{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:59:16Z","timestamp":1790751556675,"version":"4.1.0"},"reference-count":80,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T00:00:00Z","timestamp":1637280000000},"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":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Recently, two\u2010dimensional\u2010to\u2010three\u2010dimensional (2D\u20103D) deformable registration has been applied to deform liver tumor contours from prior reference images onto estimated cone\u2010beam computed tomography (CBCT) target images to automate on\u2010board tumor localizations. Biomechanical modeling has also been introduced to fine\u2010tune the intra\u2010liver deformation\u2010vector\u2010fields (DVFs) solved by 2D\u20103D deformable registration, especially at low\u2010contrast regions, using tissue elasticity information and liver boundary DVFs. However, the caudal liver boundary shows low contrast from surrounding tissues in the cone\u2010beam projections, which degrades the accuracy of the intensity\u2010based 2D\u20103D deformable registration there and results in less accurate boundary conditions for biomechanical modeling. We developed a deep\u2010learning (DL)\u2010based method to optimize the liver boundary DVFs after 2D\u20103D deformable registration to further improve the accuracy of subsequent biomechanical modeling and liver tumor localization.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The DL\u2010based network was built based on the U\u2010Net architecture. The network was trained in a supervised fashion to learn motion correlation between cranial and caudal liver boundaries to optimize the liver boundary DVFs. Inputs of the network had three channels, and each channel featured the 3D DVFs estimated by the 2D\u20103D deformable registration along one Cartesian direction (x, y, z). To incorporate patient\u2010specific liver boundary information into the DVFs, the DVFs were masked by a liver boundary ring structure generated from the liver contour of the prior reference image. The network outputs were the optimized DVFs along the liver boundary with higher accuracy. From these optimized DVFs, boundary conditions were extracted for biomechanical modeling to further optimize the solution of intra\u2010liver tumor motion.<\/jats:p><jats:p>We evaluated the method using 34 liver cancer patient cases, with 24 for training and 10 for testing. We evaluated and compared the performance of three methods: 2D\u20103D deformable registration, 2D\u20103D\u2010Bio (2D\u20103D deformable registration with biomechanical modeling), and DL\u2010Bio (DL model prediction with biomechanical modeling). The tumor localization errors were quantified through calculating the center\u2010of\u2010mass\u2010errors (COMEs), DICE coefficients, and Hausdorff distance between deformed liver tumor contours and manually segmented \u201cgold\u2010standard\u201d contours.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The predicted DVFs by the DL model showed improved accuracy at the liver boundary, which translated into more accurate liver tumor localizations through biomechanical modeling. On a total of 90 evaluated images and tumor contours, the average (\u00b1 sd) liver tumor COMEs of the 2D\u20103D, 2D\u20103D\u2010Bio, and DL\u2010Bio techniques were 4.7 \u00b1 1.9\u00a0mm, 2.9 \u00b1 1.0\u00a0mm, and 1.7 \u00b1 0.4\u00a0mm. The corresponding average (\u00b1 sd) DICE coefficients were 0.60 \u00b1 0.12, 0.71 \u00b1 0.07, and 0.78 \u00b1 0.03; and the average (\u00b1 sd) Hausdorff distances were 7.0 \u00b1 2.6\u00a0mm, 5.4 \u00b1 1.5\u00a0mm, and 4.5 \u00b1 1.3\u00a0mm, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>DL\u2010Bio solves a general correlation model to improve the accuracy of the DVFs at the liver boundary. With improved boundary conditions, the accuracy of biomechanical modeling can be further increased for accurate intra\u2010liver low\u2010contrast tumor localization.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15275","type":"journal-article","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T07:39:20Z","timestamp":1633937960000},"page":"7790-7805","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Automatic liver tumor localization using deep learning\u2010based liver boundary motion estimation and biomechanical modeling (DL\u2010Bio)"],"prefix":"10.1002","volume":"48","author":[{"given":"Hua\u2010Chieh","family":"Shao","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology University of Texas Southwestern Medical Center  Dallas Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokun","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Texas Southwestern Medical Center  Dallas Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael R.","family":"Folkert","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Texas Southwestern Medical Center  Dallas Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Texas Southwestern Medical Center  Dallas Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Texas Southwestern Medical Center  Dallas Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,11,19]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2005.01.002"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/bjs.6895"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.12.047"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-018-0969-2"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rpor.2019.12.006"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.05.023"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.09.001"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2020.09.008"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.07.1977"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab2ba8"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.21037\/jtd.2018.01.155"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2007.12.009"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360-3016(03)00076-2"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.01.047"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-017-0799-7"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.08.021"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4738966"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