{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T18:55:42Z","timestamp":1790621742869,"version":"4.1.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T00:00:00Z","timestamp":1661385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T00:00:00Z","timestamp":1661385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Objectives<\/jats:title>\n                <jats:p>Relapse occurs in ~20% of patients with classical Hodgkin lymphoma (cHL) despite treatment adaption based on 2-deoxy-2-[<jats:sup>18<\/jats:sup>F]fluoro-<jats:sc>d<\/jats:sc>-glucose positron emission tomography\/computed tomography response. The objective was to evaluate pre-treatment FDG PET\/CT\u2013derived machine learning (ML) models for predicting outcome in patients with cHL.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>All cHL patients undergoing pre-treatment PET\/CT at our institution between 2008 and 2018 were retrospectively identified. A 1.5 \u00d7 mean liver standardised uptake value (SUV) and a fixed 4.0 SUV threshold were used to segment PET\/CT data. Feature extraction was performed using PyRadiomics with ComBat harmonisation. Training (80%) and test (20%) cohorts stratified around 2-year event-free survival (EFS), age, sex, ethnicity and disease stage were defined. Seven ML models were trained and hyperparameters tuned using stratified 5-fold cross-validation. Area under the curve (AUC) from receiver operator characteristic analysis was used to assess performance.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>A total of 289 patients (153 males), median age 36 (range 16\u201388 years), were included. There was no significant difference between training (<jats:italic>n<\/jats:italic> = 231) and test cohorts (<jats:italic>n<\/jats:italic> = 58) (<jats:italic>p<\/jats:italic> value &gt; 0.05). A ridge regression model using a 1.5 \u00d7 mean liver SUV segmentation had the highest performance, with mean training, validation and test AUCs of 0.82 \u00b1 0.002, 0.79 \u00b1 0.01 and 0.81 \u00b1 0.12. However, there was no significant difference between a logistic model derived from metabolic tumour volume and clinical features or the highest performing radiomic model.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Outcome prediction using pre-treatment FDG PET\/CT\u2013derived ML models is feasible in cHL patients. Further work is needed to determine optimum predictive thresholds for clinical use.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Key points<\/jats:title>\n                <jats:p><jats:italic>\u2022 A fixed threshold segmentation method led to more robust radiomic features.<\/jats:italic><\/jats:p>\n                <jats:p><jats:italic>\u2022 A radiomic-based model for predicting 2-year event-free survival in classical Hodgkin lymphoma patients is feasible.<\/jats:italic><\/jats:p>\n                <jats:p><jats:italic>\u2022 A predictive model based on ridge regression was the best performing model on our dataset.<\/jats:italic><\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s00330-022-09039-0","type":"journal-article","created":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T08:03:36Z","timestamp":1661414616000},"page":"7237-7247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Utility of pre-treatment FDG PET\/CT\u2013derived machine learning models for outcome prediction in classical Hodgkin lymphoma"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2681-9922","authenticated-orcid":false,"given":"Russell","family":"Frood","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matt","family":"Clark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cathy","family":"Burton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charalampos","family":"Tsoumpas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro F.","family":"Frangi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fergus","family":"Gleeson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chirag","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Scarsbrook","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,25]]},"reference":[{"issue":"1","key":"9039_CR1","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/s41572-020-0189-6","volume":"6","author":"JM Connors","year":"2020","unstructured":"Connors JM, Cozen W, Steidl C et al (2020) Hodgkin lymphoma. Nat Rev Dis Prim 6(1):61","journal-title":"Nat