{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:23:45Z","timestamp":1774351425110,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Funda\u00e7\u00e3o D. Anna de Sommer Champalimaud e Dr. Carlos Montez Champalimaud"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The objective is to assess the performance of seven semiautomatic and two fully automatic segmentation methods on [<jats:sup>18<\/jats:sup>F]FDG PET\/CT lymphoma images and evaluate their influence on tumor quantification. All lymphoma lesions identified in 65 whole-body [<jats:sup>18<\/jats:sup>F]FDG PET\/CT staging images were segmented by two experienced observers using manual and semiautomatic methods. Semiautomatic segmentation using absolute and relative thresholds, <jats:italic>k<\/jats:italic>-means and Bayesian clustering, and a self-adaptive configuration (SAC) of <jats:italic>k<\/jats:italic>-means and Bayesian was applied. Three state-of-the-art deep learning\u2013based segmentations methods using a 3D U-Net architecture were also applied. One was semiautomatic and two were fully automatic, of which one is publicly available. Dice coefficient (DC) measured segmentation overlap, considering manual segmentation the ground truth. Lymphoma lesions were characterized by 31 features. Intraclass correlation coefficient (ICC) assessed features agreement between different segmentation methods. Nine hundred twenty [<jats:sup>18<\/jats:sup>F]FDG-avid lesions were identified. The SAC Bayesian method achieved the highest median intra-observer DC (0.87). Inter-observers\u2019 DC was higher for SAC Bayesian than manual segmentation (0.94 vs 0.84, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). Semiautomatic deep learning\u2013based median DC was promising (0.83 (Obs1), 0.79 (Obs2)). Threshold-based methods and publicly available 3D U-Net gave poorer results (0.56\u2009\u2264\u2009DC\u2009\u2264\u20090.68). Maximum, mean, and peak standardized uptake values, metabolic tumor volume, and total lesion glycolysis showed excellent agreement (ICC\u2009\u2265\u20090.92) between manual and SAC Bayesian segmentation methods. The SAC Bayesian classifier is more reproducible and produces similar lesion features compared to manual segmentation, giving the best concordant results of all other methods. Deep learning\u2013based segmentation can achieve overall good segmentation results but failed in few patients impacting patients\u2019 clinical evaluation.\n<\/jats:p>","DOI":"10.1007\/s10278-023-00823-y","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T18:02:11Z","timestamp":1681495331000},"page":"1864-1876","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Evaluation of Semiautomatic and Deep Learning\u2013Based Fully Automatic Segmentation Methods on [18F]FDG PET\/CT Images from Patients with Lymphoma: Influence on Tumor Characterization"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4320-8437","authenticated-orcid":false,"given":"Cl\u00e1udia S.","family":"Constantino","sequence":"first","affiliation":[]},{"given":"S\u00f3nia","family":"Leoc\u00e1dio","sequence":"additional","affiliation":[]},{"given":"Francisco P. M.","family":"Oliveira","sequence":"additional","affiliation":[]},{"given":"Mariana","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Carla","family":"Oliveira","sequence":"additional","affiliation":[]},{"given":"Joana C.","family":"Castanheira","sequence":"additional","affiliation":[]},{"given":"\u00c2ngelo","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Sofia","family":"Vaz","sequence":"additional","affiliation":[]},{"given":"Ricardo","family":"Teixeira","sequence":"additional","affiliation":[]},{"given":"Manuel","family":"Neves","sequence":"additional","affiliation":[]},{"given":"Paulo","family":"L\u00facio","sequence":"additional","affiliation":[]},{"given":"Cristina","family":"Jo\u00e3o","sequence":"additional","affiliation":[]},{"given":"Durval C.","family":"Costa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"823_CR1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1053\/j.semnuclmed.2017.09.001","volume":"48","author":"TC El-Galaly","year":"2018","unstructured":"El-Galaly TC, Gormsen LC, Hutchings M. PET\/CT for Staging; Past, Present, and Future. Semin Nucl Med. 2018;48:4\u201316.","journal-title":"Semin Nucl Med."