{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T14:50:15Z","timestamp":1786978215931,"version":"build-2736575974"},"reference-count":56,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2022,5,27]],"date-time":"2022-05-27T00:00:00Z","timestamp":1653609600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Although the surface registration technique has the advantage of being relatively safe and the operation time is short, it generally has the disadvantage of low accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This research proposes automated machine learning (AutoML)\u2010based surface registration to improve the accuracy of image\u2010guided surgical navigation systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The state\u2010of\u2010the\u2010art surface registration concept is that first, using a neural network model, a new point\u2010cloud that matches the facial information acquired by a passive probe of an optical tracking system (OTS) is extracted from the facial information obtained by computerized tomography. Target registration error (TRE) representing the accuracy of surface registration is then calculated by applying the iterative closest point (ICP) algorithm to the newly extracted point\u2010cloud and OTS information. In this process, the hyperparameters used in the neural network model and ICP algorithm are automatically optimized using Bayesian optimization with expected improvement to yield improved registration accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Using the proposed surface registration methodology, the average TRE for the targets located in the sinus space and nasal cavity of the soft phantoms is 0.939\u00a0\u00b1\u00a00.375\u00a0mm, which shows 57.8% improvement compared to the average TRE of 2.227\u00a0\u00b1\u00a00.193\u00a0mm calculated by the conventional surface registration method (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.01). The performance of the proposed methodology is evaluated, and the average TREs computed by the proposed methodology and the conventional method are 0.767\u00a0\u00b1\u00a00.132 and 2.615\u00a0\u00b1\u00a00.378\u00a0mm, respectively. Additionally, for one healthy adult, the clinical applicability of the AutoML\u2010based surface registration is also presented.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our findings showed that the registration accuracy could be improved while maintaining the advantages of the surface registration technique.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.15696","type":"journal-article","created":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T05:04:37Z","timestamp":1652245477000},"page":"4845-4860","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Automated machine learning (AutoML)\u2010based surface registration methodology for image\u2010guided surgical navigation system"],"prefix":"10.1002","volume":"49","author":[{"given":"Hakje","family":"Yoo","sequence":"first","affiliation":[{"name":"Korea University Research Institute for Medical Bigdata Science College of Medicine Korea University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taeyong","family":"Sim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Sejong University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,5,27]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joms.2017.01.004"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01990-6"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/rcs.1626"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3001207"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1227\/01.NEU.0000383751.63835.2F"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14145"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1166\/jmihi.2020.3071"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/rcs.1509"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.otc.2017.01.012"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1097\/SCS.0000000000003283"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.3171\/2009.3.JNS081457"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijom.2006.09.015"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.3109\/10929088.2011.579791"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12206-020-0540-6"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11125464"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"AokiY GoforthH SrivatsanRA LuceyS.PointNetLK: robust & efficient point cloud registration using PointNet.Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2019;7163\u20107172.","DOI":"10.1109\/CVPR.2019.00733"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"LuW WanG ZhouY FuX YuanP SongS.DeepVCP: an end\u2010to\u2010end deep neural network for point cloud registration.Proceedings of the IEEE\/CVF International Conference on Computer Vision.2019;12\u201021.","DOI":"10.1109\/ICCV.2019.00010"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970946"},{"key":"e_1_2_9_20_1","unstructured":"BeslPJ McKayND.Method for registration of 3\u2010D shapes.Sensor Fusion IV: Control Paradigms and Data Structures. Vol1611.International Society for Optics and Photonics.1992;586\u2010606."},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_1"},{"key":"e_1_2_9_22_1","unstructured":"MelisG DyerC BlunsomP.On the state of the art of evaluation in neural language models.2017. arXiv preprint arXiv:1707.05589."