{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:04:02Z","timestamp":1789535042091,"version":"build-2803163510"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012899","name":"Lanzhou University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012899","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Most malignant subsolid nodules (SSNs) are non-mucinous adenocarcinomas, and prognosis varies substantially with the degree of invasion. Previous studies have shown that the solid component of SSNs is closely associated with invasiveness. With advances in image analysis, three-dimensional (3D) computed tomography (CT) features may provide more comprehensive information than conventional two-dimensional (2D) measurements. This study aimed to investigate the value of 2D and 3D CT features for predicting the extent of invasion in SSNs and to compare the diagnostic performance and potential clinical utility of 2D- and 3D-based predictive models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>This single-center retrospective model-development study included 234 SSNs from 223 patients with pathologically confirmed lung non-mucinous adenocarcinoma. Minimally invasive adenocarcinoma and Grade 1 tumors were classified as the low-risk group, whereas Grades 2 and 3 tumors were classified as the high-risk group. Patients were randomly assigned at the patient level to a training set comprising 171 SSNs from 164 patients and a held-out internal test set comprising 63 SSNs from 59 patients. 2D and 3D CT parameters, including consolidation-to-tumor ratio of volume (CTRV), were evaluated. Least absolute shrinkage and selection operator regression was used for feature selection, and models based on five machine-learning algorithms were developed using 5\u00d75-fold nested cross-validation within the training set. The best-performing 2D and 3D models were selected according to the area under the receiver operating characteristic curve (AUC) calculated from pooled out-of-fold (OOF) predictions and were subsequently evaluated in the held-out test set. Model performance was assessed in terms of discrimination, calibration, and decision curve analysis, and AUCs were compared using the paired DeLong test.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The best-performing 2D and 3D models were 2D-XGB and 3D-RF, respectively, with pooled OOF AUCs of 0.713 (0.632\u20130.790) and 0.712 (0.633\u20130.785). In the held-out test set, 2D-XGB achieved an AUC of 0.766 (0.648\u20130.869), whereas 3D-RF achieved an AUC of 0.847 (0.745\u20130.931). No significant difference in AUC was observed between the two models based on either the pooled OOF predictions or the held-out test set predictions. Permutation importance analysis indicated that consolidation-to-tumor ratio was the most influential feature in 2D-XGB, whereas mass and CTRV\n                      <jats:sub>-100<\/jats:sub>\n                      were among the most important features in 3D-RF. Compared with 2D-XGB, 3D-RF showed higher net benefit across a wider range of threshold probabilities and better calibration.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Both 2D- and 3D-based models showed comparable discriminative performance for predicting the degree of invasion in lung non-mucinous adenocarcinomas presenting as SSNs. The 3D-RF model showed better calibration and a broader range of clinical net benefit, suggesting potential advantages for risk estimation and clinical decision-making. Mass and CTRV derived from multiple density thresholds may provide additional information for characterizing solid components and may support clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1916349","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:28:51Z","timestamp":1789532931000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative analysis of two-dimensional and three-dimensional machine learning models for predicting the degree of invasion in lung non-mucinous adenocarcinomas presenting as subsolid nodules"],"prefix":"10.3389","volume":"16","author":[{"given":"Yi-Ming","family":"Hui","sequence":"first","affiliation":[{"name":"Department of Thoracic Surgery, The Second Hospital and Clinical Medical School, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Zhi","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Second Hospital and Clinical Medical School, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Second Hospital and Clinical Medical School, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Qi","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Second Hospital and Clinical Medical School, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai-Ming","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Second Hospital and Clinical Medical School, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Zhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Second