{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T09:54:05Z","timestamp":1790675645269,"version":"4.1.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100006775","name":"GE Healthcare","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006775","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["U10CA098543"],"award-info":[{"award-number":["U10CA098543"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U10CA098413"],"award-info":[{"award-number":["U10CA098413"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U10CA180886"],"award-info":[{"award-number":["U10CA180886"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U10CA180899"],"award-info":[{"award-number":["U10CA180899"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["CA29511"],"award-info":[{"award-number":["CA29511"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U24CA180803"],"award-info":[{"award-number":["U24CA180803"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006058","name":"St. Baldrick's Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006058","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EJNMMI Phys"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>For pediatric lymphoma, quantitative FDG PET\/CT imaging features such as metabolic tumor volume (MTV) are important for prognosis and risk stratification strategies. However, feature extraction is difficult and time-consuming in cases of high disease burden. The purpose of this study was to fully automate the measurement of PET imaging features in PET\/CT images of pediatric lymphoma.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p><jats:sup>18<\/jats:sup>F-FDG PET\/CT baseline images of 100 pediatric Hodgkin lymphoma patients were retrospectively analyzed. Two nuclear medicine physicians identified and segmented FDG avid disease using PET thresholding methods. Both PET and CT images were used as inputs to a three-dimensional patch-based, multi-resolution pathway convolutional neural network architecture, DeepMedic. The model was trained to replicate physician segmentations using an ensemble of three networks trained with 5-fold cross-validation. The maximum SUV (SUV<jats:sub>max<\/jats:sub>), MTV, total lesion glycolysis (TLG), surface-area-to-volume ratio (SA\/MTV), and a measure of disease spread (Dmax<jats:sub>patient<\/jats:sub>) were extracted from the model output. Pearson\u2019s correlation coefficient and relative percent differences were calculated between automated and physician-extracted features.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Median Dice similarity coefficient of patient contours between automated and physician contours was 0.86 (IQR 0.78\u20130.91). Automated SUV<jats:sub>max<\/jats:sub> values matched exactly the physician determined values in 81\/100 cases, with Pearson\u2019s correlation coefficient (<jats:italic>R<\/jats:italic>) of 0.95. Automated MTV was strongly correlated with physician MTV (<jats:italic>R<\/jats:italic> = 0.88), though it was slightly underestimated with a median (IQR) relative difference of \u2212 4.3% (\u2212 10.0\u20135.7%). Agreement of TLG was excellent (<jats:italic>R<\/jats:italic> = 0.94), with median (IQR) relative difference of \u2212 0.4% (\u2212 5.2\u20137.0%). Median relative percent differences were 6.8% (<jats:italic>R<\/jats:italic> = 0.91; IQR 1.6\u20134.3%) for SA\/MTV, and 4.5% (<jats:italic>R<\/jats:italic> = 0.51; IQR \u2212 7.5\u201340.9%) for Dmax<jats:sub>patient<\/jats:sub>, which was the most difficult feature to quantify automatically.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>An automated method using an ensemble of multi-resolution pathway 3D CNNs was able to quantify PET imaging features of lymphoma on baseline FDG PET\/CT images with excellent agreement to reference physician PET segmentation. Automated methods with faster throughput for PET quantitation, such as MTV and TLG, show promise in more accessible clinical and research applications.