{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:19:06Z","timestamp":1790684346782,"version":"4.1.0"},"reference-count":34,"publisher":"IOP Publishing","issue":"18","license":[{"start":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T00:00:00Z","timestamp":1694476800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T00:00:00Z","timestamp":1694476800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100010086","name":"Foundation of Liaoning Province Education Administration","doi-asserted-by":"crossref","award":["2022-MS-114"],"award-info":[{"award-number":["2022-MS-114"]}],"id":[{"id":"10.13039\/501100010086","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2023,9,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . Whole-body positron emission tomography\/computed tomography (PET\/CT) scans are an important tool for diagnosing various malignancies (e.g. malignant melanoma, lymphoma, or lung cancer), and accurate segmentation of tumors is a key part of subsequent treatment. In recent years, convolutional neural network based segmentation methods have been extensively investigated. However, these methods often give inaccurate segmentation results, such as oversegmentation and undersegmentation. To address these issues, we propose a postprocessing method based on a graph convolutional network (GCN) to refine inaccurate segmentation results and improve the overall segmentation accuracy.\n                    <jats:italic>Approach<\/jats:italic>\n                    . First, nnU-Net is used as an initial segmentation framework, and the uncertainty in the segmentation results is analyzed. Certain and uncertain pixels are used to establish the nodes of a graph. Each node and its 6 neighbors form an edge, and 32 nodes are randomly selected as uncertain nodes to form edges. The highly uncertain nodes are used as the subsequent refinement targets. Second, the nnU-Net results of the certain nodes are used as labels to form a semisupervised graph network problem, and the uncertain part is optimized by training the GCN to improve the segmentation performance. This describes our proposed nnU-Net + GCN segmentation framework.\n                    <jats:italic>Main results.<\/jats:italic>\n                    We perform tumor segmentation experiments with the PET\/CT dataset from the MICCIA2022 autoPET challenge. Among these data, 30 cases are randomly selected for testing, and the experimental results show that the false-positive rate is effectively reduced with nnU-Net + GCN refinement. In quantitative analysis, there is an improvement of 2.1% for the average Dice score, 6.4 for the 95% Hausdorff distance (HD95), and 1.7 for the average symmetric surface distance.\n                    <jats:italic>Significance<\/jats:italic>\n                    . The quantitative and qualitative evaluation results show that GCN postprocessing methods can effectively improve the tumor segmentation performance.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/acede6","type":"journal-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T18:40:42Z","timestamp":1691433642000},"page":"185018","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["3D PET\/CT tumor segmentation based on nnU-Net with GCN refinement"],"prefix":"10.1088","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7124-7383","authenticated-orcid":true,"given":"Hengzhi","family":"Xue","sequence":"first","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingqing","family":"Fang","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudong","family":"Yao","sequence":"additional","affiliation":[{"name":"Northeastern University"},{"name":"Department of Electrical and Computer Engineering, Steven Institute of Technology, Hoboken, NJ 07102,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueyang","family":"Teng","sequence":"additional","affiliation":[{"name":"Northeastern University"},{"name":"Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Shenyang, 110169,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,9,12]]},"reference":[{"key":"pmbacede6bib1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106043","type":"journal-article","article-title":"Recurrent feature fusion learning for multi-modality PET-CT tumor segmentation","volume":"203","author":"Bi","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmbacede6bib2","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1007\/s00259-020-05080-7","type":"journal-article","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":"Blanc-Durand","year":"2021","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbacede6bib3","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/978-3-030-87602-9_24","type":"book","article-title":"Uncertainty-based dynamic graph neighborhoods for medical