{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:07:34Z","timestamp":1778778454768,"version":"3.51.4"},"reference-count":30,"publisher":"IOP Publishing","issue":"20","license":[{"start":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T00:00:00Z","timestamp":1633392000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T00:00:00Z","timestamp":1633392000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"The Research Industrialization Plan of Xi\u2019an","award":["XA2020-RGZNTJ-0075"],"award-info":[{"award-number":["XA2020-RGZNTJ-0075"]}]},{"DOI":"10.13039\/501100007128","name":"The Natural Science Foundation of Shaanxi Province","doi-asserted-by":"crossref","award":["2021SF-189"],"award-info":[{"award-number":["2021SF-189"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Fundamental Research Funds for the Central Universities","award":["JC2102"],"award-info":[{"award-number":["JC2102"]}]},{"name":"The Research Plan of Improving Public Scientific Quality in Shaanxi Province","award":["2020PSL(Y)097"],"award-info":[{"award-number":["2020PSL(Y)097"]}]},{"name":"The Science and technology of Xi\u2019an city","award":["No.20YXYJ001(2)"],"award-info":[{"award-number":["No.20YXYJ001(2)"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2021,10,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Ankylosing spondylitis (AS) is a disabling systemic disease that seriously threatens the patient\u2019s quality of life. Magnetic resonance imaging (MRI) is highly preferred in clinical diagnosis due to its high contrast and tissue resolution. However, since the uncertainty and intensity inhomogeneous of the AS lesions in MRI, it is still challenging and time-consuming for doctors to quantify the lesions to determine the grade of the patient\u2019s condition. Thus, an automatic AS grading method is presented in this study, which integrates the lesion segmentation and grading in a pipeline.\n                    <jats:italic>Approach<\/jats:italic>\n                    . To tackle the large variations in lesion shapes, sizes, and intensity distributions, a lightweight hybrid multi-scale convolutional neural network with reinforcement learning (LHR-Net) is proposed for the AS lesion segmentation. Specifically, the proposed LHR-Net is equipped with the newly proposed hybrid multi-scale module, which consists of multiply convolution layers with different kernel sizes and dilation rates for extracting sufficient multi-scale features. Additionally, a reinforcement learning-based data augmentation module is utilized to deal with the subjects with diffuse and fuzzy lesions that are difficult to segment. Furthermore, to resolve the incomplete segmentation results caused by the inhomogeneous intensity distributions of the AS lesions in MR images, a voxel constraint strategy is proposed to weigh the training voxel labels in the lesion regions. With the accurately segmented AS lesions, automatic AS grading is then performed by a ResNet-50-based classification network.\n                    <jats:italic>Main results<\/jats:italic>\n                    . The performance of the proposed LHR-Net was extensively evaluated on a clinically collected AS MRI dataset, which includes 100 subjects. Dice similarity coefficient (DSC), average surface distance, Hausdorff Distance at\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:msup>\n                          <mml:mrow>\n                            <mml:mn>95<\/mml:mn>\n                          <\/mml:mrow>\n                          <mml:mrow>\n                            <mml:mi mathvariant=\"normal\">th<\/mml:mi>\n                          <\/mml:mrow>\n                        <\/mml:msup>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    percentile (HD95), predicted positive volume, and sensitivity were employed to quantitatively evaluate the segmentation results. The average DSC of the proposed LHR-Net on the AS dataset reached 0.71 on the test set, which outperforms the other state-of-the-art segmentation method by 0.04.\n                    <jats:italic>Significance<\/jats:italic>\n                    . With the accurately segmented lesions, 31 subjects in the test set (38 subjects) were correctly graded, which demonstrates that the proposed LHR-Net might provide a potential automatic method for reproducible computer-assisted diagnosis of AS grading.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ac262a","type":"journal-article","created":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T18:16:16Z","timestamp":1631556976000},"page":"205002","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Automatic segmentation and grading of ankylosing spondylitis on MR images via lightweight hybrid multi-scale convolutional neural network with reinforcement learning"],"prefix":"10.1088","volume":"66","author":[{"given":"Shuiping","family":"Gou","sequence":"first","affiliation":[{"name":"Xidian University"},{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfei","family":"Lu","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0554-5136","authenticated-orcid":false,"given":"Nuo","family":"Tong","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luguang","family":"Huang","sequence":"additional","affiliation":[{"name":"Fourth Military Medical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ningtao","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Han","sequence":"additional","affiliation":[{"name":"Fourth Military Medical University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2021,10,5]]},"reference":[{"key":"pmbac262abib1","first-page":"33","type":"journal-article","article-title":"Pyramid methods in image processing","volume":"29","author":"Adelson","year":"1984","journal-title":"RCA Eng."},{"key":"pmbac262abib2","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1109\/TMI.2016.2528821","type":"journal-article","article-title":"Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation","volume":"35","author":"Brosch","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbac262abib3","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","type":"preprint"},{"key":"pmbac262abib4","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-319-46723-8_48","type":"book","article-title":"Automatic liver and lesion segmentation in CT networks and 3D conditional random fields","author":"Christ","year":"2016"},{"key":"pmbac262abib30","doi-asserted-by":"publisher","first-page":"1800","DOI":"10.1109\/CVPR.2017.195","type":"conference-proceedings","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Collet","year":"2017"},{"key":"pmbac262abib6","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1109\/ICCV.2017.205","type":"conference-proceedings","article-title":"Class rectification hard mining for imbalanced deep learning","author":"Dong","year":"2017"},{"key":"pmbac262abib31","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.media.2017.05.001","type":"journal-article","article-title":"3D deeply supervised network for automated segmentation of volumetric medical images","volume":"41","author":"Dou","year":"2017"},{"key":"pmbac262abib7","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","type":"conference-proceedings","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"pmbac262abib8","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","type":"journal-article","article-title":"MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation","volume":"121","author":"Ibtehaz","year":"2020","journal-title":"Neural Netw."