{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:02:16Z","timestamp":1785391336276,"version":"3.55.0"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Non-small cell lung cancer (NSCLC) exhibits high heterogeneity, and the scarcity of annotated imaging data limits the robustness and generalization capability of conventional deep learning approaches, particularly in few-shot scenarios. Therefore, developing accurate and generalizable prediction models under limited sample conditions remains a critical challenge for precision oncology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we proposed a Model-Agnostic Meta-Learning_RT (MAML_RT) framework for predicting targeted therapy response in NSCLC. The framework integrates model-agnostic meta-learning with residual transformers. Multi-task meta-training was employed to learn highly generalizable parameter initializations, enabling rapid adaptation to new cohorts with limited labeled samples. Meanwhile, the multi-head self-attention mechanism of the residual transformer was utilized to model global correlations among radiomics features and capture long-range dependencies between diverse tumor phenotypic characteristics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In a cohort of 300 patients, MAML_RT achieved an accuracy of 0.91 and an area under the receiver operating characteristic curve (AUC) of 0.93 for predicting targeted therapy efficacy. Under an extremely small-sample scenario (n = 50), the model maintained an AUC of 0.76, significantly outperforming the comparison models. Furthermore, on an independent external validation cohort, MAML_RT achieved an AUC of 0.85 and an accuracy of 0.88, demonstrating its cross-center generalization capability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed MAML_RT framework provides an effective solution for targeted therapy response prediction in NSCLC under limited labeled data conditions. By integrating meta-learning with residual transformer-based feature modeling, this approach improves model adaptability and generalization, offering potential support for clinical decision-making and individualized treatment stratification.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcell.2026.1866438","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:38:57Z","timestamp":1785389937000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MAML-residual transformer for few-shot prediction of targeted therapy response in NSCLC"],"prefix":"10.3389","volume":"14","author":[{"given":"Hua-Jun","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Oncological Radiotherapy, Affiliated Dongyang Hospital, Wenzhou Medical University","place":["Dongyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo-Chao","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Oncological Radiotherapy, Affiliated Dongyang Hospital, Wenzhou Medical University","place":["Dongyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dao-Gui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Reliability and Systems Engineering, Beihang University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo-Xiao","family":"Lv","sequence":"additional","affiliation":[{"name":"Department of Oncological Radiotherapy, Affiliated Dongyang Hospital, Wenzhou Medical University","place":["Dongyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Ying","sequence":"additional","affiliation":[{"name":"Department of Oncological Radiotherapy, Affiliated Dongyang Hospital, Wenzhou Medical University","place":["Dongyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Xin","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Reliability and Systems Engineering, Beihang University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Dong","family":"Hua","sequence":"additional","affiliation":[{"name":"School of Reliability and Systems Engineering, Beihang University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao-Qun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Pathology, Affiliated Dongyang Hospital of Wenzhou Medical University","place":["Dongyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1038\/s41698-025-00725-8","article-title":"Predicting ROS1 and ALK fusions in NSCLC from H&E slides with a two-step vision transformer approach","volume":"9","author":"Amidi","year":"2025","journal-title":"Npj Precis. Oncol."