{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T05:52:36Z","timestamp":1764049956698,"version":"3.45.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"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>Purpose<\/jats:title>\n                    <jats:p>To evaluate and compare the predictive performance of machine learning methods using clinical-semantic, radiomic, and combined features in distinguishing squamous cell carcinoma (SCC) from adenocarcinoma (ADC) in non-small cell lung cancer (NSCLC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 399 patients with pathologically confirmed NSCLC were retrospectively enrolled in 2017, and randomly divided into a training set (n=279) and a validation set (n=120). Clinical factors, semantic features, and radiomics features were collected and screened via the minimum redundancy maximum relevance (mRMR) method and least absolute shrinkage and selection operator (LASSO). We investigated 3 models constructed with 4 classifiers for histologic subtype prediction. The models were trained on the training cohort and their performance was evaluated on the independent validation cohort using accuracy, sensitivity, specificity, F1 score, precision and area under the receiver operating characteristic curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>After feature selection, 10 representative features were finalized, comprising 4 clinical-semantic and 6 radiomic features. In the validation cohort, the support vector machine (SVM) classifier demonstrated promising predictive performance. When integrating clinical-semantic and radiomic features, the combined model (AUC\u00a0=\u00a00.871) showed potential in distinguishing NSCLC pathological subtypes, outperforming models based solely on clinical-semantic (AUC\u00a0=\u00a00.594) or radiomic features (AUC\u00a0=\u00a00.713). It achieved an accuracy of 0.892, a sensitivity of 0.758, a specificity of 0.943, a F1 score of 0.794, and a precision of 0.833. However, the AUC differences were not statistically significant, highlighting the need for further multi-center prospective validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In this study, the SVM-based combined model, which integrated clinical-semantic and radiomic features, demonstrated promising performance among the four classifiers-based combined models in distinguishing between ADC and SCC. However, due to the study\u2019s single-center, retrospective design and the lack of statistically significant differences in AUC for some models, the findings should be interpreted with caution. These results show potential but require future multi-center prospective validation before clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2025.1726193","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T05:11:20Z","timestamp":1764047480000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based differentiation of lung squamous cell carcinoma and adenocarcinoma using clinical-semantic and radiomic features"],"prefix":"10.3389","volume":"15","author":[{"given":"Yanju","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingjin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinru","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoxiang","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA A Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"15009","DOI":"10.1038\/nrdp.2015.9","article-title":"Non-small-cell lung cancer","volume":"1","author":"Gridelli","year":"2015","journal-title":"Nat Rev Dis Primers"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.semcancer.2017.11.019","article-title":"Current WHO guidelines and the critical role of immunohistochemical markers in the subclassification of non-small cell lung carcinoma (NSCLC): Moving from targeted therapy to immunotherapy","volume":"52","author":"Osmani","year":"2018","journal-title":"Semin Cancer Biol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2016.11.2225","article-title":"EGFR mutation subtypes influence survival outcomes following first-line gefitinib therapy in advanced asian NSCLC patients","volume":"12","author":"Sutiman","year":"2017","journal-title":"J Thorac Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2015.90","article-title":"Refining the treatment of NSCLC according to histological and molecular subtypes","volume":"12","author":"Thomas","year":"2015","journal-title":"Nat Rev Clin Oncol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.chest.2016.10.010","article-title":"The eighth edition lung cancer stage classification","volume":"151","author":"Detterbeck","year":"2017","journal-title":"Chest"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1136\/thorax.58.11.920","article-title":"Guidelines for radiologically guided lung biopsy","volume":"58","author":"Manhire","year":"2003","journal-title":"Thorax"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1097\/PAS.0000000000000154","article-title":"Lung cancer histologic and immunohistochemical heterogeneity in the era of molecular therapies: analysis of 172 consecutive surgically resected, entirely sampled pulmonary carcinomas","volume":"38","author":"Cadioli","year":"2014","journal-title":"Am J Surg Pathol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2629462","article-title":"Automatic scoring of multiple semantic attributes with multi-task feature leverage: A study on pulmonary nodules in CT images","volume":"36","author":"Chen","year":"2017","journal-title":"IEEE Trans Med Imaging"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e233244","DOI":"10.1148\/radiol.233244","article-title":"Predicting recurrence after sublobar resection in patients with lung adenocarcinoma using preoperative chest CT scans","volume":"313","author":"Yun","year":"2024","journal-title":"Radiology"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1111\/1759-7714.15216","article-title":"Machine learning-based radiomics to distinguish pulmonary nodules between lung adenocarcinoma and tuberculosis","volume":"15","author":"Li","year":"2024","journal-title":"Thorac Cancer"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07195-9","article-title":"Improved differentiation between primary lung cancer and pulmonary metastasis by combining dual-energy CT-derived biomarkers with conventional CT attenuation","volume":"31","author":"Deniffel","year":"2021","journal-title":"Eur Radiol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.875761","article-title":"The machine