Rev Dis Prim"},{"issue":"2","key":"9039_CR2","doi-asserted-by":"publisher","first-page":"116","DOI":"10.3322\/caac.21438","volume":"68","author":"S Shanbhag","year":"2018","unstructured":"Shanbhag S, Ambinder RF (2018) Hodgkin lymphoma: a review and update on recent progress. CA Cancer J Clin 68(2):116\u2013132","journal-title":"CA Cancer J Clin"},{"issue":"1","key":"9039_CR3","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1111\/bjh.15616","volume":"184","author":"MA Spinner","year":"2019","unstructured":"Spinner MA, Varma G, Advani RH (2019) Modern principles in the management of nodular lymphocyte-predominant Hodgkin lymphoma. Br J Haematol 184(1):17\u201329","journal-title":"Br J Haematol"},{"issue":"1","key":"9039_CR4","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1111\/bjh.12878","volume":"166","author":"GA Follows","year":"2014","unstructured":"Follows GA, Ardeshna KM, Barrington SF et al (2014) Guidelines for the first line management of classical Hodgkin lymphoma. Br J Haematol 166(1):34\u201349","journal-title":"Br J Haematol"},{"issue":"5","key":"9039_CR5","doi-asserted-by":"publisher","first-page":"145","DOI":"10.3390\/cancers10050145","volume":"10","author":"S Kanoun","year":"2018","unstructured":"Kanoun S, Rossi C, Casasnovas O (2018) [18F]FDG-PET\/CT in Hodgkin lymphoma: current usefulness and perspectives. Cancers (Basel) 10(5):145","journal-title":"Cancers (Basel)"},{"issue":"4","key":"9039_CR6","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1111\/joim.12813","volume":"284","author":"TC El-Galaly","year":"2018","unstructured":"El-Galaly TC, Villa D, Gormsen LC, Baech J, Lo A, Cheah CY (2018) FDG-PET\/CT in the management of lymphomas: current status and future directions. J Intern Med 284(4):358\u2013376","journal-title":"J Intern Med"},{"key":"9039_CR7","unstructured":"SEER (2018) SEER cancer statistics review. In: 1975-2016."},{"issue":"21","key":"9039_CR8","doi-asserted-by":"publisher","first-page":"2493","DOI":"10.1200\/JCO.2015.65.4194","volume":"34","author":"G Hapgood","year":"2016","unstructured":"Hapgood G, Zheng Y, Sehn LH et al (2016) Evaluation of the risk of relapse in classical Hodgkin lymphoma at event-free survival time points and survival comparison with the general population in British Columbia. J Clin Oncol 34(21):2493\u20132500","journal-title":"J Clin Oncol"},{"issue":"10","key":"9039_CR9","doi-asserted-by":"publisher","first-page":"3198","DOI":"10.1007\/s00259-021-05233-2","volume":"48","author":"R Frood","year":"2021","unstructured":"Frood R, Burton C, Tsoumpas C et al (2021) Baseline PET\/CT imaging parameters for prediction of treatment outcome in Hodgkin and diffuse large B cell lymphoma: a systematic review. Eur J Nucl Med Mol Imaging 48(10):3198\u20133220","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"6","key":"9039_CR10","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1053\/j.sult.2010.10.001","volume":"31","author":"PE Kinahan","year":"2010","unstructured":"Kinahan PE, Fletcher JW (2010) Positron emission tomography-computed tomography standardized uptake values in clinical practice and assessing response to therapy. Semin Ultrasound CT MR 31(6):496\u2013505","journal-title":"Semin Ultrasound CT MR"},{"issue":"1","key":"9039_CR11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s13139-017-0493-6","volume":"52","author":"H-J Im","year":"2018","unstructured":"Im H-J, Bradshaw T, Solaiyappan M, Cho SY (2018) Current methods to define metabolic tumor volume in positron emission tomography: which one is better? Nucl Med Mol Imaging 52(1):5\u201315","journal-title":"Nucl Med Mol Imaging"},{"issue":"12","key":"9039_CR12","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","volume":"14","author":"P Lambin","year":"2017","unstructured":"Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14(12):749\u2013762","journal-title":"Nat Rev Clin Oncol"},{"issue":"1","key":"9039_CR13","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1038\/s41598-018-37197-z","volume":"9","author":"SA Milgrom","year":"2019","unstructured":"Milgrom SA, Elhalawani H, Lee J et al (2019) A PET radiomics model to predict refractory mediastinal Hodgkin lymphoma. Sci Rep 9(1):1322","journal-title":"Sci Rep"},{"issue":"10","key":"9039_CR14","doi-asserted-by":"publisher","first-page":"E559","DOI":"10.1097\/RLU.0000000000002732","volume":"44","author":"K-H