{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T14:42:03Z","timestamp":1788532923043,"version":"build-2803163510"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82272080"],"award-info":[{"award-number":["82272080"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Insights Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To explore the diagnostic value of a multi-classification model based on deep learning in distinguishing the pathological subtypes of lung adenocarcinoma or glandular prodromal lesions with pure ground-glass nodules (pGGN) on CT.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>A total of 590 cases of pGGN confirmed by pathology as lung adenocarcinoma or glandular prodromal lesions were collected retrospectively, of which 462 cases of pGGN were used as training and testing set, and 128 cases of pGGN as external verification set. The research is based on the Swin Transformer network and uses a five-fold cross-validation method to train the model. The diagnostic efficacy of deep learning model and radiologist on the external verification set was compared. The classification efficiency of the model is evaluated by confusion matrix, accuracy, precision and F1-score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The accuracy of the training and testing sets of the deep learning model is 95.21% and 91.41% respectively, and the integration accuracy is 94.65%. The accuracy, precision and recall rate of the optimal model are 87.01%, 87.57% and 87.01% respectively, and the F1-score is 87.09%. In the external verification set, the accuracy of the model is 91.41%, and the F1-score is 91.42%. The classification efficiency of the deep learning model is better than that of radiologists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The multi-classification model based on deep learning has a good ability to predict the pathological subtypes of lung adenocarcinoma or glandular prodromal lesions with pGGN, and its classification efficiency is better than that of radiologists, which can improve the diagnostic accuracy of pulmonary pGGN.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Critical relevance statement<\/jats:title>\n                    <jats:p>Swin Transformer deep learning models can noninvasively predict the pathological subtypes of pGGN, which can be used as a preoperative auxiliary diagnostic tool to improve the diagnostic accuracy of pGGN, thereby optimizing the prognosis of patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>The Swin Transformer model can predict the pathological subtype of pure ground-glass nodules.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Compared with the performance of radiologists, the deep learning model performs better.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Swin Transformer model can be used as a tool for preoperative diagnosis.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1186\/s13244-025-02113-3","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T04:12:44Z","timestamp":1760674364000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Predicting pathological subtypes of pure ground-glass nodules using Swin Transformer deep learning model"],"prefix":"10.1186","volume":"16","author":[{"given":"Yanhua","family":"Wen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menna Allah","family":"Mahmoud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wensheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huicong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohuan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0171-3662","authenticated-orcid":false,"given":"Yubao","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"2113_CR1","first-page":"12","volume":"74","author":"RL Siegel","year":"2024","unstructured":"Siegel RL, Giaquinto AN, Jemal A (2024) Cancer statistics, 2024. CA Cancer J Clin 74:12\u201349","journal-title":"CA Cancer J Clin"},{"key":"2113_CR2","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/j.jtho.2021.11.003","volume":"17","author":"AG Nicholson","year":"2015","unstructured":"Nicholson AG, Tsao MS, Beasley MB et al (2015) The 2021 WHO classification of lung tumors: impact of advances since 2015. J Thorac Oncol 17:362\u2013387","journal-title":"J Thorac Oncol"},{"key":"2113_CR3","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.1016\/j.jtho.2021.09.017","volume":"17","author":"MS Tsao","year":"2022","unstructured":"Tsao MS, Nicholson AG, Maleszewski JJ et al (2022) Introduction to 2021 WHO classification of thoracic tumors. J Thorac Oncol 17:e1\u2013e4","journal-title":"J Thorac Oncol"},{"key":"2113_CR4","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1148\/radiol.2462070712","volume":"246","author":"DM Hansell","year":"2008","unstructured":"Hansell DM, Bankier AA, MacMahon H et al (2008) Fleischner Society: glossary of terms for thoracic imaging. Radiology 246:697\u2013722","journal-title":"Radiology"},{"key":"2113_CR5","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1148\/radiol.2017161659","volume":"284","author":"H MacMahon","year":"2017","unstructured":"MacMahon H, Naidich DP, Goo JM et al (2017) Guidelines for