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s40658-020-00346-3","type":"journal-article","created":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T12:05:22Z","timestamp":1607947522000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Automated quantification of baseline imaging PET metrics on FDG PET\/CT images of pediatric Hodgkin lymphoma patients"],"prefix":"10.1186","volume":"7","author":[{"given":"Amy J.","family":"Weisman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inki","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathleen M.","family":"McCarten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandy","family":"Kessel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cindy L.","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kara M.","family":"Kelly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Jeraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve Y.","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9549-7002","authenticated-orcid":false,"given":"Tyler J.","family":"Bradshaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,12,14]]},"reference":[{"key":"346_CR1","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s00259-009-1276-9","volume":"37","author":"R Riad","year":"2010","unstructured":"Riad R, Omar W, Kotb M, Hafez M, Sidhom I, Zamzam M, et al. Role of PET\/CT in malignant pediatric lymphoma. Eur J Nucl Med Mol Imaging. 2010;37:319\u201329. https:\/\/doi.org\/10.1007\/s00259-009-1276-9.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"346_CR2","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3322\/caac.21219","volume":"64","author":"E Ward","year":"2014","unstructured":"Ward E, DeSantis C, Robbins A, Kohler B, Jemal A. Childhood and adolescent cancer statistics, 2014. CA Cancer J Clin. 2014;64:83\u2013103.","journal-title":"CA Cancer J Clin."},{"key":"346_CR3","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.1182\/blood-2008-10-184143","volume":"114","author":"CL Schwartz","year":"2009","unstructured":"Schwartz CL, Constine LS, Villaluna D, London WB, Hutchison RE, Sposto R, et al. A risk-adapted, response-based approach using ABVE-PC for children and adolescents with intermediate- and high-risk Hodgkin lymphoma: the results of P9425. Blood. 2009;114:2051\u20139. https:\/\/doi.org\/10.1182\/blood-2008-10-184143.","journal-title":"Blood."},{"key":"346_CR4","doi-asserted-by":"publisher","unstructured":"Friedman DL, Chen L, Wolden S, Buxton A, McCarten K, FitzGerald TJ, et al. Dose-intensive response-based chemotherapy and radiation therapy for children and adolescents with newly diagnosed intermediate-risk Hodgkin lymphoma: a report from the Children's Oncology Group Study AHOD0031. J Clin Oncol. 2014;32:3651-8. https:\/\/doi.org\/10.1200\/jco.2013.52.5410..","DOI":"10.1200\/jco.2013.52.5410."},{"key":"346_CR5","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1111\/bjh.16014","volume":"187","author":"KM Kelly","year":"2019","unstructured":"Kelly KM, Cole PD, Pei Q, Bush R, Roberts KB, Hodgson DC, et al. Response-adapted therapy for the treatment of children with newly diagnosed high risk Hodgkin lymphoma (AHOD0831): a report from the Children's Oncology Group. Br J Haematol. 2019;187:39\u201348. https:\/\/doi.org\/10.1111\/bjh.16014.","journal-title":"Br J Haematol."},{"key":"346_CR6","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1200\/jco.2013.54.8800","volume":"32","author":"BD Cheson","year":"2014","unstructured":"Cheson BD, Fisher RI, Barrington SF, Cavalli F, Schwartz LH, Zucca E, et al. Recommendations for initial evaluation, staging, and response assessment of Hodgkin and non-Hodgkin lymphoma: the Lugano classification. J Clin Oncol. 2014;32:3059\u201368. https:\/\/doi.org\/10.1200\/jco.2013.54.8800.","journal-title":"J Clin Oncol."},{"key":"346_CR7","doi-asserted-by":"publisher","unstructured":"Song M-K, Chung J-S, Lee J-J, Jeong SY, Lee S-M, Hong J-S, et al. Metabolic tumor volume by positron emission tomography\/computed tomography as a clinical parameter to determine therapeutic modality for early stage Hodgkin's lymphoma. Cancer Sci. 2013;104:1656\u201361. https:\/\/doi.org\/10.1111\/cas.12282.","DOI":"10.1111\/cas.12282"},{"key":"346_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1007\/s00259-014-2783-x","volume":"41","author":"S Kanoun","year":"2014","unstructured":"Kanoun S, Rossi C, Berriolo-Riedinger A, Dygai-Cochet I, Cochet A, Humbert O, et al. Baseline metabolic tumour volume is an independent prognostic factor in Hodgkin lymphoma. Eur J Nuclear Med Mol Imaging. 2014;41:1735\u201343. https:\/\/doi.org\/10.1007\/s00259-014-2783-x.","journal-title":"Eur J Nuclear Med Mol Imaging."