{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:05:25Z","timestamp":1791389125292,"version":"4.3.3"},"reference-count":39,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T00:00:00Z","timestamp":1680739200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFC0118100"],"award-info":[{"award-number":["2019YFC0118100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172401"],"award-info":[{"award-number":["62172401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12026602"],"award-info":[{"award-number":["12026602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515010439"],"award-info":[{"award-number":["2022A1515010439"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A0505020019"],"award-info":[{"award-number":["2022A0505020019"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The fusion of computed tomography (CT) and ultrasound (US) image can enhance lesion detection ability and improve the success rate of liver interventional radiology. The image\u2010based fusion methods encounter the challenge of registration initialization due to the random scanning pose and limited field of view of US. Existing automatic methods those used vessel geometric information and intensity\u2010based metric are sensitive to parameters and have low success rate. The learning\u2010based methods require a large number of registered datasets for training.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>The aim of this study is to provide a fully automatic and robust US\u20103D CT registration method without registered training data and user\u2010specified parameters assisted by the revolutionary deep learning\u2010based segmentation, which can further be used for preparing training samples for the study of learning\u2010based\u00a0methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We propose a fully automatic CT\u20103D US registration method by two improved registration metrics. We propose to use 3D U\u2010Net\u2010based multi\u2010organ segmentation of US and CT to assist the conventional registration. The rigid transform is searched in the space of any paired vessel bifurcation planes where the best transform is decided by a segmentation overlap metric, which is more related to the segmentation precision than Dice coefficient. In nonrigid registration phase, we propose a hybrid context and edge based image similarity metric with a simple mask that can remove most noisy US voxels to guide the B\u2010spline transform registration. We evaluate our method on 42 paired CT\u20103D US datasets scanned with two different US devices from two hospitals. We compared our methods with other exsiting methods with both quantitative measures of target registration error (TRE) and the Jacobian determinent with paired <jats:italic>t<\/jats:italic>\u2010test and qualitative registration imaging\u00a0results.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The results show that our method achieves fully automatic rigid registration TRE of 4.895 mm, deformable registration TRE of 2.995 mm in average, which outperforms state\u2010of\u2010the\u2010art automatic linear methods and nonlinear registration metrics with paired <jats:italic>t<\/jats:italic>\u2010test's <jats:italic>p<\/jats:italic> value less than 0.05. The proposed overlap metric achieves better results than self similarity description (SSD), edge matching (EM), and block matching (BM) with <jats:italic>p<\/jats:italic> values of 1.624E\u201010, 4.235E\u20109, and 0.002, respectively. The proposed hybrid edge and context\u2010based metric outperforms context\u2010only, edge\u2010only, and intensity statistics\u2010only\u2010based metrics with <jats:italic>p<\/jats:italic> values of 0.023, 3.81E\u20105, and 1.38E\u201015, respectively. The 3D US segmentation has achieved mean Dice similarity coefficient (DSC) of 0.799, 0.724, 0.788, and precision of 0.871, 0.769, 0.862 for gallbladder, vessel, and branch vessel,\u00a0respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The deep learning\u2010based US segmentation can achieve satisfied result to assist robust conventional rigid registration. The Dice similarity coefficient\u2010based metrics, hybrid context, and edge image similarity metric contribute to robust and accurate\u00a0registration.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16396","type":"journal-article","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T11:23:00Z","timestamp":1680002580000},"page":"6243-6258","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A robust and automatic CT\u20103D ultrasound registration method based on segmentation, context, and edge hybrid metric"],"prefix":"10.1002","volume":"50","author":[{"given":"Baochun","family":"He","sequence":"first","affiliation":[{"name":"Center for Medical AI Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China"},{"name":"Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Radiology The Second Affiliated Hospital of Harbin Medical University Harbin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmei","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Radiology The Second Affiliated Hospital of Harbin Medical University Harbin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Inpatient Ultrasound The Second Affiliated Hospital of Harbin Medical University Harbin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huoling","family":"Luo","sequence":"additional","affiliation":[{"name":"Center for Medical AI Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxi","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Interventional Radiology Shenzhen People's Hospital Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Ni","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Shenzhen People's Hospital Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianchong","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary and Pancreatic Surgery Shenzhen People's Hospital Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangyuan","family":"Kuang","sequence":"additional","affiliation":[{"name":"College of Medicine and Biological Information Engineering Northeastern University Shenyang China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huijie","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Radiology The Second Affiliated Hospital of Harbin Medical