{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T01:52:45Z","timestamp":1790301165686,"version":"4.1.0"},"reference-count":30,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T00:00:00Z","timestamp":1703635200000},"content-version":"am","delay-in-days":354,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#am"},{"start":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T00:00:00Z","timestamp":1673049600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000147","name":"Division of Civil, Mechanical and Manufacturing Innovation","doi-asserted-by":"publisher","award":["1662429"],"award-info":[{"award-number":["1662429"]}],"id":[{"id":"10.13039\/100000147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000147","name":"Division of Civil, Mechanical and Manufacturing Innovation","doi-asserted-by":"publisher","award":["CAREER 1653358"],"award-info":[{"award-number":["CAREER 1653358"]}],"id":[{"id":"10.13039\/100000147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal Orthopaedic Research"],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this study, we aimed to democratize access to convolutional neural networks (CNN) for segmenting cartilage volumes, generating state\u2010of\u2010the\u2010art results for specialized, real\u2010world applications in hospitals and research. Segmentation of cross\u2010sectional and\/or longitudinal magnetic resonance (MR) images\u00a0of articular cartilage facilitates both clinical management of joint damage\/disease and fundamental research. Manual delineation of such images is a time\u2010consuming task susceptible to high intra\u2010 and interoperator variability and prone to errors. Thus, enabling reliable and efficient analyses of MRIs of cartilage requires automated segmentation of cartilage volumes. Two main limitations arise in the development of hospital\u2010 or population\u2010specific deep learning (DL) models for image segmentation: specialized knowledge and specialized hardware. We present a relatively easy and accessible implementation of a DL model to automatically segment MRIs of human knees with state\u2010of\u2010the\u2010art accuracy. In representative examples, we trained CNN models in 6\u20108\u2009h\u00a0and obtained results quantitatively comparable to state\u2010of\u2010the\u2010art for every anatomical structure. We established and evaluated our methods using two publicly available MRI data sets originating from the Osteoarthritis Initiative, Stryker Imorphics, and Zuse Institute Berlin (ZIB), as representative test cases. We use Google Colabfor editing and adapting the Python codes and selecting the runtime environment leveraging high\u2010performance graphical processing units. We designed our solution for novice users to apply to any data set with relatively few adaptations requiring only basic programming skills. To facilitate the adoption of our methods, we provide a complete guideline for using our methods and software, as well as the software tools themselves.\u00a0Clinical significance:\u00a0We establish and detail methods that clinical personal can apply to create their own DL\u00a0models without specialized knowledge of DL nor specialized hardware\/infrastructure and obtain results comparable with the state\u2010of\u2010the\u2010art to facilitate both clinical management of joint damage\/disease and fundamental research.<\/jats:p>","DOI":"10.1002\/jor.25509","type":"journal-article","created":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T10:43:43Z","timestamp":1672137823000},"page":"1754-1766","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Democratization of deep learning for segmenting cartilage from MRIs of human knees: Application to data from the osteoarthritis initiative"],"prefix":"10.1002","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4779-0225","authenticated-orcid":false,"given":"Borja","family":"Rodriguez\u2010Vila","sequence":"first","affiliation":[{"name":"Department of Electronics Universidad Rey Juan Carlos  Madrid Spain"},{"name":"Medical Image Analysis and Biometry Laboratory Universidad Rey Juan Carlos  Madrid Spain"},{"name":"IAsalud, School for Doctoral Studies and Research Universidad Europea de Madrid  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vera","family":"Gonzalez\u2010Hospital","sequence":"additional","affiliation":[{"name":"IAsalud, School for Doctoral Studies and Research Universidad Europea de Madrid  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrique","family":"Puertas","sequence":"additional","affiliation":[{"name":"IAsalud, School for Doctoral Studies and Research Universidad Europea de Madrid  Madrid Spain"},{"name":"Department of Computer Science and Technology, School of Architecture, Engineering and Design Universidad Europea de Madrid  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan\u2010Jose","family":"Beunza","sequence":"additional","affiliation":[{"name":"IAsalud, School for Doctoral Studies and Research Universidad Europea de Madrid  Madrid Spain"},{"name":"Department of Medicine, School of Biomedical and Health Sciences Universidad Europea de Madrid  