},{"key":"823_CR2","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1053\/j.semnuclmed.2017.09.007","volume":"48","author":"BD Cheson","year":"2018","unstructured":"Cheson BD. PET\/CT in Lymphoma: Current Overview and Future Directions. Semin Nucl Med. 2018;48:76\u201381.","journal-title":"Semin Nucl Med."},{"key":"823_CR3","doi-asserted-by":"crossref","unstructured":"Kim H, Yoo IR, Boo SH, Park HL, O JH, Kim SH. Prognostic Value of Pre- and Post-Treatment FDG PET\/CT Parameters in Small Cell Lung Cancer Patients. Nucl Med Mol Imaging. 2018;52:31\u20138.","DOI":"10.1007\/s13139-017-0490-9"},{"key":"823_CR4","doi-asserted-by":"publisher","first-page":"20170508","DOI":"10.1259\/bjr.20170508","volume":"91","author":"H Zaidi","year":"2018","unstructured":"Zaidi H, Karakatsanis N. Towards enhanced PET quantification in clinical oncology. Br J Radiol. 2018;91:20170508.","journal-title":"Br J Radiol."},{"key":"823_CR5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0225959","volume":"14","author":"W Wen","year":"2019","unstructured":"Wen W, Xuan D, Hu Y, Li X, Liu L, Xu D. Prognostic value of maximum standard uptake value, metabolic tumor volume, and total lesion glycolysis of positron emission tomography\/computed tomography in patients with breast cancer: A systematic review and meta-analysis. PLoS One. 2019;14:e0225959.","journal-title":"PLoS One."},{"key":"823_CR6","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 C-A, Baues C, Klaeser B, Moccia A, et al. Metabolic Tumor Volume for Response Prediction in Advanced-Stage Hodgkin Lymphoma. J Nucl Med. 2019;60:207\u201311.","journal-title":"J Nucl Med."},{"key":"823_CR7","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, Frangi AF, Gleeson F, Patel C, et al. 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. 2021;48:3198\u2013220.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"823_CR8","doi-asserted-by":"publisher","first-page":"221","DOI":"10.3324\/haematol.2020.263194","volume":"107","author":"C Rossi","year":"2022","unstructured":"Rossi C, Tosolini M, Gravelle P, Pericart S, Kanoun S, Evrard S, et al. Baseline SUVmax is related to tumor cell proliferation and patient outcome in follicular lymphoma. Haematologica. 2022;107:221\u201330.","journal-title":"Haematologica."},{"key":"823_CR9","doi-asserted-by":"publisher","first-page":"40","DOI":"10.2967\/jnumed.119.229450","volume":"61","author":"A-S Cottereau","year":"2020","unstructured":"Cottereau A-S, Nioche C, Dirand A-S, Clerc J, Morschhauser F, Casasnovas O, et al. 18F-FDG PET Dissemination Features in Diffuse Large B-Cell Lymphoma Are Predictive of Outcome. J Nucl Med. 2020;61:40\u20135.","journal-title":"J Nucl Med."},{"key":"823_CR10","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1007\/s00259-021-05480-3","volume":"49","author":"JJ Eertink","year":"2022","unstructured":"Eertink JJ, van de Brug T, Wiegers SE, Zwezerijnen GJC, Pfaehler EAG, Lugtenburg PJ, et al. 18F-FDG PET baseline radiomics features improve the prediction of treatment outcome in diffuse large B-cell lymphoma. Eur J Nucl Med Mol Imaging. 2022;49:932\u201342.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"823_CR11","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.media.2017.12.007","volume":"44","author":"M Hatt","year":"2018","unstructured":"Hatt M, Laurent B, Ouahabi A, Fayad H, Tan S, Li L, et al. The first MICCAI challenge on PET tumor segmentation. Med Image Anal. 2018;44:177\u201395.","journal-title":"Med Image Anal."},{"key":"823_CR12","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1007\/s00259-020-05080-7","volume":"48","author":"P Blanc-Durand","year":"2021","unstructured":"Blanc-Durand P, J\u00e9gou S, Kanoun S, Berriolo-Riedinger A, Bodet-Milin C, Kraeber-Bod\u00e9r\u00e9 F, et al. 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. Eur J Nucl Med Mol Imaging. 