segmentation","volume":"vol 12928","author":"Demir","year":"2021"},{"key":"pmbacede6bib4","doi-asserted-by":"publisher","first-page":"72","DOI":"10.3390\/metabo11020072","type":"journal-article","article-title":"Reproducibility of baseline tumour metabolic volume measurements in diffuse large B-Cell lymphoma: is there a superior method?","volume":"11","author":"Eude","year":"2021","journal-title":"Metabolites"},{"key":"pmbacede6bib5","doi-asserted-by":"publisher","first-page":"3507","DOI":"10.1109\/JBHI.2021.3059453","type":"journal-article","article-title":"Multimodal spatial attention module for targeting multimodal PET-CT lung tumor segmentation","volume":"25","author":"Fu","year":"2021","journal-title":"IEEE J Biomed Health Inform."},{"key":"pmbacede6bib6","first-page":"583","type":"conference-proceedings","article-title":"A joint 3D UNet-graph neural network-based method for airway segmentation from chest CTs","volume":"vol 11861","author":"Garcia-Uceda Juarez","year":"2019"},{"key":"pmbacede6bib7","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1038\/s41597-022-01718-3","type":"journal-article","article-title":"A whole-body FDG-PET\/CT dataset with manually annotated tumor lesions","volume":"9","author":"Gatidis","year":"2022","journal-title":"Sci. Data"},{"key":"pmbacede6bib8","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s00259-016-3427-0","type":"journal-article","article-title":"Characterization of PET\/CT images using texture analysis: the past, the present\u2026 any future?","volume":"44","author":"Hatt","year":"2017","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbacede6bib9","first-page":"327","type":"conference-proceedings","article-title":"Feedback graph attention convolutional network for MR images enhancement by exploring self-similarity features","author":"Hu","year":"2021"},{"key":"pmbacede6bib10","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1007\/s00259-018-3953-z","type":"journal-article","article-title":"Defining the optimal method for measuring baseline metabolic tumour volume in diffuse large B cell lymphoma","volume":"45","author":"Ilyas","year":"2018","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"pmbacede6bib11","article-title":"nnU-Net: self-adapting framework for U-net-based medical image segmentation","author":"Isensee","year":"2018","type":"preprint"},{"key":"pmbacede6bib12","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1007\/s10278-020-00341-1","type":"journal-article","article-title":"Tumor segmentation and feature extraction from whole-body FDG-PET\/CT using cascaded 2D and 3D convolutional neural networks","volume":"33","author":"Jemaa","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"pmbacede6bib13","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-3-319-67389-9_17","type":"conference-proceedings","article-title":"3D convolutional neural networks with graph refinement for airway segmentation using incomplete data labels","volume":"vol 10541","author":"Jin","year":"2017"},{"key":"pmbacede6bib14","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017","type":"preprint"},{"key":"pmbacede6bib15","doi-asserted-by":"crossref","first-page":"2.098111E6","DOI":"10.21037\/qims-20-607","type":"journal-article","article-title":"Clinical value of dual-phase F-18 sodium fluoride PET\/CT for diagnosing bone metastasis in cancer patients with solitary bone lesion","volume":"10","author":"Lee","year":"2020","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbacede6bib16","doi-asserted-by":"publisher","first-page":"2204","DOI":"10.1364\/BOE.417212","type":"journal-article","article-title":"Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images","volume":"12","author":"Li","year":"2021","journal-title":"Biomed Opt Exp"},{"key":"pmbacede6bib17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22796-8_11","type":"book","article-title":"Graph-FCN for image semantic segmentation","volume":"vol 11554","author":"Lu","year":"2020"},{"key":"pmbacede6bib18","doi-asserted-by":"crossref","DOI":"10.1109\/3DV.2016.79","type":"conference-proceedings","article-title":"V-net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"pmbacede6bib19","doi-asserted-by":"crossref","first-page":"29209","DOI":"10.21037\/qims-21-19","type":"journal-article","article-title":"Two-stage multitask U-Net construction for pulmonary nodule segmentation and malignancy risk prediction","volume":"12","author":"Ni","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbacede6bib20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICME51207.2021.9428116","type":"conference-proceedings","article-title":"Weakly-supervised image semantic segmentation using graph convolutional networks","author":"Pan","year":"2021"},{"key":"pmbacede6bib21","doi-asserted-by":"publisher","first-page":"1941","DOI":"10.2967\/jnumed.122.264063","type":"journal-article","article-title":"Fully-automated, semantic segmentation of whole-body 18F-FDG PET\/CT images based on data-centric artificial intelligence","volume":"63","author":"Shiyam Sundar","year":"2022","journal-title":"J. Nucl. Med."