},{"key":"346_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/1748-717X-7-5","volume":"7","author":"D Tseng","year":"2012","unstructured":"Tseng D, Rachakonda LP, Su Z, Advani R, Horning S, Hoppe RT, et al. Interim-treatment quantitative PET parameters predict progression and death among patients with Hodgkin's disease. Radiat Oncol. 2012;7:5. https:\/\/doi.org\/10.1186\/1748-717X-7-5.","journal-title":"Radiat Oncol."},{"key":"346_CR10","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1182\/blood-2017-07-795476","volume":"131","author":"AS Cottereau","year":"2018","unstructured":"Cottereau AS, Versari A, Loft A, Casasnovas O, Bellei M, Ricci R, et al. Prognostic value of baseline metabolic tumor volume in early-stage Hodgkin lymphoma in the standard arm of the H10 trial. Blood. 2018;131:1456\u201363. https:\/\/doi.org\/10.1182\/blood-2017-07-795476.","journal-title":"Blood."},{"key":"346_CR11","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1182\/blood-2017-04-773838","volume":"131","author":"M Akhtari","year":"2018","unstructured":"Akhtari M, Milgrom SA, Pinnix CC, Reddy JP, Dong W, Smith GL, et al. Reclassifying patients with early-stage Hodgkin lymphoma based on functional radiographic markers at presentation. Blood. 2018;131:84\u201394. https:\/\/doi.org\/10.1182\/blood-2017-04-773838.","journal-title":"Blood."},{"key":"346_CR12","doi-asserted-by":"publisher","first-page":"2196","DOI":"10.1182\/blood-2017-06-788877","volume":"130","author":"AJ Moskowitz","year":"2017","unstructured":"Moskowitz AJ, Sch\u00f6der H, Gavane S, Thoren KL, Fleisher M, Yahalom J, et al. Prognostic significance of baseline metabolic tumor volume in relapsed and refractory Hodgkin lymphoma. Blood. 2017;130:2196\u2013203. https:\/\/doi.org\/10.1182\/blood-2017-06-788877.","journal-title":"Blood."},{"key":"346_CR13","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1186\/s12885-018-4432-4","volume":"18","author":"JMM Rogasch","year":"2018","unstructured":"Rogasch JMM, Hundsdoerfer P, Hofheinz F, Wedel F, Schatka I, Amthauer H, et al. Pretherapeutic FDG-PET total metabolic tumor volume predicts response to induction therapy in pediatric Hodgkin\u2019s lymphoma. BMC Cancer. 2018;18:521. https:\/\/doi.org\/10.1186\/s12885-018-4432-4.","journal-title":"BMC Cancer."},{"key":"346_CR14","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s12149-011-0539-2","volume":"26","author":"P Sharma","year":"2012","unstructured":"Sharma P, Gupta A, Patel C, Bakhshi S, Malhotra A, Kumar R. Pediatric lymphoma: metabolic tumor burden as a quantitative index for treatment response evaluation. Ann Nucl Med. 2012;26:58\u201366. https:\/\/doi.org\/10.1007\/s12149-011-0539-2.","journal-title":"Ann Nucl Med."},{"key":"346_CR15","doi-asserted-by":"publisher","unstructured":"Burggraaff CN, Rahman F, Ka\u00dfner I, Pieplenbosch S, Barrington SF, Jauw YWS, et al. Optimizing workflows for fast and reliable metabolic tumor volume measurements in diffuse large B cell lymphoma. Mol Imaging Biol. 2020;22:1102\u201310. https:\/\/doi.org\/10.1007\/s11307-020-01474-z.","DOI":"10.1007\/s11307-020-01474-z"},{"key":"346_CR16","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1097\/MNM.0b013e3282eff2d5","volume":"28","author":"JM Zijlstra","year":"2007","unstructured":"Zijlstra JM, Comans EF, van Lingen A, Hoekstra OS, Gundy CM, Willem Coebergh J, et al. FDG PET in lymphoma: the need for standardization of interpretation. An observer variation study. Nucl Med Commun. 2007;28:798\u2013803. https:\/\/doi.org\/10.1097\/MNM.0b013e3282eff2d5.","journal-title":"Nucl Med Commun."},{"key":"346_CR17","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1109\/ISBI.2017.7950495","volume-title":"Automated 3D lymphoma lesion segmentation from PET\/CT characteristics. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","author":"\u00c9 Grossiord","year":"2017","unstructured":"Grossiord \u00c9, Talbot H, Passat N, Meignan M, Najman L. Automated 3D lymphoma lesion segmentation from PET\/CT characteristics. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017); 2017. p. 174\u20138."},{"key":"346_CR18","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.compmedimag.2016.11.008","volume":"60","author":"L Bi","year":"2017","unstructured":"Bi L, Kim J, Kumar A, Wen L, Feng D, Fulham M. Automatic detection and classification of regions of FDG uptake in whole-body PET-CT lymphoma studies. Comput Med Imaging Graph. 