Lue","year":"2019","unstructured":"Lue K-H, Wu Y-F, Liu S-H et al (2019) Prognostic value of pretreatment radiomic features of 18F-FDG PET in patients with Hodgkin lymphoma. Clin Nucl Med 44(10):E559\u2013E565","journal-title":"Clin Nucl Med"},{"key":"9039_CR15","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s41824-020-00078-8","volume":"4","author":"M Sollini","year":"2020","unstructured":"Sollini M, Kirienko M, Cavinato L et al (2020) Methodological framework for radiomics applications in Hodgkin\u2019s lymphoma. Eur J Hybrid Imaging 4:9","journal-title":"Eur J Hybrid Imaging"},{"key":"9039_CR16","doi-asserted-by":"publisher","first-page":"6347404","DOI":"10.1155\/2021\/6347404","volume":"2021","author":"Y Zhou","year":"2021","unstructured":"Zhou Y, Zhu Y, Chen Z, Li J, Sang S, Deng S (2021) Radiomic features of 18F-FDG PET in Hodgkin lymphoma are predictive of outcomes. Contrast Media Mol Imaging 2021:6347404","journal-title":"Contrast Media Mol Imaging"},{"issue":"13","key":"9039_CR17","doi-asserted-by":"publisher","first-page":"2790","DOI":"10.1007\/s00259-019-04495-1","volume":"46","author":"PJ Brown","year":"2019","unstructured":"Brown PJ, Zhong J, Frood R et al (2019) Prediction of outcome in anal squamous cell carcinoma using radiomic feature analysis of pre-treatment FDG PET-CT. Eur J Nucl Med Mol Imaging 46(13):2790\u20132799","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"1","key":"9039_CR18","doi-asserted-by":"publisher","first-page":"78.e9","DOI":"10.1016\/j.crad.2020.08.030","volume":"76","author":"J Zhong","year":"2021","unstructured":"Zhong J, Frood R, Brown P et al (2021) Machine learning-based FDG PET-CT radiomics for outcome prediction in larynx and hypopharynx squamous cell carcinoma. Clin Radiol 76(1):78.e9\u201378.e17","journal-title":"Clin Radiol"},{"key":"9039_CR19","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.neuroimage.2017.11.024","volume":"167","author":"J-P Fortin","year":"2018","unstructured":"Fortin J-P, Cullen N, Sheline YI et al (2018) Harmonization of cortical thickness measurements across scanners and sites. Neuroimage 167:104\u2013120","journal-title":"Neuroimage"},{"issue":"3","key":"9039_CR20","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44(3):837\u2013845","journal-title":"Biometrics"},{"issue":"9","key":"9039_CR21","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1158\/1055-9965.EPI-21-0103","volume":"30","author":"AM Berkman","year":"2021","unstructured":"Berkman AM, Andersen CR, Puthenpura V et al (2021) Impact of race, ethnicity, and socioeconomic status over time on the long-term survival of adolescent and young adult Hodgkin lymphoma survivors. Cancer Epidemiol Biomark Prev 30(9):1717\u20131725","journal-title":"Cancer Epidemiol Biomark Prev"},{"key":"9039_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2407-9-141","volume":"9","author":"P Pahwa","year":"2009","unstructured":"Pahwa P, Karunanayake CP, Spinelli JJ et al (2009) Ethnicity and incidence of Hodgkin lymphoma in Canadian population. BMC Cancer 9:1\u20139. https:\/\/doi.org\/10.1186\/1471-2407-9-141","journal-title":"BMC Cancer"},{"issue":"2","key":"9039_CR23","doi-asserted-by":"publisher","first-page":"207","DOI":"10.2967\/jnumed.118.210047","volume":"60","author":"J Mettler","year":"2019","unstructured":"Mettler J, M\u00fcller H, Voltin CA et al (2019) Metabolic tumor volume for response prediction in advanced-stage Hodgkin lymphoma. J Nucl Med 60(2):207\u2013211","journal-title":"J Nucl Med"},{"key":"9039_CR24","doi-asserted-by":"publisher","unstructured":"Tseng D, Rachakonda LP, Su Z et al (2012) Interim-treatment quantitative PET parameters predict progression and death among patients with Hodgkin\u2019s disease. Radiat Oncol. https:\/\/doi.org\/10.1186\/1748-717X-7-5","DOI":"10.1186\/1748-717X-7-5"},{"issue":"5","key":"9039_CR25","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1111\/ejh.12268","volume":"92","author":"R Gallicchio","year":"2014","unstructured":"Gallicchio R, Mansueto G, Simeon V et al (2014) F-18 FDG PET\/CT quantization parameters as predictors of outcome in patients with diffuse large B-cell lymphoma. Eur J Haematol 92(5):382\u2013389","journal-title":"Eur J Haematol"},{"issue":"6","key":"9039_CR26","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1111\/ejh.12467","volume":"94","author":"HJA Adams","year":"2015","unstructured":"Adams