2021;48:1362\u201370.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"823_CR13","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abb6bd","volume":"65","author":"AJ Weisman","year":"2020","unstructured":"Weisman AJ, Kieler MW, Perlman S, Hutchings M, Jeraj R, Kostakoglu L, et al. Comparison of 11 automated PET segmentation methods in lymphoma. Phys Med Biol. 2020;65:235019.","journal-title":"Phys Med Biol."},{"key":"823_CR14","doi-asserted-by":"crossref","unstructured":"Boellaard R, O\u2019Doherty MJ, Weber WA, Mottaghy FM, Lonsdale MN, Stroobants SG, et al. FDG PET and PET\/CT: EANM procedure guidelines for tumour PET imaging: version 1.0. Eur J Nucl Med Mol Imaging. 2010;37:181\u2013200.","DOI":"10.1007\/s00259-009-1297-4"},{"key":"823_CR15","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1007\/s00259-018-3953-z","volume":"45","author":"H Ilyas","year":"2018","unstructured":"Ilyas H, Mikhaeel NG, Dunn JT, Rahman F, M\u00f8ller H, Smith D, et al. Defining the optimal method for measuring baseline metabolic tumour volume in diffuse large B cell lymphoma. Eur J Nucl Med Mol Imaging. 2018;45:1142\u201354.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"823_CR16","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.","journal-title":"Blood."},{"key":"823_CR17","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1182\/blood-2017-07-795476","volume":"131","author":"A-S Cottereau","year":"2018","unstructured":"Cottereau A-S, 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.","journal-title":"Blood."},{"key":"823_CR18","doi-asserted-by":"crossref","unstructured":"Boellaard R, Delgado-Bolton R, Oyen WJG, Giammarile F, Tatsch K, Eschner W, et al. FDG PET\/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015;42:328\u201354.","DOI":"10.1007\/s00259-014-2961-x"},{"key":"823_CR19","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 Nucl Med Mol Imaging. 2014;41:1735\u201343.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"823_CR20","doi-asserted-by":"publisher","first-page":"3801","DOI":"10.1158\/1078-0432.CCR-15-2825","volume":"22","author":"A-S Cottereau","year":"2016","unstructured":"Cottereau A-S, Lanic H, Mareschal S, Meignan M, Vera P, Tilly H, et al. Molecular Profile and FDG-PET\/CT Total Metabolic Tumor Volume Improve Risk Classification at Diagnosis for Patients with Diffuse Large B-Cell Lymphoma. Clin Cancer Res. 2016;22:3801\u20139.","journal-title":"Clin Cancer Res."},{"key":"823_CR21","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1093\/annonc\/mdw011","volume":"27","author":"AS Cottereau","year":"2016","unstructured":"Cottereau AS, Becker S, Broussais F, Casasnovas O, Kanoun S, Roques M, et al. Prognostic value of baseline total metabolic tumor volume (TMTV0) measured on FDG-PET\/CT in patients with peripheral T-cell lymphoma (PTCL). Ann Oncol. 2016;27:719\u201324.","journal-title":"Ann Oncol."},{"key":"823_CR22","doi-asserted-by":"publisher","first-page":"2165","DOI":"10.1007\/s00259-010-1423-3","volume":"37","author":"H Zaidi","year":"2010","unstructured":"Zaidi H, El Naqa I. PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques. Eur J Nucl Med Mol Imaging. 2010;37:2165\u201387.","journal-title":"Eur J Nucl Med Mol Imaging."},{"key":"823_CR23","doi-asserted-by":"crossref","unstructured":"Hatt M, Cheze le Rest C, Turzo A, Roux C, Visvikis D. A Fuzzy Locally Adaptive Bayesian Segmentation Approach for Volume Determination in PET. IEEE Trans Med Imaging. 2009;28:881\u201393.","DOI":"10.1109\/TMI.2008.2012036"},{"key":"823_CR24","doi-asserted-by":"publisher","first-page":"3071","DOI":"10.1007\/s00330-020-07390-8","volume":"31","author":"CS Constantino","year":"2021","unstructured":"Constantino CS, Oliveira FPM, Silva M, Oliveira C, Castanheira JC, Silva \u00c2, et al. Are lesion features reproducible between 18F-FDG PET\/CT images when acquired on analog or digital PET\/CT scanners? Eur Radiol. 2021;31:3071\u20139.","journal-title":"Eur Radiol."},{"key":"823_CR25","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","volume":"26","author":"K Clark","year":"2013","unstructured":"Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, et al. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. J Digit Imaging. 2013;26:1045\u201357.","journal-title":"J Digit Imaging."},{"key":"823_CR26","doi-asserted-by":"crossref","unstructured":"Gatidis S, Kuestner T. A whole-body FDG-PET\/CT dataset with manually annotated tumor lesions (FDG-PET-CT-Lesions). Cancer Imaging Arch. 2022.","DOI":"10.1038\/s41597-022-01718-3"},{"key":"823_CR27","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1038\/s41597-022-01718-3","volume":"9","author":"S Gatidis","year":"2022","unstructured":"Gatidis S, Hepp T, Fr\u00fch M, La Foug\u00e8re C, Nikolaou K, Pfannenberg C, et al. A whole-body FDG-PET\/CT Dataset with manually annotated Tumor Lesions. Sci Data. 2022;9:601.","journal-title":"Sci Data."},{"key":"823_CR28","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18:203\u201311.","journal-title":"Nat Methods."},{"key":"823_CR29","doi-asserted-by":"publisher","first-page":"4006","DOI":"10.1038\/ncomms5006","volume":"5","author":"HJWL Aerts","year":"2014","unstructured":"Aerts HJWL, Velazquez ER, Leijenaar RTH, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014;5:4006.","journal-title":"Nat Commun."},{"key":"823_CR30","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/s13139-018-0543-8","volume":"52","author":"HJ Kim","year":"2018","unstructured":"Kim HJ, Lee R, Choi H, Paeng JC, Cheon GJ, Lee DS, et al. Application of Quantitative Indexes of FDG PET to Treatment Response Evaluation in Indolent Lymphoma. Nucl Med Mol Imaging. 2018;52:342\u20139.","journal-title":"Nucl Med Mol Imaging."},{"key":"823_CR31","doi-asserted-by":"crossref","unstructured":"O JH, Lodge MA, Wahl RL. Practical PERCIST: A Simplified Guide to PET Response Criteria in Solid Tumors 1.0. Radiology. 2016;280:576\u201384.","DOI":"10.1148\/radiol.2016142043"},{"key":"823_CR32","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1179\/1607845415Y.0000000033","volume":"21","author":"M Xie","year":"2016","unstructured":"Xie M, Zhai W, Cheng S, Zhang H, Xie Y, He W. Predictive value of F-18 FDG PET\/CT quantization parameters for progression-free survival in patients with diffuse large B-cell lymphoma. Hematology. 2016;21:99\u2013105.","journal-title":"Hematology."},{"key":"823_CR33","doi-asserted-by":"crossref","unstructured":"Boo SH, O JH, Kwon SJ, Yoo IR, Kim SH, Park GS, et al. Predictive Value of Interim and End-of-Therapy 18F-FDG PET\/CT in Patients with Follicular Lymphoma. Nucl Med Mol Imaging. 2019;53:263\u20139.","DOI":"10.1007\/s13139-019-00602-0"},{"key":"823_CR34","doi-asserted-by":"publisher","first-page":"7998","DOI":"10.1007\/s00330-022-08784-6","volume":"32","author":"BS Kelly","year":"2022","unstructured":"Kelly BS, Judge C, Bollard SM, Clifford SM, Healy GM, Aziz A, et al. Radiology artificial intelligence: a systematic review and evaluation of methods (RAISE). Eur Radiol. 2022;32:7998\u20138007.","journal-title":"Eur Radiol."}],"container-title":["Journal of Digital Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-023-00823-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-023-00823-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-023-00823-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T17:10:57Z","timestamp":1691428257000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-023-00823-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,14]]},"references-count":34,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["823"],"URL":"https:\/\/doi.org\/10.1007\/s10278-023-00823-y","relation":{},"ISSN":["1618-727X"],"issn-type":[{"value":"1618-727X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,14]]},"assertion":[{"value":"3 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2023","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 study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Ethics Committee of Champalimaud Foundation. The need for written informed consent was waived in the terms defined by the ethics approval.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}