{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T14:37:55Z","timestamp":1791297475816,"version":"4.1.0"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["CRC1181"],"award-info":[{"award-number":["CRC1181"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["CRC1483"],"award-info":[{"award-number":["CRC1483"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["FOR2438"],"award-info":[{"award-number":["FOR2438"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["PANDORA FOR2886"],"award-info":[{"award-number":["PANDORA FOR2886"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["MASCARA 01EC1903A"],"award-info":[{"award-number":["MASCARA 01EC1903A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["4DNanoscope"],"award-info":[{"award-number":["4DNanoscope"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010767","name":"Innovative Medicines Initiative","doi-asserted-by":"publisher","award":["Hippocrates"],"award-info":[{"award-number":["Hippocrates"]}],"id":[{"id":"10.13039\/501100010767","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010767","name":"Innovative Medicines Initiative","doi-asserted-by":"publisher","award":["RT-Cure"],"award-info":[{"award-number":["RT-Cure"]}],"id":[{"id":"10.13039\/501100010767","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"publisher","award":["EFI MIRACLE"],"award-info":[{"award-number":["EFI MIRACLE"]}],"id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective:<\/jats:title>\n                    <jats:p>We investigated whether a neural network based on the shape of joints can differentiate between rheumatoid arthritis (RA), psoriatic arthritis (PsA), and healthy controls (HC), which class patients with undifferentiated arthritis (UA) are assigned to, and whether this neural network is able to identify disease-specific regions in joints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We trained a novel neural network on 3D articular bone shapes of hand joints of RA and PsA patients as well as HC. Bone shapes were created from high-resolution peripheral-computed-tomography (HR-pQCT) data of the second metacarpal bone head. Heat maps of critical spots were generated using GradCAM. After training, we fed shape patterns of UA into the neural network to classify them into RA, PsA, or HC.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Hand bone shapes from 932 HR-pQCT scans of 617 patients were available. The network could differentiate the classes with an area-under-receiver-operator-curve of 82% for HC, 75% for RA, and 68% for PsA. Heat maps identified anatomical regions such as bare area or ligament attachments prone to erosions and bony spurs. When feeding UA data into the neural network, 86% were classified as \u201cRA,\u201d 11% as \u201cPsA,\u201d and 3% as \u201cHC\u201d based on the joint shape.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We investigated neural networks to differentiate the shape of joints of RA, PsA, and HC and extracted disease-specific characteristics as heat maps on 3D joint shapes that can be utilized in clinical routine examination using ultrasound. Finally, unspecific diseases such as UA could be grouped using the trained network based on joint shape.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2022.850552","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T07:04:55Z","timestamp":1646895895000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Deep Learning-Based Classification of Inflammatory Arthritis by Identification of Joint Shape Patterns\u2014How Neural Networks Can Tell Us Where to \u201cDeep Dive\u201d Clinically"],"prefix":"10.3389","volume":"9","author":[{"given":"Lukas","family":"Folle","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Simon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koray","family":"Tascilar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerhard","family":"Kr\u00f6nke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna-Maria","family":"Liphardt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georg","family":"Schett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnd","family":"Kleyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,3,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.1056\/NEJMra1004965","article-title":"The pathogenesis of rheumatoid arthritis","volume":"365","author":"McInnes","year":"2011","journal-title":"N Engl J Med."},{"key":"B2","first-page":"239","article-title":"Psoriatic arthritis.","volume-title":"Moderate-to-Severe Psoriasis, Third Edition. Vol. 376.","author":"Ritchlin","year":"2008"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2569","DOI":"10.1002\/art.27584","article-title":"2010 Rheumatoid arthritis classification criteria: an American College of Rheumatology\/European League Against Rheumatism collaborative initiative","volume":"62","author":"Aletaha","year":"2010","journal-title":"Arthritis Rheum."},{"key":"B4","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1002\/art.21972","article-title":"Classification criteria for psoriatic arthritis: development of new criteria from a large international study","volume":"54","author":"Taylor","year":"2006","journal-title":"Arthritis Rheum."},{"key":"B5","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1136\/annrheumdis-2011-200205","article-title":"Undifferentiated arthritis characteristics and outcomes when applying the 2010 and 1987 criteria for rheumatoid arthritis","volume":"71","author":"Krabben","year":"2012","journal-title":"Ann Rheum Dis."},{"key":"B6","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1136\/ard.2010.132423","article-title":"A comparative study of periarticular bone lesions in rheumatoid arthritis and psoriatic arthritis","volume":"70","author":"Finzel","year":"2011","journal-title":"Ann Rheum Dis."},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1097\/RHU.0000000000001720","article-title":"A machine learning approach for predicting sustained remission in rheumatoid arthritis patients on biologic agents","volume-title":"JCR J Clin Rheumatol","author":"Venerito","year":""},{"key":"B8","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1093\/rheumatology\/kez677","article-title":"A machine-learning approach to cardiovascular risk prediction in psoriatic arthritis","volume":"59","author":"Navarini","year":"2020","journal-title":"Rheumatology."