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9713-1204","authenticated-orcid":false,"given":"David M.","family":"Pierce","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering University of Connecticut  Storrs Connecticut USA"},{"name":"Department of Biomedical Engineering University of Connecticut  Storrs Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,1,7]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.23176"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101851"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/10255842.2017.1383984"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0730-725X(99)00040-5"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng-071516-044442"},{"key":"e_1_2_7_7_1","unstructured":"HeimannT MorrisonB StynerMA NiethammerM WarfieldSK. Segmentation of knee images: a grand challenge. MICCAI Workshop on Medical Image Analysis for the Clinic Proceedings of the 13th International Conference Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI). Beijing China.\u00a02010."},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-69920-0"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172322"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_7_11_1","doi-asserted-by":"crossref","unstructured":"PanfilovE TiulpinA KleinS NieminenMT SaarakkalaS. Improving robustness of deep learning based knee MRI segmentation: mixup and adversarial domain adaptation. Proceedings of theIEEE\/CVF International Conference on Computer Vision Workshop (ICCVW) 2019:450\u2010459.","DOI":"10.1109\/ICCVW.2019.00057"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.11.009"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-021-00934-z"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101793"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28111"},{"key":"e_1_2_7_16_1","unstructured":"GoodfellowI Pouget\u2010AbadieJ MirzaM et al. Generative adversarial nets.Proceedings of the International Conference on Neural Information Processing Systems 2014:2672\u20132680."},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200078"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08190-4"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/info11020108"},{"key":"e_1_2_7_20_1","volume-title":"The osteoarthritis initiative: protocol for the cohort study","author":"Nevitt M","year":"2006"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr\/68875123"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1136\/ard.16.4.494"},{"key":"e_1_2_7_23_1","unstructured":"SeimH KainmuellerD LameckerH BindernagelM MalinowskiJ ZachowS. Model\u2010based auto\u2010segmentation of knee bones and cartilage in MRI data. MICCAI Workshop on Medical Image Analysis for the Clinic Proceedings of the 13th International Conference Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI). Beijing China.\u00a02010."},{"key":"e_1_2_7_24_1","unstructured":"HowardJ.fastai.2018. Available athttps:\/\/github.com\/fastai\/fastai"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_7_26_1","first-page":"1","article-title":"A method of establishing groups of equal amplitudes in plant sociology based on similarity of species content and its application to analyses of the vegetation on danish commons. kongelige danske videnskabernes selskab","volume":"5","author":"Sorenson T","year":"1948","journal-title":"Biologiske Skrifter"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.1.015006"},{"key":"e_1_2_7_28_1","first-page":"1","article-title":"TensorFlow: large\u2010scale machine learning on heterogeneous distributed systems","author":"Abadi M","year":"2016","journal-title":"arXiv"},{"key":"e_1_2_7_29_1","unstructured":"PaszkeA GrossS MassaF et al. PyTorch: an imperative style high\u2010performance deep learning library.\u00a0Neural Information Processing Systems (NeurIPS) 2019;32:8024\u20108035."},{"key":"e_1_2_7_30_1","unstructured":"CholletF.Keras.2022. Available athttps:\/\/keras.io"},{"key":"e_1_2_7_31_1","first-page":"1","article-title":"Theano: a Python framework for fast computation of mathematical expressions","author":"The Theano Development Team","year":"2016","journal-title":"arXiv"}],"container-title":["Journal of Orthopaedic Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jor.25509","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jor.25509","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/am-pdf\/10.1002\/jor.25509","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jor.25509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T19:27:53Z","timestamp":1692214073000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jor.25509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,7]]},"references-count":30,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1002\/jor.25509"],"URL":"https:\/\/doi.org\/10.1002\/jor.25509","archive":["Portico"],"relation":{},"ISSN":["0736-0266","1554-527X"],"issn-type":[{"value":"0736-0266","type":"print"},{"value":"1554-527X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,7]]},"assertion":[{"value":"2022-07-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}