University Harbin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Interventional Radiology Shenzhen People's Hospital Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fucang","family":"Jia","sequence":"additional","affiliation":[{"name":"Center for Medical AI Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China"},{"name":"Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China"},{"name":"Pazhou Lab Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,4,6]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcl.2015.05.012"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00270-010-9979-7"},{"key":"e_1_2_8_4_1","doi-asserted-by":"crossref","unstructured":"CiforA RisserL HeinrichMP ChungD SchnabelJA.Rigid registration of untracked freehand 2D ultrasound sweeps to 3D CT of liver tumours. In:Abdominal Imaging. Computation and Clinical Applications.2013:155\u2010164.","DOI":"10.1007\/978-3-642-41083-3_18"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.14366\/usg.14021"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00270-014-0897-y"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.2106\/JBJS.H.01362"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.02.003"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2008.06.006"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-008-0270-1"},{"key":"e_1_2_8_11_1","doi-asserted-by":"crossref","unstructured":"LangeT EulensteinS H\u00fcnerbeinM LameckerH SchlagPM.Augmenting intraoperative 3D ultrasound with preoperative models for navigation in liver surgery. In:MICCAI.2004:534\u2010541.","DOI":"10.1007\/978-3-540-30136-3_66"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/57\/1\/69"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"HaqueH OmiY RuskoL AnnagiP KazuyukiO.Automated registration of 3D ultrasound and CT\/MR images for liver. In:IEEE International Ultrasonics Symposium (IUS).2016:1\u20104.","DOI":"10.1109\/ULTSYM.2016.7728738"},{"key":"e_1_2_8_14_1","doi-asserted-by":"crossref","unstructured":"SunY MoelkerA NiessenWJ WalsumT.Towards robust CT\u2010ultrasound registration using deep learning methods. In:Understanding and Interpreting Machine Learning in Medical Image Computing Applications.Springer;2018:43\u201051.","DOI":"10.1007\/978-3-030-02628-8_5"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/56\/1\/008"},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"NamWH KangDG LeeD RaJB.Robust registration of 3\u2010D ultrasound and CT images of the liver for image\u2010guided intervention. In:ISBI.2010:1201\u20101204.","DOI":"10.1109\/ISBI.2010.5490210"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/7.18692"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4903945"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"ShechtmanE IraniM.Matching local self\u2010similarities across images and videos. In:CVPR.2007:1\u20108.","DOI":"10.1109\/CVPR.2007.383198"},{"key":"e_1_2_8_20_1","first-page":"1","article-title":"Weakly\u2010supervised convolutional neural networks for multimodal image registration","volume":"49","author":"Hu Y","year":"2018","journal-title":"IEEE Trans Med Imaging"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106117"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs\u20101091982\/v1"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2018.11.020"},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"GuoH XuX XuS WoodBJ YanP.End\u2010to\u2010end ultrasound frame to volume registration. In:MICCAI.2021:56\u201065.","DOI":"10.1007\/978-3-030-87202-1_6"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"MarkovaV RonchettiM WeinW ZettinigO PrevostR.Global multi\u2010modal 2D\/3D registration via local descriptors learning. In:MICCAI.2022:269\u2010279.","DOI":"10.1007\/978-3-031-16446-0_26"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"WeinW KutterO AichertA ZikicD KamenA NavabN.Automatic non\u2010linear mapping of pre\u2010precedure CT volumes to 3D ultrasound. In:ISBI.2010:1225\u20101228.","DOI":"10.1109\/ISBI.2010.5490216"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"HeinrichMP JenkinsonM PapiezBW BradyM SchnabelJA.Towards realtime multimodal fusion for image\u2010guided interventions using self\u2010similarities. In:MICCAI.2013:187\u2010194.","DOI":"10.1007\/978-3-642-40811-3_24"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2012.05.008"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1006\/cgip.1994.1042"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.1644513"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2035616"},{"key":"e_1_2_8_33_1","unstructured":"Sandk\u00fchlerR JudC AndermattS CattinPC.AirLab: autograd image registration laboratory.arXiv preprint arXiv:1806.09907.2018."},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.796284"},{"key":"e_1_2_8_35_1","doi-asserted-by":"crossref","unstructured":"RueckertD AljabarP HeckemannRF HajalJV HammersA.Diffeomorphic registration using B\u2010splines. In:MICCAI.2006:702\u2010709.","DOI":"10.1007\/11866763_86"},{"key":"e_1_2_8_36_1","doi-asserted-by":"crossref","unstructured":"HuY ModatM GibsonE et\u00a0al.Label\u2010driven weakly\u2010supervised learning for multimodal deformable image registration. In:ISBI.2018:1070\u20101074.","DOI":"10.1109\/ISBI.2018.8363756"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02400-6"},{"key":"e_1_2_8_38_1","doi-asserted-by":"crossref","unstructured":"HeinrichMP.Closing the gap between deep and conventional image registration using probabilistic dense displacement networks. In:MICCAI.2019:50\u201058.","DOI":"10.1007\/978-3-030-32226-7_6"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-020-01060-x"},{"key":"e_1_2_8_40_1","doi-asserted-by":"crossref","unstructured":"SunJ ShenZ WangY BaoH ZhouX.LoFTR: Detector\u2010free local feature matching with transformers. In:CVPR.2021:8922\u20108931.","DOI":"10.1109\/CVPR46437.2021.00881"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T05:46:00Z","timestamp":1697089560000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,6]]},"references-count":39,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["10.1002\/mp.16396"],"URL":"https:\/\/doi.org\/10.1002\/mp.16396","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,6]]},"assertion":[{"value":"2022-11-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}