{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T08:54:37Z","timestamp":1791968077555,"version":"4.3.4"},"reference-count":32,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T00:00:00Z","timestamp":1638403200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T00:00:00Z","timestamp":1638403200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR\u201011\u2010LABX\u20100063"],"award-info":[{"award-number":["ANR\u201011\u2010LABX\u20100063"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010190","name":"Grand \u00c9quipement National De Calcul Intensif","doi-asserted-by":"publisher","award":["2019\u2010101203"],"award-info":[{"award-number":["2019\u2010101203"]}],"id":[{"id":"10.13039\/501100010190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001677","name":"Institut National de la Sant\u00e9 et de la Recherche M\u00e9dicale","doi-asserted-by":"publisher","award":["INCa\u2010INSERM\u2010DGOS\u201012563"],"award-info":[{"award-number":["INCa\u2010INSERM\u2010DGOS\u201012563"]}],"id":[{"id":"10.13039\/501100001677","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":[[2022,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:bold>Purpose<\/jats:bold>\n                    . Motion\u2010mask segmentation from thoracic computed tomography (CT) images is the process of extracting the region that encompasses lungs and viscera, where large displacements occur during breathing. It has been shown to help image registration between different respiratory phases. This registration step is, for example, useful for radiotherapy planning or calculating local lung ventilation. Knowing the location of motion discontinuity, that is, sliding motion near the pleura, allows a better control of the registration preventing unrealistic estimates. Nevertheless, existing methods for motion\u2010mask segmentation are not robust enough to be used in clinical routine. This article shows that it is feasible to overcome this lack of robustness by using a lightweight deep\u2010learning approach usable on a standard computer, and this even without data augmentation or advanced model\u00a0design.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Methods<\/jats:bold>\n                    . A convolutional neural\u2010network architecture with three 2D U\u2010nets for the three main orientations (sagittal, coronal, axial) was proposed. Predictions generated by the three U\u2010nets were combined by majority voting to provide a single 3D segmentation of the motion mask. The networks were trained on a database of nonsmall cell lung cancer 4D CT images of 43 patients. Training and evaluation were done with a K\u2010fold cross\u2010validation strategy. Evaluation was based on a visual grading by two experts according to the appropriateness of the segmented motion mask for the registration task, and on a comparison with motion masks obtained by a baseline method using level sets. A second database (76 CT images of patients with early\u2010stage COVID\u201019), unseen during training, was used to assess the generalizability of the trained neural\u00a0network.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Results<\/jats:bold>\n                    . The proposed approach outperformed the baseline method in terms of quality and robustness: the success rate increased from  to  without producing any failure. It also achieved a speed\u2010up factor of 60 with GPU, or 17 with CPU. The memory footprint was low: less than 5 GB GPU RAM for training and less than 1 GB GPU RAM for inference. When evaluated on a dataset with images differing by several characteristics (CT device, pathology, and field of view), the proposed method improved the success rate from  to .\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Conclusion<\/jats:bold>\n                    . With 5\u2010s processing time on a mid\u2010range GPU and success rates around , the proposed approach seems fast and robust enough to be routinely used in clinical practice. The success rate can be further improved by incorporating more diversity in training data via data augmentation and additional annotated images from different scanners and diseases. The code and trained model are publicly\u00a0available.\n                  <\/jats:p>","DOI":"10.1002\/mp.15347","type":"journal-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T01:00:28Z","timestamp":1636938028000},"page":"420-431","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving motion\u2010mask segmentation in thoracic CT with multiplanar U\u2010nets"],"prefix":"10.1002","volume":"49","author":[{"given":"Ludmilla","family":"Penarrubia","sequence":"first","affiliation":[{"name":"Univ Lyon Universit\u00e9 Claude Bernard Lyon 1 INSA\u2010Lyon CNRS, Inserm  CREATIS UMR 5220, U1294, F\u201069621 Lyon France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Pinon","sequence":"additional","affiliation":[{"name":"Univ Lyon Universit\u00e9 Claude Bernard Lyon 1 INSA\u2010Lyon CNRS, Inserm  CREATIS UMR 5220, U1294, F\u201069621 Lyon France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Roux","sequence":"additional","affiliation":[{"name":"Univ Lyon Universit\u00e9 Claude Bernard Lyon 1 INSA\u2010Lyon CNRS, Inserm  CREATIS UMR 5220, U1294, F\u201069621 Lyon France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eduardo Enrique","family":"D\u00e1vila Serrano","sequence":"additional","affiliation":[{"name":"Univ Lyon Universit\u00e9 Claude Bernard Lyon 1 INSA\u2010Lyon CNRS, Inserm  CREATIS UMR 5220, U1294, F\u201069621 Lyon France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean\u2010Christophe","family":"Richard","sequence":"additional","affiliation":[{"name":"Univ Lyon Universit\u00e9 Claude Bernard Lyon 1 INSA\u2010Lyon CNRS, Inserm  CREATIS UMR 5220, U1294, F\u201069621 Lyon France"},{"name":"Service de R\u00e9animation M\u00e9dicale H\u00f4pital de la Croix Rousse Hospices Civils de Lyon  France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maciej","family":"Orkisz","sequence":"additional","affiliation":[{"name":"Univ Lyon Universit\u00e9 