2017;60:3\u201310. https:\/\/doi.org\/10.1016\/j.compmedimag.2016.11.008.","journal-title":"Comput Med Imaging Graph."},{"key":"346_CR19","doi-asserted-by":"publisher","unstructured":"Li H, Jiang H, Li S, Wang M, Wang Z, Lu G, et al. DenseX-Net: An End-to-End Model for Lymphoma Segmentation in Whole-body PET\/CT Images. IEEE Access. 2020;8:8004\u201318. https:\/\/doi.org\/10.1109\/ACCESS.2019.2963254.","DOI":"10.1109\/ACCESS.2019.2963254"},{"key":"346_CR20","doi-asserted-by":"publisher","first-page":"e200016","DOI":"10.1148\/ryai.2020200016","volume":"2","author":"AJ Weisman","year":"2020","unstructured":"Weisman AJ, Kieler MW, Perlman SB, Hutchings M, Jeraj R, Kostakoglu L, et al. Convolutional neural networks for automated PET\/CT detection of diseased lymph node burden in patients with lymphoma. Radiology. 2020;2:e200016. https:\/\/doi.org\/10.1148\/ryai.2020200016.","journal-title":"Radiology"},{"key":"346_CR21","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1148\/radiol.2019191114","volume":"294","author":"L Sibille","year":"2019","unstructured":"Sibille L, Seifert R, Avramovic N, Vehren T, Spottiswoode B, Zuehlsdorff S, et al. 18F-FDG PET\/CT uptake classification in lymphoma and lung cancer by using deep convolutional neural networks. Radiology. 2019;294:445\u201352. https:\/\/doi.org\/10.1148\/radiol.2019191114.","journal-title":"Radiology"},{"key":"346_CR22","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","volume":"36","author":"K Kamnitsas","year":"2017","unstructured":"Kamnitsas K, Ledig C, Newcombe VF, Simpson JP, Kane AD, Menon DK, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal. 2017;36:61\u201378. https:\/\/doi.org\/10.1016\/j.media.2016.10.004.","journal-title":"Med Image Anal."},{"key":"346_CR23","doi-asserted-by":"publisher","first-page":"40","DOI":"10.2967\/jnumed.119.229450","volume":"61","author":"AS Cottereau","year":"2020","unstructured":"Cottereau AS, Nioche C, Dirand AS, Clerc J, Morschhauser F, Casasnovas O, et al. (18)F-FDG PET dissemination features in diffuse large B-cell lymphoma are predictive of outcome. J Nucl Med. 2020;61:40\u20135. https:\/\/doi.org\/10.2967\/jnumed.119.229450.","journal-title":"J Nucl Med."},{"key":"346_CR24","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1007\/s00259-018-4041-0","volume":"45","author":"P Decazes","year":"2018","unstructured":"Decazes P, Becker S, Toledano MN, Vera P, Desbordes P, Jardin F, et al. Tumor fragmentation estimated by volume surface ratio of tumors measured on 18F-FDG PET\/CT is an independent prognostic factor of diffuse large B-cell lymphoma. Eur J Nucl Med Mol Imaging. 2018;45:1672\u20139. https:\/\/doi.org\/10.1007\/s00259-018-4041-0.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"346_CR25","doi-asserted-by":"publisher","unstructured":"Hu H, Decazes P, Vera P, Li H, Ruan S. Detection and segmentation of lymphomas in 3D PET images via clustering with entropy-based optimization strategy. Int J Comput Assist Radiol Surg. 2019. https:\/\/doi.org\/10.1007\/s11548-019-02049-2.","DOI":"10.1007\/s11548-019-02049-2"}],"container-title":["EJNMMI Physics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40658-020-00346-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40658-020-00346-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40658-020-00346-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T12:58:06Z","timestamp":1607950686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ejnmmiphys.springeropen.com\/articles\/10.1186\/s40658-020-00346-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["346"],"URL":"https:\/\/doi.org\/10.1186\/s40658-020-00346-3","relation":{},"ISSN":["2197-7364"],"issn-type":[{"value":"2197-7364","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]},"assertion":[{"value":"5 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The protocol was reviewed and approved by the National Cancer Institute and the Pediatric Central Institutional Review Board or the institutional review boards of the participating institutions. Written informed consent was obtained from patients, parents, and\/or guardians in accordance with the Declaration of Helsinki as required by government regulations.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Author R.J. is a co-founder of AIQ solutions.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"76"}}