{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T10:21:28Z","timestamp":1783419688116,"version":"3.54.6"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["2023YFH0079"],"award-info":[{"award-number":["2023YFH0079"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019M663471"],"award-info":[{"award-number":["2019M663471"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2021YGCX008"],"award-info":[{"award-number":["ZYGX2021YGCX008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"German Research Foundation (DFG), Research Training Group GRK","award":["2274"],"award-info":[{"award-number":["2274"]}]},{"name":"F\u00f6rderprogramm f\u00fcr Forschung und Lehre, Medical Faculty, LMU Munich","award":["1084"],"award-info":[{"award-number":["1084"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Radiat Oncol"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Objectives<\/jats:title>\n                <jats:p>Deep learning-based auto-segmentation of head and neck cancer (HNC) tumors is expected to have better reproducibility than manual delineation. Positron emission tomography (PET) and computed tomography (CT) are commonly used in tumor segmentation. However, current methods still face challenges in handling whole-body scans where a manual selection of a bounding box may be required. Moreover, different institutions might still apply different guidelines for tumor delineation. This study aimed at exploring the auto-localization and segmentation of HNC tumors from entire PET\/CT scans and investigating the transferability of trained baseline models to external real world cohorts.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We employed 2D Retina Unet to find HNC tumors from whole-body PET\/CT and utilized a regular Unet to segment the union of the tumor and involved lymph nodes. In comparison, 2D\/3D Retina Unets were also implemented to localize and segment the same target in an end-to-end manner. The segmentation performance was evaluated via Dice similarity coefficient (DSC) and Hausdorff distance 95th percentile (HD<jats:sub>95<\/jats:sub>). Delineated PET\/CT scans from the HECKTOR challenge were used to train the baseline models by 5-fold cross-validation. Another 271 delineated PET\/CTs from three different institutions (MAASTRO, CRO, BERLIN) were used for external testing. Finally, facility-specific transfer learning was applied to investigate the improvement of segmentation performance against baseline models.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Encouraging localization results were observed, achieving a maximum omnidirectional tumor center difference lower than 6.8\u00a0cm for external testing. The three baseline models yielded similar averaged cross-validation (CV) results with a DSC in a range of 0.71\u20130.75, while the averaged CV HD<jats:sub>95<\/jats:sub> was 8.6, 10.7 and 9.8\u00a0mm for the regular Unet, 2D and 3D Retina Unets, respectively. More than a 10% drop in DSC and a 40% increase in HD<jats:sub>95<\/jats:sub> were observed if the baseline models were tested on the three external cohorts directly. After the facility-specific training, an improvement in external testing was observed for all models. The regular Unet had the best DSC (0.70) for the MAASTRO cohort, and the best HD<jats:sub>95<\/jats:sub> (7.8 and 7.9\u00a0mm) in the MAASTRO and CRO cohorts. The 2D Retina Unet had the best DSC (0.76 and 0.67) for the CRO and BERLIN cohorts, and the best HD<jats:sub>95<\/jats:sub> (12.4\u00a0mm) for the BERLIN cohort.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>The regular Unet outperformed the other two baseline models in CV and most external testing cohorts. Facility-specific transfer learning can potentially improve HNC segmentation performance for individual institutions, where the 2D Retina Unets could achieve comparable or even better results than the regular Unet.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s13014-023-02388-0","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T11:02:35Z","timestamp":1704711755000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Comparison of deep learning networks for fully automated head and neck tumor delineation on multi-centric PET\/CT images"],"prefix":"10.1186","volume":"19","author":[{"given":"Yiling","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elia","family":"Lombardo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michele","family":"Avanzo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Fanetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Franchin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Zschaeck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Weing\u00e4rtner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claus","family":"Belka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Riboldi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Kurz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Landry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,8]]},"reference":[{"key":"2388_CR1","doi-asserted-by":"crossref","unstructured":"Economopoulou P, Psyrri A. Head and neck cancers: essentials for clinicians. Chap 1 (2017).","DOI":"10.1136\/esmoopen-2016-000122"},{"issue":"4","key":"2388_CR2","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.sdentj.2019.05.010","volume":"31","author":"OA Elkashty","year":"2019","unstructured":"Elkashty OA, Ashry R, Tran SD. Head and Neck cancer management and cancer stem cells implication. Saudi Dent J. 2019;31(4):395\u2013416.","journal-title":"Saudi Dent J"},{"key":"2388_CR3","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.oraloncology.2018.10.034","volume":"87","author":"V Gr\u00e9goire","year":"2018","unstructured":"Gr\u00e9goire V, Grau C, Lapeyre M, Maingon P. Target volume selection and delineation (T and N) for primary radiation treatment of oral cavity, oropharyngeal, hypopharyngeal and laryngeal squamous cell carcinoma. Oral Oncol. 2018;87:131\u20137.","journal-title":"Oral Oncol"},{"issue":"2","key":"2388_CR4","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.radonc.2016.09.009","volume":"121","author":"SK Vinod","year":"2016","unstructured":"Vinod SK, Jameson MG, Min M, Holloway LC. Uncertainties in volume delineation in radiation oncology: a systematic review and recommendations for future studies. Radiother Oncol. 2016;121(2):169\u201379.","journal-title":"Radiother Oncol"},{"issue":"11","key":"2388_CR5","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1080\/0284186X.2021.1949034","volume":"60","author":"J Ren","year":"2021","unstructured":"Ren J, Eriksen JG, Nijkamp J, Korreman SS. Comparing different CT, PET and MRI multi-modality image combinations for deep learning-based head and neck Tumor segmentation. Acta Oncol (Stockholm Sweden). 2021;60(11):1399\u2013406.","journal-title":"Acta Oncol (Stockholm Sweden)"},{"key":"2388_CR6","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.radonc.2020.07.037","volume":"151","author":"K Jensen","year":"2020","unstructured":"Jensen K, Friborg J, Hansen CR, Sams\u00f8e E, Johansen J, Andersen M, et al. The Danish Head and Neck Cancer Group (DAHANCA) 2020 radiotherapy guidelines. Radiother Oncol. 2020;151:149\u201351.","journal-title":"Radiother Oncol"},{"key":"2388_CR7","doi-asserted-by":"crossref","unstructured":"Han MW, Lee HJ, Cho KJ, Kim JS, Roh JL, Choi SH et al. Role of FDG-PET as a biological marker for predicting the hypoxic status of tongue cancer. 2012;34(10):1395\u2013402.","DOI":"10.1002\/hed.21945"},{"issue":"5","key":"2388_CR8","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1007\/s00330-005-0088-y","volume":"16","author":"SJ Rosenbaum","year":"2006","unstructured":"Rosenbaum SJ, Lind T, Antoch G, Bockisch A. False-positive FDG PET uptake\u2013the role of PET\/CT. Eur Radiol. 2006;16(5):1054\u201365.","journal-title":"Eur Radiol"},{"key":"2388_CR9","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T, editors. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-assisted Intervention-MICCAI 2015; Cham: Springer International Publishing.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2388_CR10","doi-asserted-by":"publisher","unstructured":"Han MW, Lee HJ, Cho KJ, Kim JS, Roh JL, Choi SH et al. Role of FDG-PET as a biological marker for predicting the hypoxic status of tongue cancer. 2012;34(10):1395\u2009\u2013\u2009402. Isensee Fabian, J\u00e4ger Paul, Wasserthal Jakob, Zimmerer David, Petersen Jens, Kohl Simon, Schock Justus, Klein Andre, Ro\u00df Tobias, Wirkert Sebastian, Neher Peter, Dinkelacker Stefan, K\u00f6hler Gregor, Maier-Hein Klaus (2020). batchgenerators - a python framework for data augmentation. https:\/\/doi.org\/10.5281\/zenodo.3632567.","DOI":"10.5281\/zenodo.3632567"},{"key":"2388_CR11","doi-asserted-by":"crossref","unstructured":"Xie J, Peng Y, editors. The Head and Neck Tumor Segmentation based on 3D U-Net. Head and Neck Tumor Segmentation and Outcome Prediction; 2022 2022\/\/; Cham: Springer International Publishing.","DOI":"10.1007\/978-3-030-98253-9_8"},{"key":"2388_CR12","doi-asserted-by":"crossref","unstructured":"Andrearczyk V, Oreiller V, Boughdad S, Rest CCL, Elhalawani H, Jreige M, et al. editors. Overview of the HECKTOR Challenge at MICCAI 2021: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET\/CT images. Head and Neck Tumor Segmentation and Outcome Prediction; 2022 2022\/\/; Cham: Springer International Publishing.","DOI":"10.1007\/978-3-030-98253-9_1"},{"key":"2388_CR13","doi-asserted-by":"publisher","first-page":"102336","DOI":"10.1016\/j.media.2021.102336","volume":"77","author":"V Oreiller","year":"2022","unstructured":"Oreiller V, Andrearczyk V, Jreige M, Boughdad S, Elhalawani H, Castelli J, et al. Head and neck Tumor segmentation in PET\/CT: the HECKTOR challenge. Med Image Anal. 2022;77:102336.","journal-title":"Med Image Anal"},{"issue":"3","key":"2388_CR14","first-page":"297","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice LR. Measures of the amount of. Ecologic Association between Species. 