Hospital and Clinical Medical School, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Peng","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Second Hospital and Clinical Medical School, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m3673","article-title":"Pulmonary nodules","volume":"371","author":"Au-Yong","year":"2020","journal-title":"BMJ (Clinical Res Ed)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1056\/NEJMoa1102873","article-title":"Reduced lung-cancer mortality with low-dose computed tomographic screening","volume":"365","author":"Aberle","year":"2011","journal-title":"N Engl J Med"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2021.11.003","article-title":"The 2021 WHO classification of lung tumors: Impact of advances since 2015","volume":"17","author":"Nicholson","year":"2022","journal-title":"J Thorac Oncol Off Publ Int Assoc For Study Lung Cancer"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2020.06.001","article-title":"A grading system for invasive pulmonary adenocarcinoma: A proposal from the International Association for the Study of Lung Cancer Pathology Committee","volume":"15","author":"Moreira","year":"2020","journal-title":"J Thorac Oncol Off Publ Int Assoc For Study Lung Cancer"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2021.04.007","article-title":"Long-term prognosis of patients with resected adenocarcinoma in situ and minimally invasive adenocarcinoma of the lung","volume":"16","author":"Yotsukura","year":"2021","journal-title":"J Thorac Oncol Off Publ Int Assoc For Study Lung Cancer"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1038\/s41379-021-00994-5","article-title":"Prognostic and predictive value of the newly proposed grading system of invasive pulmonary adenocarcinoma in Chinese patients: A retrospective multicohort study","volume":"35","author":"Hou","year":"2022","journal-title":"Modern Pathology: Off J United States Can Acad Pathology Inc"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2013.02.022","article-title":"Comparison of three measurements on computed tomography for the prediction of less invasiveness in patients with clinical stage I non-small cell lung cancer","volume":"95","author":"Matsuguma","year":"2013","journal-title":"Ann Thorac Surg"},{"key":"B8","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1097\/jto.0000000000000019","article-title":"Correlation between the size of the solid component on thin-section CT and the invasive component on pathology in small lung adenocarcinomas manifesting as ground-glass nodules","volume":"9","author":"Lee","year":"2014","journal-title":"J Thorac Oncol Off Publ Int Assoc For Study Lung Cancer"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1067\/mtc.2002.122298","article-title":"Proportion of ground-glass opacity on high-resolution computed tomography in clinical T1 N0 M0 adenocarcinoma of the lung: A predictor of lymph node metastasis","volume":"124","author":"Matsuguma","year":"2002","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtcvs.2013.08.058","article-title":"Tumor invasiveness as defined by the newly proposed IASLC\/ATS\/ERS classification has prognostic significance for pathologic stage IA lung adenocarcinoma and can be predicted by radiologic parameters","volume":"147","author":"Takahashi","year":"2014","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B11","doi-asserted-by":"publisher","first-page":"8561","DOI":"10.1200\/JCO.2017.35.15_suppl.8561","article-title":"A nonrandomized confirmatory phase III study of sublobar surgical resection for peripheral ground glass opacity dominant lung cancer defined with thoracic thin-section computed tomography (JCOG0804\/WJOG4507L)","volume":"35","author":"Suzuki","year":"2017","journal-title":"J Clin Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(21)02333-3","article-title":"Segmentectomy versus lobectomy in small-sized peripheral non-small-cell lung cancer (JCOG0802\/WJOG4607L): A multicentre, open-label, phase 3, randomised, controlled, non-inferiority trial","volume":"399","author":"Saji","year":"2022","journal-title":"Lancet (London England)"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2014.01.025","article-title":"Influence of radiation dose and iterative reconstruction algorithms for measurement accuracy and reproducibility of pulmonary nodule volumetry: A phantom study","volume":"83","author":"Kim","year":"2014","journal-title":"Eur J Radiol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2016142975","article-title":"Lung adenocarcinoma: Correlation of quantitative CT findings with pathologic findings","volume":"280","author":"Ko","year":"2016","journal-title":"Radiology"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0080249","article-title":"Semi-automatic quantification of subsolid pulmonary nodules: Comparison with manual