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1007\/s11739-020-02583-x","article-title":"A convolutional neural network with transfer learning for automatic discrimination between low and high-grade synovitis: a pilot study","volume":"16","author":"Venerito","year":"2021","journal-title":"Intern Emerg Med."},{"key":"B10","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1038\/s42256-019-0077-5","article-title":"Learning with known operators reduces maximum training error bounds","volume":"1","author":"Maier","year":"2019","journal-title":"Nat Mach Intell."},{"key":"B11","doi-asserted-by":"publisher","first-page":"9697","DOI":"10.1038\/s41598-021-89111-9","article-title":"Deep learning methods allow fully automated segmentation of metacarpal bones to quantify volumetric bone mineral density","volume":"11","author":"Folle","year":"2021","journal-title":"Sci Rep."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1016\/j.joca.2019.01.019","article-title":"The ageing joint-standard age- and sex-related values of bone erosions and osteophytes in the hand joints of healthy individuals","volume":"27","author":"Berlin","year":"2019","journal-title":"Osteoarthr Cartil."},{"key":"B13","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.bone.2018.07.017","article-title":"A comparative analysis of articular bone in large cohort of patients with chronic inflammatory diseases of the joints, the gut and the skin","volume":"116","author":"Simon","year":"2018","journal-title":"Bone."},{"key":"B14","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1186\/s13075-018-1691-z","article-title":"Simultaneous quantification of bone erosions and enthesiophytes in the joints of patients with psoriasis or psoriatic arthritis - effects of age and disease duration","volume":"20","author":"Simon","year":"2018","journal-title":"Arthritis Res Ther."},{"key":"B15","article-title":"Supervised autoencoders: Improving generalization performance with unsupervised regularizers","volume-title":"Adv Neural Inf Process Syst.","author":"Le","year":"2018"},{"key":"B16","unstructured":"Striving for simplicity: the all convolutional net\n            SpringenbergJT\n            DosovitskiyA\n            BroxT\n            RiedmillerM\n          ICLR (Workshop Track)2015"},{"key":"B17","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/s13075-021-02484-0","article-title":"Deep learning for detection of radiographic sacroiliitis: achieving expert-level performance","volume":"23","author":"Bressem","year":"2021","journal-title":"Arthritis Res Ther."},{"key":"B18","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1046\/j.1525-1497.2002.10750.x","article-title":"Simplifying likelihood ratios","volume":"17","author":"McGee","year":"2002","journal-title":"J Gen Intern Med."},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.3115\/1072064.1072067","volume-title":"MUC-4 Evaluation Metrics.","author":"Chinchor","year":"1992"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e190606","DOI":"10.1001\/jamanetworkopen.2019.0606","article-title":"Assessment of a deep learning model based on electronic health record data to forecast clinical outcomes in patients with rheumatoid arthritis","volume":"2","author":"Norgeot","year":"2019","journal-title":"JAMA Netw Open."},{"key":"B21","doi-asserted-by":"publisher","first-page":"5648","DOI":"10.1038\/s41598-020-62634-3","article-title":"Convolutional neural network for classification of two-dimensional array images generated from clinical information may support diagnosis of rheumatoid arthritis","volume":"10","author":"Fukae","year":"2020","journal-title":"Sci Rep."},{"key":"B22","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1136\/annrheumdis-2020-217160","article-title":"Machine-learning, MRI bone shape and important clinical outcomes in osteoarthritis: data from the osteoarthritis initiative","volume":"80","author":"Bowes","year":"2021","journal-title":"Ann Rheum Dis."},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1111\/imj.15173","article-title":"A pilot study of a machine-learning tool to assist in the diagnosis of hand arthritis","volume-title":"Intern Med J.","author":"Reed","year":"2020"},{"key":"B24","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1007\/s10067-019-04487-4","article-title":"Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network","volume":"39","author":"\u00dcreten","year":"2020","journal-title":"Clin Rheumatol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1136\/annrheumdis-2019-216636","article-title":"Applying cascaded convolutional neural network design further enhances automatic scoring of arthritis disease activity on ultrasound images from rheumatoid arthritis patients","volume":"79","author":"Christensen","year":"2020","journal-title":"Ann Rheum Dis."},{"key":"B26","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1136\/annrheumdis-2012-202958","article-title":"Bone loss before the clinical onset of rheumatoid arthritis in subjects with anticitrullinated protein antibodies","volume":"73","author":"Kleyer","year":"2014","journal-title":"Ann Rheum Dis."},{"key":"B27","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1136\/annrheumdis-2014-206347","article-title":"Analysis of periarticular bone changes in patients with cutaneous psoriasis without associated psoriatic arthritis","volume":"75","author":"Simon","year":"2016","journal-title":"Ann Rheum Dis."},{"key":"B28","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1046\/j.1469-7580.2001.19950503.x","article-title":"The anatomical basis for disease localisation in seronegative spondyloarthropathy at entheses and related sites","volume":"199","author":"Benjamin","year":"2001","journal-title":"J Anat."},{"key":"B29","doi-asserted-by":"publisher","first-page":"3306","DOI":"10.1002\/art.20566","article-title":"The \u201centhesis organ\u201d concept: why enthesopathies may not present as focal insertional disorders","volume":"50","author":"Benjamin","year":"2004","journal-title":"Arthritis Rheum."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.850552\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T07:05:03Z","timestamp":1646895903000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.850552\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,10]]},"references-count":29,"alternative-id":["10.3389\/fmed.2022.850552"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2022.850552","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,10]]},"article-number":"850552"}}