},{"key":"B2","first-page":"1","article-title":"Enhancing lung disease diagnosis through meta learning: a framework utilizing few-shot learning techniques","author":"Anandhi","year":"2024"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.21037\/atm.2020.04.35","article-title":"Adjuvant EGFR TKIs in NSCLC harboring EGFR mutations: looking for a consensus way","volume":"8","author":"Attili","year":"2020","journal-title":"Ann. Transl. Med."},{"key":"B4","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA Cancer J. Clin."},{"key":"B5","doi-asserted-by":"publisher","first-page":"19","DOI":"10.2967\/jnumed.112.107375","article-title":"Are pretreatment 18F-FDG PET tumor textural features in non\u2013small cell lung cancer associated with response and survival after chemoradiotherapy?","volume":"54","author":"Cook","year":"2013","journal-title":"J. Nucl. Med."},{"key":"B6","doi-asserted-by":"publisher","first-page":"7481","DOI":"10.21037\/jtd-20-2946","article-title":"Treatment of a lung lobectomy patient with severe post-surgical infection in the anterior thoracic wall by multiple debridement and drainage procedures: a case report","volume":"12","author":"Dai","year":"2020","journal-title":"J. Thorac. Dis."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1183\/13993003\/erj.42.suppl_57.1819","article-title":"Major changes in men with non-small-cell lung cancer (nsclc) in 10 years: the Kbp-2000-Cphg and Kbp-2010-Cphg cohorts","volume":"42","author":"Debieuvre","year":"2013","journal-title":"Eur. Respir. J."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.31557\/APJCP.2025.26.6.1987","article-title":"High proportion of cytomegalovirus DNA from tissue samples of non-small cell lung carcinoma in Persahabatan hospital national respiratory center, Indonesia","volume":"26","author":"Dharmawan","year":"2025","journal-title":"Asian pac. J. Cancer Prev."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.21037\/jtd-22-364","article-title":"Diagnosis and treatment of non-small cell lung cancer: current advances and challenges","volume":"14","author":"Diebels","year":"2022","journal-title":"J. Thorac. Dis."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.21037\/jtd.2020.02.60","article-title":"Different efficacy in the non-small cell lung cancer patient with bilateral synchronous lesions treated with neoadjuvant gefitinib therapy: a case report","volume":"12","author":"Du","year":"2020","journal-title":"J. Thorac. Dis."},{"key":"B11","doi-asserted-by":"publisher","first-page":"6592","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. Journal Surgery Lond. Engl."},{"key":"B12","doi-asserted-by":"publisher","first-page":"e720","DOI":"10.1097\/CAD.0000000000001139","article-title":"What management for epidermal growth factor receptor-mutated non-small-cell lung cancer, with squamous cell transformation and T790M-acquired resistance mechanisms? A case report and review of literature","volume":"33","author":"Helissey","year":"2022","journal-title":"Anticancer Drugs"},{"key":"B13","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","article-title":"Accurate predictions on small data with a tabular foundation model","volume":"637","author":"Hollmann","year":"2025","journal-title":"Nature"},{"key":"B14","first-page":"1132","article-title":"MLLCD: a meta learning-based method for lung cancer diagnosis using histopathology images","author":"Hu","year":"2023"},{"key":"B15","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41392-025-02243-6","article-title":"Advances in molecular pathology and therapy of non-small cell lung cancer","volume":"10","author":"Huang","year":"2025","journal-title":"Signal Transduct. Target Ther."},{"key":"B16","doi-asserted-by":"publisher","first-page":"17163","DOI":"10.1109\/ACCESS.2024.3368939","article-title":"Transformer based hierarchical model for non-small cell lung cancer detection and classification","volume":"12","author":"Imran","year":"2024","journal-title":"IEEE Access"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2584","DOI":"10.1111\/1759-7714.14594","article-title":"\u201cSex Differences in the Characteristics and Survival of Patients with Non\u2010small\u2010cell Lung Cancer: a Retrospective Analytical Study Based on Real\u2010world Clinical Data of the Korean Population,\u201d thorac","volume":"13","author":"Jeon","year":"2022","journal-title":"Cancer"},{"key":"B18","doi-asserted-by":"publisher","first-page":"107972","DOI":"10.1016\/j.ultras.2026.107972","article-title":"Adaptive sampling for efficient lamb wavefield reconstruction in composite laminates with spatial-temporal masked