{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T22:27:12Z","timestamp":1788474432237,"version":"build-2803163510"},"reference-count":43,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100019335","name":"Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security","doi-asserted-by":"publisher","award":["AGK2019004"],"award-info":[{"award-number":["AGK2019004"]}],"id":[{"id":"10.13039\/501100019335","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":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Scoliosis is a type of spinal deformity, which is harmful to a person's health. In severe cases, it can trigger paralysis or death. The measurement of Cobb angle plays an essential role in assessing the severity of\u00a0scoliosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>The aim of this paper is to propose an automatic system for landmark detection and Cobb angle estimation, which can effectively help clinicians diagnose and treat\u00a0scoliosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A novel hybrid framework was proposed to measure Cobb angle precisely for clinical diagnosis, which was referred as W\u2010Transformer due to its w\u2010shaped architecture. First, a convolutional neural network of cascade residual blocks as our backbone was designed. Then a transformer was fused to learn the dependency information between spine and landmarks. In addition, a reinforcement branch was designed to improve the overlap of landmarks, and an improved prediction module was proposed to fine\u2010tune the final coordinates of landmarks in Cobb angles estimation. Besides, the public Accurate Automated Spinal Curvature Estimation (AASCE) MICCAI 2019 challenge was served as data set. It supplies 609 manually labeled spine anterior\u2013posterior (AP) X\u2010ray images, each of which contains a total of 68 landmark labels and three Cobb Angles\u00a0tags.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>From the perspective of the AASCE MICCAI 2019 challenge, we achieved a lower symmetric mean absolute percentage error (SMAPE) of 8.26% for all Cobb angles and the lowest averaged detection error of 50.89 in terms of landmark detection, compared with many state\u2010of\u2010the\u2010art methods. We also provided the SMAPEs for the Cobb angles of the proximal\u2010thoracic (PT), the main\u2010thoracic (MT), and the thoracic\u2010lumbar (TL) area, which are 5.27%, 14.59%, and 20.97% respectively, however, these data were not covered in most previous studies. Statistical analysis demonstrates that our model has obtained a high level of Pearson correlation coefficient of 0.9398 (), which shows excellent reliability of our model. Our model can yield 0.9489 (), 0.8817 (), and 0.9149 () for PT, MT, and TL, respectively. The overall variability of Cobb angle measurement is less than 4, implying clinical value. And the mean absolute deviation (standard deviation) for three regions is 3.64 (4.13), 3.84 (4.66), and 3.80 (4.19). The results of Student paired \u2010test indicate that no statistically significant differences are observed between manual measurement and our automatic approach (\u2010value is always 0.05). Regarding the diagnosis of scoliosis (Cobb angle 10), the proposed method achieves a high sensitivity of 0.9577 and a specificity of 0.8475 for all spinal\u00a0regions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study offers a brand\u2010new automatic approach that is potentially of great benefit of the complex task of landmark detection and Cobb angle evaluation, which can provide helpful navigation information about the early diagnosis of\u00a0scoliosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.15561","type":"journal-article","created":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T01:39:45Z","timestamp":1645580385000},"page":"3246-3262","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["W\u2010Transformer: Accurate Cobb angles estimation by using a transformer\u2010based hybrid structure"],"prefix":"10.1002","volume":"49","author":[{"given":"Yifan","family":"Yao","sequence":"first","affiliation":[{"name":"School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongbin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiuqing","family":"Dong","sequence":"additional","affiliation":[{"name":"Division of Electronics Engineering Jeonbuk National University Jeonju Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiangqiang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery Changzheng Hospital Second Military Medical University Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicai","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,3,7]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.brs.0000179086.30449.96"},{"key":"e_1_2_8_3_1","doi-asserted-by":"crossref","unstructured":"LinY LiuL MaK ZhengY.Seg4Reg+: consistency learning between spine segmentation and Cobb angle regression. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:490\u2010499.","DOI":"10.1007\/978-3-030-87240-3_47"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6357171"},{"key":"e_1_2_8_5_1","doi-asserted-by":"crossref","unstructured":"ChenH ShenC QinJ NiD HengPA.Automatic localization and identification of vertebrae in spine CT via a joint learning model with deep neural networks. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention 2015.","DOI":"10.1007\/978-3-319-24553-9_63"},{"key":"e_1_2_8_6_1","doi-asserted-by":"crossref","unstructured":"KhanalB DahalL AdhikariP KhanalB.Automatic Cobb angle detection using vertebra detector and vertebra corners regression. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:81\u201087.","DOI":"10.1007\/978-3-030-39752-4_9"},{"key":"e_1_2_8_7_1","doi-asserted-by":"crossref","unstructured":"YiJ WuP HuangQ QuH MetaxasDN.Vertebra\u2010focused landmark detection for scoliosis assessment. InIEEE 17th International Symposium on Biomedical Imaging (ISBI).IEEE;2020:736\u2010740.","DOI":"10.1109\/ISBI45749.2020.9098675"},{"key":"e_1_2_8_8_1","doi-asserted-by":"crossref","unstructured":"HuangC TangH FanW CheungK ToM&QianZet al. Fully\u2010automated analysis of scoliosis from spinal X\u2010ray images. In IEEE 33rd International Symposium on Computer\u2010Based Medical Systems (CBMS). IEEE; 2020:114\u2010119.","DOI":"10.1109\/CBMS49503.2020.00029"},{"key":"e_1_2_8_9_1","doi-asserted-by":"crossref","unstructured":"TaoR XuS WuH ZhangC LvC.Automated spinal curvature assessment from X\u2010ray images using landmarks estimation network via rotation proposals. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging 2019:95\u2010100.","DOI":"10.1007\/978-3-030-39752-4_11"},{"key":"e_1_2_8_10_1","doi-asserted-by":"crossref","unstructured":"ChenK PengC LiY ChengD WeiS.Accurate automated keypoint detections for spinal curvature estimation. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:63\u201068.","DOI":"10.1007\/978-3-030-39752-4_6"},{"key":"e_1_2_8_11_1","doi-asserted-by":"crossref","unstructured":"ZhongZ LiJ ZhangZ JiaoZ GaoX.A coarse\u2010to\u2010fine deep heatmap regression method for adolescent idiopathic scoliosis assessment. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:101\u2010106.","DOI":"10.1007\/978-3-030-39752-4_12"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"WuH BaileyC RasoulinejadP LiS.Automatic landmark estimation for adolescent idiopathic scoliosis assessment using BoostNet. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2017:127\u2010135.","DOI":"10.1007\/978-3-319-66182-7_15"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.05.005"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101542"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938402"},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"BayatA SekuboyinaA HofmannF El HusseiniM KirschkeJS MenzeBH.Vertebral labelling in radiographs: learning a coordinate corrector to enforce spinal shape. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:39\u201046.","DOI":"10.1007\/978-3-030-39752-4_4"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"HuoL CaiB LiangP et\u00a0al.Joint spinal centerline extraction and curvature estimation with row\u2010wise classification and curve graph network. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:377\u2010386.","DOI":"10.1007\/978-3-030-87240-3_36"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"DubostF ColleryB RenaudierA et\u00a0al.Automated estimation of the spinal curvature via spine centerline extraction with ensembles of cascaded neural networks. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:88\u201094.","DOI":"10.1007\/978-3-030-39752-4_10"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"LinY ZhouH\u2010Y MaK YangX ZhengY.Seg4Reg networks for automated spinal curvature estimation. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:69\u201074.","DOI":"10.1007\/978-3-030-39752-4_7"},{"key":"e_1_2_8_20_1","doi-asserted-by":"crossref","unstructured":"ZhaoS WangB YangK LiY.Automatic spine curvature estimation by a top\u2010down approach. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:75\u201080.","DOI":"10.1007\/978-3-030-39752-4_8"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"AlharbiRH AlshayeMB AlkanhalMM AlharbiNM AlzahraniMA AlrehailiOA.Deep learning based algorithm for automatic scoliosis angle measurement. In3rd International Conference on Computer Applications & Information Security (ICCAIS).IEEE;2020:1\u20105.","DOI":"10.1109\/ICCAIS48893.2020.9096753"},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"LawH DengJ.Cornernet: detecting objects as paired keypoints. InProceedings of the European Conference on Computer Vision (ECCV) 2018:734\u2010750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"YiJ WuP HuangQ et\u00a0al.Multi\u2010scale cell instance segmentation with keypoint graph based bounding boxes. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2019:369\u2010377.","DOI":"10.1007\/978-3-030-32239-7_41"},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"YiJ TangH WuP et\u00a0al.Object\u2010guided instance segmentation for biological images. InProceedings of the AAAI Conference on Artificial Intelligence 2020;34:12677\u201012684.","DOI":"10.1609\/aaai.v34i07.6960"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"NewellA YangK DengJ.Stacked hourglass networks for human pose estimation. InEuropean Conference on Computer Vision.Springer;2016:483\u2010499.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_2_8_26_1","article-title":"Transunet: transformers make strong encoders for medical image segmentation","author":"Chen J","year":"2021","journal-title":"arXiv preprint arXiv:2102.04306"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"WangW ChenC DingM LiJ YuH ZhaS.TransBTS: multimodal brain tumor segmentation using transformer. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021:109\u2010119.","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"e_1_2_8_28_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 2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_29_1","unstructured":"ShazeerN ParmarN UszkoreitJ et\u00a0al.Attention is all you need. InAdvances in Neural Information Processing Systems.2017:5998\u20106008."},{"key":"e_1_2_8_30_1","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy A","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"ZhouX ZhuoJ KrahenbuhlP.Bottom\u2010up object detection by grouping extreme and center points. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2019:850\u2010859.","DOI":"10.1109\/CVPR.2019.00094"},{"key":"e_1_2_8_32_1","volume-title":"Caffey's Pediatric Diagnostic Imaging E\u2010Book","author":"Coley BD","year":"2013"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2783320"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tjem.2018.08.001"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/9083916"},{"key":"e_1_2_8_36_1","doi-asserted-by":"crossref","unstructured":"HuJ ShenL SunG.Squeeze\u2010and\u2010excitation networks. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018:7132\u20107141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_8_37_1","article-title":"Parameter\u2010free spatial attention network for person re\u2010identification","author":"Wang H","year":"2018","journal-title":"arXiv preprint arXiv:1811.12150"},{"key":"e_1_2_8_38_1","doi-asserted-by":"crossref","unstructured":"WangJ WangL LiuC.A multi\u2010task learning method for direct estimation of spinal curvature. InInternational Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging.Springer;2019:113\u2010118.","DOI":"10.1007\/978-3-030-39752-4_14"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-020-06577-3"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spinee.2012.11.051"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1097\/BRS.0b013e318265a829"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-019-06115-w"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-013-2693-9"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-018-5472-9"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15561","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15561","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T22:01:01Z","timestamp":1726696861000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,7]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["10.1002\/mp.15561"],"URL":"https:\/\/doi.org\/10.1002\/mp.15561","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,7]]},"assertion":[{"value":"2021-07-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}