{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T18:17:35Z","timestamp":1769019455765,"version":"3.49.0"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2022,4,18]],"date-time":"2022-04-18T00:00:00Z","timestamp":1650240000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Mitteldeutsche Kinderkrebsforschung"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Introduction<\/jats:title>\n<jats:p>The automatic classification of lymphoma lesions in PET is a main topic of ongoing research. An automatic algorithm would enable the swift evaluation of PET parameters, like texture and heterogeneity markers, concerning their prognostic value for patients outcome in large datasets. Moreover, the determination of the metabolic tumor volume would be facilitated. The aim of our study was the development and evaluation of an automatic algorithm for segmentation and classification of lymphoma lesions in PET.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>Pre-treatment PET scans from 60 Hodgkin lymphoma patients from the EuroNet-PHL-C1 trial were evaluated. A watershed algorithm was used for segmentation. For standardization of the scan length, an automatic cropping algorithm was developed. All segmented volumes were manually classified into one of 14 categories. The random forest method and a nested cross-validation was used for automatic classification and evaluation.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Overall, 853 volumes were segmented and classified. 203\/246 tumor lesions and 554\/607 non-tumor volumes were classified correctly by the automatic algorithm, corresponding to a sensitivity, a specificity, a positive and a negative predictive value of 83%, 91%, 79% and 93%. In 44\/60 (73%) patients, all tumor lesions were correctly classified. In ten out of the 16 patients with misclassified tumor lesions, only one false-negative tumor lesion occurred. The automatic classification of focal gastrointestinal uptake, brown fat tissue and composed volumes consisting of more than one tissue was challenging.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Our algorithm, trained on a small number of patients and on PET information only, showed a good performance and is suitable for automatic lymphoma classification.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0267275","type":"journal-article","created":{"date-parts":[[2022,4,18]],"date-time":"2022-04-18T17:35:55Z","timestamp":1650303355000},"page":"e0267275","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["Automatic classification of lymphoma lesions in FDG-PET\u2013Differentiation between tumor and non-tumor uptake"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6066-8753","authenticated-orcid":true,"given":"Thomas W","family":"Georgi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Axel","family":"Zieschank","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Kornrumpf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Kurch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osama","family":"Sabri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"K\u00f6rholz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8205-8665","authenticated-orcid":true,"given":"Christine","family":"Mauz-K\u00f6rholz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Regine","family":"Kluge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Posch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2022,4,18]]},"reference":[{"key":"pone.0267275.ref001","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s00259-017-3690-8","article-title":"FDG PET for therapy monitoring in Hodgkin and non-Hodgkin lymphomas","volume":"44","author":"SF Barrington","year":"2017","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"pone.0267275.ref002","doi-asserted-by":"crossref","first-page":"2024","DOI":"10.1200\/JCO.2017.76.8093","article-title":"Positron Emission Tomography-Guided Therapy of Aggressive Non-Hodgkin Lymphomas (PETAL): A Multicenter, Randomized Phase III Trial","volume":"36","author":"U D\u00fchrsen","year":"2018","journal-title":"J Clin Oncol"},{"key":"pone.0267275.ref003","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1080\/10428190903040048","article-title":"Report on the First International Workshop on interim-PET scan in lymphoma","volume":"50","author":"M Meignan","year":"2009","journal-title":"Leuk Lymphoma"},{"key":"pone.0267275.ref004","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1080\/10428194.2017.1298752","article-title":"Report of the 6th International Workshop on PET in lymphoma","volume":"58","author":"C Nanni","year":"2017","journal-title":"Leuk Lymphoma"},{"key":"pone.0267275.ref005","doi-asserted-by":"crossref","first-page":"1844","DOI":"10.1200\/JCO.2010.32.5225","article-title":"Role of functional imaging in the management of lymphoma","volume":"29","author":"BD Cheson","year":"2011","journal-title":"J Clin Oncol"},{"key":"pone.0267275.ref006","doi-asserted-by":"crossref","first-page":"3059","DOI":"10.1200\/JCO.2013.54.8800","article-title":"Recommendations for initial evaluation, staging, and response assessment of Hodgkin and non-Hodgkin lymphoma: the Lugano classification","volume":"32","author":"BD Cheson","year":"2014","journal-title":"J Clin Oncol"},{"key":"pone.0267275.ref007","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1016\/S0140-6736(12)60035-X","article-title":"Hodgkin\u2019s lymphoma in adults","volume":"380","author":"W Townsend","year":"2012","journal-title":"Lancet"},{"key":"pone.0267275.ref008","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1016\/S0140-6736(12)60605-9","article-title":"Non-Hodgkin lymphoma","volume":"380","author":"KR Shankland","year":"2012","journal-title":"Lancet"},{"key":"pone.0267275.ref009","doi-asserted-by":"crossref","first-page":"2975","DOI":"10.1200\/JCO.2014.59.4853","article-title":"Pediatric Hodgkin Lymphoma","volume":"33","author":"C Mauz-K\u00f6rholz","year":"2015","journal-title":"J Clin