AutoEncoder","volume":"162","author":"Ji","year":"2026","journal-title":"Ultrasonics"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1101\/2021.10.11.21264761","article-title":"Explainable transformer-based neural network for the prediction of survival outcomes in non-small cell lung cancer (NSCLC)","author":"Kipkogei","year":"2021"},{"key":"B20","first-page":"125","article-title":"Siamese neural networks for one-shot image recognition","author":"Koch","year":"2015"},{"key":"B21","doi-asserted-by":"publisher","first-page":"112293","DOI":"10.1016\/j.ress.2026.112293","article-title":"A maximum entropy moment quadrature method for Quasi-Real-time flight duration reliability assessment of UAVs","volume":"271","author":"Li","year":"2026","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"B22","article-title":"A universal representation transformer layer for few-shot image classification","author":"Liu","year":"2020","journal-title":"arXiv:2006.11702"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1523743","DOI":"10.3389\/fonc.2024.1523743","article-title":"Advances in adjuvant therapy for operable N2 non-small cell lung cancer: a narrative review","volume":"14","author":"Liu","year":"2025","journal-title":"Front. Oncol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"108024","DOI":"10.1016\/j.ultras.2026.108024","article-title":"A curvature-adaptive phased-array synthetic aperture focusing method for flaw detection and size quantification in cylinder-like parts","volume":"164","author":"Liu","year":"2026","journal-title":"Ultrasonics"},{"key":"B25","first-page":"828","article-title":"Meta-learning on augmented gene expression profiles for enhanced lung cancer detection","author":"Moghaddam","year":"2025"},{"key":"B26","first-page":"2505","article-title":"A comparative study of vision transformer encoders and few-shot learning for medical image classification","author":"Nurgazin","year":"2023"},{"key":"B27","doi-asserted-by":"publisher","first-page":"111458","DOI":"10.1016\/j.knosys.2024.111458","article-title":"Cross-domain few-shot learning via adaptive transformer networks","volume":"285","author":"Paeedeh","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"B28","doi-asserted-by":"publisher","first-page":"100205","DOI":"10.1016\/j.cjme.2025.100205","article-title":"Modular and multifunctional phononic-crystal platform for route reconfiguration and information demodulation","author":"Pan","year":"2025","journal-title":"Chin. J. Mech. Eng."},{"key":"B29","first-page":"5445","article-title":"Signal transformer: complex-valued attention and meta-learning for signal recognition","author":"Peng","year":"2024"},{"key":"B30","doi-asserted-by":"publisher","first-page":"7292","DOI":"10.1109\/JSEN.2026.3653513","article-title":"Prediction of sperm retrieval outcomes based on testicular ultrasound images and dense convolutional sparse coding","volume":"26","author":"Qi","year":"2026","journal-title":"IEEE Sensors J."},{"key":"B31","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.21037\/jtd-25-187","article-title":"Advances in immunotherapy for driver gene-positive non-small cell lung cancer: a narrative review","volume":"14","author":"Qian","year":"2025","journal-title":"J. Thorac. Dis."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1785968","DOI":"10.3389\/fimmu.2026.1785968","article-title":"Predicting response to immunochemotherapy in EGFR-mutant lung adenocarcinoma after third-generation TKI resistance using CT Radiomics-Based habitat imaging","volume":"17","author":"Qie","year":"2026","journal-title":"Front. Immunol."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1685","DOI":"10.1111\/cas.14368","article-title":"A Japanese lung cancer registry study on demographics and treatment modalities in medically treated patients","volume":"111","author":"Sekine","year":"2020","journal-title":"Cancer Sci."},{"key":"B34","doi-asserted-by":"publisher","first-page":"2771","DOI":"10.21037\/jtd.2020.03.29","article-title":"Potential treatment strategy for the rare osimertinib resistant mutation EGFR L718Q","volume":"12","author":"Song","year":"2020","journal-title":"J. Thorac. Dis."},{"key":"B35","doi-asserted-by":"publisher","first-page":"103650","DOI":"10.1016\/j.ndteint.2026.103650","article-title":"Delamination detection in composite laminates using lamb wave tomographic method based on sparse and probabilistic reconstruction","volume":"160","author":"Tong","year":"2026","journal-title":"NDT and E Int."