{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T19:01:14Z","timestamp":1791831674446,"version":"4.3.4"},"reference-count":37,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T00:00:00Z","timestamp":1680134400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100019266","name":"Korea Medical Device Development Fund","doi-asserted-by":"publisher","award":["9991006735"],"award-info":[{"award-number":["9991006735"]}],"id":[{"id":"10.13039\/100019266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF\u20102020R1A4A1018714"],"award-info":[{"award-number":["NRF\u20102020R1A4A1018714"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF\u20102020R1A2C2008949"],"award-info":[{"award-number":["NRF\u20102020R1A2C2008949"]}],"id":[{"id":"10.13039\/501100003725","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":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Osteonecrosis of the femoral head (ONFH) is characterized as bone cell death in the hip joint, involving a severe pain in the groin. The staging of ONFH is commonly based on Magnetic resonance imaging and computed tomography (CT), which are important for establishing effective treatment plans. There have been some attempts to automate ONFH staging using deep learning, but few of them used only MR\u00a0images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To propose a deep learning model for MR\u2010only ONFH staging, which can reduce additional cost and radiation exposure from the acquisition of CT\u00a0images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We integrated information from the MR images of five different imaging protocols by a newly proposed attention fusion method, which was composed of intra\u2010modality attention and inter\u2010modality attention. In addition, a self\u2010supervised learning was used to learn deep representations from a large amount of paired MR\u2010CT dataset. The encoder part of the MR\u2010CT translation network was used as a pretraining network for the staging, which aimed to overcome the lack of annotated data for staging. Ablation studies were performed to investigate the contributions of each proposed method. The area under the receiver operating characteristic curve (AUROC) was used to evaluate the performance of the\u00a0networks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our model improved the performance of the four\u2010way classification of the association research circulation osseous (ARCO) stage using MR images of the multiple protocols by 6.8%p in AUROC over a plain VGG network. Each proposed method increased the performance by 4.7%p (self\u2010supervised learning) and 2.6%p (attention fusion) in AUROC, which was demonstrated by the ablation\u00a0experiments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We have shown the feasibility of the MR\u2010only ONFH staging by using self\u2010supervised learning and attention fusion. A large amount of paired MR\u2010CT data in hospitals can be used to further improve the performance of the staging, and the proposed method has potential to be used in the diagnosis of various diseases that require staging from multiple MR\u00a0protocols.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.16380","type":"journal-article","created":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T01:56:28Z","timestamp":1679450188000},"page":"5528-5540","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Attention fusion network with self\u2010supervised learning for staging of osteonecrosis of the femoral head (ONFH) using multiple MR protocols"],"prefix":"10.1002","volume":"50","author":[{"given":"Bomin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Bio and Brain Engineering KAIST Daejeon Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geun Young","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology Chung\u2010Ang University Gwangmyeong Hospital Chung\u2010Ang University College of Medicine Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung\u2010Hong","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Bio and Brain Engineering KAIST Daejeon Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,3,30]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1302\/2058-5241.4.180036"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.2106\/00004623-200205000-00023"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199205283262206"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.blo.0000150275.98701.4e"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2007.03.019"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2019.11.029"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00429-013-0687-3"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00775-2020"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0273-z"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2014.12.061"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS\u2010A.V\u2010net: Fully convolutional neural networks for volumetric medical image segmentation. In2016 Fourth International Conference on 3D Vision (3DV).IEEE;2016:565\u2010571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","unstructured":"GordienkoY GangP HuiJ et\u00a0al.Deep learning with lung segmentation and bone shadow exclusion techniques for chest X\u2010ray analysis of lung cancer. InInternational Conference on Computer Science Engineering and Education Applications.Springer;2018:638\u2010647.","DOI":"10.1007\/978-3-319-91008-6_63"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.05.029"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528162"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.18.20817"},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2016:770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3037079"},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","unstructured":"LiuW AnguelovD ErhanD et\u00a0al.Ssd: Single shot multibox detector. InEuropean Conference on Computer Vision.2016:21\u201037.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106254"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106229"},{"key":"e_1_2_10_22_1","doi-asserted-by":"crossref","unstructured":"HuJ ShenL SunG.Squeeze\u2010and\u2010excitation networks. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2018:7132\u20107141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"WooS ParkJ LeeJ\u2010Y KweonIS.Cbam: Convolutional block attention module. InProceedings of the European Conference on Computer Vision (ECCV).2018:3\u201019.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"DengJ DongW SocherR LiL\u2010J LiK Fei\u2010FeiL.Imagenet: A large\u2010scale hierarchical image database. In2009 IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2009:248\u2010255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_10_25_1","doi-asserted-by":"crossref","unstructured":"DoerschC GuptaA EfrosAA.Unsupervised visual representation learning by context prediction. InProceedings of the IEEE International Conference on Computer Vision.2015:1422\u20101430.","DOI":"10.1109\/ICCV.2015.167"},{"key":"e_1_2_10_26_1","doi-asserted-by":"crossref","unstructured":"ZhangR IsolaP EfrosAA.Colorful image colorization. InEuropean Conference on Computer Vision.2016:649\u2010666.","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"NorooziM FavaroP.Unsupervised learning of visual representations by solving jigsaw puzzles. InEuropean Conference on Computer Vision.2016:69\u201084.","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"e_1_2_10_28_1","unstructured":"ChenT KornblithS NorouziM HintonG.A simple framework for contrastive learning of visual representations. InInternational Conference on Machine Learning.2020:1597\u20101607."},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","unstructured":"HeK FanH WuY XieS GirshickR.Momentum contrast for unsupervised visual representation learning. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2020:9729\u20109738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12748"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2035616"},{"key":"e_1_2_10_32_1","unstructured":"SimonyanK ZissermanA.Very deep convolutional networks for large\u2010scale image recognition. InInternational Conference on Learning Representations.2015."},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: Convolutional networks for biomedical image segmentation. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_10_34_1","unstructured":"KingmaDP BaJ.Adam: A Method for stochastic optimization. InInternational Conference on Learning Representations.2015."},{"key":"e_1_2_10_35_1","article-title":"SGDR: Stochastic gradient descent with restarts","author":"Loshchilov I","year":"2016","journal-title":"CoRR"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2016.2644865"},{"key":"e_1_2_10_37_1","unstructured":"PaszkeA GrossS ChintalaS et\u00a0al.Automatic Differentiation in PyTorch. InProceedings of the 31th Conference on Neural Information Processing System.2017."},{"key":"e_1_2_10_38_1","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford A","year":"2021"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16380","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T19:27:12Z","timestamp":1694287632000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,30]]},"references-count":37,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["10.1002\/mp.16380"],"URL":"https:\/\/doi.org\/10.1002\/mp.16380","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,30]]},"assertion":[{"value":"2022-07-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}