{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T07:35:38Z","timestamp":1771572938484,"version":"3.50.1"},"reference-count":32,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2019,5,11]],"date-time":"2019-05-11T00:00:00Z","timestamp":1557532800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61601019"],"award-info":[{"award-number":["61601019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871022"],"award-info":[{"award-number":["61871022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2019,7]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Histological subtypes of non\u2010small cell lung cancer (<jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content>) are crucial for systematic treatment decisions. However, the current studies which used noninvasive radiomic methods to classify <jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content> histology subtypes mainly focused on two main subtypes: squamous cell carcinoma (<jats:styled-content style=\"fixed-case\">SCC<\/jats:styled-content>) and adenocarcinoma (<jats:styled-content style=\"fixed-case\">ADC<\/jats:styled-content>), while multi\u2010subtype classifications that included the other two subtypes of <jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content>: large cell carcinoma (<jats:styled-content style=\"fixed-case\">LCC<\/jats:styled-content>) and not otherwise specified (<jats:styled-content style=\"fixed-case\">NOS<\/jats:styled-content>), were very few in the previous studies. The aim of this work was to establish a multi\u2010subtype classification model for the four main subtypes of <jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content> and improve the classification performance and generalization ability compared with previous studies.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this work, we extracted 1029 features from regions of interest in computed tomography (<jats:styled-content style=\"fixed-case\">CT<\/jats:styled-content>) images of 349 patients from two different datasets using radiomic methods. Based on \u201cthree\u2010in\u2010one\u201d concept, we proposed a model called SLS wrapping three algorithms, synthetic minority oversampling technique, \u21132,1\u2010norm minimization, and support vector machines, into one hybrid technique to classify the four main subtypes of NSCLC: <jats:styled-content style=\"fixed-case\">SCC<\/jats:styled-content>,<jats:styled-content style=\"fixed-case\"> ADC<\/jats:styled-content>,<jats:styled-content style=\"fixed-case\"> LCC<\/jats:styled-content>, and <jats:styled-content style=\"fixed-case\">NOS<\/jats:styled-content>, which could cover the whole range of <jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content>.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We analyzed the 247 features obtained by dimension reduction, and found that the extracted features from three methods: first order statistics, gray level co\u2010occurrence matrix, and gray level size zone matrix, were more conducive to the classification of <jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content> subtypes. The proposed <jats:styled-content style=\"fixed-case\">SLS<\/jats:styled-content> model achieved an average classification accuracy of 0.89 on the training set (95% confidence interval [<jats:styled-content style=\"fixed-case\">CI<\/jats:styled-content>]: 0.846 to 0.912) and a classification accuracy of 0.86 on the test set (95% <jats:styled-content style=\"fixed-case\">CI<\/jats:styled-content>: 0.779 to 0.941).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The experiment results showed that the subtypes of <jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content> could be well classified by radiomic method. Our <jats:styled-content style=\"fixed-case\">SLS<\/jats:styled-content> model can accurately classify and diagnose the four subtypes of <jats:styled-content style=\"fixed-case\">NSCLC<\/jats:styled-content> based on <jats:styled-content style=\"fixed-case\">CT<\/jats:styled-content> images, and thus it has the potential to be used in the clinical practice to provide valuable information for lung cancer treatment and further promote the personalized medicine.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.13551","type":"journal-article","created":{"date-parts":[[2019,4,19]],"date-time":"2019-04-19T14:03:46Z","timestamp":1555682626000},"page":"3091-3100","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":63,"title":["Multi\u2010subtype classification model for non\u2010small cell lung cancer based on radiomics: <scp>SLS<\/scp> model"],"prefix":"10.1002","volume":"46","author":[{"given":"Jian","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer and Information Technology Beijing Jiaotong University Beijing 100044 China"},{"name":"Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing 100083 China"},{"name":"School of Biological Science and Medical Engineering Beihang University Beijing 100083 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology Beijing Jiaotong University Beijing 100044 China"},{"name":"Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing 100083 China"},{"name":"School of Biological Science and Medical Engineering Beihang University Beijing 100083 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science and Technology University Beijing 100192 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology City University of Hong Kong Hong Kong SAR China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of\u00a0Medical Science Beijing 100730 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing 100083 China"},{"name":"School of Biological Science and Medical Engineering Beihang University Beijing 100083 China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,5,11]]},"reference":[{"key":"e_1_2_7_2_1","first-page":"7","article-title":"Cancer statistics, 2017","volume":"67","author":"Siegel RL","year":"2017","journal-title":"CA"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1586\/14737140.2014.949245"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.advms.2014.08.008"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2015.90"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2011.11.036"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2016.00071"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2018.04.003"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-017-5221-1"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12194-017-0433-2"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.18383\/j.tom.2016.00244"},{"key":"e_1_2_7_12_1","unstructured":"AertsHJWL VelazquezER LeijenaarRTH et\u00a0al.Data From NSCLC\u2010Radiomics. The Cancer Imaging Archive;2015https:\/\/doi.org\/10.7937\/k9\/tcia.2015.pf0m9rei"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5006"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9622-7"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339"},{"key":"e_1_2_7_16_1","first-page":"2","article-title":"Grey level co\u2010occurrence matrices: generalisation and some new features","volume":"2","author":"Kannan B","year":"2012","journal-title":"Int J Comput Sci Eng Inform Technol"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8655(90)90112-F"},{"key":"e_1_2_7_18_1","unstructured":"SemlerL DettoriL FurstJ.Wavelet\u2010based texture classification of tissues in computed tomography. The 18 IEEE International Symposium on Computer\u2010Based Medical Systems (CBMS'05);2005 Dublin Ireland 265\u2013270."},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(2003)131<1485:ESRF>2.0.CO;2"},{"key":"e_1_2_7_20_1","first-page":"152","volume-title":"Neural Information Processing","author":"Jeatrakul P","year":"2010"},{"key":"e_1_2_7_21_1","doi-asserted-by":"crossref","unstructured":"ImamT TingKM KamruzzamanJ.z\u2010SVM: an SVM for improved classification of imbalanced data. In: Proc. of 19th AUS\u2010AI;2006:264\u2010273.","DOI":"10.1007\/11941439_30"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_7_23_1","unstructured":"LiuJ JiS YeJ et\u00a0al.Multi\u2010task feature learning via efficient l2 1\u2010norm minimization. In: Proceedings of the Twenty\u2010Fifth Conference on Uncertainty in Artificial Intelligence;2009:339\u2010348."},{"key":"e_1_2_7_24_1","unstructured":"NieF HuangH CaiX et\u00a0al.Efficient and robust feature selection via joint \u21132 1\u2010norms minimization. NIPS;2010."},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_2_7_26_1","first-page":"236","article-title":"Multi\u2010Class Support Vector Machine","volume":"16","author":"Franc V","year":"2002","journal-title":"Proc. Int'l Conf. Pattern Recognition (ICPR)"},{"key":"e_1_2_7_27_1","first-page":"164","article-title":"A decision based one\u2010against\u2010one method for multi\u2010class support vector machine","volume":"7","author":"Debnath R","year":"2004","journal-title":"CA"},{"key":"e_1_2_7_28_1","unstructured":"LiuY ZhengYF.One\u2010against\u2010all multi\u2010class SVM classification using reliability measures. In:IEEE International Joint Conference on Neural Networks;2005."},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2015.1020159"},{"key":"e_1_2_7_30_1","volume-title":"Cross\u2010Validation for Detecting and Preventing Overfitting","author":"Moore AW","year":"2001"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2012.12.003"},{"key":"e_1_2_7_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2011.11.036"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2012.06.010"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13551","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.13551","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T15:06:17Z","timestamp":1693839977000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.13551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,11]]},"references-count":32,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2019,7]]}},"alternative-id":["10.1002\/mp.13551"],"URL":"https:\/\/doi.org\/10.1002\/mp.13551","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,11]]},"assertion":[{"value":"2018-10-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-04-08","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-05-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}