},{"key":"B36","doi-asserted-by":"publisher","first-page":"120","DOI":"10.47852\/bonviewjcce42024395","article-title":"VAE-CNN: deep learning on small sample dataset improves hydrogen yield prediction in co-gasification","volume":"4","author":"Vaiyapuri","year":"2025","journal-title":"J. Comput. Cogn. Eng."},{"key":"B37","doi-asserted-by":"publisher","first-page":"4973","DOI":"10.21037\/jtd-20-2089","article-title":"A new method for accurately localizing and resecting pulmonary nodules","volume":"12","author":"Wang","year":"2020","journal-title":"J. Thorac. Dis."},{"key":"B38","doi-asserted-by":"publisher","first-page":"5125","DOI":"10.3390\/cancers15215125","article-title":"Evaluating the potential of Delta radiomics for assessing tyrosine kinase inhibitor treatment response in non-small cell lung cancer patients","volume":"15","author":"Wang","year":"2023","journal-title":"Cancers"},{"key":"B39","doi-asserted-by":"publisher","first-page":"77","DOI":"10.20892\/j.issn.2095-3941.2024.0497","article-title":"Updates to the 2024 CSCO advanced non-small cell lung cancer guidelines","volume":"22","author":"Wang","year":"2025","journal-title":"Cancer Biol. Med."},{"key":"B40","doi-asserted-by":"publisher","first-page":"btae684","DOI":"10.1093\/bioinformatics\/btae684","article-title":"MMOSurv: meta-learning for few-shot survival analysis with multi-omics data","volume":"41","author":"Wen","year":"2025","journal-title":"Bioinformatics"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.04573","article-title":"Zero-shot meta-learning for tabular prediction tasks with adversarially pre-trained transformer","volume":"267","author":"Wu","year":"2025","journal-title":"arXiv:2502.04573"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1056\/NEJMoa2027071","article-title":"Osimertinib in resected EGFR-mutated non-small-cell lung cancer","volume":"383","author":"Wu","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"B43","doi-asserted-by":"publisher","first-page":"5553171","DOI":"10.1155\/stc\/5553171","article-title":"Structural response reconstruction based on experimental approximation and model reduction","volume":"2026","author":"Yang","year":"2026","journal-title":"Struct. Control Health Monit."},{"key":"B44","doi-asserted-by":"publisher","first-page":"1978","DOI":"10.1093\/annonc\/mdz399","article-title":"Final overall survival results of WJTOG3405, a randomized phase III trial comparing gefitinib versus cisplatin with docetaxel as the first-line treatment for patients with stage IIIB\/IV or postoperative recurrent EGFR mutation-positive non-small-cell lung cancer","volume":"30","author":"Yoshioka","year":"2019","journal-title":"Ann. Oncol."},{"key":"B45","doi-asserted-by":"publisher","first-page":"2240","DOI":"10.1158\/1078-0432.CCR-12-2246","article-title":"Analysis of tumor specimens at the time of acquired resistance to EGFR-TKI therapy in 155 patients with EGFR-mutant lung cancers","volume":"19","author":"Yu","year":"2013","journal-title":"Clin. Cancer Res."},{"key":"B46","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.21037\/tlcr-2025-164","article-title":"Literature review of advances and challenges in KRASG12C mutant non-small cell lung cancer","volume":"14","author":"Yuan","year":"2025","journal-title":"Transl. Lung Cancer Res."},{"key":"B47","doi-asserted-by":"publisher","first-page":"4554","DOI":"10.21037\/jtd-21-171","article-title":"The role of salvage surgery in the treatment of a gefitinib-resistant non-small cell lung cancer patient: a case report","volume":"13","author":"Zang","year":"2021","journal-title":"J. Thorac. Dis."},{"key":"B48","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/s0140-6736(18)32633-3","article-title":"Changes in lung cancer incidence by sex and smoking status in China: a multicentre observational study","volume":"392","author":"Zhang","year":"2018","journal-title":"Lancet"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1501844","DOI":"10.3389\/fchem.2024.1501844","article-title":"Recent advances in the treatment of non-small cell lung cancer with MET inhibitors","volume":"12","author":"Zhang","year":"2024","journal-title":"Front. Chem."}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1866438\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:38:58Z","timestamp":1785389938000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1866438\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":49,"alternative-id":["10.3389\/fcell.2026.1866438"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2026.1866438","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]},"article-number":"1866438"}}