measurements","volume":"8","author":"Scholten","year":"2013","journal-title":"PloS One"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/s0022-5223(03)00885-7","article-title":"Histogram analysis of computed tomography numbers of clinical T1 N0 M0 lung adenocarcinoma, with special reference to lymph node metastasis and tumor invasiveness","volume":"126","author":"Nomori","year":"2003","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B17","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s40644-023-00577-4","article-title":"The solid component within part-solid nodules: 3-dimensional quantification, correlation with the Malignant grade of nonmucinous pulmonary adenocarcinomas, and comparisons with 2-dimentional measures and semantic features in low-dose computed tomography","volume":"23","author":"Liu","year":"2023","journal-title":"Cancer Imaging: Off Publ Int Cancer Imaging Soc"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017161659","article-title":"Guidelines for management of incidental pulmonary nodules detected on CT images: From the Fleischner Society 2017","volume":"284","author":"MacMahon","year":"2017","journal-title":"Radiology"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-016-4317-3","article-title":"Software performance in segmenting ground-glass and solid components of subsolid nodules in pulmonary adenocarcinomas","volume":"26","author":"Cohen","year":"2016","journal-title":"Eur Radio"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07450-z","article-title":"Natural history of pathologically confirmed pulmonary subsolid nodules with deep learning-assisted nodule segmentation","volume":"31","author":"Qi","year":"2021","journal-title":"Eur Radio"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1093\/icvts\/ivw037","article-title":"Is volumetric 3-dimensional computed tomography useful to predict histological tumour invasiveness? Analysis of 211 lesions of CT1N0M0 lung adenocarcinoma","volume":"22","author":"Shikuma","year":"2016","journal-title":"Interactive Cardiovasc Thorac Surg"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezx273","article-title":"A novel model uses metabolic and volumetric parameters to predict less invasive lung adenocarcinomas\u2020","volume":"53","author":"Ishikawa","year":"2018","journal-title":"Eur J Cardio-Thoracic Surgery: Off J Eur Assoc For Cardio-Thoracic Surg"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-018-0147-7","article-title":"Solid component proportion is an important predictor of tumor invasiveness in clinical stage T(1)N(0)M(0) (CT(1)N(0)M(0)) lung adenocarcinoma","volume":"18","author":"Li","year":"2018","journal-title":"Cancer Imaging: Off Publ Int Cancer Imaging Soc"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1097\/jto.0000000000000020","article-title":"Prognostic impact of tumor size eliminating the ground glass opacity component: Modified clinical T descriptors of the tumor, node, metastasis classification of lung cancer","volume":"8","author":"Nakamura","year":"2013","journal-title":"J Thorac Oncol Off Publ Int Assoc For Study Lung Cancer"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdt230","article-title":"Solid tumor size on high-resolution computed tomography and maximum standardized uptake on positron emission tomography for new clinical T descriptors with T1 lung adenocarcinoma","volume":"24","author":"Tsutani","year":"2013","journal-title":"Ann Oncol Off J Eur Soc For Med Oncol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.179.2.2014294","article-title":"Solitary pulmonary nodule: High-resolution CT and radiologic-pathologic correlation","volume":"179","author":"Zwirewich","year":"1991","journal-title":"Radiology"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.160.2.3726105","article-title":"Solitary pulmonary nodules: CT assessment","volume":"160","author":"Siegelman","year":"1986","journal-title":"Radiology"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.167.2.2833764","article-title":"Solitary bronchioloalveolar carcinoma: CT criteria","volume":"167","author":"Kuhlman","year":"1988","journal-title":"Radiology"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2333031018","article-title":"Malignant versus benign nodules at CT screening for lung cancer: Comparison of thin-section CT findings","volume":"233","author":"Li","year":"2004","journal-title":"Radiology"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cllc.2011.06.005","article-title":"Development and validation of a clinical prediction model to estimate the probability of Malignancy in solitary pulmonary nodules in Chinese people","volume":"12","author":"Li","year":"2011","journal-title":"Clin Lung Cancer"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1001\/archinte.1997.00440290031002","article-title":"The probability of Malignancy in solitary pulmonary nodules. Application to small radiologically