HJA, de Klerk JMH, Fijnheer R et al (2015) Prognostic superiority of the National Comprehensive Cancer Network International Prognostic Index over pretreatment whole-body volumetric-metabolic FDG-PET\/CT metrics in diffuse large B-cell lymphoma. Eur J Haematol 94(6):532\u2013539","journal-title":"Eur J Haematol"},{"issue":"3","key":"9039_CR27","doi-asserted-by":"publisher","first-page":"332","DOI":"10.2967\/jnumed.119.238923","volume":"62","author":"SF Barrington","year":"2021","unstructured":"Barrington SF, Zwezerijnen BGJC, de Vet HCW et al (2021) Automated segmentation of baseline metabolic total tumor burden in diffuse large B-cell lymphoma: which method is most successful? A study on behalf of the PETRA consortium. J Nucl Med 62(3):332\u2013337","journal-title":"J Nucl Med"},{"key":"9039_CR28","doi-asserted-by":"publisher","unstructured":"Driessen J, Zwezerijnen GJ, Sch\u00f6der H et al (2022) The impact of semi-automatic segmentation methods on metabolic tumor volume, intensity and dissemination radiomics in 18 F-FDG PET scans of patients with classical Hodgkin lymphoma. J Nucl Med. https:\/\/doi.org\/10.2967\/jnumed.121.263067","DOI":"10.2967\/jnumed.121.263067"},{"issue":"8","key":"9039_CR29","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.2967\/jnumed.117.199935","volume":"59","author":"F Orlhac","year":"2018","unstructured":"Orlhac F, Boughdad S, Philippe C et al (2018) A postreconstruction harmonization method for multicenter radiomic studies in PET. J Nucl Med 59(8):1321\u20131328","journal-title":"J Nucl Med"},{"issue":"2","key":"9039_CR30","doi-asserted-by":"publisher","first-page":"172","DOI":"10.2967\/jnumed.121.262464","volume":"63","author":"F Orlhac","year":"2022","unstructured":"Orlhac F, Eertink JJ, Cottereau AS et al (2022) A guide to ComBat harmonization of imaging biomarkers in multicenter studies. J Nucl Med 63(2):172\u2013179","journal-title":"J Nucl Med"},{"key":"9039_CR31","doi-asserted-by":"publisher","first-page":"204062072091449","DOI":"10.1177\/2040620720914490","volume":"11","author":"N Lang","year":"2020","unstructured":"Lang N, Crump M (2020) PET-adapted approaches to primary therapy for advanced Hodgkin lymphoma. Ther Adv Hematol 11:204062072091449","journal-title":"Ther Adv Hematol"},{"issue":"1","key":"9039_CR32","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s00330-019-06360-z","volume":"30","author":"JE Park","year":"2020","unstructured":"Park JE, Kim D, Kim HS et al (2020) Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement. Eur Radiol 30(1):523\u2013536","journal-title":"Eur Radiol"},{"issue":"1","key":"9039_CR33","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s00330-020-07108-w","volume":"31","author":"D Pinto dos Santos","year":"2021","unstructured":"Pinto dos Santos D, Dietzel M, Baessler B (2021) A decade of radiomics research: are images really data or just patterns in the noise? Eur Radiol 31(1):2\u20135","journal-title":"Eur Radiol"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-022-09039-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-022-09039-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-022-09039-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T12:21:09Z","timestamp":1663158069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-022-09039-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,25]]},"references-count":33,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["9039"],"URL":"https:\/\/doi.org\/10.1007\/s00330-022-09039-0","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,25]]},"assertion":[{"value":"15 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The scientific guarantor of this publication is Prof. Andrew Scarsbrook.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"Scarsbrook is an Associate Editor of <i>European Radiology<\/i> and a member of the Editorial Board for the journal. They have not taken part in the review or selection process of this article.The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No complex statistical methods were necessary for this paper.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was obtained from all subjects (patients) in this study.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"\u2022 retrospective\u2022 diagnostic or prognostic study\u2022 performed at one institution","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}