2013.09.026"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2019.05.012"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-020-01661-w"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.02.003"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/485067"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2017.02.003"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab2667"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2020.11.014"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360-3016(02)02884-5"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.1869074"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/53\/21\/017"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4821099"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4825097"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2015.02.022"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-019-0033-6"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.02.002"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9290(72)90031-0"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1361-8415(98)80010-8"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"HuT DesaiJP.A biomechanical model of the liver for reality\u2010based haptic feedback.International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2003.","DOI":"10.1007\/978-3-540-39899-8_10"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/53\/1\/022"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2007.905387"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.06.229"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.10.040"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2623745"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaa730"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims.2019.07.04"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aa7675"},{"key":"e_1_2_9_46_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT U\u2010net: convolutional networks for biomedical image segmentation.International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_47_1","doi-asserted-by":"crossref","unstructured":"ShenC MaG JiaX.Low\u2010dose CT reconstruction assisted by a global CT image manifold prior.15th International Meeting on Fully Three\u2010Dimensional Image Reconstruction in Radiology and Nuclear Medicine.International Society for Optics and Photonics;2019.","DOI":"10.1117\/12.2534959"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172322"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00097"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/57\/11\/3499"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2015.01.011"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12307"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-018-1192-x"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2019.10.002"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2035616"},{"key":"e_1_2_9_56_1","unstructured":"HanG LiangZ YouJ.A fast ray\u2010tracing technique for TCT and ECT studies. Paper presented at:Nuclear Science Symposium 1999. Conference Record. 1999 IEEE; October 24\u201030 1999; Seattle WA."},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2010.03.003"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.878228"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/60\/22\/8833"},{"key":"e_1_2_9_60_1","unstructured":"FangQ BoasDA.Tetrahedral mesh generation from volumetric binary and grayscale images. Paper presented at:IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2009. ISBI'09; June 28\u2010July 1 2009; Boston MA."},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4005694"},{"key":"e_1_2_9_62_1","volume-title":"Keras","author":"Fran\u00e7ois C","year":"2015"},{"key":"e_1_2_9_63_1","first-page":"265","volume-title":"Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation","author":"Abadi M","year":"2015"},{"key":"e_1_2_9_64_1","volume-title":"Adam: a method for stochastic optimization","author":"Kingma DP","year":"2014"},{"key":"e_1_2_9_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1361-8415(98)80022-4"},{"key":"e_1_2_9_66_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/55\/1\/012"},{"key":"e_1_2_9_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-6333-3"},{"key":"e_1_2_9_68_1","volume-title":"A Method of Establishing Groups of Equal Amplitude in Plant Sociology Based on Similarity of Species Content and its Application to Analyses of the Vegetation on Danish Commons","author":"S\u00f8rensen TJ","year":"1948"},{"key":"e_1_2_9_69_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.1.000612"},{"key":"e_1_2_9_70_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.2198315"},{"key":"e_1_2_9_71_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.201.2.8888223"},{"key":"e_1_2_9_72_1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E96.D.798"},{"key":"e_1_2_9_73_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/61\/24\/8676"},{"key":"e_1_2_9_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46976-8_9"},{"key":"e_1_2_9_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.186"},{"key":"e_1_2_9_76_1","doi-asserted-by":"publisher","DOI":"10.1177\/1533034615587615"},{"key":"e_1_2_9_77_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12326"},{"key":"e_1_2_9_78_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab9358"},{"key":"e_1_2_9_79_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/abe9f6"},{"key":"e_1_2_9_80_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14252"},{"key":"e_1_2_9_81_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4926559"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15275","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15275","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T20:29:44Z","timestamp":1692822584000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15275"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,19]]},"references-count":80,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["10.1002\/mp.15275"],"URL":"https:\/\/doi.org\/10.1002\/mp.15275","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,19]]},"assertion":[{"value":"2021-07-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-02","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}