1945;26(3):297\u2013302.","journal-title":"Ecologic Association between Species"},{"key":"2388_CR15","doi-asserted-by":"publisher","first-page":"102195","DOI":"10.1016\/j.artmed.2021.102195","volume":"121","author":"A Balagopal","year":"2021","unstructured":"Balagopal A, Morgan H, Dohopolski M, Timmerman R, Shan J, Heitjan DF, et al. PSA-Net: deep learning\u2013based physician style\u2013aware segmentation network for postoperative Prostate cancer clinical target volumes. Artif Intell Med. 2021;121:102195.","journal-title":"Artif Intell Med"},{"issue":"1","key":"2388_CR16","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(1):4006.","journal-title":"Nat Commun"},{"key":"2388_CR17","doi-asserted-by":"publisher","DOI":"10.7937\/tcia.2019.8kap372n","author":"L Wee","year":"2019","unstructured":"Wee L, Dekker A. Data from head-neck-radiomics-hn1. The Cancer Imaging Archive. 2019. https:\/\/doi.org\/10.7937\/tcia.2019.8kap372n.","journal-title":"The Cancer Imaging Archive"},{"issue":"6","key":"2388_CR18","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(6):1045\u201357.","journal-title":"J Digit Imaging"},{"issue":"9","key":"2388_CR19","doi-asserted-by":"publisher","first-page":"5155","DOI":"10.1118\/1.4961121","volume":"43","author":"P Zaffino","year":"2016","unstructured":"Zaffino P, Raudaschl P, Fritscher K, Sharp GC, Spadea MF. Technical note: plastimatch mabs, an open source tool for automatic image segmentation. Med Phys. 2016;43(9):5155.","journal-title":"Med Phys"},{"key":"2388_CR20","unstructured":"Jaeger PF, Kohl SA, Bickelhaupt S, Isensee F, Kuder TA, Schlemmer HP, Maier-Hein KH. Retina U-Net: embarrassingly simple exploitation of segmentation supervision for medical object detection. In Machine Learning for Health Workshop 2020 Apr 30 (pp. 171\u201383). PMLR."},{"key":"2388_CR21","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770\u2013778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2388_CR22","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K. Doll\u00e1r PJae-p. focal loss for dense object detection2017 August 01, 2017:[arXiv:1708.02002 p.].","DOI":"10.1109\/ICCV.2017.324"},{"key":"2388_CR23","doi-asserted-by":"crossref","unstructured":"Girshick RJae-p, Fast R-CNN. 2015 April 01, 2015:[arXiv:1504.08083 p.].","DOI":"10.1109\/ICCV.2015.169"},{"key":"2388_CR24","doi-asserted-by":"publisher","unstructured":"Castro E, Cardoso JS, Pereira JC. Elastic deformations for data augmentation in breast cancer mass detection, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), 2018, pp.\u00a0230\u2013234, https:\/\/doi.org\/10.1109\/BHI.2018.8333411.","DOI":"10.1109\/BHI.2018.8333411"},{"key":"2388_CR25","doi-asserted-by":"crossref","unstructured":"Isensee F, Kickingereder P, Wick W, Bendszus M, Maier-Hein KH, editors. Brain Tumor segmentation and radiomics survival prediction: contribution to the brats 2017 challenge. International MICCAI Brainlesion Workshop; 2017.","DOI":"10.1007\/978-3-319-75238-9_25"},{"key":"2388_CR26","doi-asserted-by":"crossref","unstructured":"Kawula M, Hadi I, Nierer L, Vagni M, Cusumano D, Boldrini L et al. Patient-specific transfer learning for auto-segmentation in adaptive 0.35 T MRgRT of Prostate cancer: a bi-centric evaluation. Med Phys. 2022.","DOI":"10.1002\/mp.16056"},{"issue":"1","key":"2388_CR27","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s12880-015-0068-x","volume":"15","author":"AA Taha","year":"2015","unstructured":"Taha AA, Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging. 2015;15(1):29.","journal-title":"BMC Med Imaging"},{"issue":"200","key":"2388_CR28","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","volume":"32","author":"M Friedman","year":"1937","unstructured":"Friedman M. The Use of ranks to avoid the Assumption of Normality Implicit in the analysis of Variance. J Am Stat Assoc. 1937;32(200):675\u2013701.","journal-title":"J Am Stat Assoc"},{"key":"2388_CR29","unstructured":"Nemenyi P, Bjorn. Distribution-free multiple comparisons. Ph.D. Princeton University; 1963."}],"container-title":["Radiation Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13014-023-02388-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13014-023-02388-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13014-023-02388-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T11:11:55Z","timestamp":1704712315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ro-journal.biomedcentral.com\/articles\/10.1186\/s13014-023-02388-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,8]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["2388"],"URL":"https:\/\/doi.org\/10.1186\/s13014-023-02388-0","relation":{},"ISSN":["1748-717X"],"issn-type":[{"value":"1748-717X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,8]]},"assertion":[{"value":"1 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The HECKTOR and MAASTRO cohorts are publicly available datasets. The CRO patient data are part of two studies approved by the Unique Regional Ethics Committee, with following approval numbers: CRO-2017-50 and CRO-2019-66. Informed consent was obtained from all CRO patients. The studies involving human participants from BERLIN cohort were reviewed and approved by Ethikkomission der Charit\u00e9, Charit\u00e9 Universit\u00e4tsmedizin Berlin, Berlin, Germany. The patients\/participants provided their written informed consent to participate in this study, and their data was anonymised.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"3"}}