{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T08:56:50Z","timestamp":1790758610557,"version":"4.1.0"},"reference-count":40,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2018,10,28]],"date-time":"2018-10-28T00:00:00Z","timestamp":1540684800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000133","name":"Agency for Healthcare Research and Quality","doi-asserted-by":"publisher","award":["R01\u2010HS022888"],"award-info":[{"award-number":["R01\u2010HS022888"]}],"id":[{"id":"10.13039\/100000133","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":[[2018,11]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>The purpose of this study was to expedite the contouring process for <jats:styled-content style=\"fixed-case\">MRI<\/jats:styled-content>\u2010guided adaptive radiotherapy (<jats:styled-content style=\"fixed-case\">MR<\/jats:styled-content>\u2010<jats:styled-content style=\"fixed-case\">IGART<\/jats:styled-content>), a convolutional neural network (<jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content>) deep\u2010learning (<jats:styled-content style=\"fixed-case\">DL<\/jats:styled-content>) model is proposed to accurately segment the liver, kidneys, stomach, bowel and duodenum in 3D <jats:styled-content style=\"fixed-case\">MR<\/jats:styled-content> images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Images and structure contours for 120 patients were collected retrospectively. Treatment sites included pancreas, liver, stomach, adrenal gland, and prostate. The proposed <jats:styled-content style=\"fixed-case\">DL<\/jats:styled-content> model contains a voxel\u2010wise label prediction <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content> and a correction network which consists of two sub\u2010networks. The prediction <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content> and sub\u2010networks in the correction network each includes a dense block which consists of twelve densely connected convolutional layers. The correction network was designed to improve the voxel\u2010wise labeling accuracy of a <jats:styled-content style=\"fixed-case\">CNN<\/jats:styled-content> by learning and enforcing implicit anatomical constraints in the segmentation process. Its sub\u2010networks learn to fix the erroneous classification of its previous network by taking as input both the original images and the softmax probability maps generated from its previous sub\u2010network. The parameters of each sub\u2010network were trained independently using piecewise training. The model was trained on 100 datasets, validated on 10 datasets and tested on the remaining 10 datasets. Dice coefficient, Hausdorff distance (<jats:styled-content style=\"fixed-case\">HD<\/jats:styled-content>) were calculated to evaluate the segmentation accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed <jats:styled-content style=\"fixed-case\">DL<\/jats:styled-content> model was able to segment the organs with good accuracy. The correction network outperformed the conditional random field (<jats:styled-content style=\"fixed-case\">CRF<\/jats:styled-content>), a most comparable method that is usually applied as a post\u2010processing step. For the 10 testing patients, the average Dice coefficients were 95.3\u00a0\u00b1\u00a00.73, 93.1\u00a0\u00b1\u00a02.22, 85.0\u00a0\u00b1\u00a03.75, 86.6\u00a0\u00b1\u00a02.69, and 65.5\u00a0\u00b1\u00a08.90 for liver, kidneys, stomach, bowel, and duodenum, respectively. The mean Hausdorff Distance (<jats:styled-content style=\"fixed-case\">HD<\/jats:styled-content>) were 5.41\u00a0\u00b1\u00a02.34, 6.23\u00a0\u00b1\u00a04.59, 6.88\u00a0\u00b1\u00a04.89, 5.90\u00a0\u00b1\u00a04.05, and 7.99\u00a0\u00b1\u00a06.84\u00a0mm, respectively. Manual contouring, as to correct the automatic segmentation results, was four times as fast as manual contouring from scratch.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The proposed method can automatically segment the liver, kidneys, stomach, bowel, and duodenum in 3D <jats:styled-content style=\"fixed-case\">MR<\/jats:styled-content> images with good accuracy. It is useful to expedite the manual contouring for <jats:styled-content style=\"fixed-case\">MR<\/jats:styled-content>\u2010<jats:styled-content style=\"fixed-case\">IGART<\/jats:styled-content>.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.13221","type":"journal-article","created":{"date-parts":[[2018,9,30]],"date-time":"2018-09-30T11:54:45Z","timestamp":1538308485000},"page":"5129-5137","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":124,"title":["A novel <scp>MRI<\/scp> segmentation method using <scp>CNN<\/scp>\u2010based correction network for <scp>MRI<\/scp>\u2010guided adaptive radiotherapy"],"prefix":"10.1002","volume":"45","author":[{"given":"Yabo","family":"Fu","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas R.","family":"Mazur","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Stanford University Stanford CA 94305 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonggang","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of radiology Medical College of Wisconsin Milwaukee WI 53226 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H. Harold","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael C.","family":"Roach","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren","family":"Henke","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deshan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology School of Medicine Washington University in Saint Louis St.Louis MO 63110 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2018,10,28]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2015.02.057"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2015.01.015"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2014.02.008"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.meddos.2014.02.003"},{"key":"e_1_2_7_6_1","first-page":"e1618","article-title":"Online