management of incidental pulmonary nodules detected on CT images: from the Fleischner Society 2017. Radiology 284:228\u2013243","journal-title":"Radiology"},{"key":"2113_CR6","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1148\/radiol.09090547","volume":"255","author":"SM Lee","year":"2010","unstructured":"Lee SM, Park CM, Goo JM et al (2010) Transient part-solid nodules detected at screening thin-section CT for lung cancer: comparison with persistent part-solid nodules. Radiology 255:242\u2013251","journal-title":"Radiology"},{"key":"2113_CR7","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/s00330-019-06344-z","volume":"30","author":"LL Qi","year":"2020","unstructured":"Qi LL, Wu BT, Tang W et al (2020) Long-term follow-up of persistent pulmonary pure ground-glass nodules with deep learning-assisted nodule segmentation. Eur Radiol 30:744\u2013755","journal-title":"Eur Radiol"},{"key":"2113_CR8","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.lungcan.2014.03.009","volume":"84","author":"T Eguchi","year":"2014","unstructured":"Eguchi T, Kondo R, Kawakami S et al (2014) Computed tomography attenuation predicts the growth of pure ground-glass nodules. Lung Cancer 84:242\u2013247","journal-title":"Lung Cancer"},{"key":"2113_CR9","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1007\/s00330-018-5530-z","volume":"29","author":"L Fan","year":"2019","unstructured":"Fan L, Fang M, Li Z et al (2019) Radiomics signature: a biomarker for the preoperative discrimination of lung invasive adenocarcinoma manifesting as a ground-glass nodule. Eur Radiol 29:889\u2013897","journal-title":"Eur Radiol"},{"key":"2113_CR10","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1183\/09031936.00027511","volume":"39","author":"PE Van Schil","year":"2012","unstructured":"Van Schil PE, Asamura H, Rusch VW et al (2012) Surgical implications of the new IASLC\/ATS\/ERS adenocarcinoma classification. Eur Respir J 39:478\u2013486","journal-title":"Eur Respir J"},{"key":"2113_CR11","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.humpath.2015.12.010","volume":"51","author":"JM Boland","year":"2016","unstructured":"Boland JM, Froemming AT, Wampfler JA et al (2016) Adenocarcinoma in situ, minimally invasive adenocarcinoma, and invasive pulmonary adenocarcinoma\u2014analysis of interobserver agreement, survival, radiographic characteristics, and gross pathology in 296 nodules. Hum Pathol 51:41\u201350","journal-title":"Hum Pathol"},{"key":"2113_CR12","doi-asserted-by":"publisher","first-page":"3945","DOI":"10.3390\/cancers13163945","volume":"13","author":"WC Hsu","year":"2021","unstructured":"Hsu WC, Huang PC, Pan KT et al (2021) Predictors of invasive adenocarcinomas among pure ground-glass nodules less than 2 cm in diameter. Cancers (Basel) 13:3945","journal-title":"Cancers (Basel)"},{"key":"2113_CR13","doi-asserted-by":"publisher","first-page":"109772","DOI":"10.1016\/j.ejrad.2021.109772","volume":"141","author":"Z Xiong","year":"2021","unstructured":"Xiong Z, Jiang Y, Che S et al (2021) Use of CT radiomics to differentiate minimally invasive adenocarcinomas and invasive adenocarcinomas presenting as pure ground-glass nodules larger than 10mm. Eur J Radiol 141:109772","journal-title":"Eur J Radiol"},{"key":"2113_CR14","doi-asserted-by":"publisher","first-page":"3650","DOI":"10.1007\/s00330-020-06776-y","volume":"30","author":"Y Sun","year":"2020","unstructured":"Sun Y, Li C, Jin L et al (2020) Radiomics for lung adenocarcinoma manifesting as pure ground-glass nodules: invasive prediction. Eur Radiol 30:3650\u20133659","journal-title":"Eur Radiol"},{"key":"2113_CR15","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436\u2013444","journal-title":"Nature"},{"key":"2113_CR16","doi-asserted-by":"publisher","first-page":"20180028","DOI":"10.1259\/bjr.20180028","volume":"91","author":"A Murphy","year":"2018","unstructured":"Murphy A, Skalski M, Gaillard F (2018) The utilisation of convolutional neural networks in detecting pulmonary nodules: a review. Br J Radiol 91:20180028","journal-title":"Br J Radiol"},{"key":"2113_CR17","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, Las Vegas, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2113_CR18","doi-asserted-by":"publisher","DOI":"10.1093\/bioadv\/vbad001","volume":"3","author":"S Zhang","year":"2023","unstructured":"Zhang S, Fan R, Liu Y et al (2023) Applications of transformer-based language models in bioinformatics: a survey. Bioinform Adv 3:vbad001","journal-title":"Bioinform Adv"},{"key":"2113_CR19","doi-asserted-by":"publisher","first-page":"4431536","DOI":"10.1155\/2022\/4431536","volume":"2022","author":"J Hu","year":"2022","unstructured":"Hu J, Zheng S, Wang B et al (2022) Super-resolution Swin Transformer and attention network for medical CT imaging. Biomed Res Int 2022:4431536","journal-title":"Biomed Res Int"},{"key":"2113_CR20","doi-asserted-by":"publisher","first-page":"e232558","DOI":"10.1148\/radiol.232558","volume":"310","author":"AA Bankier","year":"2024","unstructured":"Bankier AA, MacMahon H, Colby T et al (2024) Fleischner Society: glossary of terms for thoracic imaging. Radiology 