learning model for distinguishing pathological subtypes of non-small cell lung cancer","volume":"12","author":"Zhao","year":"2022","journal-title":"Front Oncol"},{"key":"B14","doi-asserted-by":"publisher","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":"B15","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-017-5221-1","article-title":"Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer","volume":"28","author":"Zhu","year":"2018","journal-title":"Eur Radiol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.608598","article-title":"Machine learning for histologic subtype classification of non-small cell lung cancer: A retrospective multicenter radiomics study","volume":"10","author":"Yang","year":"2021","journal-title":"Front Oncol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2016.00071","article-title":"Exploratory study to identify radiomics classifiers for lung cancer histology","volume":"6","author":"Wu","year":"2016","journal-title":"Front Oncol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.7150\/thno.81789","article-title":"Development and validation of a nonenhanced CT based radiomics model to detect brown adipose tissue","volume":"13","author":"Li","year":"2023","journal-title":"Theranostics"},{"key":"B20","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1186\/s12967-024-05393-3","article-title":"CT-based radiomics nomogram to predict proliferative hepatocellular carcinoma and explore the tumor microenvironment","volume":"22","author":"Wang","year":"2024","journal-title":"J Transl Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/s10238-024-01377-1","article-title":"The diagnostic value of multimodal imaging based on MR combined with ultrasound in benign and Malignant breast diseases","volume":"24","author":"Bai","year":"2024","journal-title":"Clin Exp Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2025.1570860","article-title":"MRI-based deep learning with clinical and imaging features to differentiate medulloblastoma and ependymoma in children","volume":"12","author":"Yimit","year":"2025","journal-title":"Front Mol Biosci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"13","DOI":"10.20982\/tqmp.04.1.p013","article-title":"The mann-whitney U: A test for assessing whether two independent samples come from the same distribution","volume":"4","author":"Nachar","year":"2008","journal-title":"TQMP"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2007.893749","article-title":"Detection of the number of signals using the benjamini-hochberg procedure","volume":"55","author":"Chung","year":"2007","journal-title":"IEEE Trans Signal Processing"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.4097\/kjae.2015.68.6.540","article-title":"T test as a parametric statistic","volume":"68","author":"Kim","year":"2015","journal-title":"Korean J Anesthesiol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.17.12.684","article-title":"The distribution of chi-square","volume":"17","author":"Wilson","year":"1931","journal-title":"Proc Natl Acad Sci U S A"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2016.06.110","article-title":"High-resolution CT findings of primary lung cancer with cavitation: a comparison between adenocarcinoma and squamous cell carcinoma","volume":"71","author":"Kunihiro","year":"2016","journal-title":"Clin Radiol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2014.04.019","article-title":"Morphological computed tomography features of surgically resectable pulmonary squamous cell carcinomas: impact on prognosis and comparison with adenocarcinomas","volume":"83","author":"Koenigkam Santos","year":"2014","journal-title":"Eur J Radiol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2371041650","article-title":"Tumor cavitation in stage I non-small cell lung cancer: epidermal growth factor receptor expression and prediction of poor outcome","volume":"237","author":"Onn","year":"2005","journal-title":"Radiology"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1097\/JTO.0b013e3181f1923b","article-title":"Survival differences by gender for resected non-small cell lung cancer: a retrospective analysis of 12,509 cases in a Japanese Lung Cancer Registry study","volume":"5","author":"Sakurai","year":"2010","journal-title":"J Thorac Oncol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-020-05065-6","article-title":"Machine learning based on clinico-biological features integrated 18F-FDG PET\/CT radiomics for distinguishing squamous cell carcinoma from adenocarcinoma of lung","volume":"48","author":"Ren","year":"2021","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B32","doi-asserted-by":"publisher","first-page":"20190159","DOI":"10.1259\/bjr.20190159","article-title":"Non-invasive classification of non-small cell lung cancer: a comparison between random forest models utilising radiomic and semantic features","volume":"92","author":"Bashir","year":"2019","journal-title":"Br J Radiol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1097\/RLU.0000000000002810","article-title":"A machine-learning approach using PET-based radiomics to predict the histological subtypes of lung cancer","volume":"44","author":"Hyun","year":"2019","journal-title":"Clin Nucl Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"e0300170","DOI":"10.1371\/journal.pone.0300170","article-title":"Machine learning for differentiating lung squamous cell cancer from adenocarcinoma using Clinical-Metabolic characteristics and 18F-FDG PET\/CT radiomics","volume":"19","author":"Zhang","year":"2024","journal-title":"PloS One"},{"key":"B35","doi-asserted-by":"publisher","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":"B36","doi-asserted-by":"publisher","first-page":"32088","DOI":"10.1038\/s41598-024-83786-6","article-title":"Radiomics for differentiating adenocarcinoma and squamous cell carcinoma in non-small cell lung cancer beyond nodule morphology in chest CT","volume":"14","author":"Selvam","year":"2024","journal-title":"Sci Rep"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1726193\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T05:11:21Z","timestamp":1764047481000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1726193\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"references-count":36,"alternative-id":["10.3389\/fonc.2025.1726193"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1726193","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,25]]},"article-number":"1726193"}}