indeterminate nodules","volume":"157","author":"Swensen","year":"1997","journal-title":"Arch Internal Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1378\/chest.06-1261","article-title":"A clinical model to estimate the pretest probability of lung cancer in patients with solitary pulmonary nodules","volume":"131","author":"Gould","year":"2007","journal-title":"Chest"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1214726","article-title":"Probability of cancer in pulmonary nodules detected on first screening CT","volume":"369","author":"McWilliams","year":"2013","journal-title":"N Engl J Med"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2024.07.003","article-title":"Comparative analysis of three-dimensional and two-dimensional models for predicting the Malignancy probability of subsolid nodules","volume":"79","author":"Hui","year":"2024","journal-title":"Clin Radiol"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3904\/kjim.2001.16.4.236","article-title":"Predictors for benign solitary pulmonary nodule in tuberculosis-endemic area","volume":"16","author":"Kim","year":"2001","journal-title":"Korean J Internal Med"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1258\/ar.2011.100377","article-title":"High resolution spiral CT for determining the Malignant potential of solitary pulmonary nodules: Refining and testing the test","volume":"52","author":"Harders","year":"2011","journal-title":"Acta Radiologica (Stockholm Sweden 1987)"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1097\/00004728-199611000-00021","article-title":"Evaluation of the air bronchogram sign on CT in solitary pulmonary lesions","volume":"20","author":"Kui","year":"1996","journal-title":"J Comput Assisted Tomogr"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.156.5.2017952","article-title":"Prevalence of air bronchograms in small peripheral carcinomas of the lung on thin-section CT: Comparison with benign tumors","volume":"156","author":"Kuriyama","year":"1991","journal-title":"AJR Am J Roentgenology"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-008-0306-z","article-title":"Computer-aided diagnosis of lung cancer: Definition and detection of ground-glass opacity type of nodules by high-resolution computed tomography","volume":"27","author":"Okada","year":"2009","journal-title":"Jpn J Radiol"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2019.07.026","article-title":"A radiomics model for determining the invasiveness of solitary pulmonary nodules that manifest as part-solid nodules","volume":"74","author":"Weng","year":"2019","journal-title":"Clin Radiol"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0097867","article-title":"Tumor size and computed tomography attenuation of pulmonary pure ground-glass nodules are useful for predicting pathological invasiveness","volume":"9","author":"Eguchi","year":"2014","journal-title":"PloS One"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-022-01359-x","article-title":"Artificial intelligence in lung cancer: Current applications and perspectives","volume":"41","author":"Chassagnon","year":"2023","journal-title":"Jpn J Radiol"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.3779\/j.issn.1009-3419.2022.102.12","article-title":"Clinical study of artificial intelligence-assisted diagnosis system in predicting the invasive subtypes of early-stage lung adenocarcinoma appearing as pulmonary nodules","volume":"25","author":"Su","year":"2022","journal-title":"Zhongguo Fei Ai Za Zhi = Chin J Lung Cancer"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3779\/j.issn.1009-3419.2023.102.28","article-title":"Application value of artificial intelligence-assisted three-dimensional reconstruction in planning thoracoscopic segmentectomy","volume":"26","author":"Zheng","year":"2023","journal-title":"Zhongguo Fei Ai Za Zhi = Chin J Lung Cancer"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2019.09.130","article-title":"Three-dimensional mean CT attenuation value of pure and part-solid ground-glass lung nodules may predict invasiveness in early adenocarcinoma","volume":"74","author":"Kitazawa","year":"2019","journal-title":"Clin Radiol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"ii1","DOI":"10.1136\/thoraxjnl-2015-207168","article-title":"British Thoracic Society guidelines for the investigation and management of pulmonary nodules","volume":"70","author":"Callister","year":"2015","journal-title":"Thorax"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1916349\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:28:54Z","timestamp":1789532934000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1916349\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":46,"alternative-id":["10.3389\/fonc.2026.1916349"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1916349","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1916349"}}