{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:57:23Z","timestamp":1791489443071,"version":"4.3.4"},"reference-count":39,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2020,4,3]],"date-time":"2020-04-03T00:00:00Z","timestamp":1585872000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R00AR070902"],"award-info":[{"award-number":["R00AR070902"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R61AR073552"],"award-info":[{"award-number":["R61AR073552"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance in Med"],"published-print":{"date-parts":[[2020,10]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>To learn bone shape features from spherical bone map of knee MRI images using established convolutional neural networks (CNN) and use these features to diagnose and predict osteoarthritis (OA).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A bone segmentation model was trained on 25 manually annotated 3D MRI volumes to segment the femur, tibia, and patella from 47\u00a0078 3D MRI volumes. Each bone segmentation was converted to a 3D point cloud and transformed into spherical coordinates. Different fusion strategies were performed to merge spherical maps obtained by each bone. A total of 41\u00a0822 merged spherical maps with corresponding Kellgren\u2010Lawrence grades for radiographic OA were used to train a CNN classifier model to diagnose OA using bone shape learned features. Several OA Diagnosis models were tested and the weights for each trained model were transferred to the OA Incidence models. The OA incidence task consisted of predicting OA from a healthy scan within a range of eight time points, from 1 y to 8 y. The validation performance was compared and the test set performance was reported.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The OA Diagnosis model had an area\u2010under\u2010the\u2010curve (AUC) of 0.905 on the test set with a sensitivity and specificity of 0.815 and 0.839. The OA Incidence models had an AUC ranging from 0.841 to 0.646 on the test set for the range from 1 y to 8 y.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Bone shape was successfully used as a predictive imaging biomarker for OA. This approach is novel in the field of deep learning applications for musculoskeletal imaging and can be expanded to other OA biomarkers.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mrm.28251","type":"journal-article","created":{"date-parts":[[2020,4,3]],"date-time":"2020-04-03T16:18:56Z","timestamp":1585930736000},"page":"2190-2203","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Learning osteoarthritis imaging biomarkers from bone surface spherical encoding"],"prefix":"10.1002","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4093-8266","authenticated-orcid":false,"given":"Alejandro","family":"Morales Martinez","sequence":"first","affiliation":[{"name":"Department of Radiology and Biomedical Imaging University of California San Francisco California"},{"name":"Graduate Program in Bioengineering University of California San Francisco California"},{"name":"Graduate Program in Bioengineering University of California Berkeley California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Caliva","sequence":"additional","affiliation":[{"name":"Department of Radiology and Biomedical Imaging University of California San Francisco California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Io","family":"Flament","sequence":"additional","affiliation":[{"name":"Department of Radiology and Biomedical Imaging University of California San Francisco California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics University of California San Francisco California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhee","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology and Biomedical Imaging University of California San Francisco California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1116-1171","authenticated-orcid":false,"given":"Peng","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology The Hong Kong University Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rutwik","family":"Shah","sequence":"additional","affiliation":[{"name":"Department of Radiology and Biomedical Imaging University of California San Francisco California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0201-871X","authenticated-orcid":false,"given":"Sharmila","family":"Majumdar","sequence":"additional","affiliation":[{"name":"Department of Radiology and Biomedical Imaging University of California San Francisco California"},{"name":"Graduate Program in Bioengineering University of California San Francisco California"},{"name":"Graduate Program in Bioengineering University of California Berkeley California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentina","family":"Pedoia","sequence":"additional","affiliation":[{"name":"Department of Radiology and Biomedical Imaging University of California San Francisco California"},{"name":"Graduate Program in Bioengineering University of California San Francisco California"},{"name":"Graduate Program in Bioengineering University of California Berkeley California"},{"name":"Center for Digital Health Innovation (CDHI) University of California San Francisco California"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2020,4,3]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/acr.22721"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2013-204763"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.21562"},{"key":"e_1_2_6_5_1","first-page":"574","article-title":"Assessment of subchondral bone density distribution patterns in patients subjected to correction osteotomy","volume":"19","author":"M\u00fcller\u2010Gerbl M","year":"1994","journal-title":"Trans Orth Soc"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00351749"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-67138-8"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2009.04.011"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2010.02.015"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.34526"},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.37987"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2014.08.013"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2012.12.007"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2013-204052"},{"key":"e_1_2_6_15_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2015-207602"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2015.05.027"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25065"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11999-017-5368-8"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-017-9955-8"},{"key":"e_1_2_6_20_1","doi-asserted-by":"publisher","DOI":"10.5588\/ijtld.17.0520"},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-22437-z"},{"key":"e_1_2_6_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001269.2001295"},{"key":"e_1_2_6_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2532122"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494198"},{"key":"e_1_2_6_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27178"},{"key":"e_1_2_6_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26841"},{"key":"e_1_2_6_27_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172322"},{"key":"e_1_2_6_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11999-016-4732-4"},{"key":"e_1_2_6_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2008.06.016"},{"key":"e_1_2_6_30_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS\u2010A.V\u2010net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 Fourth International Conference on 3D Vision (3DV) Stanford CA June2016. pp.565\u2010571.https:\/\/arxiv.org\/abs\/1606.04797. Accessed October 22 2018.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_6_31_1","doi-asserted-by":"crossref","unstructured":"DengJ DongW SocherR LiL\u2010J LiK Fei\u2010FeiL.ImageNet: A large\u2010scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Miami FL 2009. pp.248\u2010255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_6_32_1","first-page":"2825","article-title":"Scikit\u2010learn: Machine learning in Python","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"J Mach Learn Res"},{"key":"e_1_2_6_33_1","article-title":"Deep residual learning for image recognition","author":"He K","year":"2015","journal-title":"ArXiv151203385 Cs"},{"key":"e_1_2_6_34_1","unstructured":"PaszkeA GrossS ChintalaS et al.Automatic differentiation in PyTorch. In 31st Conference on Neural Information Processing Systems (NIPS) Long Beach CA 2017."},{"key":"e_1_2_6_35_1","unstructured":"HuangG LiuZ van derMaatenL WeinbergerKQ.Densely connected convolutional networks. August2016.https:\/\/arxiv.org\/abs\/1608.06993. Accessed November 6 2018."},{"key":"e_1_2_6_36_1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems 25","author":"Krizhevsky A","year":"2012"},{"key":"e_1_2_6_37_1","unstructured":"IandolaFN HanS MoskewiczMW AshrafK DallyWJ KeutzerK.SqueezeNet: AlexNet\u2010level accuracy with 50x fewer parameters and <0.5MB model size. February 2016.https:\/\/arxiv.org\/abs\/1602.07360v4. Accessed September 26 2019."},{"key":"e_1_2_6_38_1","article-title":"Delving deep into rectifiers: Surpassing human\u2010level performance on ImageNet classification","author":"He K","year":"2015","journal-title":"ArXiv150201852 Cs"},{"key":"e_1_2_6_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_6_40_1","article-title":"Grad\u2010CAM: Visual explanations from deep networks via gradient\u2010based localization","author":"Selvaraju RR","year":"2016","journal-title":"ArXiv161002391 Cs"}],"container-title":["Magnetic Resonance in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fmrm.28251","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.28251","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mrm.28251","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.28251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T15:08:19Z","timestamp":1693408099000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/mrm.28251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,3]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["10.1002\/mrm.28251"],"URL":"https:\/\/doi.org\/10.1002\/mrm.28251","archive":["Portico"],"relation":{},"ISSN":["0740-3194","1522-2594"],"issn-type":[{"value":"0740-3194","type":"print"},{"value":"1522-2594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,3]]},"assertion":[{"value":"2019-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-02-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-04-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}