3389","volume":"16","author":[{"given":"Zhichao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Oncology, The First Affiliated Hospital of Yangtze University","place":["Jingzhou, China"]},{"name":"Hubei Provincial Clinical Research Center for Personalized Cancer Diagnosis and Therapy","place":["Jingzhou, Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Oncology, The First Affiliated Hospital of Yangtze University","place":["Jingzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuchu","family":"He","sequence":"additional","affiliation":[{"name":"Department of Oncology, The First Affiliated Hospital of Yangtze University","place":["Jingzhou, China"]},{"name":"Hubei Provincial Clinical Research Center for Personalized Cancer Diagnosis and Therapy","place":["Jingzhou, Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Oncology, The First Affiliated Hospital of Yangtze University","place":["Jingzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Oncology, The First Affiliated Hospital of Yangtze University","place":["Jingzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,20]]},"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":"10.1016\/j.ejca.2026.116246","article-title":"Why are patients with non-small cell lung cancer in stage I-IIIA considered inoperable? A registry-based study from the capital region of Denmark","volume":"235","author":"Budolfsen","year":"2026","journal-title":"Eur J Cancer"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1809697","article-title":"Overall survival with durvalumab after chemoradiotherapy in stage III NSCLC","volume":"379","author":"Antonia","year":"2018","journal-title":"N Engl J Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s13046-024-02997-x","article-title":"Validation of a multiomic model of plasma extracellular vesicle PD-L1 and radiomics for prediction of response to immunotherapy in NSCLC","volume":"43","author":"de Miguel-Perez","year":"2024","journal-title":"J Exp Clin Cancer Res"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(23)00082-1","article-title":"Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study","volume":"5","author":"Saad","year":"2023","journal-title":"Lancet Digit Health"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2025-012526","article-title":"Attention-guided framework for integrative omics and temporal dynamics in predicting major pathological response in neoadjuvant immunochemotherapy for NSCLC","volume":"13","author":"Gan","year":"2025","journal-title":"J Immunother Cancer"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-021-00473-5","article-title":"PD-L1 as a biomarker of response to immune-checkpoint inhibitors","volume":"18","author":"Doroshow","year":"2021","journal-title":"Nat Rev Clin Oncol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.annonc.2023.10.125","article-title":"Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review","volume":"35","author":"Prelaj","year":"2024","journal-title":"Ann Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-09174-8","article-title":"Can quantitative peritumoral CT radiomics features predict the prognosis of patients with non-small cell lung cancer? A systematic review","volume":"33","author":"Wu","year":"2023","journal-title":"Eur Radiol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-24-1926","article-title":"Longitudinal blood immune-inflammatory and radiomic profiling to decode different patterns of acquired resistance to immunotherapy in patients with NSCLC","volume":"31","author":"Mazzaschi","year":"2025","journal-title":"Clin Cancer Res"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2025.111011","article-title":"Multiomic based Bayesian network toxicity modeling for simultaneous prediction of multiple toxicity outcomes in NSCLC","volume":"210","author":"Nair","year":"2025","journal-title":"Radiother Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2024.1434171","article-title":"Applications of CT-based radiomics for the prediction of immune checkpoint markers and immunotherapeutic outcomes in non-small cell lung cancer","volume":"15","author":"Zheng","year":"2024","journal-title":"Front Immunol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1097\/JS9.0000000000002821","article-title":"Multichannel deep learning prediction of major pathological response after neoadjuvant immunochemotherapy in lung cancer: a multicenter diagnostic study","volume":"111","author":"Geng","year":"2025","journal-title":"Int J Surg"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-026-01305-4","article-title":"Integrated predictive model for visceral pleural invasion in small NSCLC with high clinical utility","volume":"10","author":"Yang","year":"2026","journal-title":"NPJ Precis Onc"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.semcancer.2023.01.006","article-title":"Artificial intelligence in lung cancer diagnosis and prognosis: Current application and future perspective","volume":"89","author":"Huang","year":"2023","journal-title":"Semin Cancer Biol"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2025.09.037","article-title":"Predictions of response in non-small cell lung cancer patients treated with immune checkpoint inhibitors using clinical data, deep learning, and radiomics","volume":"33","author":"Wang","year":"2025","journal-title":"Acad Radiol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s13244-025-02184-2","article-title":"Contrast-enhanced CT-based radiomics for predicting visceral pleural invasion in early-stage non-small cell lung cancer","volume":"17","author":"Luo","year":"2026","journal-title":"Insights Imaging"},{"key":"B18","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1038\/s41746-025-01801-0","article-title":"Re-identification of patients from imaging features extracted by foundation models","volume":"8","author":"Nebbia","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202407339","article-title":"CRCFound: A colorectal cancer CT image foundation model based on self-supervised learning","volume":"12","author":"Yang","year":"2025","journal-title":"Adv