},{"key":"pmbac262abib9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","type":"journal-article","article-title":"nnU-Net: breaking the spell on successful medical image segmentation","volume":"18","author":"Isensee","year":"2019","journal-title":"Nat Methods"},{"key":"pmbac262abib10","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1007\/978-3-030-59710-8_54","type":"book","article-title":"Shape-aware semi-supervised 3d semantic segmentation for medical images","author":"Li","year":"2020"},{"key":"pmbac262abib12","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/3DV.2016.79","type":"conference-proceedings","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"pmbac262abib13","doi-asserted-by":"publisher","first-page":"1928","DOI":"10.5555\/3045390.3045594","type":"preprint","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"pmbac262abib11","doi-asserted-by":"publisher","first-page":"2","DOI":"10.5555\/2997189.2997322","type":"conference-proceedings","article-title":"Self-paced learning for latent variable models","author":"Pawan Kumar","year":"2010"},{"key":"pmbac262abib14","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","type":"book","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"pmbac262abib15","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-030-00937-3_48","type":"conference-proceedings","article-title":"A multi-scale pyramid of 3D fully convolutional networks for abdominal multi-organ segmentation","author":"Roth","year":"2018"},{"key":"pmbac262abib16","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/j.aott.2016.06.010","type":"journal-article","article-title":"Total hip arthroplasty in patients with ankylosing spondylitis: midterm radiologic and functional results","volume":"50","author":"Saglam","year":"2016","journal-title":"Acta Orthop. Traumatol. Turc."},{"key":"pmbac262abib17","doi-asserted-by":"publisher","first-page":"ii1","DOI":"10.1136\/ard.2008.104018","type":"journal-article","article-title":"The assessment of spondyloarthritis international society (ASAS) handbook: a guide to assess spondyloarthritis","volume":"68","author":"Sieper","year":"2009","journal-title":"Ann. Rheum. Dis."},{"key":"pmbac262abib18","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/JBHI.2020.2986926","type":"journal-article","article-title":"Multi-scale self-guided attention for medical image segmentation","volume":"25","author":"Sinha","year":"2021","journal-title":"IEEE J. Biomed. Heal. Inform."},{"key":"pmbac262abib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CVPR.2015.7298594","type":"conference-proceedings","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"pmbac262abib20","doi-asserted-by":"publisher","first-page":"52--58","DOI":"10.1016\/S0883-5403(00)91155-0","type":"journal-article","article-title":"Primary total hip arthroplasty in patients with ankylosing spondylitis","volume":"15","author":"Tang","year":"2000","journal-title":"J. Arthroplasty"},{"key":"pmbac262abib21","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab9b57","type":"journal-article","article-title":"Self-paced DenseNet with boundary constraint for automated multi-organ segmentation on abdominal CT images","volume":"65","author":"Tong","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"pmbac262abib5","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1093\/rheumatology\/kep174","type":"journal-article","article-title":"Hip involvement in ankylosing spondylitis: epidemiology and risk factors associated with hip replacement surgery","volume":"49","author":"ASPECT-REGISPONSER-RESPONDIA working group","year":"2010","journal-title":"Rheumatology"},{"key":"pmbac262abib22","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-3-030-01201-4_30","type":"conference-proceedings","article-title":"A deep residual architecture for skin lesion segmentation","author":"Venkatesh","year":"2018"},{"key":"pmbac262abib23","doi-asserted-by":"publisher","first-page":"12648","DOI":"10.1109\/CVPR.2019.01293","type":"conference-proceedings","article-title":"Context-aware spatio-recurrent curvilinear structure segmentation","author":"Wang","year":"2019"},{"key":"pmbac262abib24","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1007\/978-3-030-32248-9_30","type":"book","article-title":"CLCI-Net: cross-level Fusion and Context inference networks for lesion segmentation of chronic stroke","author":"Yang","year":"2019"},{"key":"pmbac262abib25","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1007\/s00296-012-2510-5","type":"journal-article","article-title":"Health-related quality of life in Turkish patients with Ankylosing spondylitis: impact of peripheral involvement on quality of life in terms of disease activity, functional status, severity of pain, and social and emotional functioning","volume":"33","author":"Y\u0131lmaz","year":"2013","journal-title":"Rheumatol. Int."},{"key":"pmbac262abib26","doi-asserted-by":"publisher","first-page":"4271","DOI":"10.24963\/ijcai.2019\/593","type":"conference-proceedings","article-title":"Light-weight hybrid convolutional network for liver tumor segmentation","author":"Zhang","year":"2019"},{"key":"pmbac262abib27","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.neucom.2020.03.097","type":"journal-article","article-title":"AFPNet: A 3D fully convolutional neural network with atrous-convolution feature pyramid for brain tumor segmentation via MRI images","volume":"402","author":"Zhou","year":"2020","journal-title":"Neurocomputing"},{"key":"pmbac262abib28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","type":"book","article-title":"Unet++: a nested u-net architecture for medical image segmentation","author":"Zhou","year":"2018"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:10:13Z","timestamp":1778775013000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac262a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,5]]},"references-count":30,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2021,10,5]]},"published-print":{"date-parts":[[2021,10,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ac262a","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,5]]},"assertion":[{"value":"Automatic segmentation and grading of ankylosing spondylitis on MR images via lightweight hybrid multi-scale convolutional neural network with reinforcement learning","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2021-05-06","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-09-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-10-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}