adaptive radiation therapy: implementation of a new process of care","volume":"9","author":"Lamb J","year":"2017","journal-title":"Cureus"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.04.041"},{"key":"e_1_2_7_9_1","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek\u00d6 AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010Net: learning dense volumetric segmentation from sparse annotation. MICCAI.2016;424\u2013432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.04.039"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.05.001"},{"key":"e_1_2_7_12_1","doi-asserted-by":"crossref","unstructured":"FritscherK RaudaschlP ZaffinoP SpadeaMF SharpGC SchubertR.Deep Neural networks for fast segmentation of 3D medical images. MICCAI.2016;158\u2013165.","DOI":"10.1007\/978-3-319-46723-8_19"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/61\/24\/8676"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.10.004"},{"key":"e_1_2_7_15_1","unstructured":"Liang\u2010ChiehCG KokkinosI MurphyK YuilleAL.Semantic image segmentation with deep convolutional nets and fully connected CRFs. International Conference on Learning Representations.2016."},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-016-1467-3"},{"key":"e_1_2_7_17_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS\u2010A.V\u2010Net: fully convolutional neural networks for volumetric medical image segmentation. 2016 Fourth International Conference on 3D Vision (3DV) 2016;565\u2013571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2548501"},{"key":"e_1_2_7_19_1","doi-asserted-by":"crossref","unstructured":"MoeskopsP WolterinkJM VeldenBHMVD et\u00a0al.Deep learning for multi\u2010task medical image segmentation in multiple modalities. MICCAI.2016.","DOI":"10.1007\/978-3-319-46723-8_55"},{"key":"e_1_2_7_20_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010Net: convolutional networks for biomedical image segmentation. MICCAI.2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2481436"},{"key":"e_1_2_7_23_1","doi-asserted-by":"crossref","unstructured":"YuL ChengJ\u2010Z DouQP et\u00a0al.Automatic 3D cardiovascular mr segmentation with densely\u2010connected volumetric ConvNets. MICCAI.2017.","DOI":"10.1007\/978-3-319-66185-8_33"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12480"},{"key":"e_1_2_7_25_1","unstructured":"BudaM MakiA MazurowskiMA.A systematic study of the class imbalance problem in convolutional neural networks. CoRR abs\/1710.05381.2017."},{"key":"e_1_2_7_26_1","doi-asserted-by":"crossref","unstructured":"HuangG LiuZ WeinbergerKQ.Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2017;2261\u20132269.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"e_1_2_7_28_1","doi-asserted-by":"crossref","unstructured":"ChristPF ElshaerMEA EttlingerF et\u00a0al.Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. MICCAI.2016;415\u2013423.","DOI":"10.1007\/978-3-319-46723-8_48"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_2_7_30_1","unstructured":"Kr\u00e4henb\u00fchlP KoltunV.Efficient inference in fully connected CRFs with gaussian edge potentials. NIPS.2011."},{"key":"e_1_2_7_31_1","doi-asserted-by":"crossref","unstructured":"LinG ShenC HengelAVD ReidID.Efficient piecewise training of deep structured models for semantic segmentation. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2016;3194\u20133203.","DOI":"10.1109\/CVPR.2016.348"},{"key":"e_1_2_7_32_1","unstructured":"RothK LucchiA NowozinS HofmannT.Stabilizing training of generative adversarial networks through regularization. NIPS.2017."},{"key":"e_1_2_7_33_1","doi-asserted-by":"crossref","unstructured":"XueY XuT ZhangH LongLR HuangX.SegAN: adversarial network with multi\u2010scale L 1 loss for medical image segmentation. Neuroinformatics.2018;1\u201310.","DOI":"10.1007\/s12021-018-9377-x"},{"key":"e_1_2_7_34_1","doi-asserted-by":"crossref","unstructured":"ZhangZ YangL ZhengY.Translating and segmenting multimodal medical volumes with cycle\u2010 and shape\u2010consistency generative adversarial network. CoRR abs\/1802.09655.2018.","DOI":"10.1109\/CVPR.2018.00963"},{"key":"e_1_2_7_35_1","unstructured":"DosovitskiyA BroxT.Generating images with perceptual similarity metrics based on deep networks. NIPS2016."},{"key":"e_1_2_7_36_1","unstructured":"ArjovskyM ChintalaS BottouL.Wasserstein generative adversarial networks. ICML.2017."},{"key":"e_1_2_7_37_1","unstructured":"GulrajaniI AhmedF ArjovskyM DumoulinV CourvilleAC.Improved training of wasserstein GANs. NIPS.2017."},{"key":"e_1_2_7_38_1","unstructured":"MeschederLM GeigerA NowozinS.Which training methods for GANs do actually Converge?ICML.2018."},{"key":"e_1_2_7_39_1","unstructured":"IoffeS SzegedyC.Batch normalization: accelerating deep network training by reducing internal covariate shift. ICML.2015."},{"key":"e_1_2_7_40_1","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","journal-title":"J Mach Learn Res"},{"key":"e_1_2_7_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.232073"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fmp.13221","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13221","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.13221","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T01:42:29Z","timestamp":1693964549000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.13221"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,28]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2018,11]]}},"alternative-id":["10.1002\/mp.13221"],"URL":"https:\/\/doi.org\/10.1002\/mp.13221","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,28]]},"assertion":[{"value":"2018-03-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-09-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-10-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}