Sci"},{"key":"B20","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1038\/s41467-025-66620-z","article-title":"A lung CT vision foundation model facilitating disease diagnosis and medical imaging","volume":"17","author":"Gao","year":"2025","journal-title":"Nat Commun"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1038\/s41467-025-56822-w","article-title":"Medical multimodal multitask foundation model for lung cancer screening","volume":"16","author":"Niu","year":"2025","journal-title":"Nat Commun"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2020-001343","article-title":"Novel, non-invasive imaging approach to identify patients with advanced non-small cell lung cancer at risk of hyperprogressive disease with immune checkpoint blockade","volume":"8","author":"Vaidya","year":"2020","journal-title":"J Immunother Cancer"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1038\/s41416-025-02948-z","article-title":"Intratumoral and peritumoral PET\/CT-based radiomics for non-invasively and dynamically predicting immunotherapy response in NSCLC","volume":"132","author":"Lin","year":"2025","journal-title":"Br J Cancer"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1158\/2326-6066.CIR-19-0476","article-title":"Changes in CT radiomic features associated with lymphocyte distribution predict overall survival and response to immunotherapy in non-small cell lung cancer","volume":"8","author":"Khorrami","year":"2020","journal-title":"Cancer Immunol Res"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.34133\/research.1024","article-title":"Foundation models meet medical image interpretation","volume":"27","author":"Jiao","year":"2026","journal-title":"Research"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110583","article-title":"Radio DINO: A foundation model for advanced radiomics and AI-driven medical imaging analysis","volume":"195","author":"Zedda","year":"2025","journal-title":"Comput Biol Med"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108638","article-title":"A novel machine learning model for efficacy prediction of immunotherapy-chemotherapy in NSCLC based on CT radiomics","volume":"178","author":"Li","year":"2024","journal-title":"Comput Biol Med"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2025-013391","article-title":"QVT score, a radiomic biomarker of vascular complexity, enables prognostication and monitoring of NSCLC immunotherapy","volume":"14","author":"Chae","year":"2026","journal-title":"J Immunother Cancer"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2025.1708692","article-title":"Radiomics reveals the biological basis for non-small cell lung cancer prognostic stratification by reflecting tumor immune microenvironment heterogeneity","volume":"16","author":"Huang","year":"2025","journal-title":"Front Immunol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1097\/JS9.0000000000002839","article-title":"Non-invasive prediction of NSCLC immunotherapy efficacy and tumor microenvironment through unsupervised machine learning-driven CT radiomic subtypes: a multi-cohort study","volume":"111","author":"Guo","year":"2025","journal-title":"Int J Surg"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2026.111501","article-title":"Influence of CT harmonization in longitudinal radiomics for NSCLC immunotherapy response prediction","volume":"203","author":"Farina","year":"2026","journal-title":"Comput Biol Med"},{"key":"B32","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1038\/s41698-025-00939-0","article-title":"Computationally integrating radiology and pathology image features for predicting treatment benefit and outcome in lung cancer","volume":"9","author":"Vaidya","year":"2025","journal-title":"NPJ Precis Onc"},{"key":"B33","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41698-025-01180-5","article-title":"Collaborative framework on responsible AI in LLM-driven CDSS for precision oncology leveraging real-world patient data","volume":"10","author":"Mathes","year":"2025","journal-title":"NPJ Precis Onc"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3530794","article-title":"The large language models on biomedical data analysis: a survey","volume":"29","author":"Lan","year":"2025","journal-title":"IEEE J BioMed Health"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2023.101302","article-title":"Tumor-immune microenvironment and NRF2 associate with clinical efficacy of PD-1 blockade combined with chemotherapy in lung squamous cell carcinoma","volume":"4","author":"Duan","year":"2023","journal-title":"Cell Rep Med"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2024.1413204","article-title":"Efficacy and safety of PD-1 inhibitors plus chemotherapy with or without endostatin for stage IV lung squamous cancer: a retrospective study","volume":"15","author":"Lv","year":"2024","journal-title":"Front Immunol"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1090838","article-title":"Identification of tumor mutation burden-associated molecular and clinical features in cancer by analyzing multi-omics data","volume":"14","author":"Li","year":"2023","journal-title":"Front Immunol"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2024.1499731","article-title":"TLS and immune cell profiling: immunomodulatory effects of immunochemotherapy on tumor microenvironment in resectable stage III NSCLC","volume":"15","author":"Yang","year":"2024","journal-title":"Front Immunol"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.21037\/tlcr-24-379","article-title":"Tumor immune microenvironment analysis of non-small cell lung cancer development through multiplex immunofluorescence","volume":"13","author":"Zhao","year":"2024","journal-title":"Transl Lung Cancer R"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1863080\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T05:34:21Z","timestamp":1784525661000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1863080\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":39,"alternative-id":["10.3389\/fonc.2026.1863080"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1863080","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"article-number":"1863080"}}