{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T18:58:03Z","timestamp":1779217083834,"version":"3.51.4"},"reference-count":44,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"vor","delay-in-days":4,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100002915","name":"Fondation pour la Recherche M\u00e9dicale","doi-asserted-by":"publisher","award":["M2R201806006004"],"award-info":[{"award-number":["M2R201806006004"]}],"id":[{"id":"10.13039\/501100002915","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":[[2021,7]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>To develop a radiomic model predicting nonresponse to induction chemotherapy in laryngeal cancers, from multicenter pretherapeutic contrast\u2010enhanced computed tomography (CE\u2010CT) and evaluate the benefit of feature harmonization in such a context.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Patients (n\u2009=\u2009104) eligible for laryngeal preservation chemotherapy were included in five centers. Primary tumor was manually delineated on the CE\u2010CT images. The following radiomic features were extracted with an in\u2010house software (MIRAS v1.1, LaTIM UMR 1101): intensity, shape, and textural features derived from Gray\u2010Level Co\u2010occurrence Matrix (GLCM), Neighborhood Gray Tone Difference Matrix (NGTDM), Gray\u2010Level Run Length Matrix (GLRLM), and Gray\u2010Level Size Zone Matrix (GLSZM). Harmonization was performed using ComBat after unsupervised hierarchical clustering, used to determine labels automatically, given the high heterogeneity of imaging characteristics across and within centers. Patients with similar feature distributions were grouped with unsupervised clustering into an optimal number of clusters (2) determined with \u201csilhouette scoring.\u201d Statistical harmonization was then carried out with ComBat on these 2 identified clusters. The cohort was split into training\/validation (n\u2009=\u200966) and testing (n\u2009=\u200932) sets. Area under the receiver operating characteristics curves (AUC) were used to evaluate the ability of radiomic features (before and after harmonization) to predict nonresponse to chemotherapy, and specificity (Sp) and sensitivity (Se) were used to quantify their performance in the testing set.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Without harmonization, none of the features identified as predictive in the training set remained significant in the testing set. After ComBat, one textural feature identified in the training set keeps a predictive trend in the testing set\u2014Zone Percentage, derived from the GLSZM, was predictive of nonresponse in the training set (AUC\u2009=\u20090.62, Se\u2009=\u200970%, Sp\u2009=\u200964%, <jats:italic>P<\/jats:italic>\u2009=\u20090.04) and obtained a satisfactory performance in the testing set (Se\u2009=\u200980%, Sp\u2009=\u200967%, <jats:italic>P<\/jats:italic>\u2009=\u20090.03), although significance was limited by the size of the testing set. These results are consistent with previously published findings in head and neck cancers.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Radiomic features from CE\u2010CT could help in the selection of patients for induction chemotherapy in laryngeal cancers, with relatively good sensitivity and specificity in predicting lack of response. Statistical harmonization with ComBat and unsupervised clustering seems to improve the predictive value of features extracted in such a heterogeneous multicenter setting.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.14948","type":"journal-article","created":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T08:04:56Z","timestamp":1621411496000},"page":"4099-4109","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Statistical harmonization can improve the development of a multicenter CT\u2010based radiomic model predictive of nonresponse to induction chemotherapy in laryngeal cancers"],"prefix":"10.1002","volume":"48","author":[{"given":"Ingrid","family":"Masson","sequence":"first","affiliation":[{"name":"LaTIM INSERM UMR 1101 Univ Brest Brest France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronrick","family":"Da\u2010ano","sequence":"additional","affiliation":[{"name":"LaTIM INSERM UMR 1101 Univ Brest Brest France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois","family":"Lucia","sequence":"additional","affiliation":[{"name":"LaTIM INSERM UMR 1101 Univ Brest Brest France"},{"name":"Radiation Oncology Department University Hospital Brest France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M\u00e9lanie","family":"Dor\u00e9","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Institut de canc\u00e9rologie de l\u2019Ouest Ren\u00e9\u2010Gauducheau Saint\u2010Herblain France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joel","family":"Castelli","sequence":"additional","affiliation":[{"name":"Radiotherapy Department Cancer Institute Eug\u00e8ne Marquis Rennes France"},{"name":"University of Rennes 1 LTSI Rennes France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Camille","family":"Goislard de Monsabert","sequence":"additional","affiliation":[{"name":"Radiotherapy Department Cancer Institute Eug\u00e8ne Marquis Rennes France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean\u2010Fran\u00e7ois","family":"Ram\u00e9e","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology Centre Hospitalier de Vend\u00e9e La Roche sur Yon