Oncol"},{"key":"pone.0267275.ref010","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/j.ijrobp.2019.02.001","article-title":"The Optimal Use of Imaging in Radiation Therapy for Lymphoma: Guidelines from the International Lymphoma Radiation Oncology Group (ILROG)","volume":"104","author":"NG Mikhaeel","year":"2019","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"pone.0267275.ref011","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1007\/s00259-020-05080-7","article-title":"Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET\/CT for total metabolic tumour volume prediction using a convolutional neural network","volume":"48","author":"P Blanc-Durand","year":"2021","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"pone.0267275.ref012","doi-asserted-by":"crossref","first-page":"30","DOI":"10.2967\/jnumed.120.242412","article-title":"Deep-Learning 18 F-FDG Uptake Classification Enables Total Metabolic Tumor Volume Estimation in Diffuse Large B-Cell Lymphoma","volume":"62","author":"N Capobianco","year":"2021","journal-title":"J Nucl Med"},{"key":"pone.0267275.ref013","doi-asserted-by":"crossref","first-page":"332","DOI":"10.2967\/jnumed.119.238923","article-title":"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","volume":"62","author":"SF Barrington","year":"2021","journal-title":"J Nucl Med"},{"key":"pone.0267275.ref014","doi-asserted-by":"crossref","first-page":"3198","DOI":"10.1007\/s00259-021-05233-2","article-title":"Baseline PET\/CT imaging parameters for prediction of treatment outcome in Hodgkin and diffuse large B cell lymphoma: a systematic review","volume":"48","author":"R Frood","year":"2021","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"pone.0267275.ref015","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.ymeth.2020.06.020","article-title":"Functional imaging using radiomic features in assessment of lymphoma","volume":"188","author":"ME Mayerhoefer","year":"2021","journal-title":"Methods"},{"key":"pone.0267275.ref016","doi-asserted-by":"crossref","first-page":"e041252","DOI":"10.1136\/bmjopen-2020-041252","article-title":"Additional value of volumetric and texture analysis on FDG PET assessment in paediatric Hodgkin lymphoma: an Italian multicentric study protocol","volume":"11","author":"E Lopci","year":"2021","journal-title":"BMJ Open"},{"key":"pone.0267275.ref017","doi-asserted-by":"crossref","first-page":"e559","DOI":"10.1097\/RLU.0000000000002732","article-title":"Prognostic Value of Pretreatment Radiomic Features of 18F-FDG PET in Patients With Hodgkin Lymphoma","volume":"44","author":"KH Lue","year":"2019","journal-title":"Clin Nucl Med"},{"key":"pone.0267275.ref018","unstructured":"https:\/\/clinicaltrials.gov\/ct2\/show\/NCT00433459. accessed on 24.01.2022"},{"key":"pone.0267275.ref019","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1055\/s-0033-1354416","article-title":"The EuroNet Paediatric Hodgkin Network\u2014modern imaging data management for real time central review in multicentre trials","volume":"225","author":"L Kurch","year":"2013","journal-title":"Klin Padiatr"},{"key":"pone.0267275.ref020","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/34.87344","article-title":"Watersheds in digital spaces: an efficient algorithm based on immersion simulations","volume":"06","author":"L Vincent","year":"1991","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"pone.0267275.ref021","doi-asserted-by":"crossref","first-page":"628179","DOI":"10.3389\/fmed.2021.628179","article-title":"Evaluation of an Automatic Classification Algorithm Using Convolutional Neural Networks in Oncological Positron Emission Tomography","volume":"8","author":"P Pinochet","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"pone.0267275.ref022","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"1","author":"Leo Breiman","year":"2001","journal-title":"Machine learning"},{"key":"pone.0267275.ref023","doi-asserted-by":"crossref","first-page":"3913","DOI":"10.1038\/s41598-018-22319-4","article-title":"Radiomics Features Differentiate Between Normal and Tumoral High-FDG Uptake","volume":"8","author":"CY Hsu","year":"2018","journal-title":"Sci Rep"},{"key":"pone.0267275.ref024","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/s11307-006-0075-y","article-title":"Standardized uptake value atlas: characterization of physiological 2-deoxy-2-[18F]fluoro-D-glucose uptake in normal tissues","volume":"9","author":"Y Wang","year":"2007","journal-title":"Mol Imaging Biol"},{"key":"pone.0267275.ref025","doi-asserted-by":"crossref","first-page":"670","DOI":"10.3109\/0284186X.2010.550933","article-title":"Is there a common SUV threshold in oncological FDG PET\/CT, at least for some common indications? A retrospective study","volume":"50","author":"NC Nguyen","year":"2011","journal-title":"Acta Oncol"},{"key":"pone.0267275.ref026","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13550-020-00744-9","article-title":"Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET","volume":"11","author":"E Pfaehler","year":"2021","journal-title":"EJNMMI Res"},{"key":"pone.0267275.ref027","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1148\/radiol.2019191114","article-title":"18 F-FDG PET\/CT Uptake Classification in Lymphoma and Lung Cancer by Using Deep Convolutional Neural Networks","volume":"294","author":"L Sibille","year":"2020","journal-title":"Radiology"},{"key":"pone.0267275.ref028","unstructured":"https:\/\/clinicaltrials.gov\/ct2\/show\/NCT02684708. accessed on 24.01.2022"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0267275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,18]],"date-time":"2022-04-18T17:36:34Z","timestamp":1650303394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0267275"}},"subtitle":[],"editor":[{"given":"Domenico","family":"Albano","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,4,18]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0267275","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,18]]}}}