},{"key":"pmbacede6bib22","first-page":"755","type":"journal-article","article-title":"An uncertainty-driven GCN refinement strategy for organ segmentation","volume":"121","author":"Soberanis-Mukul","year":"2020","journal-title":"Proceedings of Machine Learning Research"},{"key":"pmbacede6bib23","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neucom.2020.05.121","type":"journal-article","article-title":"Interactive prostate MR image segmentation based on ConvLSTMs and GGNN","volume":"438","author":"Tian","year":"2021","journal-title":"Neurocomputing"},{"key":"pmbacede6bib24","doi-asserted-by":"publisher","first-page":"4164","DOI":"10.1002\/mp.14327","type":"journal-article","article-title":"Graph-convolutional-network-based interactive prostate segmentation in MR images","volume":"47","author":"Tian","year":"2020","journal-title":"Med. Phys."},{"key":"pmbacede6bib25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105913","type":"journal-article","article-title":"Integrating segmentation information into CNN for breast cancer diagnosis of mammographic masses","volume":"200","author":"Tsochatzidis","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmbacede6bib26","doi-asserted-by":"crossref","first-page":"4.095108E6","DOI":"10.21037\/qims-21-1155","type":"journal-article","article-title":"Automatic evaluation of endometrial receptivity in three-dimensional transvaginal ultrasound images based on 3D U-Net segmentation","volume":"12","author":"Wang","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbacede6bib27","first-page":"1.600612E6","type":"journal-article","article-title":"Deep learning based fully automatic segmentation of the left ventricular endocardium and epicardium from cardiac cine MRI","volume":"11","author":"Wang","year":"2021","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbacede6bib28","first-page":"1","type":"conference-proceedings","article-title":"Graph neural network and superpixel based brain tissue segmentation","author":"Wu","year":"2022"},{"key":"pmbacede6bib29","doi-asserted-by":"crossref","first-page":"4.747757E6","DOI":"10.21037\/qims-21-1116","type":"journal-article","article-title":"A deep learning-based post-processing method for automated pulmonary lobe and airway trees segmentation using chest CT images in PET\/CT","volume":"12","author":"Xing","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbacede6bib30","doi-asserted-by":"crossref","first-page":"74962","DOI":"10.21037\/qims-20-66","type":"journal-article","article-title":"LCPR-Net: low-count PET image reconstruction using the domain transform and cycle-consistent generative adversarial networks","volume":"11","author":"Xue","year":"2021","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbacede6bib31","first-page":"36","type":"conference-proceedings","article-title":"Linking convolutional neural networks with graph convolutional networks: application in pulmonary artery-vein separation","volume":"vol 11849","author":"Zhai","year":"2019"},{"key":"pmbacede6bib32","article-title":"Dual graph convolutional network for semantic segmentation","author":"Zhang","year":"2020","type":"journal-article"},{"key":"pmbacede6bib33","doi-asserted-by":"crossref","first-page":"4.538548E6","DOI":"10.21037\/qims-21-1005","type":"journal-article","article-title":"Clinical evaluation of a novel atlas-based PET\/CT brain image segmentation and quantification method for epilepsy","volume":"12","author":"Zhang","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbacede6bib34","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","type":"journal-article","article-title":"UNet++: redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2020","journal-title":"IEEE Trans Med Imaging"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:31:24Z","timestamp":1778776284000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acede6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,12]]},"references-count":34,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2023,9,12]]},"published-print":{"date-parts":[[2023,9,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/acede6","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,12]]},"assertion":[{"value":"3D PET\/CT tumor segmentation based on nnU-Net with GCN refinement","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2023-04-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-08-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-09-12","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}