France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Selima","family":"Sellami","sequence":"additional","affiliation":[{"name":"Radiation Oncology Department University Hospital Brest France"},{"name":"Radiotherapy Department Centre Hospitalier de Cornouaille Quimper France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitris","family":"Visvikis","sequence":"additional","affiliation":[{"name":"LaTIM INSERM UMR 1101 Univ Brest Brest France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathieu","family":"Hatt","sequence":"additional","affiliation":[{"name":"LaTIM INSERM UMR 1101 Univ Brest Brest France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulrike","family":"Schick","sequence":"additional","affiliation":[{"name":"LaTIM INSERM UMR 1101 Univ Brest Brest France"},{"name":"Radiation Oncology Department University Hospital Brest France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,7,5]]},"reference":[{"key":"e_1_2_9_2_1","unstructured":"John Andrew Ridge MD.Head and Neck Tumors. Cancer Network. Published June 2 2016. Accessed August 5 2019.https:\/\/www.cancernetwork.com\/cancer\u2010management\/head\u2010and\u2010neck\u2010tumors."},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djp007"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa031317"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199106133242402"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/88.13.890"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12123"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172361"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10050258"},{"key":"e_1_2_9_10_1","article-title":"Impact of reconstruction algorithms on CT radiomic features of pulmonary tumors: analysis of intra\u2010 and inter\u2010reader variability and inter\u2010reconstruction algorithm variability","volume":"11","author":"Kim H","year":"2016","journal-title":"PLoS One"},{"key":"e_1_2_9_11_1","unstructured":"ZwanenburgA LegerS Valli\u00e8resM L\u00f6ckS.Image biomarker standardisation initiative. arXiv:161207003 [cs]. Published online December 21 2016. Accessed April 1 2019.http:\/\/arxiv.org\/abs\/1612.07003."},{"key":"e_1_2_9_12_1","unstructured":"DesseroitMC TixierF Cheze Le RestC.Comparison of three quantization methods for the calculation of textural features in PET\/CT images: impact on prognostic models in non\u2010small cell lung cancer. In: IEEE NSS\u2010MIC;2016."},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep11075"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20170498"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/61\/24\/8736"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-017-3898-7"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/60\/14\/5471"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-10371-5"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxj037"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019182023"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-018-4231-9"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.117.199935"},{"key":"e_1_2_9_23_1","unstructured":"MurtaghF ContrerasP.Methods of Hierarchical Clustering. arXiv:11050121 [cs math stat]. Published online April 30 2011. Accessed September 5 2019.http:\/\/arxiv.org\/abs\/1105.0121."},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-66110-w"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.117.200501"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2015.61.2978"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2017.75.7385"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.21181"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190928"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.06.002"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(17)30252-8"},{"key":"e_1_2_9_33_1","first-page":"1","article-title":"Perfusion CT radiomics as potential prognostic biomarker in head and neck squamous cell carcinoma","author":"Bogowicz M","year":"2019","journal-title":"Acta Oncol"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/61\/13\/R150"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40336-018-0292-9"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5006"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20160665"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360-3016(97)00853-5"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.3109\/0284186X.2015.1061214"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12188"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/0284186X.2017.1346382"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2005.04.010"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/0284186X.2018.1445283"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.17856"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibtech.2017.02.012"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.14948","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.14948","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.14948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T06:29:01Z","timestamp":1693117741000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.14948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":44,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["10.1002\/mp.14948"],"URL":"https:\/\/doi.org\/10.1002\/mp.14948","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]},"assertion":[{"value":"2020-09-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}