},{"key":"e_1_2_9_23_1","first-page":"25","volume-title":"Advances in Neural Information Processing Systems","author":"Snoek J","year":"2012"},{"key":"e_1_2_9_24_1","unstructured":"BergstraJ YaminsD CoxD.Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures.International Conference on Machine Learning. Vol28.PMLR.2013;115\u2010123."},{"key":"e_1_2_9_25_1","unstructured":"SculleyD SnoekJ WiltschkoA RahimiA.Winner's curse? On pace progress and empirical rigor.2018."},{"issue":"9","key":"e_1_2_9_26_1","first-page":"722","article-title":"Drainage of retro\u2010parapharyngeal abscess: an additional indication for endoscopic sinus surgery","volume":"262","author":"Nicolai P","year":"2005","journal-title":"Eur Arch Otorhinolaryngol Head Neck"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-008-0384-1"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/2945.466720"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/24699322.2017.1389411"},{"key":"e_1_2_9_30_1","first-page":"447","article-title":"Image registration","volume":"2","author":"Fitzpatrick JM","year":"2000","journal-title":"Handb Med Imaging"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.3171\/jns.2007.106.6.1012"},{"key":"e_1_2_9_32_1","unstructured":"BrochuE CoraVM De FreitasN.A tutorial on Bayesian optimization of expensive cost functions with application to active user modeling and hierarchical reinforcement learning.2010. arXiv preprint arXiv:1012.2599."},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"e_1_2_9_34_1","first-page":"117","article-title":"The application of Bayesian methods for seeking the extremum","volume":"2","author":"Mockus J","year":"1978","journal-title":"Towards Global Optim"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_2_9_36_1","unstructured":"SnoekJ RippelO SwerskyK et\u00a0al.Scalable Bayesian optimization using deep neural networks.International Conference on Machine Learning.PMLR.2015;2171\u20102180."},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"DahlGE SainathTN HintonGE.Improving deep neural networks for LVCSR using rectified linear units and dropout.2013 IEEE International Conference on Acoustics Speech and Signal Processing.IEEE.2013;8609\u20108613.","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"e_1_2_9_38_1","unstructured":"MelisG DyerC BlunsomP.On the state of the art of evaluation in neural language models.Proceedings of the International Conference on Learning Representations (ICLR\u201918) [1].2017. published online: iclr.cc."},{"key":"e_1_2_9_39_1","doi-asserted-by":"crossref","unstructured":"BenassiR BectJ VazquezE.Robust Gaussian process\u2010based global optimization using a fully Bayesian expected improvement criterion.International Conference on Learning and Intelligent Optimization. Berlin Heidelberg.Springer.2011;176\u2010190.","DOI":"10.1007\/978-3-642-25566-3_13"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jspi.2010.04.018"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4895847"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1227\/NEU.0b013e318209cc45"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/24699322.2017.1389392"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.anl.2020.01.007"},{"issue":"81","key":"e_1_2_9_45_1","first-page":"1","article-title":"Stereotactic neuro\u2010navigation phantom designs: a systematic review","volume":"14","author":"\u0160vaco M","year":"2020","journal-title":"Front Neurorobot"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-017-1675-5"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.otohns.2004.09.141"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.3109\/10929080500066922"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joms.2012.03.037"},{"key":"e_1_2_9_50_1","first-page":"195","article-title":"On the stability of inverse problems","volume":"39","author":"Tikhonov AN","year":"1943","journal-title":"Dokl Akad Nauk SSSR"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/0262-8856(92)90066-C"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.5194\/isprsannals-II-5-W2-211-2013"},{"key":"e_1_2_9_54_1","doi-asserted-by":"crossref","unstructured":"ZengA YuKT SongS et\u00a0al.Multi\u2010view self\u2010supervised deep learning for 6d pose estimation in the amazon picking challenge.2017 IEEE International Conference on Robotics and Automation (ICRA).IEEE;2017;1386\u20101383.","DOI":"10.1109\/ICRA.2017.7989165"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.3171\/2021.5.FOCUS20735"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00701-019-03867-8"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1002\/rcs.1977"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15696","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15696","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T20:23:24Z","timestamp":1692476604000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,27]]},"references-count":56,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["10.1002\/mp.15696"],"URL":"https:\/\/doi.org\/10.1002\/mp.15696","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,27]]},"assertion":[{"value":"2021-10-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-05-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}