Claude Bernard Lyon 1 INSA\u2010Lyon CNRS, Inserm  CREATIS UMR 5220, U1294, F\u201069621 Lyon France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Sarrut","sequence":"additional","affiliation":[{"name":"Univ Lyon Universit\u00e9 Claude Bernard Lyon 1 INSA\u2010Lyon CNRS, Inserm  CREATIS UMR 5220, U1294, F\u201069621 Lyon France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,12,2]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aa6070"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12891"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2019.12.004"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-02064-3"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2265603"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2017.09.121"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.2828378"},{"key":"e_1_2_8_9_1","doi-asserted-by":"crossref","unstructured":"Schmidt\u2010RichbergA EhrhardtJ WernerR HandelsH.Slipping objects in image registration: improved motion field estimation with direction\u2010dependent regularization. In:Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2009 LNCS 5761(London UK) Springer;2009:755\u2010762.","DOI":"10.1007\/978-3-642-04268-3_93"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/58\/5\/1303"},{"key":"e_1_2_8_11_1","doi-asserted-by":"crossref","unstructured":"DerksenA HeldmannS PolzinT BerkelsB.Image registration with sliding motion constraints for 4D CT motion correction. In:Informatik Aktuell \u2013 Bildverarbeitung f\u00fcr die Medizin 2015(L\u00fcbeck Germany) Springer Vieweg;2015:335\u2010340.","DOI":"10.1007\/978-3-662-46224-9_58"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.10.008"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3679009"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2017.07.003"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190692"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: convolutional networks for biomedical image segmentation. In:Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2015 LNCS 9351(Munich Germany) Springer;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek\u00d6 AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010net: learning dense volumetric segmentation from sparse annotation.Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2016 LNCS 9901(Athens Greece) Springer;2016:424\u2010432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS\u2010A.V\u2010net: fully convolutional neural networks for volumetric medical image segmentation. In:Fourth International Conference on 3D Vision \u2013 3DV(Stanford CA USA) IEEE;2016:565\u2010571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2845918"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"IsenseeF PetersenJ KleinA et\u00a0al.nnU\u2010netself\u2010adapting framework for U\u2010net\u2010based medical image segmentation. In:Informatik aktuell \u2013 Bildverarbeitung f\u00fcr die Medizin (L\u00fcbeck Germany) Vieweg Springer;2018.","DOI":"10.1007\/978-3-658-25326-4_7"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101592"},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"MoeskopsP WolterinkJM Van der VeldenBH et\u00a0al.Deep learning for multi\u2010task medical image segmentation in multiple modalities. In:Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2016 LNCS 9901(Athens Greece) Springer;2016:478\u2010486.","DOI":"10.1007\/978-3-319-46723-8_55"},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"LyksborgM PuontiO AgnM LarsenR.An ensemble of 2D convolutional neural networks for tumor segmentation. In:Scandinavian Conference on Image Analysis \u2013 SCIA 2015 LNCS 9127(Copenhagen Denmark) Springer;2015:201\u2010211.","DOI":"10.1007\/978-3-319-19665-7_17"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"PrasoonA PetersenK IgelC LauzeF DamE NielsenM.Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. In:Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2013 LNCS 8150(Nagoya Japan) Springer;2013:246\u2010253.","DOI":"10.1007\/978-3-642-40763-5_31"},{"key":"e_1_2_8_26_1","unstructured":"Automatic liver lesion segmentation using A deep convolutional neural network method. arXiv:abs\/1704.07239 (2017)."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-020-02292-y"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"PerslevM DamEB PaiA IgelC.One network to segment them all: A general lightweight system for accurate 3D medical image segmentation. In:Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019 LNCS 11765(Shenzhen China) Springer;2019:30\u201038.","DOI":"10.1007\/978-3-030-32245-8_4"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"RothHR LuL SeffA et\u00a0al.A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. In:Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2014 LNCS 8673(Boston MA USA) Springer;2014:520\u2010527.","DOI":"10.1007\/978-3-319-10404-1_65"},{"key":"e_1_2_8_30_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization. In:3rd International Conference on Learning Representations \u2013 ICLR(San Diego CA USA) (2015)."},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-015-0068-x"},{"key":"e_1_2_8_32_1","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek\u00d6 AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010Net: learning dense volumetric segmentation from sparse annotation. In:Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI 2016 LNCS 9901Springer International Publishing;2016:424\u2010432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2012.031"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15347","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15347","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T08:36:43Z","timestamp":1791967003000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,2]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["10.1002\/mp.15347"],"URL":"https:\/\/doi.org\/10.1002\/mp.15347","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,2]]},"assertion":[{"value":"2021-05-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}