310:e232558","journal-title":"Radiology"},{"key":"2113_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8","volume":"10","author":"J Yang","year":"2023","unstructured":"Yang J, Shi R, Wei D et al (2023) MedMNIST v2\u2014a large-scale lightweight benchmark for 2D and 3D biomedical image classification. Sci Data 10:41","journal-title":"Sci Data"},{"key":"2113_CR22","doi-asserted-by":"publisher","first-page":"103106","DOI":"10.1016\/j.ebiom.2020.103106","volume":"62","author":"L Jin","year":"2020","unstructured":"Jin L, Yang J, Kuang K et al (2020) Deep-learning-assisted detection and segmentation of rib fractures from CT scans: development and validation of FracNet. EBioMedicine 62:103106","journal-title":"EBioMedicine"},{"key":"2113_CR23","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/S1556-0864(15)31593-8","volume":"1","author":"DH Garfield","year":"2006","unstructured":"Garfield DH, Cadranel JL, Wislez M et al (2006) The bronchioloalveolar carcinoma and peripheral adenocarcinoma spectrum of diseases. J Thorac Oncol 1:344\u2013359","journal-title":"J Thorac Oncol"},{"key":"2113_CR24","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1378\/chest.12-2987","volume":"144","author":"HJ Lim","year":"2013","unstructured":"Lim HJ, Ahn S, Lee KS et al (2013) Persistent pure ground-glass opacity lung nodules \u2265 10 mm in diameter at CT scan: histopathologic comparisons and prognostic implications. Chest 144:1291\u20131299","journal-title":"Chest"},{"key":"2113_CR25","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1309\/AJCPBS85VJEOBPDO","volume":"131","author":"R De Oliveira Duarte Achcar","year":"2009","unstructured":"De Oliveira Duarte Achcar R, Nikiforova MN, Yousem SA (2009) Micropapillary lung adenocarcinoma: EGFR, K-ras, and BRAF mutational profile. Am J Clin Pathol 131:694\u2013700","journal-title":"Am J Clin Pathol"},{"key":"2113_CR26","first-page":"127","volume":"69","author":"WL Bi","year":"2019","unstructured":"Bi WL, Hosny A, Schabath MB et al (2019) Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin 69:127\u2013157","journal-title":"CA Cancer J Clin"},{"key":"2113_CR27","doi-asserted-by":"publisher","first-page":"6215085","DOI":"10.1155\/2016\/6215085","volume":"2016","author":"W Li","year":"2016","unstructured":"Li W, Cao P, Zhao D et al (2016) Pulmonary nodule classification with deep convolutional neural networks on computed tomography images. Comput Math Methods Med 2016:6215085","journal-title":"Comput Math Methods Med"},{"key":"2113_CR28","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","volume":"19","author":"D Shen","year":"2017","unstructured":"Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221\u2013248","journal-title":"Annu Rev Biomed Eng"},{"key":"2113_CR29","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y et al (2021) Swin Transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision. IEEE, Montreal, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2113_CR30","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-50989-1","volume":"9","author":"L Qi","year":"2019","unstructured":"Qi L, Xue K, Li C et al (2019) Analysis of CT morphologic features and attenuation for differentiating among transient lesions, atypical adenomatous hyperplasia, adenocarcinoma in situ, minimally invasive and invasive adenocarcinoma presenting as pure ground-glass nodules. Sci Rep 9:14586","journal-title":"Sci Rep"},{"key":"2113_CR31","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.ejrad.2019.01.021","volume":"112","author":"W Zhao","year":"2019","unstructured":"Zhao W, Xu Y, Yang Z et al (2019) Development and validation of a radiomics nomogram for identifying invasiveness of pulmonary adenocarcinomas appearing as subcentimeter ground-glass opacity nodules. Eur J Radiol 112:161\u2013168","journal-title":"Eur J Radiol"}],"container-title":["Insights into Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-025-02113-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13244-025-02113-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-025-02113-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T04:12:47Z","timestamp":1760674367000},"score":1,"resource":{"primary":{"URL":"https:\/\/insightsimaging.springeropen.com\/articles\/10.1186\/s13244-025-02113-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2113"],"URL":"https:\/\/doi.org\/10.1186\/s13244-025-02113-3","relation":{},"ISSN":["1869-4101"],"issn-type":[{"value":"1869-4101","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"8 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Our trial protocol conforms to the ethical guidelines of the Declaration of Helsinki and has been approved by the Ethics Review Committees of the Fifth Affiliated Hospital of Guangzhou Medical University, Guilin People\u2019s Hospital, and the First Affiliated Hospital of Guangzhou Medical University. The approval numbers are KY01-2022-02-14, 2024-195KY, and (MER) 2017-38, respectively.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Because of the retrospective nature of the study, the need for informed consent was waived by the institutional review board.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"223"}}